On Mon, Jan 3, 2011 at 10:29 PM, Jonathan Disher wrote:
That's what we've been doing.  Again, the problem is, we still have to pull
the datanode out of rotation and change config, replace disk, put it back...
even if I have spares on hand and finish this in a few minutes, I still have
one empty disk and many tens of not-empty disks.
Aside from performance is there another issue? Ideally of course the
new disks would automatically get re-balanced, and you could
rate-limit the transfers to limit the impact on the machine.
Monitoring and identifying
the failure isn't the problem, we have that down pat.  I'm hoping for a
better way to re-balance the disks in the node after a failure.  I suspect
the sad answer is that what I'm doing now is the best thing for it.
HDFS-1312 tracks re-balancing disks within a datanode. Currently
people re-balance the directories manually when the datanode is
powered off (datanodes don't care which blocks reside in which volumes
so you can safely rebalance by hand).

On Jan 3, 2011, at 10:21 PM, Esteban Gutierrez Moguel wrote:

Hadoop will throw an exception according to the kind of error:
AccessControlException if its permission related or IOException for any
other disk related task.
A safer approach to handle physical failures would be monitoring syslog
messages (Syslog4j, nagios, ganglia, etc.) and if you are lucky enough and
the node doesn't hangs after the disk failure, you could shutdown it
On Mon, Jan 3, 2011 at 13:55, Jonathan Disher wrote:

The problem is, what do you define as a failure?  If the disk is failing,
writes will fail to the filesystem - how does Hadoop differentiate between
permissions and physical disk failure?  They both return error.

And yeah, the idea of stopping the datanode, removing the affected mount
from hdfs-site.xml, and restarting has been discussed.  The problem is, when
that disk gets replaced, and readded, then I have horrible internal balance
issues.  Thus causing the problem I have now :(

On Jan 3, 2011, at 9:07 AM, Eli Collins wrote:

Hey Jonathan,

There's an option (dfs.datanode.failed.volumes.tolerated, introduced
in HDFS-1161) that allows you to specify the number of volumes that
are allowed to fail before a datanode stops offering service.

There's an operational issue that still needs to be addressed
(HDFS-1158) that you should be aware of - the DN will still not start
if any of the volumes have failed, so to restart the DN you'll need
you'll need to either unconfigure the failed volumes or fix them. I'd
like to make DN startup respect the config value so it tolerates
failed volumes on startup as well.


On Sun, Jan 2, 2011 at 7:20 PM, Jonathan Disher <jdisher@parad.net>
I see that there was a thread on this in December, but I can't retrieve
it to reply properly, oh well.

So, I have a 30 node cluster (plus separate namenode, jobtracker, etc).
Each is a 12 disk machine - two mirrored 250GB OS disks, ten 1TB data disks
in JBOD.  Original system config was six 1TB data disks - we added the last
four disks months later.  I'm sure you can all guess, we have some
interesting internal usage balancing issues on most of the nodes.  To date,
when individual disks get critically low on space (earlier this week I had a
node with six disks around 97% full, four around 70%), we've been pulling
them from the cluster, formatting the data disks, and sticking them back in
(with a rebalance running to keep the cluster in some semblance of order).

Obviously if there was a better way to do this, I'd love to see it.  I
see that there are recommendations of killing the DataNode process and
manually moving files, but my concern is that the DataNode process will
spend an enormous amount of time tracking down these moves (currently around
820,000 blocks/node).  And it's not necessarily easy to automate, so there's
the danger of nuking blocks, and making the problems worse.  Are there
alternatives to manual moves (or more automated ways that exist)?  Or has my
brute-force rebalance got the best chance of success, albeit slowly?

We are also building a new cluster - starting around 1.2PB raw,
eventually growing to around 5PB, for near-line storage of data.  Our
storage nodes will probably be 4U systems with 72 data disks each (yeah,
good times).  The problem with this becomes obvious - with the way Hadoop
works today, if a disk fails, the datanode process chokes and dies when it
tries to write to it.  We've been told repeatedly that Hadoop doesn't
perform well when it operates on RAID arrays, but, to scale efffectively,
we're going to have to do just that - three 24 disk controllers in RAID-6
mode.  How bad is this going to be?  JBOD just doesn't scale beyond a couple
disks per machine, the failure rate will knock machines out of the cluster
too often (and at 60TB per node, rebalancing will take forever, even if I
let it saturate gigabit).

I appreciate opinions and suggestions.  Thanks!


Search Discussions

Discussion Posts


Related Discussions

Discussion Navigation
viewthread | post
posts ‹ prev | 7 of 7 | next ›
Discussion Overview
grouphdfs-user @
postedJan 3, '11 at 3:20a
activeJan 4, '11 at 5:34p



site design / logo © 2021 Grokbase