| From: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> |
|---|---|
| To: | Brad Nicholson <bnichols(at)ca(dot)afilias(dot)info> |
| Cc: | Greg Smith <greg(at)2ndquadrant(dot)com>, André Volpato <andre(dot)volpato(at)ecomtecnologia(dot)com(dot)br>, pgsql-performance(at)postgresql(dot)org |
| Subject: | Re: AIX slow buffer reads |
| Date: | 2010-10-27 22:44:59 |
| Message-ID: | 29868.1288219499@sss.pgh.pa.us |
| Views: | Whole Thread | Raw Message | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-performance |
Brad Nicholson <bnichols(at)ca(dot)afilias(dot)info> writes:
> On 10/27/2010 4:10 PM, Tom Lane wrote:
>> AFAICT from googling, AIX does have posix_fadvise, though maybe it
>> doesn't do anything useful ...
> If there is an easy way to check if it does do anything useful? If so,
> I can check it out.
If you don't see any performance change in bitmap scans between
effective_io_concurrency = 0 and effective_io_concurrency = maybe 4 or
so, then you could probably conclude it's a no-op.
regards, tom lane
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Craig Ringer | 2010-10-27 23:24:33 | Re: Massive update, memory usage |
| Previous Message | Brad Nicholson | 2010-10-27 22:37:23 | Re: AIX slow buffer reads |