Re: Report: Linux huge pages with Postgres

On Sat, Nov 27, 2010 at 2:27 PM, Tom Lane <tgl@sss.pgh.pa.us> wrote:
> For testing purposes, I figured that what I wanted to stress was
> postgres process swapping and shmem access.  I built current git HEAD
> with --enable-debug and no other options, and tested with these
> non-default settings:
>  shared_buffers         1GB
>  checkpoint_segments    50
>  fsync                  off
> (fsync intentionally off since I'm not trying to measure disk speed).
> The test machine has two dual-core Nehalem CPUs.  Test case is pgbench
> at -s 25; I ran several iterations of "pgbench -c 10 -T 60 bench"
> in each configuration.
>
> And the bottom line is: if there's any performance benefit at all,
> it's on the order of 1%.  The best result I got was about 3200 TPS
> with hugepages, and about 3160 without.  The noise in these numbers
> is more than 1% though.
>
> This is discouraging; it certainly doesn't make me want to expend the
> effort to develop a production patch.  However, perhaps someone else
> can try to show a greater benefit under some other test conditions.

Hmm.  Presumably in order to see a large benefit, you would need to
have shared_buffers set large enough to thrash the TLB.  I have no
idea how big TLBs on modern systems are, but it'd be interesting to
test this on a big machine with 8GB of shared buffers.

--
Robert Haas
EnterpriseDB: http://www.enterprisedb.com
The Enterprise PostgreSQL Company