<html><head><meta http-equiv="content-type" content="text/html; charset=utf-8"></head><body dir="auto">Filesystem quiesce failed has nothing to do with open files. <div>What it means is that the filesystem couldn’t flush dirty data and metadata within a defined time to take a snapshot. This can be caused by to high maxfilestocache or pagepool settings. </div><div>To give you an simplified example (its more complex than that, but good enough to make the point) - assume you have 100 nodes, each has 16 GB pagepool and your storage system can write data out at 10 GB/sec, it will take 160 seconds to flush all data data (assuming you did normal buffered I/O.</div><div>If i remember correct (talking out of memory here) the default timeout is 60 seconds, given that you can’t write that fast it will always timeout under this scenario. </div><div><span style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0);">There is one case where this can also happen which is a client is connected badly (flaky network or slow connection) and even your storage system is fast enough the node is too slow that it can’t de-stage within that time while everybody else can and the storage is not the bottleneck. Other than that</span> only solutions are to a) buy faster storage or b) reduce pagepool and maxfilestocache which will reduce overall performance of the system.</div><div></div><div><br></div><div>Sven</div><div><br><br><div dir="ltr">Sent from my iPad</div><div dir="ltr"><br><blockquote type="cite">On Feb 20, 2020, at 5:14 PM, Nathan Falk <nfalk@us.ibm.com> wrote:<br><br></blockquote></div><blockquote type="cite"><div dir="ltr"><span style=" font-size:10pt;font-family:sans-serif">Good point, Simon.
Yes, it is a "file system quiesce" not a "fileset quiesce"
so it is certainly possible that mmfsd is unable to quiesce because there
are processes keeping files open in another fileset.<br></span><br><br><span style=" font-size:9pt;font-family:Arial"><br></span><table width="650" style="border-collapse:collapse;"><tbody><tr height="8"><td width="650" style="border-style:none none none none;border-color:#000000;border-width:0px 0px 0px 0px;padding:0px 0px;"><span style=" font-size:12pt;color:#8f8f8f;font-family:Arial"><b>Nate
Falk</b></span><span style=" font-size:9pt;font-family:Arial"><br>IBM Spectrum Scale Level 2 Support<br>Software Defined Infrastructure, IBM Systems</span></td></tr></tbody></table><p style="margin-top:0px;margin-Bottom:0px"></p><table width="650" style="border-collapse:collapse;"><tbody><tr height="8"><td width="650" colspan="2" style="border-style:none none none none;border-color:#000000;border-width:0px 0px 0px 0px;padding:0px 0px;"></td></tr><tr valign="top" height="8"><td width="363" style="border-style:none none none none;border-color:#000000;border-width:0px 0px 0px 0px;padding:0px 0px;"></td><td width="286" style="border-style:none none none none;border-color:#000000;border-width:0px 0px 0px 0px;padding:0px 0px;"><div align="right"></div></td></tr></tbody></table><p style="margin-top:0px;margin-Bottom:0px"></p><br><br><br><br><span style=" font-size:9pt;color:#5f5f5f;font-family:sans-serif">From:
</span><span style=" font-size:9pt;font-family:sans-serif">Simon
Thompson <S.J.Thompson@bham.ac.uk></span><br><span style=" font-size:9pt;color:#5f5f5f;font-family:sans-serif">To:
</span><span style=" font-size:9pt;font-family:sans-serif">gpfsug
main discussion list <gpfsug-discuss@spectrumscale.org></span><br><span style=" font-size:9pt;color:#5f5f5f;font-family:sans-serif">Date:
</span><span style=" font-size:9pt;font-family:sans-serif">02/20/2020
04:39 PM</span><br><span style=" font-size:9pt;color:#5f5f5f;font-family:sans-serif">Subject:
</span><span style=" font-size:9pt;font-family:sans-serif">[EXTERNAL]
Re: [gpfsug-discuss] Unkillable snapshots</span><br><span style=" font-size:9pt;color:#5f5f5f;font-family:sans-serif">Sent
by: </span><span style=" font-size:9pt;font-family:sans-serif">gpfsug-discuss-bounces@spectrumscale.org</span><br><hr noshade=""><br><br><p style="margin-top:0px;margin-Bottom:0px"><span style=" font-size:12pt;font-family:Calibri">Hi
Nate,</span></p><p style="margin-top:0px;margin-Bottom:0px"></p><p style="margin-top:0px;margin-Bottom:0px"><span style=" font-size:12pt;font-family:Calibri">So
we're trying to clean up snapshots from the GUI ... we've found that if
it fails to delete one night for whatever reason, it then doesn't go back
another day and clean up 😊</span></p><p style="margin-top:0px;margin-Bottom:0px"></p><p style="margin-top:0px;margin-Bottom:0px"><span style=" font-size:12pt;font-family:Calibri">But
yes, essentially running this by hand to clean up.</span></p><p style="margin-top:0px;margin-Bottom:0px"></p><p style="margin-top:0px;margin-Bottom:0px"><span style=" font-size:12pt;font-family:Calibri">What
I have found is that lsof hangs on some of the "suspect" nodes.
But if I strace it, its hanging on a process which is using a different
fileset. For example, the file-set we can't delete is:</span></p><p style="margin-top:0px;margin-Bottom:0px"></p><p style="margin-top:0px;margin-Bottom:0px"><span style=" font-size:12pt;font-family:Calibri">rds-projects-b
which is mounted as /rds/projects/b</span></p><p style="margin-top:0px;margin-Bottom:0px"></p><p style="margin-top:0px;margin-Bottom:0px"><span style=" font-size:12pt;font-family:Calibri">But
on some suspect nodes, strace lsof /rds, that hangs at a process which
has open files in:</span></p><p style="margin-top:0px;margin-Bottom:0px"><span style=" font-size:12pt;font-family:Calibri">/rds/projects/g
which is a different file-set.</span></p><p style="margin-top:0px;margin-Bottom:0px"></p><p style="margin-top:0px;margin-Bottom:0px"><span style=" font-size:12pt;font-family:Calibri">What
I'm wondering if its these hanging processes in the "g" fileset
which is killing us rather than something in the "b" fileset.
Looking at the "g" processes, they look like a weather model
and look to be dumping a lot of files in a shared directory, so I wonder
if the mmfsd process is busy servicing that and so whilst its not got "b"
locks, its just too slow to respond?</span></p><p style="margin-top:0px;margin-Bottom:0px"></p><p style="margin-top:0px;margin-Bottom:0px"><span style=" font-size:12pt;font-family:Calibri">Does
that sound plausible?</span></p><p style="margin-top:0px;margin-Bottom:0px"></p><p style="margin-top:0px;margin-Bottom:0px"><span style=" font-size:12pt;font-family:Calibri">Thanks</span></p><p style="margin-top:0px;margin-Bottom:0px"></p><p style="margin-top:0px;margin-Bottom:0px"><span style=" font-size:12pt;font-family:Calibri">Simon</span></p><br><hr><br><span style=" font-size:11pt;font-family:Calibri"><b>From:</b> gpfsug-discuss-bounces@spectrumscale.org
<gpfsug-discuss-bounces@spectrumscale.org> on behalf of nfalk@us.ibm.com
<nfalk@us.ibm.com><b><br>Sent:</b> 20 February 2020 21:26:39<b><br>To:</b> gpfsug main discussion list<b><br>Subject:</b> Re: [gpfsug-discuss] Unkillable snapshots</span><span style=" font-size:12pt"></span><br><span style=" font-size:12pt"> </span><br><span style=" font-size:10pt">Hello Simon,</span><span style=" font-size:12pt"><br></span><span style=" font-size:10pt"><br>Sadly, that "1036" is not a node ID, but just a counter.</span><span style=" font-size:12pt"><br></span><span style=" font-size:10pt"><br>These are tricky to troubleshoot. Usually, by the time you realize it's
happening and try to collect some data, things have already timed out.</span><span style=" font-size:12pt"><br></span><span style=" font-size:10pt"><br>Since this mmdelsnapshot isn't something that's on a schedule from cron
or the GUI and is a command you are running, you could try some heavy-handed
data collection.</span><span style=" font-size:12pt"><br></span><span style=" font-size:10pt"><br>You suspect a particular fileset already, so maybe have a 'mmdsh -N all
lsof /path/to/fileset' ready to go in one window, and the 'mmdelsnapshot'
ready to go in another window? When the mmdelsnapshot times out, you can
find the nodes it was waiting on in the file system manager mmfs.log.latest
and see what matches up with the open files identified by lsof.</span><span style=" font-size:12pt"><br></span><span style=" font-size:10pt"><br>It sounds like you already know this, but the <c0n42> type of internal
node names in the log messages can be translated with 'mmfsadm dump tscomm'
or also plain old 'mmdiag --network'.</span><span style=" font-size:12pt"><br></span><span style=" font-size:10pt"><br>Thanks,</span><span style=" font-size:9pt;font-family:Arial"><br></span><table width="650" style="border-collapse:collapse;"><tbody><tr height="8"><td width="648" style="border-style:none none none none;border-color:#000000;border-width:0px 0px 0px 0px;padding:1px 1px;"><span style=" font-size:12pt;color:#8f8f8f;font-family:Arial"><b>Nate
Falk</b></span><span style=" font-size:9pt;font-family:Arial"><br>IBM Spectrum Scale Level 2 Support<br>Software Defined Infrastructure, IBM Systems</span></td></tr></tbody></table><br><table width="650" style="border-collapse:collapse;"><tbody><tr height="8"><td width="648" colspan="2" style="border-style:none none none none;border-color:#000000;border-width:0px 0px 0px 0px;padding:1px 1px;"></td></tr><tr valign="top" height="8"><td width="361" style="border-style:none none none none;border-color:#000000;border-width:0px 0px 0px 0px;padding:1px 1px;"></td><td width="284" style="border-style:none none none none;border-color:#000000;border-width:0px 0px 0px 0px;padding:1px 1px;"></td></tr></tbody></table><br><span style=" font-size:12pt"><br><br><br></span><span style=" font-size:9pt;color:#5f5f5f"><br>From: </span><span style=" font-size:9pt">Simon
Thompson <S.J.Thompson@bham.ac.uk></span><span style=" font-size:9pt;color:#5f5f5f"><br>To: </span><span style=" font-size:9pt">gpfsug
main discussion list <gpfsug-discuss@spectrumscale.org></span><span style=" font-size:9pt;color:#5f5f5f"><br>Date: </span><span style=" font-size:9pt">02/20/2020
03:14 PM</span><span style=" font-size:9pt;color:#5f5f5f"><br>Subject: </span><span style=" font-size:9pt">[EXTERNAL]
Re: [gpfsug-discuss] Unkillable snapshots</span><span style=" font-size:9pt;color:#5f5f5f"><br>Sent by: </span><span style=" font-size:9pt">gpfsug-discuss-bounces@spectrumscale.org</span><span style=" font-size:12pt"><br></span><hr noshade=""><span style=" font-size:12pt"><br></span><p style="margin-top:0px;margin-Bottom:0px"><span style=" font-size:12pt;font-family:Calibri">Hmm
... mmdiag --tokenmgr shows:</span></p><br><span style=" font-size:12pt;font-family:Calibri"><br> Server stats: requests 195417431 ServerSideRevokes 120140<br> nTokens 2146923 nranges 4124507<br> designated mnode appointed 55481 mnode
thrashing detected 1036</span><p style="margin-top:0px;margin-Bottom:0px"><span style=" font-size:12pt;font-family:Calibri">So
how do I convert "1036" to a node?</span></p><p style="margin-top:0px;margin-Bottom:0px"><span style=" font-size:12pt;font-family:Calibri">Simon</span></p><br><span style=" font-size:12pt"><br></span><hr><span style=" font-size:11pt;font-family:Calibri"><b><br>From:</b> gpfsug-discuss-bounces@spectrumscale.org <gpfsug-discuss-bounces@spectrumscale.org>
on behalf of Simon Thompson <S.J.Thompson@bham.ac.uk><b><br>Sent:</b> 20 February 2020 19:45:02<b><br>To:</b> gpfsug main discussion list<b><br>Subject:</b> [gpfsug-discuss] Unkillable snapshots</span><span style=" font-size:12pt"><br> </span><p style="margin-top:0px;margin-Bottom:0px"><span style=" font-size:12pt;font-family:Calibri">Hi,</span></p><p style="margin-top:0px;margin-Bottom:0px"><span style=" font-size:12pt;font-family:Calibri">We
have a snapshot which is stuck in the state "DeleteRequired".
When deleting, it goes through the motions but eventually gives up with:</span></p><br><span style=" font-size:12pt;font-family:Calibri"><br>Unable to quiesce all nodes; some processes are busy or holding required
resources.<br>mmdelsnapshot: Command failed. Examine previous error messages to determine
cause.</span><p style="margin-top:0px;margin-Bottom:0px"><span style=" font-size:12pt;font-family:Calibri">And
in the mmfslog on the FS manager there are a bunch of retries and "failure
to quesce" on nodes. However in each retry its never the same set
of nodes. I suspect we have one HPC job somewhere killing us.</span></p><p style="margin-top:0px;margin-Bottom:0px"><span style=" font-size:12pt;font-family:Calibri">What's
interesting is that we can delete other snapshots OK, it appears to be
one particular fileset.</span></p><p style="margin-top:0px;margin-Bottom:0px"><span style=" font-size:12pt;font-family:Calibri">My
old goto "mmfsadm dump tscomm" isn't showing any particular node,
and waiters around just tend to point to the FS manager node.</span></p><p style="margin-top:0px;margin-Bottom:0px"><span style=" font-size:12pt;font-family:Calibri">So
... any suggestions? I'm assuming its some workload holding a lock open
or some such, but tracking it down is proving elusive!</span></p><p style="margin-top:0px;margin-Bottom:0px"><span style=" font-size:12pt;font-family:Calibri">Generally
the FS is also "lumpy" ... at times it feels like a wifi connection
on a train using a terminal, I guess its all related though.</span></p><p style="margin-top:0px;margin-Bottom:0px"><span style=" font-size:12pt;font-family:Calibri">Thanks</span></p><p style="margin-top:0px;margin-Bottom:0px"><span style=" font-size:12pt;font-family:Calibri">Simon
</span></p><br><tt><span style=" font-size:10pt"><br>_______________________________________________<br>gpfsug-discuss mailing list<br>gpfsug-discuss at spectrumscale.org</span></tt><span style=" font-size:12pt;color:blue"><u><br></u></span><a href="http://gpfsug.org/mailman/listinfo/gpfsug-discuss"><tt><span style=" font-size:10pt;color:blue"><u>http://gpfsug.org/mailman/listinfo/gpfsug-discuss</u></span></tt></a><span style=" font-size:12pt"><br><br><br></span><br><tt><span style=" font-size:10pt">_______________________________________________<br>gpfsug-discuss mailing list<br>gpfsug-discuss at spectrumscale.org<br></span></tt><a href="http://gpfsug.org/mailman/listinfo/gpfsug-discuss"><tt><span style=" font-size:10pt">http://gpfsug.org/mailman/listinfo/gpfsug-discuss</span></tt></a><tt><span style=" font-size:10pt"><br></span></tt><br><br><br>
<span>_______________________________________________</span><br><span>gpfsug-discuss mailing list</span><br><span>gpfsug-discuss at spectrumscale.org</span><br><span>http://gpfsug.org/mailman/listinfo/gpfsug-discuss</span><br></div></blockquote></div></body></html>