| From: | Scott Marlowe <scott(dot)marlowe(at)gmail(dot)com> |
|---|---|
| To: | Jon Nelson <jnelson+pgsql(at)jamponi(dot)net> |
| Cc: | Greg Smith <greg(at)2ndquadrant(dot)com>, pgsql-performance(at)postgresql(dot)org |
| Subject: | Re: sniff test on some PG 8.4 numbers |
| Date: | 2013-03-11 03:02:00 |
| Message-ID: | CAOR=d=182cu9njJiJbgmJXR39opbm0d9JNnHh29U0idCR5Xw9Q@mail.gmail.com |
| Views: | Whole Thread | Raw Message | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-performance |
On Sun, Mar 10, 2013 at 7:18 PM, Jon Nelson <jnelson+pgsql(at)jamponi(dot)net> wrote:
> It seems as though you say the write numbers are not believable,
> suggesting a value of 7,500 (roughly 1/4 what I'm getting). If I run
> the read test for 30 seconds I get - highly variable - between 300K
> and 400K tps. Why are these tps so high compared to your expectations?
> Note: I did get better results with HT on vs. with HT off, so I've
> left HT on for now.
go back and re-read greg's post. He explains why he thinks you'll
sustain less. Basically it's caching effects because no pg_xlog / wal
log writing happening. Once you get a feel for how fast it is, run
the test for 30 minutes to several hours to see how it goes. Then when
you have a weekend just leave it running a couple days. Still pretty
good numbers so far.
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Greg Smith | 2013-03-11 04:28:18 | Re: sniff test on some PG 8.4 numbers |
| Previous Message | Jon Nelson | 2013-03-11 01:18:09 | Re: sniff test on some PG 8.4 numbers |