[Top] [All Lists]

Fragmentation Issue We Are Having

To: xfs@xxxxxxxxxxx
Subject: Fragmentation Issue We Are Having
From: David Fuller <dfuller@xxxxxxxxx>
Date: Wed, 11 Apr 2012 18:04:25 -0700
Dkim-signature: v=1; a=rsa-sha1; c=relaxed; d=epoch.com; h=mime-version :from:date:message-id:subject:to:content-type; s=smtp; bh=Z5rKv1 FOI+goSguIscoHJpYWSdQ=; b=EVvImnCp+5p9Zio20JsofbNZLMWqNpGlzckVeS gqp9PGCRrsJwOSeJSrdEMdGlA7Tk7FerzN886CqqhZExZw76rmU5ru78V8J174eY 0qo/gPPK606QX48oSjxGAxuCiZ9HgVqeiRh/VRob1mbXuSeKqE6sVT/NaGP7rje1 tDhSw=
Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=epoch.com; s=gmail; h=mime-version:from:date:message-id:subject:to:content-type; bh=3kRiS2Dqg8oH3b2MohV1ZaT2xA0Xj6aqQjUG8SbDdpk=; b=HvUyI+NBKGMKAhvAIfsO0du92h1PrhdoyXWL6yF4S+wM2dpsoi8ncp2/jGnjsHEjdj EZEPg9j4MIdUUqjFcm+9CB8tFyXAjzq+BwZtS59hvcoQD2I2Do3MzCvJu6FOxW7gGs4v sMXBXpg9rsSB4jvoBgA8pE7nT9btxYdt8toK4=
Domainkey-signature: a=rsa-sha1; c=nofws; d=epoch.com; h=mime-version:from :date:message-id:subject:to:content-type; q=dns; s=smtp; b=aPSUa aXr7XS5rVZ5lHkmIHTW2jNM1ktKJ8CwaqE28ckESDFOFyvy2D21excXy29lLiRTh NVq3IHOPcvZmU+3KlD/Sj76ge1M6akFnkCf3L1jaTEMhdedk8C4SF8JPPKdzR/FN xVNzhrethVY8dObK4Fv634L4my9xLCWsF+Indk=
We seen to be having an issue whereby our database server
gets to 90% or higher fragmentation.  When it gets to this point 
we would need to remove form production and defrag using the 
xfs_fsr tool.  The server does get a lot of writes and reads.  Is
there something we can do to reduce the fragmentation or could
this be a result of hard disk tweaks we use or mount options?

here is some fo the tweaks we do:

/bin/echo "512" > /sys/block/sda/queue/read_ahead_kb
/bin/echo "10000" > /sys/block/sda/queue/nr_requests
/bin/echo "512" > /sys/block/sdb/queue/read_ahead_kb
/bin/echo "10000" > /sys/block/sdb/queue/nr_requests
/bin/echo "noop" > /sys/block/sda/queue/scheduler
/bin/echo "noop" > /sys/block/sdb/queue/scheduler

Adn here are the mount options on one of our servers:

 xfs     rw,noikeep,allocsize=256M,logbufs=8,sunit=128,swidth=2304 

the sunit and swidth vary on each server based on disk drives.

We do use LVM on the volume where the mysql data is stored
as we need this for snapshotting.  Here is an example of a current state:

xfs_db -c frag -r /dev/mapper/vgmysql-lvmysql
actual 42586, ideal 3134, fragmentation factor 92.64%

David Fuller

<Prev in Thread] Current Thread [Next in Thread>