Re: Sys stats Multi block read time less than single block read time

On 6/21/06, Allen, Brandon <Brandon.Allen_at_oneneck.com> wrote:
>
> Multiblock is sometimes faster than single block due to read-ahead
> functionality performed by your OS or disk array.
>
> Regards,
> Brandon
>
>
> Privileged/Confidential Information may be contained in this message or
> attachments hereto. Please advise immediately if you or your employer do not
> consent to Internet email for messages of this kind. Opinions, conclusions
> and other information in this message that do not relate to the official
> business of this company shall be understood as neither given nor endorsed
> by it.
>
> --
> http://www.freelists.org/webpage/oracle-l
>
>
>

It is a real bummer...Oracle regulary reports that our SAN has a better multiblock read than single block. Which is probably true - even non-Oracle I/O tests we've done show that behaviour (most probably due to SAN "smarts")

The pain with that is, if memory serves, systems stats are then ineffectual because Oracle doesn't like MREADTIM being less than SREADTIM. We've hacked around our system stats gathering to limit MREADTIM to no lower then SREADTIM + 0.00001 or thereabouts - we want system stats to be active so we can fiddle with MBRC versus db_file_multiblock_read_count

-- 
Connor McDonald
===========================
email: connor_mcdonald_at_yahoo.com
web:   http://www.oracledba.co.uk

"Semper in excremento, sole profundum qui variat"

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