Oracle, Linux and direct I/O

Some time ago, I've published my intention to test various file systems on Linux for their ability to support direct I/O async I/O. Let me remind everybody who might not know, direct I/O bypasses the Linux buffer cache, behaving as if the file was a raw device. The primary goal is to avoid the overhead associated with the double buffering. The only easily available file system that supports direct I/O is JFS from IBM. So, I re-created my /oradata partition as JFS and set the filesystemio_options to setall. So far, so good. Everything worked like a charm.
I discovered that there was no signifficant difference between single user queries on Ext3 and JFS. For a single user configuration, everything was just about the same, but the usage of memory was signficantly higher with Ext3. I suspect that the benefits of direct I/O and JFS would show only under heavy, multi-user stress because Ext3 based database would cause swapping to start much sooner because of the dynamic buffer cache which would compete with oracle processes for memory. In other words, I was unsuccessful in producing a benchmark that makes sense, but I did notice (vmstat) that the system page I/O was signifficantly lower with JFS then with Ext3. I have quite a big sandbox at home (Athlon 1300 MHZ, 512k cache, 640 MB RAM, 3 disk drives
(120G, 40G, 20G, RH 8.0) and bringing it to start swapping would take
much more energy that I've had this weekend.

Mladen Gogala
Oracle DBA

Note:
This message is for the named person's use only. It may contain confidential, proprietary or legally privileged information. No confidentiality or privilege is waived or lost by any mistransmission. If you receive this message in error, please immediately delete it and all copies of it from your system, destroy any hard copies of it and notify the sender. You must not, directly or indirectly, use, disclose, distribute, print, or copy any part of this message if you are not the intended recipient. Wang Trading LLC and any of its subsidiaries each reserve the right to monitor all e-mail communications through its networks. Any views expressed in this message are those of the individual sender, except where the message states otherwise and the sender is authorized to state them to be the views of any such entity.

-- 
Please see the official ORACLE-L FAQ: http://www.orafaq.net
-- 
Author: Mladen Gogala
  INET: mladen_at_wangtrading.com

Fat City Network Services    -- 858-538-5051 http://www.fatcity.com
San Diego, California        -- Mailing list and web hosting services
---------------------------------------------------------------------
To REMOVE yourself from this mailing list, send an E-Mail message
to: ListGuru_at_fatcity.com (note EXACT spelling of 'ListGuru') and in
the message BODY, include a line containing: UNSUB ORACLE-L


(or the name of mailing list you want to be removed from).  You may

also send the HELP command for other information (like subscribing).