Re: RAC interconnect packet size??
From: Greg Rahn <greg_at_structureddata.org>
Date: Tue, 21 Apr 2009 23:09:09 -0700
Message-ID: <a9c093440904212309r6ceb526bsf5ab09a1eccd02ba_at_mail.gmail.com>
Using MTU 9000 Jumbo Frames generally does just one thing: it lowers the system cpu time for systems that have significant amounts of interconnect traffic. The reduction in sys cpu time results from not having to break up database blocks into multiple frames (less system calls = less cpu used) when sent over the inconnect. It is quite convenient that an 8k db block fits in one single Jumbo Frame. Perhaps yet another reason that the default 8k db block is a nice choice.
Date: Tue, 21 Apr 2009 23:09:09 -0700
Message-ID: <a9c093440904212309r6ceb526bsf5ab09a1eccd02ba_at_mail.gmail.com>
Using MTU 9000 Jumbo Frames generally does just one thing: it lowers the system cpu time for systems that have significant amounts of interconnect traffic. The reduction in sys cpu time results from not having to break up database blocks into multiple frames (less system calls = less cpu used) when sent over the inconnect. It is quite convenient that an 8k db block fits in one single Jumbo Frame. Perhaps yet another reason that the default 8k db block is a nice choice.
On Tue, Apr 21, 2009 at 5:52 AM, Bobak, Mark <Mark.Bobak_at_proquest.com> wrote:
> You definitely *want* jumbo frames. --
Regards,
Greg Rahn
http://structureddata.org
-- http://www.freelists.org/webpage/oracle-lReceived on Wed Apr 22 2009 - 01:09:09 CDT