Robert Lor <Robert(dot)Lor(at)Sun(dot)COM> writes:
> I ran pgbench and fired up a DTrace script using the lwlock probes we've
> added, and it looks like BufMappingLock is the most contended lock, but
> CheckpointStartLocks are held for longer duration!
Those numbers look a bit suspicious --- I'd expect to see some of the
LWLocks being taken in both shared and exclusive modes, but you don't
show any such cases. You sure your script is counting correctly?
Also, it'd be interesting to count time spent holding shared lock
separately from time spent holding exclusive.
regards, tom lane
In response to
pgsql-performance by date
|Next:||From: Jim C. Nasby||Date: 2006-07-21 13:56:53|
|Subject: Re: [HACKERS] Sun Donated a Sun Fire T2000 to the PostgreSQL|
|Previous:||From: Petronenko D.S.||Date: 2006-07-21 13:35:30|
|Subject: postgres benchmarks|
pgsql-hackers by date
|Next:||From: Jim C. Nasby||Date: 2006-07-21 13:43:10|
|Subject: Re: Freezing tuples on pages dirtied by vacuum|
|Previous:||From: Jim C. Nasby||Date: 2006-07-21 13:29:01|
|Subject: Re: How does the planner deal with multiple possible indexes?|