| From: | Scott Marlowe <scott(dot)marlowe(at)gmail(dot)com> |
|---|---|
| To: | Charles Nadeau <charles(dot)nadeau(at)gmail(dot)com> |
| Cc: | Mark Kirkwood <mark(dot)kirkwood(at)catalyst(dot)net(dot)nz>, "pgsql-performa(dot)" <pgsql-performance(at)postgresql(dot)org> |
| Subject: | Re: Very poor read performance, query independent |
| Date: | 2017-07-15 17:58:32 |
| Message-ID: | CAOR=d=0ut7s-PRrQX7thXjo8mSn1ssP4zhfjy6Y1TFm23KXKaA@mail.gmail.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-performance |
On Sat, Jul 15, 2017 at 11:53 AM, Charles Nadeau
<charles(dot)nadeau(at)gmail(dot)com> wrote:
> Mark,
>
> I increased the read ahead to 16384 and it doesn't improve performance. My
> RAID 0 use a stripe size of 256k, the maximum size supported by the
> controller.
Are your queries still spilling to disk for sorts? If this is the
case, and they're just too big to fit in memory, then you need to move
your temp space, where sorts happen, onto another disk array that
isn't your poor overworked raid-10 array. Contention between sorts and
reads can kill performance quick, esp on spinning rust.
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Mark Kirkwood | 2017-07-15 23:48:08 | Re: Very poor read performance, query independent |
| Previous Message | Charles Nadeau | 2017-07-15 17:53:56 | Re: Very poor read performance, query independent |