<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body text="#000000" bgcolor="#FFFFFF">
<p><br>
</p>
<br>
<div class="moz-cite-prefix">On 07/24/2018 06:30 PM, Ravishankar N
wrote:<br>
</div>
<blockquote type="cite"
cite="mid:6438250d-7d1e-89bf-bfdb-9d79fb284e9d@redhat.com">
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<p><br>
</p>
<br>
<div class="moz-cite-prefix">On 07/24/2018 02:56 PM, Raghavendra
Gowdappa wrote:<br>
</div>
<blockquote type="cite"
cite="mid:CAFkORY8-FWYY433UJRrOtO4BOLDyHSEOVPar_a7RwC_RMxLzRA@mail.gmail.com">
<div dir="ltr">
<div>All,<br>
<br>
</div>
I was trying to debug regression failures on [1] and observed
that split-brain-resolution.t was failing consistently.<br>
<div>
<div>
<div><br>
=========================<br>
TEST 45 (line 88): 0 get_pending_heal_count patchy<br>
./tests/basic/afr/split-brain-resolution.t .. 45/45
RESULT 45: 1<br>
./tests/basic/afr/split-brain-resolution.t .. Failed
17/45 subtests <br>
<br>
Test Summary Report<br>
-------------------<br>
./tests/basic/afr/split-brain-resolution.t (Wstat: 0
Tests: 45 Failed: 17)<br>
Failed tests: 24-26, 28-36, 41-45<br>
</div>
<div><br>
</div>
<div><br>
</div>
<div>On probing deeper, I observed a curious fact - on
most of the failures stat was not served from md-cache,
but instead was wound down to afr which failed stat with
EIO as the file was in split brain. So, I did another
test:</div>
<div>* disabled md-cache</div>
<div>* mount glusterfs with attribute-timeout 0 and
entry-timeout 0</div>
<div><br>
</div>
<div>Now the test fails always. So, I think the test
relied on stat requests being absorbed either by kernel
attribute cache or md-cache. When its not happening
stats are reaching afr and resulting in failures of cmds
like getfattr etc. </div>
</div>
</div>
</div>
</blockquote>
<br>
This indeed seems to be the case. Is there any way we can avoid
the stat? When a getfattr is performed on the mount, aren't lookup
+ getfattr are the only fops that need to be hit in gluster? <br>
</blockquote>
<br>
Or should afr allow (f)stat even for replica-2 split-brains because
it is allowing lookup anyway (lookup cbk contains stat information
from one of its children) ?<br>
-Ravi<br>
<blockquote type="cite"
cite="mid:6438250d-7d1e-89bf-bfdb-9d79fb284e9d@redhat.com"> -Ravi<br>
<br>
<blockquote type="cite"
cite="mid:CAFkORY8-FWYY433UJRrOtO4BOLDyHSEOVPar_a7RwC_RMxLzRA@mail.gmail.com">
<div dir="ltr">
<div>
<div>
<div>Thoughts?<br>
</div>
<div><br>
</div>
<div>[1] <a href="https://review.gluster.org/#/c/20549/"
moz-do-not-send="true">https://review.gluster.org/#/c/20549/</a><br>
</div>
</div>
</div>
</div>
<br>
<fieldset class="mimeAttachmentHeader"></fieldset>
<br>
<pre wrap="">_______________________________________________
Gluster-devel mailing list
<a class="moz-txt-link-abbreviated" href="mailto:Gluster-devel@gluster.org" moz-do-not-send="true">Gluster-devel@gluster.org</a>
<a class="moz-txt-link-freetext" href="https://lists.gluster.org/mailman/listinfo/gluster-devel" moz-do-not-send="true">https://lists.gluster.org/mailman/listinfo/gluster-devel</a></pre>
</blockquote>
<br>
<br>
<fieldset class="mimeAttachmentHeader"></fieldset>
<br>
<pre wrap="">_______________________________________________
Gluster-devel mailing list
<a class="moz-txt-link-abbreviated" href="mailto:Gluster-devel@gluster.org">Gluster-devel@gluster.org</a>
<a class="moz-txt-link-freetext" href="https://lists.gluster.org/mailman/listinfo/gluster-devel">https://lists.gluster.org/mailman/listinfo/gluster-devel</a></pre>
</blockquote>
<br>
</body>
</html>