Comments on: Notes from land of I/O http://dom.as/2008/08/11/notes-from-land-of-io/ Sat, 17 Dec 2011 20:14:59 +0000 hourly 1 http://wordpress.com/ By: uncache! « domas mituzas: vaporware, inc. http://dom.as/2008/08/11/notes-from-land-of-io/#comment-1339 Fri, 26 Jun 2009 10:39:54 +0000 http://dammit.lt/?p=184#comment-1339 [...] selective OS cache purges, another is for those who run high performance databases. Remember the O_DIRECT serialization everywhere? Well, XFS does direct I/O in parallel, unless there are cached pages (and they can [...]

]]> By: Domas Mituzas http://dom.as/2008/08/11/notes-from-land-of-io/#comment-1338 Mon, 22 Jun 2009 07:06:59 +0000 http://dammit.lt/?p=184#comment-1338 All of them don’t serialize, if there’re no dirty pages.
All of them do, if there are.

Just make sure you don’t have dirty pages (don’t open ibdata with other programs), and you’ll be fine.

]]> By: Jeff http://dom.as/2008/08/11/notes-from-land-of-io/#comment-1337 Mon, 22 Jun 2009 07:01:16 +0000 http://dammit.lt/?p=184#comment-1337 Domas,

Did you ever find a kernel/xfs version that doesn’t serialize requests when using XFS/MySQL/O_DIRECT?

As far as I can tell, the only workaround (if you want O_DIRECT) is to have a battery backed write cache to minimize the serialization impact, since it seems that XFS, ext3, etc. all have this issue.

]]> By: angus http://dom.as/2008/08/11/notes-from-land-of-io/#comment-1336 Sat, 24 Jan 2009 10:54:29 +0000 http://dammit.lt/?p=184#comment-1336 it will be fun to reproduce it on ext4.
a xfs vs ext4 match !

]]> By: Mark Callaghan http://dom.as/2008/08/11/notes-from-land-of-io/#comment-1335 Tue, 19 Aug 2008 02:48:57 +0000 http://dammit.lt/?p=184#comment-1335 I reproduced the same performance (serialized writes when one file is used) for ext-2, O_DIRECT and SW RAID 0.

]]> By: Domas Mituzas http://dom.as/2008/08/11/notes-from-land-of-io/#comment-1334 Mon, 11 Aug 2008 19:22:32 +0000 http://dammit.lt/?p=184#comment-1334 Mark,

I didn’t test this with multiple files, but it may be one of workarounds. Of course, if you have write-behind caching at RAID controller level, it mitigates lots of the issue.

I didn’t try AIO though – may be one of possible workarounds too. It all also can be kernel dependent, there’re lots and lots of variables around and it is better to test ;-)

]]> By: Peter Zaitsev http://dom.as/2008/08/11/notes-from-land-of-io/#comment-1333 Mon, 11 Aug 2008 18:23:39 +0000 http://dammit.lt/?p=184#comment-1333 Mark,

Indeed using file per table helps a lot but you also need to keep in mind UNDO (in the main tablespace) and also you may have couple of tables being hot even in case of file_per_table configuration.

In general this is a big gotcha for O_DIRECT for write intensive workloads.

]]> By: Mark Callaghan http://dom.as/2008/08/11/notes-from-land-of-io/#comment-1332 Mon, 11 Aug 2008 17:57:47 +0000 http://dammit.lt/?p=184#comment-1332 Domas,

So if you use O_DIRECT with ext-2 and InnoDB, do you want to use file per table to reduce the problem from not getting concurrent IO requests to a file?

]]>