Home > Storage > PowerFlex > White Papers > Dell APEX Block Storage for Azure: PostgreSQL Deployment and Performance on Kubernetes > Use case 2: TPCB-like workload
Pgbench uses the ‘-b tpcb-like’ option for running a UPDATE and SELECT statements or a read/write workload. The following example shows the pgbench parameters that were used to run TPCB-like workload on the PostgreSQL databases:
#pgbench --host <hostname> -U <username> -c <No. of concurrent sessions> -j <No. of worker threads> -T <No. of seconds to test the run> -b tpcb-like <database name> -p <port-number>
The test process runs the TPCB-like workload by increasing the number of concurrent database sessions gradually. The test goal is to achieve a maximum physical read and write IOPS generated by the databases while keeping the Dell APEX Block storage volume read latency about one millisecond.
The following figure shows that that the physical read and write IOPS increases with the number of concurrent database sessions for a TPCB-like workload.
The following figure shows that Dell APEX Block Storage can achieve a sustained rate of 65,000 physical read and write IOPS for during the TPCB-like workload with 900 concurrent database sessions.