<!DOCTYPE html><html><head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body>
<p>Hi,</p>
<p>
<b>Question 1: Is it expected behavior that pools disappeared
after the Luster upgrade?</b></p>
<p>No this should not happen. Pool will disappear only if you do a
--writeconf on the targets. You should check the kernel logs to
see what happened.</p>
<p>Maybe you have some kind of configuration corruption/mismatch.
You can dump MGS configurations with:</p>
<p><tt>[root@mgs ~] debugfs -c -R 'dump CONFIGS/cluster-client
/tmp/cluster-client' /dev/<mgt_device> &&
llog_reader /tmp/cluster-client<br>
</tt><tt>[root@mgs ~] </tt><tt>debugfs -c -R 'dump
CONFIGS/cluster-MDT0000 /tmp/cluster-MDT0000'
/dev/<mgt_device> && llog_reader
/tmp/cluster-MDT0000</tt></p>
<p><tt>...</tt></p>
<p><b>
Question 2: Is it safe to ignore warning messages "OST ... not
found in pool ..." when adding OST to the pool.</b></p>
<p>Sometime, it takes time to synchronize all clients and targets
(because one or several nodes are unresponsive). But this can hide
a MGS communication issue too. You should check the kernel
messages.<br>
You can verify the clients states with "lfs pool_list cluster.ssd"
and the MDT states with "lctl pool_list cluster.ssd" (or lctl
get_param lov.cluster-*.pools.ssd for both).<br>
</p>
<p>Those kinds of behavior will be fixed by <a href="https://review.whamcloud.com/c/fs/lustre-release/+/53202">53202</a>:
<span id="output" class="style-scope gr-linked-text"><a href="https://jira.whamcloud.com/browse/LU-17308" target="_blank" rel="noopener" class="style-scope gr-linked-text">LU-17308</a> mgs: move
pool_cmd check to the kernel.</span></p>
<p><span id="output" class="style-scope gr-linked-text">Etienne<br>
</span></p>
<div class="moz-cite-prefix">On 8/1/24 14:00, Pavlo Khmel via
lustre-discuss wrote:<br>
</div>
<blockquote type="cite" cite="mid:CAHdVB2+oKru5LZCOCGC5cxS_u6hWXHubuo=1cCTf=8F9DWqCJQ@mail.gmail.com">
<div dir="ltr">Hi,<br>
<br>
I upgraded Luster from 2.12.8 to 2.15.5 (server and clients).
After upgrade, I found that all Lustre pools disappeared. There
were 2 pools:<br>
- cluster.ssh<br>
- cluster.hdd<br>
<br>
[root@mds1 ~]# lctl pool_list cluster<br>
Pools from cluster:<br>
<br>
[root@mds1 ~]# lctl pool_list cluster.ssd<br>
Pool: cluster.ssd<br>
lctl pool_list: cannot open
/proc/fs/lustre/lov/cluster-MDT0000-mdtlov/pools/ssd: No such
file or directory (2)<br>
<br>
[root@mds1 ~]# ls -la
/proc/fs/lustre/lov/cluster-MDT0000-mdtlov/pools/<br>
total 0<br>
dr-xr-xr-x 2 root root 0 Aug 1 10:49 .<br>
dr-xr-xr-x 4 root root 0 Aug 1 10:49 ..<br>
<br>
On the client side "lfs getstripe" still shows pool names.<br>
<br>
[root@login2 ~]# lfs getstripe /cluster<br>
. . .<br>
/cluster/home<br>
stripe_count: 1 stripe_size: 1048576 pattern: raid0
stripe_offset: -1 pool: hdd<br>
/cluster/apps<br>
stripe_count: 1 stripe_size: 1048576 pattern: raid0
stripe_offset: -1 pool: ssd<br>
<br>
I created pools again:<br>
<br>
[root@mds1 ~]# lctl pool_new cluster.ssd<br>
Pool cluster.ssd created<br>
<br>
[root@mds1 ~]# lctl pool_add cluster.ssd OST[0-3]<br>
Warning, OST cluster-OST0000_UUID not found in pool cluster.ssd<br>
OST cluster-OST0001_UUID added to pool cluster.ssd<br>
. . .<br>
<br>
Adding OSTs to the pool shows a warings message "OST ... not
found in pool ..." sometimes.<br>
<br>
Question 1: Is it expected behavior that pools disappeared after
the Luster upgrade?<br>
Question 2: Is it safe to ignore warning messages "OST ... not
found in pool ..." when adding OST to the pool.<br>
<div><br>
</div>
<div>Best regards,</div>
<div>Pavlo Khmel</div>
</div>
<br>
<fieldset class="moz-mime-attachment-header"></fieldset>
<pre class="moz-quote-pre" wrap="">_______________________________________________
lustre-discuss mailing list
<a class="moz-txt-link-abbreviated" href="mailto:lustre-discuss@lists.lustre.org">lustre-discuss@lists.lustre.org</a>
<a class="moz-txt-link-freetext" href="http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org">http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org</a>
</pre>
</blockquote>
</body>
</html>