Re: OT: high WIO on Linux

Kevin,

   A good observation. And one with which I agree.

   Are the depths of my I/O queues in any way "tunable" under Linux? (I'm pretty sure I recall tuning this under AIX...) I would expect that Linux will make some rather bland assumptions about the SCSI or FC "disks" it finds in my (hypothetical) RAID-array. Or is it smart enough to query the device in the hope of learning the best queue depth to use... (I have no doubt that the SCSI standards permit such queries, but that does not necessarily mean that the OS will bother to ask, nor that the device will provide a "truthful" answer.) Anyway, I would expect a RAID-array with a few GB of NVRAM to be able to support queue depths into the tens of thousands. Is that irrational?

   Normally, I wouldn't presume to ask questions like this on Oracle-L, but since I am the one who started this discussion, I think they're maybe fair game...

   Thanks to all who have provided responses thus far. They have been quite enlightening!

Cheers,
-- Mark.

Kevin Closson wrote:
> >>>In theory, Oracle's dbwr is supposed to be able to initiate
>
>>>> other io requests while wating for any given one to
>>>> complete. In practice there seems to be an empyrical limit
>>>> to this, not very clear why.
>>>>
>
> The only limiting factor on dbwr outstanding IO requests is
> the lower-level io queue depth. If you have really fast IO and
> really deep queues, you can see dbwr with well over a thousand
> outstanding IO requests.
>
> --
> http://www.freelists.org/webpage/oracle-l
>
>
>
>
>

--
http://www.freelists.org/webpage/oracle-l