On 04/08/09 13:10, Josh Berkus wrote:
> On 4/8/09 9:44 AM, Tom Lane wrote:
>> Josh Berkus<josh@agliodbs.com> writes:
>>> What about seq scans?
>>
>> If the kernel can't read-ahead a seqscan by itself, it's unlikely to
>> be smart enough to be helped by posix_fadvise ... or at least so I
>> would think. Do you have reason to think differently?
>
> Well, Solaris 10 + UFS should be helped by fadvise -- in theory at
> least, it would eliminate the need to modify your mount points for
> better readahead when setting up a PG-Solaris server. Solaris-UFS
> quite lazy about readahead. Zdenek, Jignesh?
>
Definitely this helps.. specially since forcedirectio hurts CLOGs and
helps WAL .. something that can be done without really impacting the
whole file system always helps.
Solaris by default only does readahead upto 56K and max tunable is 1MB.
If you use forcedirectio there is no readahead by the filesystem itself
ZFS is different it has no forcedirectio and hence fadvise flag for now
is ignored.
Regards,
Jignesh
> You're probably correct about Linux and FreeBSD. I don't know if OSX
> + HFS supports fadvise. If so, it could only help; readahead on HFS
> right now is nonexistant.
>
> Presumably fadvise is useless on Windows. Anyone know?
>
>