Postgres Pro
Downloads
Home   >   mailing lists

Re: Log levels for checkpoint/bgwriter monitoring - Mailing list pgsql-hackers

From Tom Lane
Subject Re: Log levels for checkpoint/bgwriter monitoring
Date
Msg-id 22147.1173422618@sss.pgh.pa.us
Whole thread Raw
In response to Re: Log levels for checkpoint/bgwriter monitoring  (Greg Smith <gsmith@gregsmith.com>)
List pgsql-hackers
Tree view 
Greg Smith <gsmith@gregsmith.com> writes:
> With the pgbench workload, a substantial percentage of the buffer cache 
> ends up pinned.

[ raised eyebrow... ]  Prove that.  AFAIK it's impossible for the
pgbench queries to pin more than about three or four buffers per backend
concurrently.
        regards, tom lane

pgsql-hackers by date:

Previous
From: Galy Lee
Date:
Subject: Re: RFC: changing autovacuum_naptime semantics
Next
From: ITAGAKI Takahiro
Date:
Subject: Re: Log levels for checkpoint/bgwriter monitoring