Re: Spinlocks, yet again: analysis and proposed patches

Greg Stark <gsstark@mit.edu>

From: Greg Stark <gsstark@mit.edu>
To: Tom Lane <tgl@sss.pgh.pa.us>
Cc: Kurt Roeckx <kurt@roeckx.be>, pgsql-hackers@postgresql.org
Date: 2005-09-12T03:40:11Z
Lists: pgsql-hackers
Tom Lane <tgl@sss.pgh.pa.us> writes:

> > Something else to consider is the OS you're using.  I've been
> > told that Linux isn't that good in NUMA and FreeBSD might be
> > better.
> 
> It's hard to see how the OS could affect behavior at the level of
> processor cache operations --- unless they did something truly
> spectacularly stupid, like mark main memory non-cacheable.

Well it could schedule processes on processors in ways that force less than
optimal memory usage patterns.

But maybe you should tell the Altix folk with their 32-processor 384Gb NUMA
machines what you've "been told" about Linux not being that good in NUMA.
Really, these kind of cargo cult anecdotes are pretty pointless.

-- 
greg