From: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> |
---|---|
To: | "t(dot)dalpozzo(at)gmail(dot)com" <t(dot)dalpozzo(at)gmail(dot)com> |
Cc: | pgsql-performance(at)postgresql(dot)org |
Subject: | Re: can't explain commit performance win7 vs linux : 8000/s vs 419/s |
Date: | 2016-06-25 18:08:35 |
Message-ID: | 17637.1466878115@sss.pgh.pa.us |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-performance |
"t(dot)dalpozzo(at)gmail(dot)com" <t(dot)dalpozzo(at)gmail(dot)com> writes:
> Performance:
> Win7: 8000 write/sec
> Linux: 419 write/sec
My immediate reaction to that is that Windows isn't actually writing
the data to disk when it should in order to guarantee that commits
are persistent. There are multiple layers that might be trying to
optimize away the writes, and I don't know enough about Windows to
help you debug it. But see
https://www.postgresql.org/docs/9.5/static/wal-reliability.html
for some discussion.
> I don't figure out why such a difference. Also what should I expect?
> Which one is reasonable?
The lower number sounds a lot more plausible for laptop-grade hardware.
If you weren't using an SSD I wouldn't believe that one was doing
persistent commits either.
regards, tom lane
From | Date | Subject | |
---|---|---|---|
Next Message | Jeff Janes | 2016-06-25 19:23:42 | Re: can't explain commit performance win7 vs linux : 8000/s vs 419/s |
Previous Message | t.dalpozzo@gmail.com | 2016-06-25 16:19:50 | can't explain commit performance win7 vs linux : 8000/s vs 419/s |