Heikki Linnakangas <heikki(at)enterprisedb(dot)com> wrote:
> It looks like the bgwriter gets starved waiting on the
> CheckpointStartLock. The CheckpointStartLock is held in shared mode over
> an XLogFlush when committing, which on an extremely busy system like a
> benchmark is always long enough to have a new transaction to acquire the
> CheckpointStartLock again.
If the starvation comes from giving unfair priorities on shared locks
against exclusive locks, does the below TODO item help us?
| Fix priority ordering of read and write light-weight locks (Neil)
NTT Open Source Software Center
In response to
pgsql-hackers by date
|Next:||From: Andrew - Supernews||Date: 2007-04-03 00:58:32|
|Subject: Re: Bug in UTF8-Validation Code?|
|Previous:||From: Bruce Momjian||Date: 2007-04-03 00:28:15|
|Subject: Re: [HACKERS] Arrays of Complex Types|