Open tbg opened 7 hours ago
As can be seen on the right here, disabling sql.metrics.statement_details.enabled improves peak throughput.
sql.metrics.statement_details.enabled
internal Slack thread
Microbenchmark shows:
$ benchdiff ./pkg/sql/tests -b -r 'Sysbench/SQL/3node/oltp_read_write' -d 1000x -c 10 name old time/op new time/op delta Sysbench/SQL/3node/oltp_read_write-24 14.1ms ± 1% 13.9ms ± 1% -1.62% (p=0.000 n=10+10) name old alloc/op new alloc/op delta Sysbench/SQL/3node/oltp_read_write-24 2.59MB ± 1% 2.54MB ± 0% -2.22% (p=0.000 n=8+7) name old allocs/op new allocs/op delta Sysbench/SQL/3node/oltp_read_write-24 17.7k ± 1% 17.5k ± 1% -1.63% (p=0.000 n=10+10)
"After" is with this diff:
Epic: CRDB-42584
Jira issue: CRDB-44822
This issue has multiple T-eam labels. Please make sure it only has one, or else issue synchronization will not work correctly.
:owl: Hoot! I am a Blathers, a bot for CockroachDB. My owner is dev-inf.
As can be seen on the right here, disabling
sql.metrics.statement_details.enabled
improves peak throughput.internal Slack thread
Microbenchmark shows:
"After" is with this diff:
Epic: CRDB-42584
Jira issue: CRDB-44822