Example: Benchmark Citus
This differs from the default behaviour of bexhoma, since we benchmark a distributed DBMS, that can be managed by bexhoma and exists in the Kubernetes cluster in the same namespace.
Citus is a PostgreSQL extension, that introduces sharding [1]. A cluster has an instance of PostgreSQL with Citus as a coordinator (here called master, managed by a Kubernetes deployment). More instances can register at the master as worker nodes (here managed by Kubernetes stateful sets). Bexhoma also deploys a service for communication external to Citus (from within the cluster) and a headless service for communication between the pods of the Citus cluster.
The results are not official benchmark results. Exact performance depends on a number of parameters. You may get different results. These examples are solely to illustrate how to use bexhoma and show the result evaluation.
References:
Citus: https://www.citusdata.com/
YCSB Repository: https://github.com/brianfrankcooper/YCSB/wiki/Running-a-Workload
Benchmarking cloud serving systems with YCSB: https://dl.acm.org/doi/10.1145/1807128.1807152
Benchbase Repository: https://github.com/cmu-db/benchbase/wiki/TPC-C
OLTP-Bench: An Extensible Testbed for Benchmarking Relational Databases: http://www.vldb.org/pvldb/vol7/p277-difallah.pdf
Orchestrating DBMS Benchmarking in the Cloud with Kubernetes: https://doi.org/10.1007/978-3-030-94437-7_6
A Cloud-Native Adoption of Classical DBMS Performance Benchmarks and Tools: https://doi.org/10.1007/978-3-031-68031-1_9
Perform YCSB Benchmark - Ingestion of Data Included
You will have to change the node selectors there (to names of nodes, that exist in your cluster - or to leave out the corresponding parameters):
BEXHOMA_NODE_SUT="cl-worker11"
BEXHOMA_NODE_LOAD="cl-worker19"
BEXHOMA_NODE_BENCHMARK="cl-worker19"
LOG_DIR="./logs_tests"
BEXHOMA_MS=1
BEXHOMA_STORAGE_CLASS="shared"
mkdir -p $LOG_DIR
For performing the experiment we can run the ycsb file.
Example:
bexhoma ycsb \
-dbms Citus \
-sf 1 \
-xwl a \
-xtb 16384 \
-xnbf 4 \
-xnlf 4 \
-nc 1 \
-ne 1 \
-nlp 8 \
-nlt 64 \
-nbp 1 \
-nbt 64 \
-nw 3 \
-nwr 1 \
-nws 48 \
-xop 10 \
-m \
-mc \
-ms $BEXHOMA_MS \
-tr \
-rnn $BEXHOMA_NODE_SUT -rnl $BEXHOMA_NODE_LOAD -rnb $BEXHOMA_NODE_BENCHMARK \
run &>$LOG_DIR/doc_ycsb_citus_1.log
This
loops over
nin [8] andtin [4]starts a clean instance of Citus (
-dbms) with 3 workers (-nw), no replication (one instance-nwr) and 32 shards (-nws)data directory inside a Docker container
creates YCSB schema in each database
starts
nloader pods per DBMSwith a loading container each
threads = 64/
n(-nlt)target throughput is
t* 16384generates YCSB data = 10.000.000 rows (i.e., SF=10,
-sf)imports it into the DBMS
loops over
min [1] andsin [4]runs
mparallel streams of YCSB queries per DBMS10.000.000 operations (
-xop)workload A = 50% read / 50% write (
--workload)target throughput is
s* 16384threads = 64/
m(-nbt)
with a maximum of 1 DBMS per time (
-ms)
tests if results match workflow (
-tr)monitors (
-m) all components (-mc)shows a summary
Status
You can watch the status while benchmark is running via bexperiments status
Dashboard: Running
Cluster Prometheus: Running
Message Queue: Running
Data directory: Running
Result directory: Running
+------------------+--------------+------------+-------------+
| 1741884177 | sut | use case | worker |
+==================+==============+============+=============+
| Citus-64-8-65536 | (1. Running) | ycsb | (3 Running) |
+------------------+--------------+------------+-------------+
The code 1730133803 is the unique identifier of the experiment.
You can find the number also in the output of ycsb.py.
Cleanup
The script is supposed to clean up and remove everything from the cluster that is related to the experiment after finishing.
If something goes wrong, you can also clean up manually with bexperiment stop (removes everything) or bexperiment stop -e 1730133803 (removes everything that is related to experiment 1730133803).
Evaluate Results
At the end of a benchmark you will see a summary like
doc_ycsb_citus_1.log
## Show Summary
### Workload
YCSB SF=1
* Type: ycsb
* Duration: 3321s
* Code: 1773433299
* YCSB driver runs the experiment.
* This experiment compares run time and resource consumption of YCSB queries.
* Workload is 'A'.
* Number of rows to insert is 1000000.
* Ordering of inserts is hashed.
* Number of operations is 10000000.
* Batch size is ''.
* Target is based on multiples of '16384'.
* Factors for loading are [4].
* Factors for benchmarking are [4].
* Experiment uses bexhoma version 0.9.4.
* System metrics are monitored by a cluster-wide installation.
* Experiment is limited to DBMS ['Citus'].
* Import is handled by 8 processes (pods).
* Loading is fixed to cl-worker19.
* Benchmarking is fixed to cl-worker19.
* SUT is fixed to cl-worker14.
* Loading is tested with [64] threads, split into [8] pods.
* Benchmarking is tested with [64] threads, split into [1] pods.
* Benchmarking is run as [1] times the number of benchmarking pods.
* Experiment is run once.
### Connections
* Citus-64-8-65536-1 uses docker image citusdata/citus:13.2.0-alpine
* RAM:541008474112
* CPU:AMD Opteron(tm) Processor 6378
* Cores:64
* host:5.15.0-164-generic
* node:cl-worker14
* disk:147894
* cpu_list:0-63
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* requests_cpu:4
* requests_memory:16Gi
* worker 0
* RAM:2164173209600
* CPU:INTEL(R) XEON(R) PLATINUM 8570
* Cores:224
* host:6.8.0-90-generic
* node:cl-worker36
* disk:1261412
* cpu_list:0-223
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 1
* RAM:540579303424
* CPU:AMD EPYC 7502 32-Core Processor
* Cores:128
* host:6.8.0-94-generic
* node:cl-worker22
* disk:379380
* cpu_list:0-127
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 2
* RAM:540590817280
* CPU:AMD EPYC 7352 24-Core Processor
* Cores:96
* host:6.8.0-90-generic
* node:cl-worker23
* disk:1212031
* cpu_list:0-95
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* eval_parameters
* code:1773433299
* BEXHOMA_REPLICAS:1
* BEXHOMA_SHARDS:48
* BEXHOMA_WORKERS:3
### Loading
| DBMS | experiment_run | threads | target | pod_count | exceptions | [OVERALL].Throughput(ops/sec) | [OVERALL].RunTime(ms) | [INSERT].Return=OK | [INSERT].99thPercentileLatency(us) |
|:-----------------|-----------------:|----------:|---------:|------------:|-------------:|--------------------------------:|------------------------:|---------------------:|-------------------------------------:|
| Citus-64-8-65536 | 1 | 64 | 65536 | 8 | 0 | 11373.2 | 88433 | 1e+06 | 25301 |
### Execution
| DBMS | experiment_run | threads | target | pod_count | exceptions | [OVERALL].Throughput(ops/sec) | [OVERALL].RunTime(ms) | [READ].Return=OK | [READ].99thPercentileLatency(us) | [UPDATE].Return=OK | [UPDATE].99thPercentileLatency(us) |
|:-------------------|-----------------:|----------:|---------:|------------:|-------------:|--------------------------------:|------------------------:|-------------------:|-----------------------------------:|---------------------:|-------------------------------------:|
| Citus-64-8-65536-1 | 1 | 64 | 65536 | 1 | 0 | 4343.14 | 2.30248e+06 | 4.99938e+06 | 2155 | 5.00062e+06 | 859647 |
### Workflow
#### Actual
* DBMS Citus-64-8-65536 - Pods [[1]]
#### Planned
* DBMS Citus-64-8-65536 - Pods [[1]]
### Monitoring
### Loading phase: SUT deployment
| DBMS | CPU [CPUs] | Max CPU | Max RAM [Gb] | Max RAM Cached [Gb] |
|:-------------------|-------------:|----------:|---------------:|----------------------:|
| Citus-64-8-65536-1 | 559.19 | 6.26 | 0.72 | 0.75 |
### Loading phase: component worker
| DBMS | CPU [CPUs] | Max CPU | Max RAM [Gb] | Max RAM Cached [Gb] |
|:-------------------|-------------:|----------:|---------------:|----------------------:|
| Citus-64-8-65536-1 | 304.59 | 3.07 | 3.05 | 5.5 |
### Loading phase: component loader
| DBMS | CPU [CPUs] | Max CPU | Max RAM [Gb] | Max RAM Cached [Gb] |
|:-------------------|-------------:|----------:|---------------:|----------------------:|
| Citus-64-8-65536-1 | 91.02 | 0 | 0.12 | 0.12 |
### Execution phase: SUT deployment
| DBMS | CPU [CPUs] | Max CPU | Max RAM [Gb] | Max RAM Cached [Gb] |
|:-------------------|-------------:|----------:|---------------:|----------------------:|
| Citus-64-8-65536-1 | 5.52 | 0 | 0.53 | 0.56 |
### Execution phase: component worker
| DBMS | CPU [CPUs] | Max CPU | Max RAM [Gb] | Max RAM Cached [Gb] |
|:-------------------|-------------:|----------:|---------------:|----------------------:|
| Citus-64-8-65536-1 | 4965.83 | 2.38 | 5.68 | 11.68 |
### Execution phase: component benchmarker
| DBMS | CPU [CPUs] | Max CPU | Max RAM [Gb] | Max RAM Cached [Gb] |
|:-------------------|-------------:|----------:|---------------:|----------------------:|
| Citus-64-8-65536-1 | 957.68 | 0.41 | 0.15 | 0.15 |
### Tests
* TEST passed: Loading Phase: [OVERALL].Throughput(ops/sec) contains no 0 or NaN
* TEST passed: Execution Phase: [OVERALL].Throughput(ops/sec) contains no 0 or NaN
* TEST passed: Loading phase: SUT deployment contains no 0 or NaN in CPU [CPUs]
* TEST passed: Loading phase: component worker contains no 0 or NaN in CPU [CPUs]
* TEST passed: Loading phase: component loader contains no 0 or NaN in CPU [CPUs]
* TEST passed: Execution phase: SUT deployment contains no 0 or NaN in CPU [CPUs]
* TEST passed: Execution phase: component worker contains no 0 or NaN in CPU [CPUs]
* TEST passed: Execution phase: component benchmarker contains no 0 or NaN in CPU [CPUs]
* TEST passed: Workflow as planned
* TEST passed: Execution Phase: contains no FAILED column
To see the summary again you can simply call bexperiments summary -e 1730133803 with the experiment code.
Detailed Evaluation
Results are transformed into pandas DataFrames and can be inspected in detail. See for example
You can connect to an evaluation server locally by bexperiments jupyter.
This forwards ports, so you have
a Jupyter notebook server at http://localhost:8888
Monitoring
Monitoring can be activated for DBMS only (-m) or for all components (-mc).
All metrics in monitoring are summed across all matching components. In this example, this means that used memory, CPU time, etc. are summed across all 3 nodes of the Citus cluster (“worker”) and the coordinator (“SUT deployment”).
Use Persistent Storage
The default behaviour of bexhoma is that the database is stored inside the ephemeral storage of the Docker container. If your cluster allows dynamic provisioning of volumes, you might request a persistent storage of a certain type (storageClass) and size.
Example:
bexhoma ycsb \
-dbms Citus \
-sf 1 \
-xwl a \
-xtb 16384 \
-xnbf 4 \
-xnlf 4 \
-nc 2 \
-ne 1 \
-nlp 8 \
-nlt 64 \
-nbp 1 \
-nbt 64 \
-nw 3 \
-nwr 1 \
-nws 48 \
-xop 10 \
-m \
-mc \
-ms $BEXHOMA_MS \
-tr \
-rss 50Gi \
-rst $BEXHOMA_STORAGE_CLASS \
-rnn $BEXHOMA_NODE_SUT -rnl $BEXHOMA_NODE_LOAD -rnb $BEXHOMA_NODE_BENCHMARK \
run &>$LOG_DIR/doc_ycsb_citus_2.log
The following status shows we have one volume of type shared.
Every Citus experiment will take the databases from these volumes and skip loading.
In this example -nc is set to two, that is the complete experiment is repeated twice for statistical confidence.
The first instance of Citus mounts the volume and generates the data.
All other instances just use the database without generating and loading data.
Bexhoma uses two types of volumes.
The first one is attached to the coordinator and is used to persist infos across experiments (and not to store actual data).
The other volumes (worker volumes) are attached to the worker pods and store the actual data.
+----------------------------------------+-----------------+--------------+--------------+-------------------+-----------------+----------------------+-----------+----------+--------+--------+
| Volumes | configuration | experiment | loaded [s] | timeLoading [s] | dbms | storage_class_name | storage | status | size | used |
+========================================+=================+==============+==============+===================+=================+======================+===========+==========+========+========+
| bexhoma-storage-citus-ycsb-1 | citus | ycsb-1 | True | 26 | Citus | shared | 50Gi | Bound | 50.0G | 40.0M |
+----------------------------------------+-----------------+--------------+--------------+-------------------+-----------------+----------------------+-----------+----------+--------+--------+
+-----------------------------------+-------------------+--------------+--------+----------------------+-----------+----------+--------+--------+
| Volumes of Workers | configuration | experiment | dbms | storage_class_name | storage | status | size | used |
+===================================+===================+==============+========+======================+===========+==========+========+========+
| bxw-bexhoma-worker-citus-ycsb-1-0 | Citus-64-8-65536 | 1742471862 | Citus | shared | 50Gi | Bound | 50.0G | 1.4G |
+-----------------------------------+-------------------+--------------+--------+----------------------+-----------+----------+--------+--------+
| bxw-bexhoma-worker-citus-ycsb-1-1 | Citus-64-8-65536 | 1742471862 | Citus | shared | 50Gi | Bound | 50.0G | 1.4G |
+-----------------------------------+-------------------+--------------+--------+----------------------+-----------+----------+--------+--------+
| bxw-bexhoma-worker-citus-ycsb-1-2 | Citus-64-8-65536 | 1742471862 | Citus | shared | 50Gi | Bound | 50.0G | 1.2G |
+-----------------------------------+-------------------+--------------+--------+----------------------+-----------+----------+--------+--------+
The result looks something like
doc_ycsb_citus_2.log
## Show Summary
### Workload
YCSB SF=1
* Type: ycsb
* Duration: 21851s
* Code: 1773437788
* YCSB driver runs the experiment.
* This experiment compares run time and resource consumption of YCSB queries.
* Workload is 'A'.
* Number of rows to insert is 1000000.
* Ordering of inserts is hashed.
* Number of operations is 10000000.
* Batch size is ''.
* Target is based on multiples of '16384'.
* Factors for loading are [4].
* Factors for benchmarking are [4].
* Experiment uses bexhoma version 0.9.4.
* System metrics are monitored by a cluster-wide installation.
* Experiment is limited to DBMS ['Citus'].
* Import is handled by 8 processes (pods).
* Loading is fixed to cl-worker19.
* Benchmarking is fixed to cl-worker19.
* SUT is fixed to cl-worker14.
* Database is persisted to disk of type shared and size 50Gi. Persistent storage is removed at experiment start.
* Loading is tested with [64] threads, split into [8] pods.
* Benchmarking is tested with [64] threads, split into [1] pods.
* Benchmarking is run as [1] times the number of benchmarking pods.
* Experiment is run 2 times.
### Connections
* Citus-64-8-65536-1-1 uses docker image citusdata/citus:13.2.0-alpine
* RAM:541008474112
* CPU:AMD Opteron(tm) Processor 6378
* Cores:64
* host:5.15.0-164-generic
* node:cl-worker14
* disk:148646
* volume_size:50.0G
* volume_used:40.0M
* cpu_list:0-63
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* requests_cpu:4
* requests_memory:16Gi
* worker 0
* RAM:2164173209600
* CPU:INTEL(R) XEON(R) PLATINUM 8570
* Cores:224
* host:6.8.0-90-generic
* node:cl-worker36
* disk:1195264
* volume_size:50.0G
* volume_used:40.0M
* cpu_list:0-223
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 1
* RAM:540590817280
* CPU:AMD EPYC 7352 24-Core Processor
* Cores:96
* host:6.8.0-90-generic
* node:cl-worker23
* disk:1211148
* volume_size:50.0G
* volume_used:40.0M
* cpu_list:0-95
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 2
* RAM:540579303424
* CPU:AMD EPYC 7502 32-Core Processor
* Cores:128
* host:6.8.0-94-generic
* node:cl-worker22
* disk:378643
* volume_size:50.0G
* volume_used:40.0M
* cpu_list:0-127
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* eval_parameters
* code:1773437788
* BEXHOMA_REPLICAS:1
* BEXHOMA_SHARDS:48
* BEXHOMA_WORKERS:3
* Citus-64-8-65536-2-1 uses docker image citusdata/citus:13.2.0-alpine
* RAM:541008474112
* CPU:AMD Opteron(tm) Processor 6378
* Cores:64
* host:5.15.0-164-generic
* node:cl-worker14
* disk:148647
* volume_size:50.0G
* volume_used:40.0M
* cpu_list:0-63
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* requests_cpu:4
* requests_memory:16Gi
* worker 0
* RAM:2164173209600
* CPU:INTEL(R) XEON(R) PLATINUM 8570
* Cores:224
* host:6.8.0-90-generic
* node:cl-worker36
* disk:1195226
* volume_size:50.0G
* volume_used:2.3G
* cpu_list:0-223
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 1
* RAM:540590817280
* CPU:AMD EPYC 7352 24-Core Processor
* Cores:96
* host:6.8.0-90-generic
* node:cl-worker23
* disk:1211152
* volume_size:50.0G
* volume_used:2.3G
* cpu_list:0-95
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 2
* RAM:540579303424
* CPU:AMD EPYC 7502 32-Core Processor
* Cores:128
* host:6.8.0-94-generic
* node:cl-worker22
* disk:378848
* volume_size:50.0G
* volume_used:2.1G
* cpu_list:0-127
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* eval_parameters
* code:1773437788
* BEXHOMA_REPLICAS:1
* BEXHOMA_SHARDS:48
* BEXHOMA_WORKERS:3
### Loading
| DBMS | experiment_run | threads | target | pod_count | exceptions | [OVERALL].Throughput(ops/sec) | [OVERALL].RunTime(ms) | [INSERT].Return=OK | [INSERT].99thPercentileLatency(us) |
|:-----------------|-----------------:|----------:|---------:|------------:|-------------:|--------------------------------:|------------------------:|---------------------:|-------------------------------------:|
| Citus-64-8-65536 | 1 | 64 | 65536 | 8 | 0 | 1231.08 | 816384 | 1e+06 | 505535 |
### Execution
| DBMS | experiment_run | threads | target | pod_count | exceptions | [OVERALL].Throughput(ops/sec) | [OVERALL].RunTime(ms) | [READ].Return=OK | [READ].99thPercentileLatency(us) | [UPDATE].Return=OK | [UPDATE].99thPercentileLatency(us) |
|:---------------------|-----------------:|----------:|---------:|------------:|-------------:|--------------------------------:|------------------------:|-------------------:|-----------------------------------:|---------------------:|-------------------------------------:|
| Citus-64-8-65536-1-1 | 1 | 64 | 65536 | 1 | 0 | 1201.25 | 8.32469e+06 | 4.99792e+06 | 2869 | 5.00208e+06 | 1.08237e+06 |
| Citus-64-8-65536-2-1 | 2 | 64 | 65536 | 1 | 0 | 918.71 | 1.08848e+07 | 5.00327e+06 | 2935 | 4.99673e+06 | 1.37626e+06 |
### Workflow
#### Actual
* DBMS Citus-64-8-65536 - Pods [[1], [1]]
#### Planned
* DBMS Citus-64-8-65536 - Pods [[1], [1]]
### Monitoring
### Loading phase: SUT deployment
| DBMS | CPU [CPUs] | Max CPU | Max RAM [Gb] | Max RAM Cached [Gb] |
|:---------------------|-------------:|----------:|---------------:|----------------------:|
| Citus-64-8-65536-1-1 | 561.06 | 1.14 | 0.72 | 0.75 |
### Loading phase: component worker
| DBMS | CPU [CPUs] | Max CPU | Max RAM [Gb] | Max RAM Cached [Gb] |
|:---------------------|-------------:|----------:|---------------:|----------------------:|
| Citus-64-8-65536-1-1 | 440.42 | 0.83 | 3.39 | 6.11 |
### Loading phase: component loader
| DBMS | CPU [CPUs] | Max CPU | Max RAM [Gb] | Max RAM Cached [Gb] |
|:---------------------|-------------:|----------:|---------------:|----------------------:|
| Citus-64-8-65536-1-1 | 204.57 | 1.03 | 0.12 | 0.12 |
### Execution phase: SUT deployment
| DBMS | CPU [CPUs] | Max CPU | Max RAM [Gb] | Max RAM Cached [Gb] |
|:---------------------|-------------:|----------:|---------------:|----------------------:|
| Citus-64-8-65536-1-1 | 20.49 | 0.01 | 0.53 | 0.56 |
| Citus-64-8-65536-2-1 | 26.14 | 0 | 0.51 | 0.83 |
### Execution phase: component worker
| DBMS | CPU [CPUs] | Max CPU | Max RAM [Gb] | Max RAM Cached [Gb] |
|:---------------------|-------------:|----------:|---------------:|----------------------:|
| Citus-64-8-65536-1-1 | 5562.96 | 1.51 | 5.63 | 12 |
| Citus-64-8-65536-2-1 | 5844.37 | 1.56 | 5.34 | 11.9 |
### Execution phase: component benchmarker
| DBMS | CPU [CPUs] | Max CPU | Max RAM [Gb] | Max RAM Cached [Gb] |
|:---------------------|-------------:|----------:|---------------:|----------------------:|
| Citus-64-8-65536-1-1 | 1100.07 | 0.32 | 0.15 | 0.15 |
| Citus-64-8-65536-2-1 | 1150.36 | 0.27 | 0.15 | 0.16 |
### Tests
* TEST passed: Loading Phase: [OVERALL].Throughput(ops/sec) contains no 0 or NaN
* TEST passed: Execution Phase: [OVERALL].Throughput(ops/sec) contains no 0 or NaN
* TEST passed: Loading phase: SUT deployment contains no 0 or NaN in CPU [CPUs]
* TEST passed: Loading phase: component worker contains no 0 or NaN in CPU [CPUs]
* TEST passed: Loading phase: component loader contains no 0 or NaN in CPU [CPUs]
* TEST passed: Execution phase: SUT deployment contains no 0 or NaN in CPU [CPUs]
* TEST passed: Execution phase: component worker contains no 0 or NaN in CPU [CPUs]
* TEST passed: Execution phase: component benchmarker contains no 0 or NaN in CPU [CPUs]
* TEST passed: Workflow as planned
* TEST passed: Execution Phase: contains no FAILED column
YCSB Example Explained
Configuration of Bexhoma
In cluster.config there is a section:
'Citus': {
'loadData': 'psql -U postgres < {scriptname}',
'attachWorker': "psql -U postgres --command=\"SELECT * from master_add_node('{worker}.{service_sut}', 5432);\"",
'template': {
'version': '10.0.2',
'alias': 'General-B',
'docker_alias': 'GP-B',
'JDBC': {
'driver': "org.postgresql.Driver",
'auth': ["postgres", "password1234"],
'url': 'jdbc:postgresql://{serverip}:9091/postgres',#/{dbname}',
'jar': 'postgresql-42.5.0.jar'
}
},
'logfile': '/usr/local/data/logfile',
'datadir': '/var/lib/postgresql/data/',
'priceperhourdollar': 0.0,
},
where
loadData: This command is used to create the schemaJDBC: These infos are used to configure YCSB
Citus uses the PostgreSQL JDBC driver.
Schema SQL File
Before ingestion, we run a script to create and distribute the tables: https://github.com/Beuth-Erdelt/Benchmark-Experiment-Host-Manager/tree/master/experiments/ycsb/Citus/initschema-ycsb.sql
After ingestion, we run a script to check the distributions. The script also vacuums and analyzes the tables: https://github.com/Beuth-Erdelt/Benchmark-Experiment-Host-Manager/blob/master/experiments/ycsb/Citus/checkschema-ycsb.sql
Benchbase’s TPC-C
Before ingestion, we run a script to create and distribute the tables: https://github.com/Beuth-Erdelt/Benchmark-Experiment-Host-Manager/blob/master/experiments/benchbase/Citus/initschema-benchbase.sql
After ingestion, we run a script to check the distributions. The script also vacuums and analyzes the tables: https://github.com/Beuth-Erdelt/Benchmark-Experiment-Host-Manager/blob/master/experiments/benchbase/Citus/checkschema-benchbase.sql
Benchbase Simple Example
TPC-C is performed at 16 warehouses. The 16 threads of the client are split into a cascading sequence of 1 and 2 pods. Citus has 3 workers.
bexhoma benchbase \
-dbms Citus \
-sf 16 \
-xsd 5 \
-xtb 1024 \
-xnbf 16 \
-nbp 1,2 \
-nbt 16 \
-nw 3 \
-nwr 1 \
-nws 48 \
-ms $BEXHOMA_MS \
-tr \
-rnn $BEXHOMA_NODE_SUT -rnl $BEXHOMA_NODE_LOAD -rnb $BEXHOMA_NODE_BENCHMARK \
run &>$LOG_DIR/doc_benchbase_citus_1.log
Evaluate Results
doc_benchbase_citus_1.log
## Show Summary
### Workload
Benchbase Workload tpcc SF=16
* Type: benchbase
* Duration: 1824s
* Code: 1773459696
* Benchbase runs a TPC-C experiment.
* This experiment compares run time and resource consumption of Benchbase queries in different DBMS.
* Benchbase data is generated and loaded using several threads.
* Benchmark is 'tpcc'. Scaling factor is 16. Target is based on multiples of '1024'. Factors for benchmarking are [16]. Benchmarking runs for 5 minutes.
* Experiment uses bexhoma version 0.9.4.
* Experiment is limited to DBMS ['Citus'].
* Import is handled by 1 processes (pods).
* Loading is fixed to cl-worker19.
* Benchmarking is fixed to cl-worker19.
* SUT is fixed to cl-worker14.
* Loading is tested with [1] threads, split into [1] pods.
* Benchmarking is tested with [16] threads, split into [1, 2] pods.
* Benchmarking is run as [1] times the number of benchmarking pods.
* Experiment is run once.
### Connections
* Citus-1-1-1024-1 uses docker image citusdata/citus:13.2.0-alpine
* RAM:541008474112
* CPU:AMD Opteron(tm) Processor 6378
* Cores:64
* host:5.15.0-164-generic
* node:cl-worker14
* disk:148689
* cpu_list:0-63
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* requests_cpu:4
* requests_memory:16Gi
* worker 0
* RAM:2164173209600
* CPU:INTEL(R) XEON(R) PLATINUM 8570
* Cores:224
* host:6.8.0-90-generic
* node:cl-worker36
* disk:1196743
* cpu_list:0-223
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 1
* RAM:540579303424
* CPU:AMD EPYC 7502 32-Core Processor
* Cores:128
* host:6.8.0-94-generic
* node:cl-worker22
* disk:380161
* cpu_list:0-127
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 2
* RAM:540590817280
* CPU:AMD EPYC 7352 24-Core Processor
* Cores:96
* host:6.8.0-90-generic
* node:cl-worker23
* disk:1212406
* cpu_list:0-95
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* eval_parameters
* code:1773459696
* BEXHOMA_REPLICAS:1
* BEXHOMA_SHARDS:48
* BEXHOMA_WORKERS:3
* Citus-1-1-1024-2 uses docker image citusdata/citus:13.2.0-alpine
* RAM:541008474112
* CPU:AMD Opteron(tm) Processor 6378
* Cores:64
* host:5.15.0-164-generic
* node:cl-worker14
* disk:148707
* cpu_list:0-63
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* requests_cpu:4
* requests_memory:16Gi
* worker 0
* RAM:2164173209600
* CPU:INTEL(R) XEON(R) PLATINUM 8570
* Cores:224
* host:6.8.0-90-generic
* node:cl-worker36
* disk:1197127
* cpu_list:0-223
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 1
* RAM:540579303424
* CPU:AMD EPYC 7502 32-Core Processor
* Cores:128
* host:6.8.0-94-generic
* node:cl-worker22
* disk:380423
* cpu_list:0-127
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 2
* RAM:540590817280
* CPU:AMD EPYC 7352 24-Core Processor
* Cores:96
* host:6.8.0-90-generic
* node:cl-worker23
* disk:1212701
* cpu_list:0-95
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* eval_parameters
* code:1773459696
* BEXHOMA_REPLICAS:1
* BEXHOMA_SHARDS:48
* BEXHOMA_WORKERS:3
### Execution
#### Per Pod
| DBMS | experiment_run | terminals | target | client | child | time | num_errors | Throughput (requests/second) | Goodput (requests/second) | efficiency | Latency Distribution.95th Percentile Latency (microseconds) | Latency Distribution.Average Latency (microseconds) |
|:-------------------|-----------------:|------------:|---------:|---------:|--------:|-------:|-------------:|-------------------------------:|----------------------------:|-------------:|--------------------------------------------------------------:|------------------------------------------------------:|
| Citus-1-1-1024-1-1 | 1 | 16 | 16384 | 1 | 1 | 300 | 0 | 681.43 | 678.253 | 0 | 57348 | 23473 |
| Citus-1-1-1024-2-2 | 1 | 8 | 8192 | 2 | 1 | 300 | 1 | 338.527 | 335.57 | 0 | 55517 | 23625 |
| Citus-1-1-1024-2-1 | 1 | 8 | 8192 | 2 | 2 | 300 | 0 | 336.55 | 333.92 | 0 | 56490 | 23764 |
#### Aggregated Parallel
| DBMS | experiment_run | terminals | target | pod_count | time | num_errors | Throughput (requests/second) | Goodput (requests/second) | efficiency | Latency Distribution.95th Percentile Latency (microseconds) | Latency Distribution.Average Latency (microseconds) |
|:-----------------|-----------------:|------------:|---------:|------------:|-------:|-------------:|-------------------------------:|----------------------------:|-------------:|--------------------------------------------------------------:|------------------------------------------------------:|
| Citus-1-1-1024-1 | 1 | 16 | 16384 | 1 | 300 | 0 | 681.43 | 678.25 | 0 | 57348 | 23473 |
| Citus-1-1-1024-2 | 1 | 16 | 16384 | 2 | 300 | 1 | 675.08 | 669.49 | 0 | 56490 | 23694.5 |
### Workflow
#### Actual
* DBMS Citus-1-1-1024 - Pods [[1, 2]]
#### Planned
* DBMS Citus-1-1-1024 - Pods [[1, 2]]
### Loading
| DBMS | time_load | terminals | pods | Throughput [SF/h] |
|:-----------------|------------:|------------:|-------:|--------------------:|
| Citus-1-1-1024-1 | 202 | 1 | 1 | 285.149 |
| Citus-1-1-1024-2 | 202 | 1 | 2 | 285.149 |
### Tests
* TEST passed: Throughput (requests/second) contains no 0 or NaN
* TEST passed: Workflow as planned
Benchbase More Complex
TPC-C is performed at 128 warehouses. The 64 threads of the client are split into a cascading sequence of 1,2,4 and 8 pods. At first, we remove old PVC:
kubectl delete pvc bexhoma-storage-citus-benchbase-128
kubectl delete pvc bxw-bexhoma-worker-citus-benchbase-128-0
kubectl delete pvc bxw-bexhoma-worker-citus-benchbase-128-1
kubectl delete pvc bxw-bexhoma-worker-citus-benchbase-128-2
kubectl delete pvc bxw-bexhoma-worker-citus-benchbase-128-3
The benchmark is run via
bexhoma benchbase \
-dbms Citus \
-sf 128 \
-xsd 20 \
-xtb 1024 \
-xnbf 16 \
-nbp 1,2,4,8 \
-nbt 64 \
-nw 4 \
-nwr 1 \
-nws 48 \
-m \
-mc \
-ms $BEXHOMA_MS \
-tr \
-rss 100Gi \
-rst $BEXHOMA_STORAGE_CLASS \
-rnn $BEXHOMA_NODE_SUT -rnl $BEXHOMA_NODE_LOAD -rnb $BEXHOMA_NODE_BENCHMARK \
run &>$LOG_DIR/doc_benchbase_citus_2.log
Evaluate Results
doc_benchbase_citus_2.log
## Show Summary
### Workload
Benchbase Workload tpcc SF=128
* Type: benchbase
* Duration: 8963s
* Code: 1773461533
* Benchbase runs a TPC-C experiment.
* This experiment compares run time and resource consumption of Benchbase queries in different DBMS.
* Benchbase data is generated and loaded using several threads.
* Benchmark is 'tpcc'. Scaling factor is 128. Target is based on multiples of '1024'. Factors for benchmarking are [16]. Benchmarking runs for 20 minutes.
* Experiment uses bexhoma version 0.9.4.
* System metrics are monitored by a cluster-wide installation.
* Experiment is limited to DBMS ['Citus'].
* Import is handled by 1 processes (pods).
* Loading is fixed to cl-worker19.
* Benchmarking is fixed to cl-worker19.
* SUT is fixed to cl-worker14.
* Database is persisted to disk of type shared and size 100Gi. Persistent storage is removed at experiment start.
* Loading is tested with [1] threads, split into [1] pods.
* Benchmarking is tested with [64] threads, split into [1, 2, 4, 8] pods.
* Benchmarking is run as [1] times the number of benchmarking pods.
* Experiment is run once.
### Connections
* Citus-1-1-1024-1 uses docker image citusdata/citus:13.2.0-alpine
* RAM:541008474112
* CPU:AMD Opteron(tm) Processor 6378
* Cores:64
* host:5.15.0-164-generic
* node:cl-worker14
* disk:148648
* volume_size:100.0G
* volume_used:40.0M
* cpu_list:0-63
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* requests_cpu:4
* requests_memory:16Gi
* worker 0
* RAM:2164173209600
* CPU:INTEL(R) XEON(R) PLATINUM 8570
* Cores:224
* host:6.8.0-90-generic
* node:cl-worker36
* disk:1195254
* volume_size:100.0G
* volume_used:6.3G
* cpu_list:0-223
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 1
* RAM:540579303424
* CPU:AMD EPYC 7502 32-Core Processor
* Cores:128
* host:6.8.0-94-generic
* node:cl-worker22
* disk:378908
* volume_size:100.0G
* volume_used:6.3G
* cpu_list:0-127
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 2
* RAM:540590817280
* CPU:AMD EPYC 7352 24-Core Processor
* Cores:96
* host:6.8.0-90-generic
* node:cl-worker23
* disk:1211162
* volume_size:100.0G
* volume_used:40.0M
* cpu_list:0-95
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 3
* RAM:1077382688768
* CPU:AMD EPYC 7742 64-Core Processor
* Cores:256
* host:6.8.0-1044-nvidia
* node:cl-worker28
* disk:1324218
* volume_size:100.0G
* volume_used:6.3G
* cpu_list:0-255
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* eval_parameters
* code:1773461533
* BEXHOMA_REPLICAS:1
* BEXHOMA_SHARDS:48
* BEXHOMA_WORKERS:4
* Citus-1-1-1024-2 uses docker image citusdata/citus:13.2.0-alpine
* RAM:541008474112
* CPU:AMD Opteron(tm) Processor 6378
* Cores:64
* host:5.15.0-164-generic
* node:cl-worker14
* disk:148648
* volume_size:100.0G
* volume_used:56.0M
* cpu_list:0-63
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* requests_cpu:4
* requests_memory:16Gi
* worker 0
* RAM:2164173209600
* CPU:INTEL(R) XEON(R) PLATINUM 8570
* Cores:224
* host:6.8.0-90-generic
* node:cl-worker36
* disk:1195256
* volume_size:100.0G
* volume_used:9.6G
* cpu_list:0-223
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 1
* RAM:540579303424
* CPU:AMD EPYC 7502 32-Core Processor
* Cores:128
* host:6.8.0-94-generic
* node:cl-worker22
* disk:378934
* volume_size:100.0G
* volume_used:7.2G
* cpu_list:0-127
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 2
* RAM:540590817280
* CPU:AMD EPYC 7352 24-Core Processor
* Cores:96
* host:6.8.0-90-generic
* node:cl-worker23
* disk:1211163
* volume_size:100.0G
* volume_used:6.5G
* cpu_list:0-95
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 3
* RAM:1077382688768
* CPU:AMD EPYC 7742 64-Core Processor
* Cores:256
* host:6.8.0-1044-nvidia
* node:cl-worker28
* disk:1324219
* volume_size:100.0G
* volume_used:7.6G
* cpu_list:0-255
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* eval_parameters
* code:1773461533
* BEXHOMA_REPLICAS:1
* BEXHOMA_SHARDS:48
* BEXHOMA_WORKERS:4
* Citus-1-1-1024-3 uses docker image citusdata/citus:13.2.0-alpine
* RAM:541008474112
* CPU:AMD Opteron(tm) Processor 6378
* Cores:64
* host:5.15.0-164-generic
* node:cl-worker14
* disk:148648
* volume_size:100.0G
* volume_used:56.0M
* cpu_list:0-63
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* requests_cpu:4
* requests_memory:16Gi
* worker 0
* RAM:2164173209600
* CPU:INTEL(R) XEON(R) PLATINUM 8570
* Cores:224
* host:6.8.0-90-generic
* node:cl-worker36
* disk:1195256
* volume_size:100.0G
* volume_used:9.6G
* cpu_list:0-223
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 1
* RAM:540579303424
* CPU:AMD EPYC 7502 32-Core Processor
* Cores:128
* host:6.8.0-94-generic
* node:cl-worker22
* disk:378865
* volume_size:100.0G
* volume_used:7.2G
* cpu_list:0-127
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 2
* RAM:540590817280
* CPU:AMD EPYC 7352 24-Core Processor
* Cores:96
* host:6.8.0-90-generic
* node:cl-worker23
* disk:1211163
* volume_size:100.0G
* volume_used:6.5G
* cpu_list:0-95
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 3
* RAM:1077382688768
* CPU:AMD EPYC 7742 64-Core Processor
* Cores:256
* host:6.8.0-1044-nvidia
* node:cl-worker28
* disk:1324219
* volume_size:100.0G
* volume_used:7.6G
* cpu_list:0-255
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* eval_parameters
* code:1773461533
* BEXHOMA_REPLICAS:1
* BEXHOMA_SHARDS:48
* BEXHOMA_WORKERS:4
* Citus-1-1-1024-4 uses docker image citusdata/citus:13.2.0-alpine
* RAM:541008474112
* CPU:AMD Opteron(tm) Processor 6378
* Cores:64
* host:5.15.0-164-generic
* node:cl-worker14
* disk:148649
* volume_size:100.0G
* volume_used:56.0M
* cpu_list:0-63
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* requests_cpu:4
* requests_memory:16Gi
* worker 0
* RAM:2164173209600
* CPU:INTEL(R) XEON(R) PLATINUM 8570
* Cores:224
* host:6.8.0-90-generic
* node:cl-worker36
* disk:1195258
* volume_size:100.0G
* volume_used:12.7G
* cpu_list:0-223
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 1
* RAM:540579303424
* CPU:AMD EPYC 7502 32-Core Processor
* Cores:128
* host:6.8.0-94-generic
* node:cl-worker22
* disk:378900
* volume_size:100.0G
* volume_used:8.9G
* cpu_list:0-127
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 2
* RAM:540590817280
* CPU:AMD EPYC 7352 24-Core Processor
* Cores:96
* host:6.8.0-90-generic
* node:cl-worker23
* disk:1211164
* volume_size:100.0G
* volume_used:8.1G
* cpu_list:0-95
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 3
* RAM:1077382688768
* CPU:AMD EPYC 7742 64-Core Processor
* Cores:256
* host:6.8.0-1044-nvidia
* node:cl-worker28
* disk:1324212
* volume_size:100.0G
* volume_used:8.9G
* cpu_list:0-255
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* eval_parameters
* code:1773461533
* BEXHOMA_REPLICAS:1
* BEXHOMA_SHARDS:48
* BEXHOMA_WORKERS:4
### Execution
#### Per Pod
| DBMS | experiment_run | terminals | target | client | child | time | num_errors | Throughput (requests/second) | Goodput (requests/second) | efficiency | Latency Distribution.95th Percentile Latency (microseconds) | Latency Distribution.Average Latency (microseconds) |
|:-------------------|-----------------:|------------:|---------:|---------:|--------:|-------:|-------------:|-------------------------------:|----------------------------:|-------------:|--------------------------------------------------------------:|------------------------------------------------------:|
| Citus-1-1-1024-1-1 | 1 | 64 | 16384 | 1 | 1 | 1200 | 0 | 423.758 | 421.972 | 0 | 647736 | 150977 |
| Citus-1-1-1024-2-2 | 1 | 32 | 8192 | 2 | 1 | 1200 | 0 | 196.626 | 195.442 | 0 | 707660 | 162723 |
| Citus-1-1-1024-2-1 | 1 | 32 | 8192 | 2 | 2 | 1200 | 2 | 195.622 | 194.374 | 0 | 709605 | 163559 |
| Citus-1-1-1024-3-2 | 1 | 16 | 4096 | 3 | 1 | 1200 | 1 | 66.6283 | 66.0692 | 0 | 1.03021e+06 | 240071 |
| Citus-1-1-1024-3-4 | 1 | 16 | 4096 | 3 | 2 | 1200 | 0 | 67.0892 | 66.54 | 0 | 1.02141e+06 | 238413 |
| Citus-1-1-1024-3-1 | 1 | 16 | 4096 | 3 | 3 | 1200 | 0 | 66.9008 | 66.365 | 0 | 1.02947e+06 | 239112 |
| Citus-1-1-1024-3-3 | 1 | 16 | 4096 | 3 | 4 | 1200 | 1 | 66.5533 | 66.045 | 0 | 1.02361e+06 | 240309 |
| Citus-1-1-1024-4-5 | 1 | 8 | 2048 | 4 | 1 | 1200 | 0 | 16.6692 | 16.5292 | 0 | 1.97172e+06 | 479661 |
| Citus-1-1-1024-4-3 | 1 | 8 | 2048 | 4 | 2 | 1200 | 0 | 16.3 | 16.1567 | 0 | 2.03328e+06 | 490344 |
| Citus-1-1-1024-4-8 | 1 | 8 | 2048 | 4 | 3 | 1200 | 0 | 16.0483 | 15.9242 | 0 | 2.09925e+06 | 498107 |
| Citus-1-1-1024-4-2 | 1 | 8 | 2048 | 4 | 4 | 1200 | 0 | 16.6633 | 16.5217 | 0 | 1.97211e+06 | 479817 |
| Citus-1-1-1024-4-1 | 1 | 8 | 2048 | 4 | 5 | 1200 | 0 | 16.4442 | 16.2975 | 0 | 2.04142e+06 | 486196 |
| Citus-1-1-1024-4-6 | 1 | 8 | 2048 | 4 | 6 | 1200 | 0 | 16.3858 | 16.2617 | 0 | 2.05619e+06 | 488125 |
| Citus-1-1-1024-4-7 | 1 | 8 | 2048 | 4 | 7 | 1200 | 0 | 16.4642 | 16.3392 | 0 | 2.02423e+06 | 485593 |
| Citus-1-1-1024-4-4 | 1 | 8 | 2048 | 4 | 8 | 1200 | 0 | 16.0517 | 15.9317 | 0 | 2.13565e+06 | 498209 |
#### Aggregated Parallel
| DBMS | experiment_run | terminals | target | pod_count | time | num_errors | Throughput (requests/second) | Goodput (requests/second) | efficiency | Latency Distribution.95th Percentile Latency (microseconds) | Latency Distribution.Average Latency (microseconds) |
|:-----------------|-----------------:|------------:|---------:|------------:|-------:|-------------:|-------------------------------:|----------------------------:|-------------:|--------------------------------------------------------------:|------------------------------------------------------:|
| Citus-1-1-1024-1 | 1 | 64 | 16384 | 1 | 1200 | 0 | 423.76 | 421.97 | 0 | 647736 | 150977 |
| Citus-1-1-1024-2 | 1 | 64 | 16384 | 2 | 1200 | 2 | 392.25 | 389.82 | 0 | 709605 | 163141 |
| Citus-1-1-1024-3 | 1 | 64 | 16384 | 4 | 1200 | 2 | 267.17 | 265.02 | 0 | 1.03021e+06 | 239476 |
| Citus-1-1-1024-4 | 1 | 64 | 16384 | 8 | 1200 | 0 | 131.03 | 129.96 | 0 | 2.13565e+06 | 488256 |
### Workflow
#### Actual
* DBMS Citus-1-1-1024 - Pods [[1, 2, 4, 8]]
#### Planned
* DBMS Citus-1-1-1024 - Pods [[1, 2, 4, 8]]
### Loading
| DBMS | time_load | terminals | pods | Throughput [SF/h] |
|:-----------------|------------:|------------:|-------:|--------------------:|
| Citus-1-1-1024-1 | 2349 | 1 | 1 | 196.169 |
| Citus-1-1-1024-2 | 2349 | 1 | 2 | 196.169 |
| Citus-1-1-1024-3 | 2349 | 1 | 4 | 196.169 |
| Citus-1-1-1024-4 | 2349 | 1 | 8 | 196.169 |
### Monitoring
### Loading phase: SUT deployment
| DBMS | CPU [CPUs] | Max CPU | Max RAM [Gb] | Max RAM Cached [Gb] |
|:-----------------|-------------:|----------:|---------------:|----------------------:|
| Citus-1-1-1024-1 | 4160.06 | 2.86 | 0.99 | 1.02 |
| Citus-1-1-1024-2 | 4160.06 | 2.86 | 0.99 | 1.02 |
| Citus-1-1-1024-3 | 4160.06 | 2.86 | 0.99 | 1.02 |
| Citus-1-1-1024-4 | 4160.06 | 2.86 | 0.99 | 1.02 |
### Loading phase: component worker
| DBMS | CPU [CPUs] | Max CPU | Max RAM [Gb] | Max RAM Cached [Gb] |
|:-----------------|-------------:|----------:|---------------:|----------------------:|
| Citus-1-1-1024-1 | 3406.88 | 2.67 | 14.79 | 44.31 |
| Citus-1-1-1024-2 | 3406.88 | 2.67 | 14.79 | 44.31 |
| Citus-1-1-1024-3 | 3406.88 | 2.67 | 14.79 | 44.31 |
| Citus-1-1-1024-4 | 3406.88 | 2.67 | 14.79 | 44.31 |
### Loading phase: component loader
| DBMS | CPU [CPUs] | Max CPU | Max RAM [Gb] | Max RAM Cached [Gb] |
|:-----------------|-------------:|----------:|---------------:|----------------------:|
| Citus-1-1-1024-1 | 8171.85 | 12.94 | 0.3 | 0.3 |
| Citus-1-1-1024-2 | 8171.85 | 12.94 | 0.3 | 0.3 |
| Citus-1-1-1024-3 | 8171.85 | 12.94 | 0.3 | 0.3 |
| Citus-1-1-1024-4 | 8171.85 | 12.94 | 0.3 | 0.3 |
### Execution phase: SUT deployment
| DBMS | CPU [CPUs] | Max CPU | Max RAM [Gb] | Max RAM Cached [Gb] |
|:-----------------|-------------:|----------:|---------------:|----------------------:|
| Citus-1-1-1024-1 | 4493.97 | 6.57 | 0.83 | 0.88 |
| Citus-1-1-1024-2 | 4191.79 | 5.43 | 0.83 | 0.9 |
| Citus-1-1-1024-3 | 2619.02 | 3.45 | 0.83 | 0.93 |
| Citus-1-1-1024-4 | 1111.79 | 1.8 | 0.83 | 0.92 |
### Execution phase: component worker
| DBMS | CPU [CPUs] | Max CPU | Max RAM [Gb] | Max RAM Cached [Gb] |
|:-----------------|-------------:|----------:|---------------:|----------------------:|
| Citus-1-1-1024-1 | 2331.2 | 3.05 | 17.51 | 51.4 |
| Citus-1-1-1024-2 | 2150.91 | 2.55 | 17.96 | 53.27 |
| Citus-1-1-1024-3 | 1620.56 | 1.84 | 18.12 | 54.54 |
| Citus-1-1-1024-4 | 826.63 | 1.11 | 18.05 | 54.59 |
### Execution phase: component benchmarker
| DBMS | CPU [CPUs] | Max CPU | Max RAM [Gb] | Max RAM Cached [Gb] |
|:-----------------|-------------:|----------:|---------------:|----------------------:|
| Citus-1-1-1024-1 | 807.47 | 1.03 | 0.4 | 0.4 |
| Citus-1-1-1024-2 | 807.47 | 0.84 | 0.4 | 0.4 |
| Citus-1-1-1024-3 | 597.82 | 1.18 | 0.33 | 0.33 |
| Citus-1-1-1024-4 | 487.97 | 0.48 | 0.25 | 0.25 |
### Tests
* TEST passed: Throughput (requests/second) contains no 0 or NaN
* TEST passed: Loading phase: SUT deployment contains no 0 or NaN in CPU [CPUs]
* TEST passed: Loading phase: component worker contains no 0 or NaN in CPU [CPUs]
* TEST passed: Loading phase: component loader contains no 0 or NaN in CPU [CPUs]
* TEST passed: Execution phase: SUT deployment contains no 0 or NaN in CPU [CPUs]
* TEST passed: Execution phase: component worker contains no 0 or NaN in CPU [CPUs]
* TEST passed: Execution phase: component benchmarker contains no 0 or NaN in CPU [CPUs]
* TEST passed: Workflow as planned
Benchbase Realistic
We run a benchmark with
PVCs for persistent database
monitoring
a sensible number of workers (4)
a sensible size (128 warehouses)
a sensible number of threads (1024)
suitable splittings (1x1280, 2x640, 5x256, 10x128)
logging the state every 30 seconds
a realistic target (4096 transactions per second)
a realistic duration (20 minutes)
a repetition (
-ncis 2)keying and thinking tima activated (
-xkey)
Note that the number of threads for each pod is a multiple of the number of warehouses. At start, Benchbase assigns each thread to a fixed warehouse. This way, we distribute the threads equally to the warehouses. Each thread also gets assigned a fixed range of districts per warehouse. Please also note, that this is not compliant to the TPC-C specifications, which state: For each active warehouse in the database, the SUT must accept requests for transactions from a population of 10 terminals.
bexhoma benchbase \
-dbms Citus \
-sf 128 \
-xsd 20 \
-xtb 1024 \
-xnbf 4 \
-nc 2 \
-nbp 1,2,5,10 \
-nbt 1280 \
-nw 4 \
-nwr 1 \
-nws 48 \
-xkey \
-xli 30 \
-m \
-mc \
-ms $BEXHOMA_MS \
-tr \
-rss 100Gi \
-rst $BEXHOMA_STORAGE_CLASS \
-rnn $BEXHOMA_NODE_SUT -rnl $BEXHOMA_NODE_LOAD -rnb $BEXHOMA_NODE_BENCHMARK \
run &>$LOG_DIR/doc_benchbase_citus_3.log
Evaluate Results
doc_benchbase_citus_3.log
## Show Summary
### Workload
Benchbase Workload tpcc SF=128
* Type: benchbase
* Duration: 5930s
* Code: 1773470555
* Benchbase runs a TPC-C experiment.
* This experiment compares run time and resource consumption of Benchbase queries in different DBMS.
* Benchbase data is generated and loaded using several threads.
* Benchmark is 'tpcc'. Scaling factor is 128. Target is based on multiples of '1024'. Factors for benchmarking are [10]. Benchmarking has keying and thinking times activated. Benchmarking runs for 20 minutes.
* Experiment uses bexhoma version 0.9.4.
* System metrics are monitored by a cluster-wide installation.
* Experiment is limited to DBMS ['Citus'].
* Import is handled by 1 processes (pods).
* Loading is fixed to cl-worker19.
* Benchmarking is fixed to cl-worker19.
* SUT is fixed to cl-worker14.
* Database is persisted to disk of type shared and size 100Gi.
* Loading is tested with [1] threads, split into [1] pods.
* Benchmarking is tested with [1280] threads, split into [1, 2, 5, 10] pods.
* Benchmarking is run as [1] times the number of benchmarking pods.
* Experiment is run 2 times.
### Connections
* Citus-1-1-1024-1-1 uses docker image citusdata/citus:13.2.0-alpine
* RAM:541008474112
* CPU:AMD Opteron(tm) Processor 6378
* Cores:64
* host:5.15.0-164-generic
* node:cl-worker14
* disk:148649
* volume_size:100.0G
* volume_used:104.0M
* cpu_list:0-63
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* requests_cpu:4
* requests_memory:16Gi
* worker 0
* RAM:2164173209600
* CPU:INTEL(R) XEON(R) PLATINUM 8570
* Cores:224
* host:6.8.0-90-generic
* node:cl-worker36
* disk:1195270
* volume_size:100.0G
* volume_used:12.7G
* cpu_list:0-223
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 1
* RAM:540590817280
* CPU:AMD EPYC 7352 24-Core Processor
* Cores:96
* host:6.8.0-90-generic
* node:cl-worker23
* disk:1211165
* volume_size:100.0G
* volume_used:9.0G
* cpu_list:0-95
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 2
* RAM:540579303424
* CPU:AMD EPYC 7502 32-Core Processor
* Cores:128
* host:6.8.0-94-generic
* node:cl-worker22
* disk:378950
* volume_size:100.0G
* volume_used:8.2G
* cpu_list:0-127
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 3
* RAM:1081649823744
* CPU:AMD EPYC 7453 28-Core Processor
* Cores:56
* host:6.8.0-90-generic
* node:cl-worker34
* disk:305885
* volume_size:100.0G
* volume_used:8.9G
* cpu_list:0-55
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* eval_parameters
* code:1773470555
* BEXHOMA_REPLICAS:1
* BEXHOMA_SHARDS:48
* BEXHOMA_WORKERS:4
* Citus-1-1-1024-1-2 uses docker image citusdata/citus:13.2.0-alpine
* RAM:541008474112
* CPU:AMD Opteron(tm) Processor 6378
* Cores:64
* host:5.15.0-164-generic
* node:cl-worker14
* disk:148649
* volume_size:100.0G
* volume_used:104.0M
* cpu_list:0-63
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* requests_cpu:4
* requests_memory:16Gi
* worker 0
* RAM:2164173209600
* CPU:INTEL(R) XEON(R) PLATINUM 8570
* Cores:224
* host:6.8.0-90-generic
* node:cl-worker36
* disk:1195272
* volume_size:100.0G
* volume_used:12.7G
* cpu_list:0-223
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 1
* RAM:540590817280
* CPU:AMD EPYC 7352 24-Core Processor
* Cores:96
* host:6.8.0-90-generic
* node:cl-worker23
* disk:1211166
* volume_size:100.0G
* volume_used:9.0G
* cpu_list:0-95
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 2
* RAM:540579303424
* CPU:AMD EPYC 7502 32-Core Processor
* Cores:128
* host:6.8.0-94-generic
* node:cl-worker22
* disk:378878
* volume_size:100.0G
* volume_used:8.2G
* cpu_list:0-127
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 3
* RAM:1081649823744
* CPU:AMD EPYC 7453 28-Core Processor
* Cores:56
* host:6.8.0-90-generic
* node:cl-worker34
* disk:305873
* volume_size:100.0G
* volume_used:8.9G
* cpu_list:0-55
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* eval_parameters
* code:1773470555
* BEXHOMA_REPLICAS:1
* BEXHOMA_SHARDS:48
* BEXHOMA_WORKERS:4
* Citus-1-1-1024-1-3 uses docker image citusdata/citus:13.2.0-alpine
* RAM:541008474112
* CPU:AMD Opteron(tm) Processor 6378
* Cores:64
* host:5.15.0-164-generic
* node:cl-worker14
* disk:148649
* volume_size:100.0G
* volume_used:104.0M
* cpu_list:0-63
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* requests_cpu:4
* requests_memory:16Gi
* worker 0
* RAM:2164173209600
* CPU:INTEL(R) XEON(R) PLATINUM 8570
* Cores:224
* host:6.8.0-90-generic
* node:cl-worker36
* disk:1195272
* volume_size:100.0G
* volume_used:12.7G
* cpu_list:0-223
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 1
* RAM:540590817280
* CPU:AMD EPYC 7352 24-Core Processor
* Cores:96
* host:6.8.0-90-generic
* node:cl-worker23
* disk:1211166
* volume_size:100.0G
* volume_used:9.0G
* cpu_list:0-95
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 2
* RAM:540579303424
* CPU:AMD EPYC 7502 32-Core Processor
* Cores:128
* host:6.8.0-94-generic
* node:cl-worker22
* disk:378878
* volume_size:100.0G
* volume_used:8.2G
* cpu_list:0-127
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 3
* RAM:1081649823744
* CPU:AMD EPYC 7453 28-Core Processor
* Cores:56
* host:6.8.0-90-generic
* node:cl-worker34
* disk:305885
* volume_size:100.0G
* volume_used:8.9G
* cpu_list:0-55
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* eval_parameters
* code:1773470555
* BEXHOMA_REPLICAS:1
* BEXHOMA_SHARDS:48
* BEXHOMA_WORKERS:4
* Citus-1-1-1024-1-4 uses docker image citusdata/citus:13.2.0-alpine
* RAM:541008474112
* CPU:AMD Opteron(tm) Processor 6378
* Cores:64
* host:5.15.0-164-generic
* node:cl-worker14
* disk:148649
* volume_size:100.0G
* volume_used:104.0M
* cpu_list:0-63
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* requests_cpu:4
* requests_memory:16Gi
* worker 0
* RAM:2164173209600
* CPU:INTEL(R) XEON(R) PLATINUM 8570
* Cores:224
* host:6.8.0-90-generic
* node:cl-worker36
* disk:1195272
* volume_size:100.0G
* volume_used:12.7G
* cpu_list:0-223
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 1
* RAM:540590817280
* CPU:AMD EPYC 7352 24-Core Processor
* Cores:96
* host:6.8.0-90-generic
* node:cl-worker23
* disk:1211166
* volume_size:100.0G
* volume_used:9.0G
* cpu_list:0-95
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 2
* RAM:540579303424
* CPU:AMD EPYC 7502 32-Core Processor
* Cores:128
* host:6.8.0-94-generic
* node:cl-worker22
* disk:378890
* volume_size:100.0G
* volume_used:8.2G
* cpu_list:0-127
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 3
* RAM:1081649823744
* CPU:AMD EPYC 7453 28-Core Processor
* Cores:56
* host:6.8.0-90-generic
* node:cl-worker34
* disk:305904
* volume_size:100.0G
* volume_used:8.9G
* cpu_list:0-55
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* eval_parameters
* code:1773470555
* BEXHOMA_REPLICAS:1
* BEXHOMA_SHARDS:48
* BEXHOMA_WORKERS:4
* Citus-1-1-1024-2-1 uses docker image citusdata/citus:13.2.0-alpine
* RAM:541008474112
* CPU:AMD Opteron(tm) Processor 6378
* Cores:64
* host:5.15.0-164-generic
* node:cl-worker14
* disk:148649
* volume_size:100.0G
* volume_used:104.0M
* cpu_list:0-63
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* requests_cpu:4
* requests_memory:16Gi
* worker 0
* RAM:2164173209600
* CPU:INTEL(R) XEON(R) PLATINUM 8570
* Cores:224
* host:6.8.0-90-generic
* node:cl-worker36
* disk:1195273
* volume_size:100.0G
* volume_used:12.3G
* cpu_list:0-223
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 1
* RAM:540590817280
* CPU:AMD EPYC 7352 24-Core Processor
* Cores:96
* host:6.8.0-90-generic
* node:cl-worker23
* disk:1211166
* volume_size:100.0G
* volume_used:8.6G
* cpu_list:0-95
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 2
* RAM:540579303424
* CPU:AMD EPYC 7502 32-Core Processor
* Cores:128
* host:6.8.0-94-generic
* node:cl-worker22
* disk:378910
* volume_size:100.0G
* volume_used:7.7G
* cpu_list:0-127
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 3
* RAM:1077382688768
* CPU:AMD EPYC 7742 64-Core Processor
* Cores:256
* host:6.8.0-1044-nvidia
* node:cl-worker28
* disk:1324217
* volume_size:100.0G
* volume_used:8.9G
* cpu_list:0-255
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* eval_parameters
* code:1773470555
* BEXHOMA_REPLICAS:1
* BEXHOMA_SHARDS:48
* BEXHOMA_WORKERS:4
* Citus-1-1-1024-2-2 uses docker image citusdata/citus:13.2.0-alpine
* RAM:541008474112
* CPU:AMD Opteron(tm) Processor 6378
* Cores:64
* host:5.15.0-164-generic
* node:cl-worker14
* disk:148649
* volume_size:100.0G
* volume_used:104.0M
* cpu_list:0-63
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* requests_cpu:4
* requests_memory:16Gi
* worker 0
* RAM:2164173209600
* CPU:INTEL(R) XEON(R) PLATINUM 8570
* Cores:224
* host:6.8.0-90-generic
* node:cl-worker36
* disk:1195275
* volume_size:100.0G
* volume_used:12.3G
* cpu_list:0-223
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 1
* RAM:540590817280
* CPU:AMD EPYC 7352 24-Core Processor
* Cores:96
* host:6.8.0-90-generic
* node:cl-worker23
* disk:1211167
* volume_size:100.0G
* volume_used:8.6G
* cpu_list:0-95
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 2
* RAM:540579303424
* CPU:AMD EPYC 7502 32-Core Processor
* Cores:128
* host:6.8.0-94-generic
* node:cl-worker22
* disk:378937
* volume_size:100.0G
* volume_used:7.7G
* cpu_list:0-127
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 3
* RAM:1077382688768
* CPU:AMD EPYC 7742 64-Core Processor
* Cores:256
* host:6.8.0-1044-nvidia
* node:cl-worker28
* disk:1324219
* volume_size:100.0G
* volume_used:8.9G
* cpu_list:0-255
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* eval_parameters
* code:1773470555
* BEXHOMA_REPLICAS:1
* BEXHOMA_SHARDS:48
* BEXHOMA_WORKERS:4
* Citus-1-1-1024-2-3 uses docker image citusdata/citus:13.2.0-alpine
* RAM:541008474112
* CPU:AMD Opteron(tm) Processor 6378
* Cores:64
* host:5.15.0-164-generic
* node:cl-worker14
* disk:148649
* volume_size:100.0G
* volume_used:104.0M
* cpu_list:0-63
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* requests_cpu:4
* requests_memory:16Gi
* worker 0
* RAM:2164173209600
* CPU:INTEL(R) XEON(R) PLATINUM 8570
* Cores:224
* host:6.8.0-90-generic
* node:cl-worker36
* disk:1195275
* volume_size:100.0G
* volume_used:12.3G
* cpu_list:0-223
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 1
* RAM:540590817280
* CPU:AMD EPYC 7352 24-Core Processor
* Cores:96
* host:6.8.0-90-generic
* node:cl-worker23
* disk:1211167
* volume_size:100.0G
* volume_used:8.6G
* cpu_list:0-95
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 2
* RAM:540579303424
* CPU:AMD EPYC 7502 32-Core Processor
* Cores:128
* host:6.8.0-94-generic
* node:cl-worker22
* disk:378936
* volume_size:100.0G
* volume_used:7.7G
* cpu_list:0-127
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 3
* RAM:1077382688768
* CPU:AMD EPYC 7742 64-Core Processor
* Cores:256
* host:6.8.0-1044-nvidia
* node:cl-worker28
* disk:1324219
* volume_size:100.0G
* volume_used:8.9G
* cpu_list:0-255
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* eval_parameters
* code:1773470555
* BEXHOMA_REPLICAS:1
* BEXHOMA_SHARDS:48
* BEXHOMA_WORKERS:4
* Citus-1-1-1024-2-4 uses docker image citusdata/citus:13.2.0-alpine
* RAM:541008474112
* CPU:AMD Opteron(tm) Processor 6378
* Cores:64
* host:5.15.0-164-generic
* node:cl-worker14
* disk:148649
* volume_size:100.0G
* volume_used:104.0M
* cpu_list:0-63
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* requests_cpu:4
* requests_memory:16Gi
* worker 0
* RAM:2164173209600
* CPU:INTEL(R) XEON(R) PLATINUM 8570
* Cores:224
* host:6.8.0-90-generic
* node:cl-worker36
* disk:1195276
* volume_size:100.0G
* volume_used:12.3G
* cpu_list:0-223
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 1
* RAM:540590817280
* CPU:AMD EPYC 7352 24-Core Processor
* Cores:96
* host:6.8.0-90-generic
* node:cl-worker23
* disk:1211167
* volume_size:100.0G
* volume_used:8.6G
* cpu_list:0-95
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 2
* RAM:540579303424
* CPU:AMD EPYC 7502 32-Core Processor
* Cores:128
* host:6.8.0-94-generic
* node:cl-worker22
* disk:378948
* volume_size:100.0G
* volume_used:7.7G
* cpu_list:0-127
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* worker 3
* RAM:1077382688768
* CPU:AMD EPYC 7742 64-Core Processor
* Cores:256
* host:6.8.0-1044-nvidia
* node:cl-worker28
* disk:1324219
* volume_size:100.0G
* volume_used:8.9G
* cpu_list:0-255
python : C:\Users\Patrick\eclipse-workspace\Benchmark-Experiment-Host-Manager\bexhoma\experiments.py:4562: FutureWarning:
Downcasting object dtype arrays on .fillna, .ffill, .bfill is deprecated and will change in a future version. Call
result.infer_objects(copy=False) instead. To opt-in to the future behavior, set `pd.set_option('future.no_silent_downcasting',
True)`
In Zeile:1 Zeichen:1
+ python benchbase.py -ms 1 -tr `
+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ CategoryInfo : NotSpecified: (C:\Users\Patric...asting', True)`:String) [], RemoteException
+ FullyQualifiedErrorId : NativeCommandError
df.fillna(0, inplace=True)
* args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
* eval_parameters
* code:1773470555
* BEXHOMA_REPLICAS:1
* BEXHOMA_SHARDS:48
* BEXHOMA_WORKERS:4
### Execution
#### Per Pod
| DBMS | experiment_run | terminals | target | client | child | time | num_errors | Throughput (requests/second) | Goodput (requests/second) | efficiency | Latency Distribution.95th Percentile Latency (microseconds) | Latency Distribution.Average Latency (microseconds) |
|:----------------------|-----------------:|------------:|---------:|---------:|--------:|-------:|-------------:|-------------------------------:|----------------------------:|-------------:|--------------------------------------------------------------:|------------------------------------------------------:|
| Citus-1-1-1024-1-1-1 | 1 | 1280 | 10240 | 1 | 1 | 1200 | 0 | 0 | 0 | 0 | -1 | -1 |
| Citus-1-1-1024-1-2-1 | 1 | 0 | 5120 | 2 | 1 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-1-2-2 | 1 | 0 | 5120 | 2 | 2 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-1-3-2 | 1 | 0 | 2048 | 3 | 1 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-1-3-1 | 1 | 0 | 2048 | 3 | 2 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-1-3-3 | 1 | 0 | 2048 | 3 | 3 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-1-3-4 | 1 | 0 | 2048 | 3 | 4 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-1-3-5 | 1 | 0 | 2048 | 3 | 5 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-1-4-9 | 1 | 0 | 1024 | 4 | 1 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-1-4-2 | 1 | 0 | 1024 | 4 | 2 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-1-4-7 | 1 | 0 | 1024 | 4 | 3 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-1-4-10 | 1 | 0 | 1024 | 4 | 4 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-1-4-5 | 1 | 0 | 1024 | 4 | 5 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-1-4-1 | 1 | 0 | 1024 | 4 | 6 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-1-4-6 | 1 | 0 | 1024 | 4 | 7 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-1-4-3 | 1 | 0 | 1024 | 4 | 8 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-1-4-8 | 1 | 0 | 1024 | 4 | 9 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-1-4-4 | 1 | 0 | 1024 | 4 | 10 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-2-1-1 | 2 | 1280 | 10240 | 1 | 1 | 1200 | 0 | 0 | 0 | 0 | -1 | -1 |
| Citus-1-1-1024-2-2-2 | 2 | 0 | 5120 | 2 | 1 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-2-2-1 | 2 | 0 | 5120 | 2 | 2 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-2-3-1 | 2 | 0 | 2048 | 3 | 1 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-2-3-2 | 2 | 0 | 2048 | 3 | 2 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-2-3-5 | 2 | 0 | 2048 | 3 | 3 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-2-3-3 | 2 | 0 | 2048 | 3 | 4 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-2-3-4 | 2 | 0 | 2048 | 3 | 5 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-2-4-5 | 2 | 0 | 1024 | 4 | 1 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-2-4-9 | 2 | 0 | 1024 | 4 | 2 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-2-4-6 | 2 | 0 | 1024 | 4 | 3 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-2-4-10 | 2 | 0 | 1024 | 4 | 4 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-2-4-4 | 2 | 0 | 1024 | 4 | 5 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-2-4-1 | 2 | 0 | 1024 | 4 | 6 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-2-4-8 | 2 | 0 | 1024 | 4 | 7 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-2-4-2 | 2 | 0 | 1024 | 4 | 8 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-2-4-3 | 2 | 0 | 1024 | 4 | 9 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-2-4-7 | 2 | 0 | 1024 | 4 | 10 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
#### Aggregated Parallel
| DBMS | experiment_run | terminals | target | pod_count | time | num_errors | Throughput (requests/second) | Goodput (requests/second) | efficiency | Latency Distribution.95th Percentile Latency (microseconds) | Latency Distribution.Average Latency (microseconds) |
|:-------------------|-----------------:|------------:|---------:|------------:|-------:|-------------:|-------------------------------:|----------------------------:|-------------:|--------------------------------------------------------------:|------------------------------------------------------:|
| Citus-1-1-1024-1-1 | 1 | 1280 | 10240 | 1 | 1200 | 0 | 0 | 0 | 0 | -1 | -1 |
| Citus-1-1-1024-1-2 | 1 | 0 | 10240 | 2 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-1-3 | 1 | 0 | 10240 | 5 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-1-4 | 1 | 0 | 10240 | 10 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-2-1 | 2 | 1280 | 10240 | 1 | 1200 | 0 | 0 | 0 | 0 | -1 | -1 |
| Citus-1-1-1024-2-2 | 2 | 0 | 10240 | 2 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-2-3 | 2 | 0 | 10240 | 5 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-2-4 | 2 | 0 | 10240 | 10 | 1200 | 0 | 0 | 0 | 0 | 0 | 0 |
### Workflow
#### Actual
* DBMS Citus-1-1-1024 - Pods [[1, 2, 5, 10], [1, 2, 5, 10]]
#### Planned
* DBMS Citus-1-1-1024 - Pods [[1, 2, 5, 10], [1, 2, 5, 10]]
### Loading
| DBMS | time_load | terminals | pods | Throughput [SF/h] |
|:-------------------|------------:|------------:|-------:|--------------------:|
| Citus-1-1-1024-1-1 | 2349 | 1 | 1 | 196.169 |
| Citus-1-1-1024-1-2 | 2349 | 1 | 2 | 196.169 |
| Citus-1-1-1024-1-3 | 2349 | 1 | 5 | 196.169 |
| Citus-1-1-1024-1-4 | 2349 | 1 | 10 | 196.169 |
| Citus-1-1-1024-2-1 | 2349 | 1 | 1 | 196.169 |
| Citus-1-1-1024-2-2 | 2349 | 1 | 2 | 196.169 |
| Citus-1-1-1024-2-3 | 2349 | 1 | 5 | 196.169 |
| Citus-1-1-1024-2-4 | 2349 | 1 | 10 | 196.169 |
### Monitoring
### Execution phase: SUT deployment
| DBMS | CPU [CPUs] | Max CPU | Max RAM [Gb] | Max RAM Cached [Gb] |
|:-------------------|-------------:|----------:|---------------:|----------------------:|
| Citus-1-1-1024-1-1 | 12.18 | 0.13 | 2.37 | 2.81 |
| Citus-1-1-1024-1-2 | 0 | 0.01 | 2.37 | 2.81 |
| Citus-1-1-1024-1-3 | 0 | 0 | 2.37 | 2.81 |
| Citus-1-1-1024-1-4 | 0 | 0 | 2.37 | 2.81 |
| Citus-1-1-1024-2-1 | 12.51 | 0.08 | 2.38 | 2.81 |
| Citus-1-1-1024-2-2 | 0 | 0 | 2.38 | 2.81 |
| Citus-1-1-1024-2-3 | 0 | 0 | 2.38 | 2.81 |
| Citus-1-1-1024-2-4 | 0 | 0 | 2.38 | 2.81 |
### Execution phase: component worker
| DBMS | CPU [CPUs] | Max CPU | Max RAM [Gb] | Max RAM Cached [Gb] |
|:-------------------|-------------:|----------:|---------------:|----------------------:|
| Citus-1-1-1024-1-1 | 14.42 | 0.02 | 2.11 | 7.99 |
| Citus-1-1-1024-1-2 | 0 | 0.02 | 2.11 | 7.98 |
| Citus-1-1-1024-1-3 | 0 | 0.02 | 2.11 | 7.98 |
| Citus-1-1-1024-1-4 | 0 | 0.02 | 2.11 | 7.98 |
| Citus-1-1-1024-2-1 | 12.84 | 0.02 | 2.09 | 2.15 |
| Citus-1-1-1024-2-2 | 0 | 0.02 | 2.09 | 2.14 |
| Citus-1-1-1024-2-3 | 0 | 0.02 | 2.09 | 2.14 |
| Citus-1-1-1024-2-4 | 0 | 0.01 | 2.09 | 2.14 |
### Execution phase: component benchmarker
| DBMS | CPU [CPUs] | Max CPU | Max RAM [Gb] | Max RAM Cached [Gb] |
|:-------------------|-------------:|----------:|---------------:|----------------------:|
| Citus-1-1-1024-1-1 | 108.41 | 0.16 | 0.18 | 0.18 |
| Citus-1-1-1024-1-2 | 0 | 0 | 0.18 | 0.18 |
| Citus-1-1-1024-1-3 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-1-4 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-2-1 | 109.27 | 0.09 | 0.19 | 0.19 |
| Citus-1-1-1024-2-2 | 0 | 0 | 0.19 | 0.19 |
| Citus-1-1-1024-2-3 | 0 | 0 | 0 | 0 |
| Citus-1-1-1024-2-4 | 0 | 0 | 0 | 0 |
### Tests
* TEST failed: Throughput (requests/second) contains 0 or NaN
* TEST failed: Execution phase: SUT deployment contains 0 or NaN in CPU [CPUs]
* TEST failed: Execution phase: component worker contains 0 or NaN in CPU [CPUs]
* TEST failed: Execution phase: component benchmarker contains 0 or NaN in CPU [CPUs]
* TEST passed: Workflow as planned
HammerDB’s TPC-C
HammerDB provides an option to benchmark PostgreSQL with citus compatibility activated. This generates the tables and functions in an empty database and additionally distributes tables and functions: https://github.com/TPC-Council/HammerDB/blob/master/src/postgresql/pgoltp.tcl
After ingestion, we run a script to check the distributions. The script also vacuums and analyzes the tables: https://github.com/Beuth-Erdelt/Benchmark-Experiment-Host-Manager/blob/master/experiments/tpcc/Citus/checkschema-tpcc.sql
HammerDB Simple Example
TPC-C is performed at 16 warehouses. The 16 threads of the client are split into a cascading sequence of 1 and 2 pods. Citus has 3 workers.
bexhoma hammerdb \
-dbms Citus \
-sf 16 \
-nc 1 \
-ne 1 \
-nlt 8 \
-nbp 1 \
-nbt 16 \
-nw 3 \
-nwr 1 \
-nws 48 \
-xlat \
-ms $BEXHOMA_MS \
-tr \
-rnn $BEXHOMA_NODE_SUT -rnl $BEXHOMA_NODE_LOAD -rnb $BEXHOMA_NODE_BENCHMARK \
run &>$LOG_DIR/doc_hammerdb_citus_1.log
Evaluate Results
doc_hammerdb_citus_1.log
## Show Summary
### Workload
HammerDB Workload SF=16 (warehouses for TPC-C)
Type: tpcc
Duration: 1127s
Code: 1771316174
HammerDB runs the benchmark.
This experiment compares run time and resource consumption of TPC-C queries in different DBMS.
TPC-C data is generated and loaded using several threads.
Scaling factor (i.e., number of warehouses) is 16. Benchmarking runs for 5 minutes. Benchmarking also logs latencies.
Experiment uses bexhoma version 0.8.20.
Experiment is limited to DBMS ['Citus'].
Import is handled by 1 processes (pods).
Loading is fixed to cl-worker19.
Benchmarking is fixed to cl-worker19.
SUT is fixed to cl-worker14.
Loading is tested with [8] threads, split into [1] pods.
Benchmarking is tested with [16] threads, split into [1] pods.
Benchmarking is run as [1] times the number of benchmarking pods.
Experiment is run once.
### Connections
Citus-BHT-8-1-1 uses docker image citusdata/citus:13.2.0-alpine
RAM:541008474112
CPU:AMD Opteron(tm) Processor 6378
Cores:64
host:5.15.0-164-generic
node:cl-worker14
disk:98677
cpu_list:0-63
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
requests_cpu:4
requests_memory:16Gi
worker 0
RAM:540579303424
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-94-generic
node:cl-worker22
disk:341983
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 1
RAM:1077382688768
CPU:AMD EPYC 7742 64-Core Processor
Cores:256
host:6.8.0-1044-nvidia
node:cl-worker28
disk:1324862
cpu_list:0-255
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 2
RAM:2164173176832
CPU:INTEL(R) XEON(R) PLATINUM 8570
Cores:224
host:6.8.0-90-generic
node:cl-worker36
disk:964457
cpu_list:0-223
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
eval_parameters
code:1771316174
BEXHOMA_REPLICAS:1
BEXHOMA_SHARDS:48
BEXHOMA_WORKERS:3
### Execution
experiment_run vusers client pod_count P95 [ms] P99 [ms] efficiency NOPM TPM duration errors
Citus-BHT-8-1-1 1 16 1 1 35.92 57.87 0.0 34130.0 78688.0 5 0
Warehouses: 16
### Workflow
#### Actual
DBMS Citus-BHT-8-1 - Pods [[1]]
#### Planned
DBMS Citus-BHT-8-1 - Pods [[1]]
### Loading
time_load terminals pods Imported warehouses [1/h]
Citus-BHT-8-1-1 114.0 1.0 1.0 505.263158
### Tests
TEST passed: NOPM contains no 0 or NaN
TEST passed: Workflow as planned
HammerDB More Complex Example
bexhoma hammerdb \
-dbms Citus \
-sf 128 \
-xsd 30 \
-nc 1 \
-ne 1 \
-nlp 1 \
-nlt 128 \
-nbp 1,2,4,8 \
-nbt 128 \
-nw 4 \
-nwr 1 \
-nws 48 \
-xlat \
-m \
-mc \
-ms $BEXHOMA_MS \
-tr \
-rss 50Gi \
-rst $BEXHOMA_STORAGE_CLASS \
-rnn $BEXHOMA_NODE_SUT -rnl $BEXHOMA_NODE_LOAD -rnb $BEXHOMA_NODE_BENCHMARK \
run &>$LOG_DIR/doc_hammerdb_citus_2.log
Evaluate Results
doc_hammerdb_citus_2.log
## Show Summary
### Workload
HammerDB Workload SF=128 (warehouses for TPC-C)
Type: tpcc
Duration: 9695s
Code: 1771317344
HammerDB runs the benchmark.
This experiment compares run time and resource consumption of TPC-C queries in different DBMS.
TPC-C data is generated and loaded using several threads.
Scaling factor (i.e., number of warehouses) is 128. Benchmarking runs for 30 minutes. Benchmarking also logs latencies.
Experiment uses bexhoma version 0.8.20.
System metrics are monitored by a cluster-wide installation.
Experiment is limited to DBMS ['Citus'].
Import is handled by 1 processes (pods).
Loading is fixed to cl-worker19.
Benchmarking is fixed to cl-worker19.
SUT is fixed to cl-worker14.
Database is persisted to disk of type shared and size 50Gi.
Loading is tested with [128] threads, split into [1] pods.
Benchmarking is tested with [128] threads, split into [1, 2, 4, 8] pods.
Benchmarking is run as [1] times the number of benchmarking pods.
Experiment is run once.
### Connections
Citus-BHT-128-1-1 uses docker image citusdata/citus:13.2.0-alpine
RAM:541008474112
CPU:AMD Opteron(tm) Processor 6378
Cores:64
host:5.15.0-164-generic
node:cl-worker14
disk:98900
volume_size:50.0G
volume_used:40.0M
cpu_list:0-63
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
requests_cpu:4
requests_memory:16Gi
worker 0
RAM:540579303424
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-94-generic
node:cl-worker22
disk:340701
volume_size:50.0G
volume_used:6.1G
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 1
RAM:1077382688768
CPU:AMD EPYC 7742 64-Core Processor
Cores:256
host:6.8.0-1044-nvidia
node:cl-worker28
disk:1323757
volume_size:50.0G
volume_used:3.2G
cpu_list:0-255
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 2
RAM:2164173176832
CPU:INTEL(R) XEON(R) PLATINUM 8570
Cores:224
host:6.8.0-90-generic
node:cl-worker36
disk:874573
volume_size:50.0G
volume_used:3.2G
cpu_list:0-223
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 3
RAM:1081742745600
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-90-generic
node:cl-worker29
disk:512319
volume_size:50.0G
volume_used:6.1G
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
eval_parameters
code:1771317344
BEXHOMA_REPLICAS:1
BEXHOMA_SHARDS:48
BEXHOMA_WORKERS:4
Citus-BHT-128-1-2 uses docker image citusdata/citus:13.2.0-alpine
RAM:541008474112
CPU:AMD Opteron(tm) Processor 6378
Cores:64
host:5.15.0-164-generic
node:cl-worker14
disk:98900
volume_size:50.0G
volume_used:40.0M
cpu_list:0-63
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
requests_cpu:4
requests_memory:16Gi
worker 0
RAM:540579303424
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-94-generic
node:cl-worker22
disk:340868
volume_size:50.0G
volume_used:8.9G
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 1
RAM:1077382688768
CPU:AMD EPYC 7742 64-Core Processor
Cores:256
host:6.8.0-1044-nvidia
node:cl-worker28
disk:1323595
volume_size:50.0G
volume_used:6.1G
cpu_list:0-255
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 2
RAM:2164173176832
CPU:INTEL(R) XEON(R) PLATINUM 8570
Cores:224
host:6.8.0-90-generic
node:cl-worker36
disk:874582
volume_size:50.0G
volume_used:6.1G
cpu_list:0-223
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 3
RAM:1081742745600
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-90-generic
node:cl-worker29
disk:512320
volume_size:50.0G
volume_used:6.1G
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
eval_parameters
code:1771317344
BEXHOMA_REPLICAS:1
BEXHOMA_SHARDS:48
BEXHOMA_WORKERS:4
Citus-BHT-128-1-3 uses docker image citusdata/citus:13.2.0-alpine
RAM:541008474112
CPU:AMD Opteron(tm) Processor 6378
Cores:64
host:5.15.0-164-generic
node:cl-worker14
disk:98900
volume_size:50.0G
volume_used:76.0M
cpu_list:0-63
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
requests_cpu:4
requests_memory:16Gi
worker 0
RAM:540579303424
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-94-generic
node:cl-worker22
disk:340869
volume_size:50.0G
volume_used:13.4G
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 1
RAM:1077382688768
CPU:AMD EPYC 7742 64-Core Processor
Cores:256
host:6.8.0-1044-nvidia
node:cl-worker28
disk:1323599
volume_size:50.0G
volume_used:10.1G
cpu_list:0-255
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 2
RAM:2164173176832
CPU:INTEL(R) XEON(R) PLATINUM 8570
Cores:224
host:6.8.0-90-generic
node:cl-worker36
disk:874581
volume_size:50.0G
volume_used:7.2G
cpu_list:0-223
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 3
RAM:1081742745600
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-90-generic
node:cl-worker29
disk:512310
volume_size:50.0G
volume_used:7.9G
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
eval_parameters
code:1771317344
BEXHOMA_REPLICAS:1
BEXHOMA_SHARDS:48
BEXHOMA_WORKERS:4
Citus-BHT-128-1-4 uses docker image citusdata/citus:13.2.0-alpine
RAM:541008474112
CPU:AMD Opteron(tm) Processor 6378
Cores:64
host:5.15.0-164-generic
node:cl-worker14
disk:98900
volume_size:50.0G
volume_used:76.0M
cpu_list:0-63
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
requests_cpu:4
requests_memory:16Gi
worker 0
RAM:540579303424
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-94-generic
node:cl-worker22
disk:387860
volume_size:50.0G
volume_used:17.9G
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 1
RAM:1077382688768
CPU:AMD EPYC 7742 64-Core Processor
Cores:256
host:6.8.0-1044-nvidia
node:cl-worker28
disk:1323604
volume_size:50.0G
volume_used:12.2G
cpu_list:0-255
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 2
RAM:2164173176832
CPU:INTEL(R) XEON(R) PLATINUM 8570
Cores:224
host:6.8.0-90-generic
node:cl-worker36
disk:874580
volume_size:50.0G
volume_used:11.2G
cpu_list:0-223
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 3
RAM:1081742745600
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-90-generic
node:cl-worker29
disk:512311
volume_size:50.0G
volume_used:12.7G
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
eval_parameters
code:1771317344
BEXHOMA_REPLICAS:1
BEXHOMA_SHARDS:48
BEXHOMA_WORKERS:4
### Execution
experiment_run vusers client pod_count P95 [ms] P99 [ms] efficiency NOPM TPM duration errors
Citus-BHT-128-1-1 1 128 1 1 445.72 905.27 0.0 20846.00 47932.00 30 0
Citus-BHT-128-1-2 1 128 2 2 454.03 948.90 0.0 29880.00 68688.00 30 0
Citus-BHT-128-1-3 1 128 3 4 0.00 0.00 0.0 30871.25 71078.25 30 0
Citus-BHT-128-1-4 1 128 4 8 429.93 890.60 0.0 33519.38 77090.75 30 0
Warehouses: 128
### Workflow
#### Actual
DBMS Citus-BHT-128-1 - Pods [[1, 4, 8, 2]]
#### Planned
DBMS Citus-BHT-128-1 - Pods [[1, 2, 4, 8]]
### Loading
time_load terminals pods Imported warehouses [1/h]
Citus-BHT-128-1-1 446.0 1.0 1.0 1033.183857
Citus-BHT-128-1-2 446.0 1.0 2.0 1033.183857
Citus-BHT-128-1-3 446.0 1.0 4.0 1033.183857
Citus-BHT-128-1-4 446.0 1.0 8.0 1033.183857
### Monitoring
### Loading phase: SUT deployment
CPU [CPUs] Max CPU Max RAM [Gb] Max RAM Cached [Gb]
Citus-BHT-128-1-1 1077.52 4.65 0.99 1.06
Citus-BHT-128-1-2 1077.52 4.65 0.99 1.06
Citus-BHT-128-1-3 1077.52 4.65 0.99 1.06
Citus-BHT-128-1-4 1077.52 4.65 0.99 1.06
### Loading phase: component worker
CPU [CPUs] Max CPU Max RAM [Gb] Max RAM Cached [Gb]
Citus-BHT-128-1-1 1106.37 3.86 13.1 39.1
Citus-BHT-128-1-2 1106.37 3.86 13.1 39.1
Citus-BHT-128-1-3 1106.37 3.86 13.1 39.1
Citus-BHT-128-1-4 1106.37 3.86 13.1 39.1
### Loading phase: component loader
CPU [CPUs] Max CPU Max RAM [Gb] Max RAM Cached [Gb]
Citus-BHT-128-1-1 3013.39 24.81 0.8 0.8
Citus-BHT-128-1-2 3013.39 24.81 0.8 0.8
Citus-BHT-128-1-3 3013.39 24.81 0.8 0.8
Citus-BHT-128-1-4 3013.39 24.81 0.8 0.8
### Execution phase: SUT deployment
CPU [CPUs] Max CPU Max RAM [Gb] Max RAM Cached [Gb]
Citus-BHT-128-1-1 739.12 0.55 1.00 1.07
Citus-BHT-128-1-2 1065.20 0.78 1.00 1.07
Citus-BHT-128-1-3 1101.19 0.76 1.01 1.08
Citus-BHT-128-1-4 1200.28 0.85 1.02 1.09
### Execution phase: component worker
CPU [CPUs] Max CPU Max RAM [Gb] Max RAM Cached [Gb]
Citus-BHT-128-1-1 8235.29 6.35 16.77 48.02
Citus-BHT-128-1-2 11562.76 7.88 20.34 58.54
Citus-BHT-128-1-3 12634.64 8.34 23.60 63.28
Citus-BHT-128-1-4 13119.50 9.79 26.24 63.79
### Execution phase: component benchmarker
CPU [CPUs] Max CPU Max RAM [Gb] Max RAM Cached [Gb]
Citus-BHT-128-1-1 371.84 0.29 0.98 0.98
Citus-BHT-128-1-2 496.60 0.34 0.98 0.98
Citus-BHT-128-1-3 512.31 0.47 0.61 0.61
Citus-BHT-128-1-4 542.51 0.39 0.33 0.34
### Tests
TEST passed: Loading phase: SUT deployment contains no 0 or NaN in CPU [CPUs]
TEST passed: Loading phase: component worker contains no 0 or NaN in CPU [CPUs]
TEST passed: Loading phase: component loader contains no 0 or NaN in CPU [CPUs]
TEST passed: Execution phase: SUT deployment contains no 0 or NaN in CPU [CPUs]
TEST passed: Execution phase: component worker contains no 0 or NaN in CPU [CPUs]
TEST passed: Execution phase: component benchmarker contains no 0 or NaN in CPU [CPUs]
TEST passed: NOPM contains no 0 or NaN
TEST passed: Workflow as planned
HammerDB Referenced Paper
We here run HammerDB TPROC-C benchmark against Citus similar to [1]. We in particular copy the setting 500 warehouses, 250 virtual users and 4 worker nodes. There has been made a contribution to HammerDB by [2] and we assume this reflects the configuration used in [1]: In case of Citus, we converted the items table to a reference table and the remaining tables to co-located distributed tables with the warehouse ID column as the distribution column. Additionally, we configured Citus to delegate stored procedure calls to worker nodes based on the warehouse ID argument. We configure the experiment to use 48 shards, run for 20 minutes and split the 250 virtual users (sequentially) into 1,2,5 and 10 pods. Database is persisted on PVCs. The experiment runs twice for confidence.
Note: In [1] YCSB is run as this: For this benchmark, the coordinator’s CPU usage becomes a scaling bottleneck. Hence, we ran the benchmark with every worker node acting as coordinator and configured YCSB to load balance across all nodes. This apparently uses [4], part of the Citus benchmark toolkit [3], and PostgreSQL loadbalancer feature [5].
[1] Citus: Distributed PostgreSQL for Data-Intensive Applications
Umur Cubukcu, Ozgun Erdogan, Sumedh Pathak, Sudhakar Sannakkayala, and Marco Slot. 2021. In Proceedings of the 2021 International Conference on Management of Data (SIGMOD ‘21). Association for Computing Machinery, New York, NY, USA, 2490–2502. https://dl.acm.org/doi/10.1145/3448016.3457551
[2] How to benchmark performance of Citus and Postgres with HammerDB on Azure
JelteF, Microsoft. Retrieved April 1, 2025, from https://techcommunity.microsoft.com/blog/adforpostgresql/how-to-benchmark-performance-of-citus-and-postgres-with-hammerdb-on-azure/3254918
[3] Citus Data Benchmark Toolkit
Citus Data. Retrieved April 1, 2025, from https://github.com/citusdata/citus-benchmark
[4] Citus Data Benchmark Toolkit HammerDB settings
Citus Data. Retrieved April 1, 2025, from https://github.com/citusdata/citus-benchmark/blob/master/run.tcl
[5] Adding Postgres 16 support to Citus 12.1, plus schema-based sharding improvements
Naisila Puka, September 22, 2023. Retrieved April 1, 2025, from https://www.citusdata.com/blog/2023/09/22/adding-postgres-16-support-to-citus-12-1
[6] Understand what you run before publishing your (silly) benchmark results
Franck Pachot, YugabyteDB. Retrieved April 1, 2025, from https://dev.to/yugabyte/understand-what-you-run-before-publishing-your-silly-benchmark-results-48bb
bexhoma hammerdb \
-dbms Citus \
-sf 500 \
-xsd 20 \
-nc 2 \
-ne 1 \
-nlp 1 \
-nlt 250 \
-nbp 1,2,5,10 \
-nbt 250 \
-nw 4 \
-nwr 1 \
-nws 48 \
-xlat \
-m \
-mc \
-ms $BEXHOMA_MS \
-tr \
-rss 200Gi \
-rst $BEXHOMA_STORAGE_CLASS \
-rnn $BEXHOMA_NODE_SUT -rnl $BEXHOMA_NODE_LOAD -rnb $BEXHOMA_NODE_BENCHMARK \
run &>$LOG_DIR/doc_hammerdb_citus_3.log
Evaluate Results
doc_hammerdb_citus_3.log
## Show Summary
### Workload
HammerDB Workload SF=500 (warehouses for TPC-C)
Type: tpcc
Duration: 18124s
Code: 1771327158
HammerDB runs the benchmark.
This experiment compares run time and resource consumption of TPC-C queries in different DBMS.
TPC-C data is generated and loaded using several threads.
Scaling factor (i.e., number of warehouses) is 500. Benchmarking runs for 20 minutes. Benchmarking also logs latencies.
Experiment uses bexhoma version 0.8.20.
System metrics are monitored by a cluster-wide installation.
Experiment is limited to DBMS ['Citus'].
Import is handled by 1 processes (pods).
Loading is fixed to cl-worker19.
Benchmarking is fixed to cl-worker19.
SUT is fixed to cl-worker14.
Database is persisted to disk of type shared and size 200Gi.
Loading is tested with [250] threads, split into [1] pods.
Benchmarking is tested with [250] threads, split into [1, 2, 5, 10] pods.
Benchmarking is run as [1] times the number of benchmarking pods.
Experiment is run 2 times.
### Connections
Citus-BHT-250-1-1-1 uses docker image citusdata/citus:13.2.0-alpine
RAM:541008474112
CPU:AMD Opteron(tm) Processor 6378
Cores:64
host:5.15.0-164-generic
node:cl-worker14
disk:98900
volume_size:200.0G
volume_used:40.0M
cpu_list:0-63
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
requests_cpu:4
requests_memory:16Gi
worker 0
RAM:540579303424
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-94-generic
node:cl-worker22
disk:462137
volume_size:200.0G
volume_used:24.3G
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 1
RAM:1077382688768
CPU:AMD EPYC 7742 64-Core Processor
Cores:256
host:6.8.0-1044-nvidia
node:cl-worker28
disk:1323624
volume_size:200.0G
volume_used:12.7G
cpu_list:0-255
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 2
RAM:2164173176832
CPU:INTEL(R) XEON(R) PLATINUM 8570
Cores:224
host:6.8.0-90-generic
node:cl-worker36
disk:874583
volume_size:200.0G
volume_used:12.6G
cpu_list:0-223
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 3
RAM:1081742745600
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-90-generic
node:cl-worker29
disk:512312
volume_size:200.0G
volume_used:24.3G
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
eval_parameters
code:1771327158
BEXHOMA_REPLICAS:1
BEXHOMA_SHARDS:48
BEXHOMA_WORKERS:4
Citus-BHT-250-1-1-2 uses docker image citusdata/citus:13.2.0-alpine
RAM:541008474112
CPU:AMD Opteron(tm) Processor 6378
Cores:64
host:5.15.0-164-generic
node:cl-worker14
disk:98900
volume_size:200.0G
volume_used:40.0M
cpu_list:0-63
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
requests_cpu:4
requests_memory:16Gi
worker 0
RAM:540579303424
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-94-generic
node:cl-worker22
disk:442239
volume_size:200.0G
volume_used:31.3G
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 1
RAM:1077382688768
CPU:AMD EPYC 7742 64-Core Processor
Cores:256
host:6.8.0-1044-nvidia
node:cl-worker28
disk:1323627
volume_size:200.0G
volume_used:12.7G
cpu_list:0-255
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 2
RAM:2164173176832
CPU:INTEL(R) XEON(R) PLATINUM 8570
Cores:224
host:6.8.0-90-generic
node:cl-worker36
disk:874585
volume_size:200.0G
volume_used:12.6G
cpu_list:0-223
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 3
RAM:1081742745600
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-90-generic
node:cl-worker29
disk:526135
volume_size:200.0G
volume_used:24.3G
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
eval_parameters
code:1771327158
BEXHOMA_REPLICAS:1
BEXHOMA_SHARDS:48
BEXHOMA_WORKERS:4
Citus-BHT-250-1-1-3 uses docker image citusdata/citus:13.2.0-alpine
RAM:541008474112
CPU:AMD Opteron(tm) Processor 6378
Cores:64
host:5.15.0-164-generic
node:cl-worker14
disk:98901
volume_size:200.0G
volume_used:196.0M
cpu_list:0-63
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
requests_cpu:4
requests_memory:16Gi
worker 0
RAM:540579303424
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-94-generic
node:cl-worker22
disk:442184
volume_size:200.0G
volume_used:35.8G
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 1
RAM:1077382688768
CPU:AMD EPYC 7742 64-Core Processor
Cores:256
host:6.8.0-1044-nvidia
node:cl-worker28
disk:1323651
volume_size:200.0G
volume_used:25.2G
cpu_list:0-255
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 2
RAM:2164173176832
CPU:INTEL(R) XEON(R) PLATINUM 8570
Cores:224
host:6.8.0-90-generic
node:cl-worker36
disk:874615
volume_size:200.0G
volume_used:25.2G
cpu_list:0-223
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 3
RAM:1081742745600
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-90-generic
node:cl-worker29
disk:526136
volume_size:200.0G
volume_used:36.3G
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
eval_parameters
code:1771327158
BEXHOMA_REPLICAS:1
BEXHOMA_SHARDS:48
BEXHOMA_WORKERS:4
Citus-BHT-250-1-1-4 uses docker image citusdata/citus:13.2.0-alpine
RAM:541008474112
CPU:AMD Opteron(tm) Processor 6378
Cores:64
host:5.15.0-164-generic
node:cl-worker14
disk:98901
volume_size:200.0G
volume_used:196.0M
cpu_list:0-63
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
requests_cpu:4
requests_memory:16Gi
worker 0
RAM:540579303424
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-94-generic
node:cl-worker22
disk:442197
volume_size:200.0G
volume_used:35.8G
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 1
RAM:1077382688768
CPU:AMD EPYC 7742 64-Core Processor
Cores:256
host:6.8.0-1044-nvidia
node:cl-worker28
disk:1323654
volume_size:200.0G
volume_used:36.2G
cpu_list:0-255
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 2
RAM:2164173176832
CPU:INTEL(R) XEON(R) PLATINUM 8570
Cores:224
host:6.8.0-90-generic
node:cl-worker36
disk:874617
volume_size:200.0G
volume_used:34.7G
cpu_list:0-223
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 3
RAM:1081742745600
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-90-generic
node:cl-worker29
disk:526136
volume_size:200.0G
volume_used:36.3G
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
eval_parameters
code:1771327158
BEXHOMA_REPLICAS:1
BEXHOMA_SHARDS:48
BEXHOMA_WORKERS:4
Citus-BHT-250-1-2-1 uses docker image citusdata/citus:13.2.0-alpine
RAM:541008474112
CPU:AMD Opteron(tm) Processor 6378
Cores:64
host:5.15.0-164-generic
node:cl-worker14
disk:98901
volume_size:200.0G
volume_used:192.0M
cpu_list:0-63
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
requests_cpu:4
requests_memory:16Gi
worker 0
RAM:540579303424
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-94-generic
node:cl-worker22
disk:404159
volume_size:200.0G
volume_used:38.6G
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 1
RAM:1077382688768
CPU:AMD EPYC 7742 64-Core Processor
Cores:256
host:6.8.0-1044-nvidia
node:cl-worker28
disk:1339019
volume_size:200.0G
volume_used:36.4G
cpu_list:0-255
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 2
RAM:1081742745600
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-90-generic
node:cl-worker29
disk:534105
volume_size:200.0G
volume_used:35.2G
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 3
RAM:2164173176832
CPU:INTEL(R) XEON(R) PLATINUM 8570
Cores:224
host:6.8.0-90-generic
node:cl-worker36
disk:874723
volume_size:200.0G
volume_used:37.8G
cpu_list:0-223
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
eval_parameters
code:1771327158
BEXHOMA_REPLICAS:1
BEXHOMA_SHARDS:48
BEXHOMA_WORKERS:4
Citus-BHT-250-1-2-2 uses docker image citusdata/citus:13.2.0-alpine
RAM:541008474112
CPU:AMD Opteron(tm) Processor 6378
Cores:64
host:5.15.0-164-generic
node:cl-worker14
disk:98901
volume_size:200.0G
volume_used:192.0M
cpu_list:0-63
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
requests_cpu:4
requests_memory:16Gi
worker 0
RAM:540579303424
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-94-generic
node:cl-worker22
disk:403347
volume_size:200.0G
volume_used:38.6G
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 1
RAM:1077382688768
CPU:AMD EPYC 7742 64-Core Processor
Cores:256
host:6.8.0-1044-nvidia
node:cl-worker28
disk:1359331
volume_size:200.0G
volume_used:36.4G
cpu_list:0-255
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 2
RAM:1081742745600
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-90-generic
node:cl-worker29
disk:554192
volume_size:200.0G
volume_used:35.2G
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 3
RAM:2164173176832
CPU:INTEL(R) XEON(R) PLATINUM 8570
Cores:224
host:6.8.0-90-generic
node:cl-worker36
disk:875565
volume_size:200.0G
volume_used:37.8G
cpu_list:0-223
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
eval_parameters
code:1771327158
BEXHOMA_REPLICAS:1
BEXHOMA_SHARDS:48
BEXHOMA_WORKERS:4
Citus-BHT-250-1-2-3 uses docker image citusdata/citus:13.2.0-alpine
RAM:541008474112
CPU:AMD Opteron(tm) Processor 6378
Cores:64
host:5.15.0-164-generic
node:cl-worker14
disk:98902
volume_size:200.0G
volume_used:192.0M
cpu_list:0-63
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
requests_cpu:4
requests_memory:16Gi
worker 0
RAM:540579303424
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-94-generic
node:cl-worker22
disk:403172
volume_size:200.0G
volume_used:39.2G
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 1
RAM:1077382688768
CPU:AMD EPYC 7742 64-Core Processor
Cores:256
host:6.8.0-1044-nvidia
node:cl-worker28
disk:1359341
volume_size:200.0G
volume_used:36.4G
cpu_list:0-255
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 2
RAM:1081742745600
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-90-generic
node:cl-worker29
disk:554193
volume_size:200.0G
volume_used:35.2G
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 3
RAM:2164173176832
CPU:INTEL(R) XEON(R) PLATINUM 8570
Cores:224
host:6.8.0-90-generic
node:cl-worker36
disk:875760
volume_size:200.0G
volume_used:37.8G
cpu_list:0-223
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
eval_parameters
code:1771327158
BEXHOMA_REPLICAS:1
BEXHOMA_SHARDS:48
BEXHOMA_WORKERS:4
Citus-BHT-250-1-2-4 uses docker image citusdata/citus:13.2.0-alpine
RAM:541008474112
CPU:AMD Opteron(tm) Processor 6378
Cores:64
host:5.15.0-164-generic
node:cl-worker14
disk:98902
volume_size:200.0G
volume_used:192.0M
cpu_list:0-63
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
requests_cpu:4
requests_memory:16Gi
worker 0
RAM:540579303424
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-94-generic
node:cl-worker22
disk:402374
volume_size:200.0G
volume_used:39.2G
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 1
RAM:1077382688768
CPU:AMD EPYC 7742 64-Core Processor
Cores:256
host:6.8.0-1044-nvidia
node:cl-worker28
disk:1360006
volume_size:200.0G
volume_used:36.4G
cpu_list:0-255
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 2
RAM:1081742745600
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-90-generic
node:cl-worker29
disk:554193
volume_size:200.0G
volume_used:35.2G
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 3
RAM:2164173176832
CPU:INTEL(R) XEON(R) PLATINUM 8570
Cores:224
host:6.8.0-90-generic
node:cl-worker36
disk:875770
volume_size:200.0G
volume_used:37.8G
cpu_list:0-223
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
eval_parameters
code:1771327158
BEXHOMA_REPLICAS:1
BEXHOMA_SHARDS:48
BEXHOMA_WORKERS:4
### Execution
experiment_run vusers client pod_count P95 [ms] P99 [ms] efficiency NOPM TPM duration errors
Citus-BHT-250-1-1-1 1 250 1 1 483.59 941.44 0.0 55028.0 126754.0 20 0
Citus-BHT-250-1-1-3 1 250 3 5 796.50 1542.36 0.0 35302.2 81188.2 20 0
Citus-BHT-250-1-1-4 1 25 4 1 634.72 1322.87 0.0 30509.0 139945.0 20 53195
Citus-BHT-250-1-2-1 2 250 1 1 572.76 1100.50 0.0 40213.0 92490.0 20 0
Citus-BHT-250-1-2-3 2 250 3 5 0.00 0.00 0.0 31189.8 71757.0 20 1
Citus-BHT-250-1-2-4 2 250 4 10 726.51 1498.14 0.0 40065.4 91997.5 20 1
Warehouses: 500
### Workflow
#### Actual
DBMS Citus-BHT-250-1 - Pods [[10, 5, 1], [5, 1, 1]]
#### Planned
DBMS Citus-BHT-250-1 - Pods [[1, 2, 5, 10], [1, 2, 5, 10]]
### Loading
time_load terminals pods Imported warehouses [1/h]
Citus-BHT-250-1-1-1 1094.0 1.0 1.0 1645.338208
Citus-BHT-250-1-1-2 1094.0 1.0 2.0 1645.338208
Citus-BHT-250-1-1-3 1094.0 1.0 5.0 1645.338208
Citus-BHT-250-1-1-4 1094.0 1.0 10.0 1645.338208
Citus-BHT-250-1-2-1 1094.0 1.0 1.0 1645.338208
Citus-BHT-250-1-2-2 1094.0 1.0 2.0 1645.338208
Citus-BHT-250-1-2-3 1094.0 1.0 5.0 1645.338208
Citus-BHT-250-1-2-4 1094.0 1.0 10.0 1645.338208
### Monitoring
### Loading phase: SUT deployment
CPU [CPUs] Max CPU Max RAM [Gb] Max RAM Cached [Gb]
Citus-BHT-250-1-1-1 6216.12 17.8 1.79 1.85
Citus-BHT-250-1-1-2 6216.12 17.8 1.79 1.85
Citus-BHT-250-1-1-3 6216.12 17.8 1.79 1.85
Citus-BHT-250-1-1-4 6216.12 17.8 1.79 1.85
### Loading phase: component worker
CPU [CPUs] Max CPU Max RAM [Gb] Max RAM Cached [Gb]
Citus-BHT-250-1-1-1 4086.25 5.48 50.35 63.98
Citus-BHT-250-1-1-2 4086.25 5.48 50.35 63.98
Citus-BHT-250-1-1-3 4086.25 5.48 50.35 63.98
Citus-BHT-250-1-1-4 4086.25 5.48 50.35 63.98
### Loading phase: component loader
CPU [CPUs] Max CPU Max RAM [Gb] Max RAM Cached [Gb]
Citus-BHT-250-1-1-1 14684.05 39.61 1.94 1.95
Citus-BHT-250-1-1-2 14684.05 39.61 1.94 1.95
Citus-BHT-250-1-1-3 14684.05 39.61 1.94 1.95
Citus-BHT-250-1-1-4 14684.05 39.61 1.94 1.95
### Execution phase: SUT deployment
CPU [CPUs] Max CPU Max RAM [Gb] Max RAM Cached [Gb]
Citus-BHT-250-1-1-1 1455.93 1.34 1.44 1.62
Citus-BHT-250-1-1-2 4849.65 2.66 1.44 1.62
Citus-BHT-250-1-1-3 1001.90 0.94 1.46 1.64
Citus-BHT-250-1-1-4 2973.79 4.66 1.47 1.65
Citus-BHT-250-1-2-1 1069.22 1.04 1.41 1.82
Citus-BHT-250-1-2-2 1728.65 2.43 1.41 1.82
Citus-BHT-250-1-2-3 890.11 0.74 1.42 1.82
Citus-BHT-250-1-2-4 1105.54 1.09 1.43 1.84
### Execution phase: component worker
CPU [CPUs] Max CPU Max RAM [Gb] Max RAM Cached [Gb]
Citus-BHT-250-1-1-1 15168.93 14.05 56.65 63.91
Citus-BHT-250-1-1-2 16188.05 17.11 60.86 63.98
Citus-BHT-250-1-1-3 11709.28 11.32 59.17 63.98
Citus-BHT-250-1-1-4 14100.02 12.42 61.50 63.99
Citus-BHT-250-1-2-1 11121.65 10.38 35.75 63.96
Citus-BHT-250-1-2-2 5008.60 9.71 48.12 63.98
Citus-BHT-250-1-2-3 9058.90 8.24 52.53 63.99
Citus-BHT-250-1-2-4 11700.82 11.48 56.05 63.99
### Execution phase: component benchmarker
CPU [CPUs] Max CPU Max RAM [Gb] Max RAM Cached [Gb]
Citus-BHT-250-1-1-1 618.68 0.58 1.75 1.75
Citus-BHT-250-1-1-2 2427.92 1.31 1.75 1.75
Citus-BHT-250-1-1-3 2443.07 0.53 1.38 1.54
Citus-BHT-250-1-1-4 1511.17 2.25 0.32 0.32
Citus-BHT-250-1-2-1 480.01 0.43 1.54 1.54
Citus-BHT-250-1-2-2 850.06 1.25 1.54 1.54
Citus-BHT-250-1-2-3 887.80 0.42 0.81 0.87
Citus-BHT-250-1-2-4 484.06 0.51 0.30 0.30
### Tests
TEST passed: Loading phase: SUT deployment contains no 0 or NaN in CPU [CPUs]
TEST passed: Loading phase: component worker contains no 0 or NaN in CPU [CPUs]
TEST passed: Loading phase: component loader contains no 0 or NaN in CPU [CPUs]
TEST passed: Execution phase: SUT deployment contains no 0 or NaN in CPU [CPUs]
TEST passed: Execution phase: component worker contains no 0 or NaN in CPU [CPUs]
TEST passed: Execution phase: component benchmarker contains no 0 or NaN in CPU [CPUs]
TEST passed: NOPM contains no 0 or NaN
TEST failed: Workflow not as planned
TPC-H
We build the schema similar to [2] in https://github.com/Beuth-Erdelt/Benchmark-Experiment-Host-Manager/blob/master/experiments/tpch/Citus/initschema-tpch.sql
select create_reference_table('nation');
select create_reference_table('region');
select create_reference_table('part');
select create_reference_table('supplier');
select create_reference_table('partsupp');
select create_reference_table('customer');
select create_distributed_table('orders', 'o_orderkey');
select create_distributed_table('lineitem', 'l_orderkey');
It is also mentioned in [1] that the big tables orders and linetime should be distributed and the others should be replicated.
As the paper used Citus 9.5, columnar storage has not been included in Citus [3].
Note that columnar storage has some limitations as no UPDATEs, no DELETEs and no FOREIGN KEYs.
Also note that Citus does not support all TPC-H queries.
In a correlated subquery there cannot be a replicated table, so we have to rewrite Q22.
[1] Citus: Distributed PostgreSQL for Data-Intensive Applications
Umur Cubukcu, Ozgun Erdogan, Sumedh Pathak, Sudhakar Sannakkayala, and Marco Slot. 2021. In Proceedings of the 2021 International Conference on Management of Data (SIGMOD ‘21). Association for Computing Machinery, New York, NY, USA, 2490–2502. https://dl.acm.org/doi/10.1145/3448016.3457551
[2] Citus TPC-H tests - schema
Dimitri Fontaine. Retrieved April 1, 2025, from https://github.com/dimitri/tpch-citus/tree/master/schema
Citus Data. Retrieved April 1, 2025, from https://docs.citusdata.com/en/stable/admin_guide/table_management.html#columnar-storage
TPC-H Simple Example
bexhoma tpch \
-dbms Citus \
-sf 1 \
-nc 1 \
-ne 1 \
-nlp 8 \
-nbp 1 \
-nw 4 \
-nwr 1 \
-nws 48 \
-xii -xic -xis \
-xdt \
-ms $BEXHOMA_MS \
-t 1200 \
-tr \
-rnn $BEXHOMA_NODE_SUT -rnl $BEXHOMA_NODE_LOAD -rnb $BEXHOMA_NODE_BENCHMARK \
run &>$LOG_DIR/test_tpch_testcase_citus_1.log
Evaluate Results
test_tpch_testcase_citus_1.log
## Show Summary
### Workload
TPC-H Queries SF=1
Type: tpch
Duration: 864s
Code: 1771345642
This includes the reading queries of TPC-H.
This experiment compares run time and resource consumption of TPC-H queries in different DBMS.
TPC-H (SF=1) data is loaded and benchmark is executed.
Query ordering is Q1 - Q22.
All instances use the same query parameters.
Timeout per query is 1200.
Import sets indexes and constraints after loading and recomputes statistics.
Experiment uses bexhoma version 0.8.20.
Experiment is limited to DBMS ['Citus'].
Import is handled by 8 processes (pods).
Loading is fixed to cl-worker19.
Benchmarking is fixed to cl-worker19.
SUT is fixed to cl-worker14.
Loading is tested with [1] threads, split into [8] pods.
Benchmarking is tested with [1] threads, split into [1] pods.
Benchmarking is run as [1] times the number of benchmarking pods.
Experiment is run once.
### Connections
Citus-BHT-8-1-1 uses docker image citusdata/citus:13.2.0-alpine
RAM:541008474112
CPU:AMD Opteron(tm) Processor 6378
Cores:64
host:5.15.0-164-generic
node:cl-worker14
disk:98943
cpu_list:0-63
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
requests_cpu:4
requests_memory:16Gi
worker 0
RAM:540579303424
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-94-generic
node:cl-worker22
disk:406553
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 1
RAM:1077382688768
CPU:AMD EPYC 7742 64-Core Processor
Cores:256
host:6.8.0-1044-nvidia
node:cl-worker28
disk:1360233
cpu_list:0-255
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 2
RAM:2164173176832
CPU:INTEL(R) XEON(R) PLATINUM 8570
Cores:224
host:6.8.0-90-generic
node:cl-worker36
disk:891172
cpu_list:0-223
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 3
RAM:1081742745600
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-90-generic
node:cl-worker29
disk:556386
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
eval_parameters
code:1771345642
BEXHOMA_REPLICAS:1
BEXHOMA_SHARDS:48
BEXHOMA_WORKERS:4
COLUMNAR:False
### Errors (failed queries)
No errors
### Warnings (result mismatch)
No warnings
### Latency of Timer Execution [ms]
DBMS Citus-BHT-8-1-1
Pricing Summary Report (TPC-H Q1) 138.49
Minimum Cost Supplier Query (TPC-H Q2) 16.56
Shipping Priority (TPC-H Q3) 34.43
Order Priority Checking Query (TPC-H Q4) 12.53
Local Supplier Volume (TPC-H Q5) 61.52
Forecasting Revenue Change (TPC-H Q6) 12.22
Forecasting Revenue Change (TPC-H Q7) 44.55
National Market Share (TPC-H Q8) 55.27
Product Type Profit Measure (TPC-H Q9) 46.31
Forecasting Revenue Change (TPC-H Q10) 25.17
Important Stock Identification (TPC-H Q11) 4.57
Shipping Modes and Order Priority (TPC-H Q12) 16.31
Customer Distribution (TPC-H Q13) 17.05
Forecasting Revenue Change (TPC-H Q14) 13.15
Top Supplier Query (TPC-H Q15) 14.85
Parts/Supplier Relationship (TPC-H Q16) 3.24
Small-Quantity-Order Revenue (TPC-H Q17) 28.50
Large Volume Customer (TPC-H Q18) 24.69
Discounted Revenue (TPC-H Q19) 23.02
Potential Part Promotion (TPC-H Q20) 19.81
Suppliers Who Kept Orders Waiting Query (TPC-H Q21) 36.37
Global Sales Opportunity Query (TPC-H Q22) 14.66
### Loading [s]
timeGenerate timeIngesting timeSchema timeIndex timeLoad
Citus-BHT-8-1-1 18.0 3.0 1.0 80.0 107.0
### Geometric Mean of Medians of Timer Run [s]
Geo Times [s]
DBMS
Citus-BHT-8-1-1 0.02
### Power@Size ((3600*SF)/(geo times))
Power@Size [~Q/h]
DBMS
Citus-BHT-8-1-1 164766.43
### Throughput@Size ((runs*queries*streams*3600*SF)/(span of time))
time [s] count SF Throughput@Size
DBMS SF num_experiment num_client
Citus-BHT-8-1 1.0 1 1 2 1 1.0 39600.0
### Workflow
orig_name SF pods num_experiment num_client benchmark_start benchmark_end
Citus-BHT-8-1-1 Citus-BHT-8-1 1.0 8 1 1 1771346436 1771346438
#### Actual
DBMS Citus-BHT-8 - Pods [[1]]
#### Planned
DBMS Citus-BHT-8 - Pods [[1]]
### Tests
TEST passed: Geo Times [s] contains no 0 or NaN
TEST passed: Power@Size [~Q/h] contains no 0 or NaN
TEST passed: Throughput@Size contains no 0 or NaN
TEST passed: No SQL errors
TEST passed: No SQL warnings
TEST passed: Workflow as planned
TPC-H More Complex Example
At first we remove possibly existing PVC:
kubectl delete pvc bexhoma-storage-citus-tpch-10
kubectl delete pvc bxw-bexhoma-worker-citus-tpch-10-0
kubectl delete pvc bxw-bexhoma-worker-citus-tpch-10-1
kubectl delete pvc bxw-bexhoma-worker-citus-tpch-10-2
kubectl delete pvc bxw-bexhoma-worker-citus-tpch-10-3
Then we run TPC-H Power Test at SF=10. Note that this takes a lot of disk space including for indexes.
bexhoma tpch \
-dbms Citus \
-sf 10 \
-nc 2 \
-ne 1,1 \
-nlp 8 \
-nbp 1 \
-nw 4 \
-nwr 1 \
-nws 48 \
-xii -xic -xis \
-xdt \
-m \
-mc \
-ms $BEXHOMA_MS \
-t 14400 \
-tr \
-rss 50Gi \
-rst $BEXHOMA_STORAGE_CLASS \
-rnn $BEXHOMA_NODE_SUT -rnl $BEXHOMA_NODE_LOAD -rnb $BEXHOMA_NODE_BENCHMARK \
run &>$LOG_DIR/test_tpch_testcase_citus_2.log
Evaluate Results
test_tpch_testcase_citus_2.log
## Show Summary
### Workload
TPC-H Queries SF=10
Type: tpch
Duration: 1891s
Code: 1771346573
This includes the reading queries of TPC-H.
This experiment compares run time and resource consumption of TPC-H queries in different DBMS.
TPC-H (SF=10) data is loaded and benchmark is executed.
Query ordering is Q1 - Q22.
All instances use the same query parameters.
Timeout per query is 14400.
Import sets indexes and constraints after loading and recomputes statistics.
Experiment uses bexhoma version 0.8.20.
System metrics are monitored by a cluster-wide installation.
Experiment is limited to DBMS ['Citus'].
Import is handled by 8 processes (pods).
Loading is fixed to cl-worker19.
Benchmarking is fixed to cl-worker19.
SUT is fixed to cl-worker14.
Database is persisted to disk of type shared and size 50Gi.
Loading is tested with [1] threads, split into [8] pods.
Benchmarking is tested with [1] threads, split into [1] pods.
Benchmarking is run as [1, 1] times the number of benchmarking pods.
Experiment is run 2 times.
### Connections
Citus-BHT-8-1-1-1 uses docker image citusdata/citus:13.2.0-alpine
RAM:541008474112
CPU:AMD Opteron(tm) Processor 6378
Cores:64
host:5.15.0-164-generic
node:cl-worker14
disk:98902
volume_size:50.0G
volume_used:40.0M
cpu_list:0-63
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
requests_cpu:4
requests_memory:16Gi
worker 0
RAM:2164173176832
CPU:INTEL(R) XEON(R) PLATINUM 8570
Cores:224
host:6.8.0-90-generic
node:cl-worker36
disk:891932
volume_size:50.0G
volume_used:40.0M
cpu_list:0-223
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 1
RAM:1077382688768
CPU:AMD EPYC 7742 64-Core Processor
Cores:256
host:6.8.0-1044-nvidia
node:cl-worker28
disk:1360193
volume_size:50.0G
volume_used:40.0M
cpu_list:0-255
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 2
RAM:540579303424
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-94-generic
node:cl-worker22
disk:405675
volume_size:50.0G
volume_used:40.0M
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 3
RAM:1081742745600
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-90-generic
node:cl-worker29
disk:556344
volume_size:50.0G
volume_used:40.0M
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
eval_parameters
code:1771346573
BEXHOMA_REPLICAS:1
BEXHOMA_SHARDS:48
BEXHOMA_WORKERS:4
COLUMNAR:False
Citus-BHT-8-1-2-1 uses docker image citusdata/citus:13.2.0-alpine
RAM:541008474112
CPU:AMD Opteron(tm) Processor 6378
Cores:64
host:5.15.0-164-generic
node:cl-worker14
disk:98902
volume_size:50.0G
volume_used:40.0M
cpu_list:0-63
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
requests_cpu:4
requests_memory:16Gi
worker 0
RAM:2164173176832
CPU:INTEL(R) XEON(R) PLATINUM 8570
Cores:224
host:6.8.0-90-generic
node:cl-worker36
disk:891933
volume_size:50.0G
volume_used:40.0M
cpu_list:0-223
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 1
RAM:1077382688768
CPU:AMD EPYC 7742 64-Core Processor
Cores:256
host:6.8.0-1044-nvidia
node:cl-worker28
disk:1360193
volume_size:50.0G
volume_used:40.0M
cpu_list:0-255
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 2
RAM:540579303424
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-94-generic
node:cl-worker22
disk:405675
volume_size:50.0G
volume_used:40.0M
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 3
RAM:1081742745600
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-90-generic
node:cl-worker29
disk:556344
volume_size:50.0G
volume_used:40.0M
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
eval_parameters
code:1771346573
BEXHOMA_REPLICAS:1
BEXHOMA_SHARDS:48
BEXHOMA_WORKERS:4
COLUMNAR:False
Citus-BHT-8-2-1-1 uses docker image citusdata/citus:13.2.0-alpine
RAM:541008474112
CPU:AMD Opteron(tm) Processor 6378
Cores:64
host:5.15.0-164-generic
node:cl-worker14
disk:98902
volume_size:50.0G
volume_used:40.0M
cpu_list:0-63
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
requests_cpu:4
requests_memory:16Gi
worker 0
RAM:540579303424
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-94-generic
node:cl-worker22
disk:407685
volume_size:50.0G
volume_used:40.0M
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 1
RAM:2164173176832
CPU:INTEL(R) XEON(R) PLATINUM 8570
Cores:224
host:6.8.0-90-generic
node:cl-worker36
disk:891857
volume_size:50.0G
volume_used:40.0M
cpu_list:0-223
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 2
RAM:1077382688768
CPU:AMD EPYC 7742 64-Core Processor
Cores:256
host:6.8.0-1044-nvidia
node:cl-worker28
disk:1360194
volume_size:50.0G
volume_used:40.0M
cpu_list:0-255
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 3
RAM:1081742745600
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-90-generic
node:cl-worker29
disk:558495
volume_size:50.0G
volume_used:40.0M
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
eval_parameters
code:1771346573
BEXHOMA_REPLICAS:1
BEXHOMA_SHARDS:48
BEXHOMA_WORKERS:4
COLUMNAR:False
Citus-BHT-8-2-2-1 uses docker image citusdata/citus:13.2.0-alpine
RAM:541008474112
CPU:AMD Opteron(tm) Processor 6378
Cores:64
host:5.15.0-164-generic
node:cl-worker14
disk:98902
volume_size:50.0G
volume_used:40.0M
cpu_list:0-63
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
requests_cpu:4
requests_memory:16Gi
worker 0
RAM:540579303424
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-94-generic
node:cl-worker22
disk:407792
volume_size:50.0G
volume_used:40.0M
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 1
RAM:2164173176832
CPU:INTEL(R) XEON(R) PLATINUM 8570
Cores:224
host:6.8.0-90-generic
node:cl-worker36
disk:891857
volume_size:50.0G
volume_used:40.0M
cpu_list:0-223
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 2
RAM:1077382688768
CPU:AMD EPYC 7742 64-Core Processor
Cores:256
host:6.8.0-1044-nvidia
node:cl-worker28
disk:1360195
volume_size:50.0G
volume_used:40.0M
cpu_list:0-255
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 3
RAM:1081742745600
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-90-generic
node:cl-worker29
disk:558495
volume_size:50.0G
volume_used:40.0M
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
eval_parameters
code:1771346573
BEXHOMA_REPLICAS:1
BEXHOMA_SHARDS:48
BEXHOMA_WORKERS:4
COLUMNAR:False
### Errors (failed queries)
No errors
### Warnings (result mismatch)
No warnings
### Latency of Timer Execution [ms]
DBMS Citus-BHT-8-1-1-1 Citus-BHT-8-1-2-1 Citus-BHT-8-2-1-1 Citus-BHT-8-2-2-1
Pricing Summary Report (TPC-H Q1) 146.40 132.92 1015.53 134.61
Minimum Cost Supplier Query (TPC-H Q2) 15.44 13.73 822.44 17.55
Shipping Priority (TPC-H Q3) 33.77 34.58 457.77 33.34
Order Priority Checking Query (TPC-H Q4) 14.07 12.12 30.72 12.26
Local Supplier Volume (TPC-H Q5) 61.25 60.20 91.65 45.73
Forecasting Revenue Change (TPC-H Q6) 12.00 11.07 12.90 11.64
Forecasting Revenue Change (TPC-H Q7) 44.10 61.19 61.55 44.29
National Market Share (TPC-H Q8) 57.80 67.23 90.10 56.14
Product Type Profit Measure (TPC-H Q9) 47.01 62.14 74.44 46.62
Forecasting Revenue Change (TPC-H Q10) 25.28 25.60 25.75 24.72
Important Stock Identification (TPC-H Q11) 4.43 4.40 4.90 4.49
Shipping Modes and Order Priority (TPC-H Q12) 17.29 16.70 17.11 16.72
Customer Distribution (TPC-H Q13) 25.00 34.63 40.37 25.69
Forecasting Revenue Change (TPC-H Q14) 13.73 13.55 13.49 13.89
Top Supplier Query (TPC-H Q15) 126.00 44.52 105.02 35.50
Parts/Supplier Relationship (TPC-H Q16) 3.45 3.33 3.50 2.98
Small-Quantity-Order Revenue (TPC-H Q17) 46.28 52.84 41.66 40.03
Large Volume Customer (TPC-H Q18) 25.17 26.02 25.08 24.90
Discounted Revenue (TPC-H Q19) 23.77 23.41 24.10 23.10
Potential Part Promotion (TPC-H Q20) 88.03 133.04 124.29 39.75
Suppliers Who Kept Orders Waiting Query (TPC-H Q21) 37.93 37.20 30.66 36.50
Global Sales Opportunity Query (TPC-H Q22) 74.58 31.31 56.44 25.73
### Loading [s]
timeGenerate timeIngesting timeSchema timeIndex timeLoad
Citus-BHT-8-1-1-1 16.0 23.0 3.0 111.0 159.0
Citus-BHT-8-1-2-1 16.0 23.0 3.0 111.0 159.0
Citus-BHT-8-2-1-1 16.0 23.0 3.0 111.0 159.0
Citus-BHT-8-2-2-1 16.0 23.0 3.0 111.0 159.0
### Geometric Mean of Medians of Timer Run [s]
Geo Times [s]
DBMS
Citus-BHT-8-1-1-1 0.03
Citus-BHT-8-1-2-1 0.03
Citus-BHT-8-2-1-1 0.05
Citus-BHT-8-2-2-1 0.02
### Power@Size ((3600*SF)/(geo times))
Power@Size [~Q/h]
DBMS
Citus-BHT-8-1-1-1 1228092.71
Citus-BHT-8-1-2-1 1273426.74
Citus-BHT-8-2-1-1 739130.20
Citus-BHT-8-2-2-1 1470456.52
### Throughput@Size ((runs*queries*streams*3600*SF)/(span of time))
time [s] count SF Throughput@Size
DBMS SF num_experiment num_client
Citus-BHT-8-1-1 10.0 1 1 3 1 10.0 264000.0
Citus-BHT-8-1-2 10.0 1 2 2 1 10.0 396000.0
Citus-BHT-8-2-1 10.0 2 1 5 1 10.0 158400.0
Citus-BHT-8-2-2 10.0 2 2 2 1 10.0 396000.0
### Workflow
orig_name SF pods num_experiment num_client benchmark_start benchmark_end
Citus-BHT-8-1-1-1 Citus-BHT-8-1-1 10.0 8 1 1 1771347406 1771347409
Citus-BHT-8-1-2-1 Citus-BHT-8-1-2 10.0 8 1 2 1771347499 1771347501
Citus-BHT-8-2-1-1 Citus-BHT-8-2-1 10.0 8 2 1 1771348297 1771348302
Citus-BHT-8-2-2-1 Citus-BHT-8-2-2 10.0 8 2 2 1771348409 1771348411
#### Actual
DBMS Citus-BHT-8 - Pods [[1, 1], [1, 1]]
#### Planned
DBMS Citus-BHT-8 - Pods [[1, 1], [1, 1]]
### Ingestion - Loader
CPU [CPUs] Max CPU Max RAM [Gb] Max RAM Cached [Gb]
Citus-BHT-8-1-1 0 0 0.0 0.0
Citus-BHT-8-1-2 0 0 0.0 0.0
### Execution - SUT
CPU [CPUs] Max CPU Max RAM [Gb] Max RAM Cached [Gb]
Citus-BHT-8-1-1 0.0 0.02 0.53 0.59
Citus-BHT-8-1-2 0.0 0.01 0.53 0.58
Citus-BHT-8-2-1 0.0 0.00 0.51 0.83
Citus-BHT-8-2-2 0.0 0.00 0.51 0.96
### Execution - Benchmarker
CPU [CPUs] Max CPU Max RAM [Gb] Max RAM Cached [Gb]
Citus-BHT-8-1-1 0.0 0.0 0.0 0.0
Citus-BHT-8-1-2 0.0 0.0 0.0 0.0
Citus-BHT-8-2-1 0.0 0.0 0.0 0.0
Citus-BHT-8-2-2 0.0 0.0 0.0 0.0
### Tests
TEST passed: Geo Times [s] contains no 0 or NaN
TEST passed: Power@Size [~Q/h] contains no 0 or NaN
TEST passed: Throughput@Size contains no 0 or NaN
TEST passed: No SQL errors
TEST passed: No SQL warnings
TEST passed: Workflow as planned
TEST failed: Ingestion Loader contains 0 or NaN in CPU [CPUs]
TEST failed: Execution SUT contains 0 or NaN in CPU [CPUs]
TEST failed: Execution Benchmarker contains 0 or NaN in CPU [CPUs]
TPC-H Test Columnar Storage
Citus provides the option to make a table using columnar storage via USING COLUMNAR.
For Bexhoma’s TPC-H, you can activate makeing the distributed tables orders and lineitem use columnar storage via -xcol.
Note that this also means there will be no foreign key constraints and no indexes on these tables.
At first we remove possibly existing PVC:
kubectl delete pvc bexhoma-storage-citus-tpch-10
kubectl delete pvc bxw-bexhoma-worker-citus-tpch-10-0
kubectl delete pvc bxw-bexhoma-worker-citus-tpch-10-1
kubectl delete pvc bxw-bexhoma-worker-citus-tpch-10-2
kubectl delete pvc bxw-bexhoma-worker-citus-tpch-10-3
The experiment runs like this:
bexhoma tpch \
-dbms Citus \
-sf 10 \
-nc 2 \
-ne 1,1 \
-nlp 8 \
-nbp 1 \
-nw 4 \
-nwr 1 \
-nws 48 \
-xcol \
-xdt \
-m \
-mc \
-ms $BEXHOMA_MS \
-t 14400 \
-tr \
-rss 50Gi \
-rst $BEXHOMA_STORAGE_CLASS \
-rnn $BEXHOMA_NODE_SUT -rnl $BEXHOMA_NODE_LOAD -rnb $BEXHOMA_NODE_BENCHMARK \
run &>$LOG_DIR/test_tpch_testcase_citus_3.log
Evaluate Results
test_tpch_testcase_citus_3.log
## Show Summary
### Workload
TPC-H Queries SF=10
Type: tpch
Duration: 1898s
Code: 1771348585
This includes the reading queries of TPC-H.
This experiment compares run time and resource consumption of TPC-H queries in different DBMS.
TPC-H (SF=10) data is loaded and benchmark is executed.
Query ordering is Q1 - Q22.
All instances use the same query parameters.
Timeout per query is 14400.
Experiment uses bexhoma version 0.8.20.
System metrics are monitored by a cluster-wide installation.
Experiment is limited to DBMS ['Citus'].
Import is handled by 8 processes (pods).
Loading is fixed to cl-worker19.
Benchmarking is fixed to cl-worker19.
SUT is fixed to cl-worker14.
Database is persisted to disk of type shared and size 50Gi.
Loading is tested with [1] threads, split into [8] pods.
Benchmarking is tested with [1] threads, split into [1] pods.
Benchmarking is run as [1, 1] times the number of benchmarking pods.
Experiment is run 2 times.
### Connections
Citus-BHT-8-1-1-1 uses docker image citusdata/citus:13.2.0-alpine
RAM:541008474112
CPU:AMD Opteron(tm) Processor 6378
Cores:64
host:5.15.0-164-generic
node:cl-worker14
disk:98902
volume_size:50.0G
volume_used:40.0M
cpu_list:0-63
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
requests_cpu:4
requests_memory:16Gi
worker 0
RAM:540579303424
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-94-generic
node:cl-worker22
disk:407742
volume_size:50.0G
volume_used:40.0M
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 1
RAM:2164173176832
CPU:INTEL(R) XEON(R) PLATINUM 8570
Cores:224
host:6.8.0-90-generic
node:cl-worker36
disk:891874
volume_size:50.0G
volume_used:40.0M
cpu_list:0-223
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 2
RAM:1077382688768
CPU:AMD EPYC 7742 64-Core Processor
Cores:256
host:6.8.0-1044-nvidia
node:cl-worker28
disk:1360198
volume_size:50.0G
volume_used:40.0M
cpu_list:0-255
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 3
RAM:1081742745600
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-90-generic
node:cl-worker29
disk:558495
volume_size:50.0G
volume_used:40.0M
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
eval_parameters
code:1771348585
BEXHOMA_REPLICAS:1
BEXHOMA_SHARDS:48
BEXHOMA_WORKERS:4
COLUMNAR:True
Citus-BHT-8-1-2-1 uses docker image citusdata/citus:13.2.0-alpine
RAM:541008474112
CPU:AMD Opteron(tm) Processor 6378
Cores:64
host:5.15.0-164-generic
node:cl-worker14
disk:98902
volume_size:50.0G
volume_used:40.0M
cpu_list:0-63
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
requests_cpu:4
requests_memory:16Gi
worker 0
RAM:540579303424
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-94-generic
node:cl-worker22
disk:407742
volume_size:50.0G
volume_used:40.0M
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 1
RAM:2164173176832
CPU:INTEL(R) XEON(R) PLATINUM 8570
Cores:224
host:6.8.0-90-generic
node:cl-worker36
disk:891871
volume_size:50.0G
volume_used:40.0M
cpu_list:0-223
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 2
RAM:1077382688768
CPU:AMD EPYC 7742 64-Core Processor
Cores:256
host:6.8.0-1044-nvidia
node:cl-worker28
disk:1360198
volume_size:50.0G
volume_used:40.0M
cpu_list:0-255
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 3
RAM:1081742745600
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-90-generic
node:cl-worker29
disk:558495
volume_size:50.0G
volume_used:40.0M
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
eval_parameters
code:1771348585
BEXHOMA_REPLICAS:1
BEXHOMA_SHARDS:48
BEXHOMA_WORKERS:4
COLUMNAR:True
Citus-BHT-8-2-1-1 uses docker image citusdata/citus:13.2.0-alpine
RAM:541008474112
CPU:AMD Opteron(tm) Processor 6378
Cores:64
host:5.15.0-164-generic
node:cl-worker14
disk:98902
volume_size:50.0G
volume_used:40.0M
cpu_list:0-63
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
requests_cpu:4
requests_memory:16Gi
worker 0
RAM:540579303424
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-94-generic
node:cl-worker22
disk:409919
volume_size:50.0G
volume_used:40.0M
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 1
RAM:2164173176832
CPU:INTEL(R) XEON(R) PLATINUM 8570
Cores:224
host:6.8.0-90-generic
node:cl-worker36
disk:891866
volume_size:50.0G
volume_used:40.0M
cpu_list:0-223
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 2
RAM:1077382688768
CPU:AMD EPYC 7742 64-Core Processor
Cores:256
host:6.8.0-1044-nvidia
node:cl-worker28
disk:1360190
volume_size:50.0G
volume_used:40.0M
cpu_list:0-255
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 3
RAM:1081742745600
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-90-generic
node:cl-worker29
disk:560646
volume_size:50.0G
volume_used:40.0M
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
eval_parameters
code:1771348585
BEXHOMA_REPLICAS:1
BEXHOMA_SHARDS:48
BEXHOMA_WORKERS:4
COLUMNAR:True
Citus-BHT-8-2-2-1 uses docker image citusdata/citus:13.2.0-alpine
RAM:541008474112
CPU:AMD Opteron(tm) Processor 6378
Cores:64
host:5.15.0-164-generic
node:cl-worker14
disk:98902
volume_size:50.0G
volume_used:40.0M
cpu_list:0-63
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
requests_cpu:4
requests_memory:16Gi
worker 0
RAM:540579303424
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-94-generic
node:cl-worker22
disk:409940
volume_size:50.0G
volume_used:40.0M
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 1
RAM:2164173176832
CPU:INTEL(R) XEON(R) PLATINUM 8570
Cores:224
host:6.8.0-90-generic
node:cl-worker36
disk:891866
volume_size:50.0G
volume_used:40.0M
cpu_list:0-223
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 2
RAM:1077382688768
CPU:AMD EPYC 7742 64-Core Processor
Cores:256
host:6.8.0-1044-nvidia
node:cl-worker28
disk:1360191
volume_size:50.0G
volume_used:40.0M
cpu_list:0-255
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
worker 3
RAM:1081742745600
CPU:AMD EPYC 7502 32-Core Processor
Cores:128
host:6.8.0-90-generic
node:cl-worker29
disk:560646
volume_size:50.0G
volume_used:40.0M
cpu_list:0-127
args:['-c', 'max_worker_processes=16', '-c', 'max_parallel_workers=16', '-c', 'max_parallel_workers_per_gather=8', '-c', 'max_parallel_maintenance_workers=4', '-c', 'max_wal_size=32GB', '-c', 'shared_buffers=16GB', '-c', 'max_connections=1024', '-c', 'autovacuum_max_workers=10', '-c', 'autovacuum_vacuum_cost_limit=3000', '-c', 'vacuum_cost_limit=1000', '-c', 'checkpoint_completion_target=0.9', '-c', 'cpu_tuple_cost=0.03', '-c', 'effective_cache_size=32GB', '-c', 'maintenance_work_mem=512MB', '-c', 'wal_buffers=64MB', '-c', 'work_mem=64MB', '-c', 'temp_buffers=64MB', '-c', 'autovacuum_work_mem=-1', '-c', 'max_stack_depth=4MB', '-c', 'max_files_per_process=4000', '-c', 'effective_io_concurrency=32', '-c', 'wal_level=replica', '-c', 'max_wal_senders=8', '-c', 'synchronous_commit=local', '-c', 'checkpoint_timeout=1h', '-c', 'checkpoint_warning=0', '-c', 'autovacuum=on', '-c', 'max_locks_per_transaction=64', '-c', 'max_pred_locks_per_transaction=64', '-c', 'default_statistics_target=500', '-c', 'random_page_cost=1.1']
eval_parameters
code:1771348585
BEXHOMA_REPLICAS:1
BEXHOMA_SHARDS:48
BEXHOMA_WORKERS:4
COLUMNAR:True
### Errors (failed queries)
Citus-BHT-8-1-1-1 Citus-BHT-8-1-2-1 Citus-BHT-8-2-1-1 Citus-BHT-8-2-2-1
Pricing Summary Report (TPC-H Q1) True True True True
Shipping Priority (TPC-H Q3) True True True True
Order Priority Checking Query (TPC-H Q4) True True True True
Local Supplier Volume (TPC-H Q5) True True True True
Forecasting Revenue Change (TPC-H Q6) True True True True
Forecasting Revenue Change (TPC-H Q7) True True True True
National Market Share (TPC-H Q8) True True True True
Product Type Profit Measure (TPC-H Q9) True True True True
Forecasting Revenue Change (TPC-H Q10) True True True True
Shipping Modes and Order Priority (TPC-H Q12) True True True True
Customer Distribution (TPC-H Q13) True True True True
Forecasting Revenue Change (TPC-H Q14) True True True True
Top Supplier Query (TPC-H Q15) True True True True
Small-Quantity-Order Revenue (TPC-H Q17) True True True True
Large Volume Customer (TPC-H Q18) True True True True
Discounted Revenue (TPC-H Q19) True True True True
Potential Part Promotion (TPC-H Q20) True True True True
Suppliers Who Kept Orders Waiting Query (TPC-H Q21) True True True True
Global Sales Opportunity Query (TPC-H Q22) True True True True
Pricing Summary Report (TPC-H Q1)
Citus-BHT-8-1-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 357
Citus-BHT-8-2-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 357
Citus-BHT-8-2-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 357
Citus-BHT-8-1-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 357
Shipping Priority (TPC-H Q3)
Citus-BHT-8-1-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 111
Citus-BHT-8-2-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 111
Citus-BHT-8-2-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 111
Citus-BHT-8-1-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 111
Order Priority Checking Query (TPC-H Q4)
Citus-BHT-8-1-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 54
Citus-BHT-8-2-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 54
Citus-BHT-8-2-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 54
Citus-BHT-8-1-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 54
Local Supplier Volume (TPC-H Q5)
Citus-BHT-8-1-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 82
Citus-BHT-8-2-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 82
Citus-BHT-8-2-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 82
Citus-BHT-8-1-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 82
Forecasting Revenue Change (TPC-H Q6)
Citus-BHT-8-1-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 56
Citus-BHT-8-2-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 56
Citus-BHT-8-2-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 56
Citus-BHT-8-1-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 56
Forecasting Revenue Change (TPC-H Q7)
Citus-BHT-8-1-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 245
Citus-BHT-8-2-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 245
Citus-BHT-8-2-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 245
Citus-BHT-8-1-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 245
National Market Share (TPC-H Q8)
Citus-BHT-8-1-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 289
Citus-BHT-8-2-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 289
Citus-BHT-8-2-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 289
Citus-BHT-8-1-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 289
Product Type Profit Measure (TPC-H Q9)
Citus-BHT-8-1-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 231
Citus-BHT-8-2-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 231
Citus-BHT-8-2-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 231
Citus-BHT-8-1-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 231
Forecasting Revenue Change (TPC-H Q10)
Citus-BHT-8-1-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 169
Citus-BHT-8-2-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 169
Citus-BHT-8-2-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 169
Citus-BHT-8-1-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 169
Shipping Modes and Order Priority (TPC-H Q12)
Citus-BHT-8-1-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 256
Citus-BHT-8-2-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 256
Citus-BHT-8-2-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 256
Citus-BHT-8-1-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 256
Customer Distribution (TPC-H Q13)
Citus-BHT-8-1-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 129
Citus-BHT-8-2-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 129
Citus-BHT-8-2-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 129
Citus-BHT-8-1-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 129
Forecasting Revenue Change (TPC-H Q14)
Citus-BHT-8-1-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 164
Citus-BHT-8-2-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 164
Citus-BHT-8-2-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 164
Citus-BHT-8-1-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 164
Top Supplier Query (TPC-H Q15)
Citus-BHT-8-1-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 109
Citus-BHT-8-2-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 109
Citus-BHT-8-2-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 109
Citus-BHT-8-1-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 109
Small-Quantity-Order Revenue (TPC-H Q17)
Citus-BHT-8-1-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 57
Citus-BHT-8-2-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 57
Citus-BHT-8-2-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 57
Citus-BHT-8-1-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 57
Large Volume Customer (TPC-H Q18)
Citus-BHT-8-1-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 123
Citus-BHT-8-2-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 123
Citus-BHT-8-2-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 123
Citus-BHT-8-1-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 123
Discounted Revenue (TPC-H Q19)
Citus-BHT-8-1-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 65
Citus-BHT-8-2-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 65
Citus-BHT-8-2-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 65
Citus-BHT-8-1-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 65
Potential Part Promotion (TPC-H Q20)
Citus-BHT-8-1-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 82
Citus-BHT-8-2-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 82
Citus-BHT-8-2-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 82
Citus-BHT-8-1-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 82
Suppliers Who Kept Orders Waiting Query (TPC-H Q21)
Citus-BHT-8-1-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 51
Citus-BHT-8-2-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 51
Citus-BHT-8-2-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 51
Citus-BHT-8-1-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "lineitem" does not exist
Position: 51
Global Sales Opportunity Query (TPC-H Q22)
Citus-BHT-8-1-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 394
Citus-BHT-8-2-1-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 394
Citus-BHT-8-2-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 394
Citus-BHT-8-1-2-1: numRun 1: : org.postgresql.util.PSQLException: ERROR: relation "orders" does not exist
Position: 394
### Warnings (result mismatch)
No warnings
### Latency of Timer Execution [ms]
DBMS Citus-BHT-8-1-1-1 Citus-BHT-8-1-2-1 Citus-BHT-8-2-1-1 Citus-BHT-8-2-2-1
Minimum Cost Supplier Query (TPC-H Q2) 67.25 63.76 1159.86 63.86
Important Stock Identification (TPC-H Q11) 6.74 6.19 9.10 6.39
Parts/Supplier Relationship (TPC-H Q16) 6.41 6.56 7.21 6.88
### Loading [s]
timeGenerate timeIngesting timeSchema timeIndex timeLoad
Citus-BHT-8-1-1-1 16.0 23.0 2.0 74.0 118.0
Citus-BHT-8-1-2-1 16.0 23.0 2.0 74.0 118.0
Citus-BHT-8-2-1-1 16.0 23.0 2.0 74.0 118.0
Citus-BHT-8-2-2-1 16.0 23.0 2.0 74.0 118.0
### Geometric Mean of Medians of Timer Run [s]
Geo Times [s]
DBMS
Citus-BHT-8-1-1-1 0.01
Citus-BHT-8-1-2-1 0.01
Citus-BHT-8-2-1-1 0.04
Citus-BHT-8-2-2-1 0.01
### Power@Size ((3600*SF)/(geo times))
Power@Size [~Q/h]
DBMS
Citus-BHT-8-1-1-1 2523050.45
Citus-BHT-8-1-2-1 2621727.57
Citus-BHT-8-2-1-1 849706.81
Citus-BHT-8-2-2-1 2552136.17
### Throughput@Size ((runs*queries*streams*3600*SF)/(span of time))
time [s] count SF Throughput@Size
DBMS SF num_experiment num_client
Citus-BHT-8-1-1 10.0 1 1 2 1 10.0 54000.0
Citus-BHT-8-1-2 10.0 1 2 2 1 10.0 54000.0
Citus-BHT-8-2-1 10.0 2 1 3 1 10.0 36000.0
Citus-BHT-8-2-2 10.0 2 2 1 1 10.0 108000.0
### Workflow
orig_name SF pods num_experiment num_client benchmark_start benchmark_end
Citus-BHT-8-1-1-1 Citus-BHT-8-1-1 10.0 8 1 1 1771349410 1771349412
Citus-BHT-8-1-2-1 Citus-BHT-8-1-2 10.0 8 1 2 1771349509 1771349511
Citus-BHT-8-2-1-1 Citus-BHT-8-2-1 10.0 8 2 1 1771350299 1771350302
Citus-BHT-8-2-2-1 Citus-BHT-8-2-2 10.0 8 2 2 1771350402 1771350403
#### Actual
DBMS Citus-BHT-8 - Pods [[1, 1], [1, 1]]
#### Planned
DBMS Citus-BHT-8 - Pods [[1, 1], [1, 1]]
### Ingestion - Loader
CPU [CPUs] Max CPU Max RAM [Gb] Max RAM Cached [Gb]
Citus-BHT-8-1-1 0 0 0.0 0.0
Citus-BHT-8-1-2 0 0 0.0 0.0
### Execution - SUT
CPU [CPUs] Max CPU Max RAM [Gb] Max RAM Cached [Gb]
Citus-BHT-8-1-1 0.0 0.02 0.53 0.58
Citus-BHT-8-1-2 0.0 0.00 0.53 0.58
Citus-BHT-8-2-1 0.0 0.01 0.51 0.83
Citus-BHT-8-2-2 0.0 0.00 0.51 0.91
### Execution - Benchmarker
CPU [CPUs] Max CPU Max RAM [Gb] Max RAM Cached [Gb]
Citus-BHT-8-1-1 0.0 0.0 0.0 0.0
Citus-BHT-8-1-2 0.0 0.0 0.0 0.0
Citus-BHT-8-2-1 0.0 0.0 0.0 0.0
Citus-BHT-8-2-2 0.0 0.0 0.0 0.0
### Tests
TEST passed: Geo Times [s] contains no 0 or NaN
TEST passed: Power@Size [~Q/h] contains no 0 or NaN
TEST passed: Throughput@Size contains no 0 or NaN
TEST failed: SQL errors
TEST passed: No SQL warnings
TEST passed: Workflow as planned
TEST failed: Ingestion Loader contains 0 or NaN in CPU [CPUs]
TEST failed: Execution SUT contains 0 or NaN in CPU [CPUs]
TEST failed: Execution Benchmarker contains 0 or NaN in CPU [CPUs]