Horton

Re: buffer assertion tripping under repeat pgbench load

Greg Smith <greg@2ndquadrant.com>

View thread View on postgr.es
From: Greg Smith <greg@2ndQuadrant.com>
To: Greg Stark <stark@mit.edu>
Cc: Tom Lane <tgl@sss.pgh.pa.us>, Simon Riggs <simon@2ndquadrant.com>, Andres Freund <andres@2ndquadrant.com>, PostgreSQL-development <pgsql-hackers@postgresql.org>
Date: 2012-12-27T00:00:51Z
Lists: pgsql-hackers 
On 12/26/12 5:28 PM, Greg Stark wrote:
> Did you ever say what kind of hardware it was? This is the local
> reference count so I can't see how it could be a race condition or
> anything like that but it sure smells a bit like one.

Agreed, that smell is the reason I'm proceeding so far like this is an 
obscure bug rather than something with my hardware or install.  The CPU 
is an Intel i7 870 using HyperThreading to simulate 8 cores, 16GB of 
RAM.  The database is on a single regular SATA drive.  I simplified the 
storage setup before I started public reports.

-- 
Greg Smith   2ndQuadrant US    greg@2ndQuadrant.com   Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.com

Commits

  1. Follow TLI of last replayed record, not recovery target TLI, in walsenders.

  2. Avoid holding vmbuffer pin after VACUUM.