Re: Spinlocks, yet again: analysis and proposed patches

Douglas McNaught <doug@mcnaught.org>

From: Douglas McNaught <doug@mcnaught.org>

To: Josh Berkus <josh@agliodbs.com>

Cc: pgsql-hackers@postgresql.org, Greg Stark <gsstark@mit.edu>, Tom Lane <tgl@sss.pgh.pa.us>, Marko Kreen <marko@l-t.ee>

Date: 2005-09-13T16:21:45Z

Lists: pgsql-hackers

Josh Berkus <josh@agliodbs.com> writes:

> Tom, All:
>
>> It seems to me what you've found is an outright bug in the linux scheduler.
>> Perhaps posting it to linux-kernel would be worthwhile.
>
> For people using this on Linux 2.6, which scheduler are you using?   Deadline 
> is the recommended one for databases, and does offer significant (+5-8%) 
> benefits in some heavy-contention environments, at least in OSDL tests.

I thought 'deadline' was an I/O scheduler, not a CPU scheduler?

-Doug