https://jira.whamcloud.com This file is an XML representation of an issue en-us 9.4.14 940014 05-12-2023 https://jira.whamcloud.com/browse/LU-1743 Lustre <p>This issue was created by maloo for Andreas Dilger &lt;adilger@whamcloud.com&gt;</p> <p>This issue relates to the following test suite run: <a href="https://maloo.whamcloud.com/test_sets/0e82b422-e499-11e1-9681-52540035b04c" class="external-link" target="_blank" rel="nofollow noopener">https://maloo.whamcloud.com/test_sets/0e82b422-e499-11e1-9681-52540035b04c</a>.</p> <p>The sub-test test_18a failed with the following error:</p> <blockquote> <p>error on ioctl 0x4008669a for '/mnt/lustre/d0.recovery-small/d18/f.recovery-small.18a' (3): Invalid argument<br/> error: setstripe: create stripe file '/mnt/lustre/d0.recovery-small/d18/f.recovery-small.18a' failed<br/> recovery-small test_18a: @@@@@@ FAIL: test_18a failed with 3 </p></blockquote> <p>Info required for matching: recovery-small 18a</p> LU-1743

failure on recovery-small test_18a:

Bug Minor Resolved Cannot Reproduce WC Triage Maloo Mon, 13 Aug 2012 15:11:24 +0000 Mon, 29 May 2017 05:00:50 +0000 Mon, 29 May 2017 05:00:50 +0000 Lustre 2.4.0 0 3 <p>This has hit 8 times on orion-head-sync and master branches since it first appeared on 2012-08-11 21:24:33:</p> <p><a href="https://maloo.whamcloud.com/test_sets/245cb502-e4a5-11e1-af05-52540035b04c" class="external-link" target="_blank" rel="nofollow noopener">https://maloo.whamcloud.com/test_sets/245cb502-e4a5-11e1-af05-52540035b04c</a><br/> <a href="https://maloo.whamcloud.com/test_sets/0e82b422-e499-11e1-9681-52540035b04c" class="external-link" target="_blank" rel="nofollow noopener">https://maloo.whamcloud.com/test_sets/0e82b422-e499-11e1-9681-52540035b04c</a><br/> <a href="https://maloo.whamcloud.com/test_sets/9ebe4ef4-e48d-11e1-9681-52540035b04c" class="external-link" target="_blank" rel="nofollow noopener">https://maloo.whamcloud.com/test_sets/9ebe4ef4-e48d-11e1-9681-52540035b04c</a><br/> <a href="https://maloo.whamcloud.com/test_sets/2f2343e8-e46e-11e1-af05-52540035b04c" class="external-link" target="_blank" rel="nofollow noopener">https://maloo.whamcloud.com/test_sets/2f2343e8-e46e-11e1-af05-52540035b04c</a><br/> <a href="https://maloo.whamcloud.com/test_sets/9527d7f6-e452-11e1-9681-52540035b04c" class="external-link" target="_blank" rel="nofollow noopener">https://maloo.whamcloud.com/test_sets/9527d7f6-e452-11e1-9681-52540035b04c</a><br/> <a href="https://maloo.whamcloud.com/test_sets/8f584f40-e452-11e1-af05-52540035b04c" class="external-link" target="_blank" rel="nofollow noopener">https://maloo.whamcloud.com/test_sets/8f584f40-e452-11e1-af05-52540035b04c</a><br/> <a href="https://maloo.whamcloud.com/test_sets/b31a44c6-e44b-11e1-9681-52540035b04c" class="external-link" target="_blank" rel="nofollow noopener">https://maloo.whamcloud.com/test_sets/b31a44c6-e44b-11e1-9681-52540035b04c</a><br/> <a href="https://maloo.whamcloud.com/test_sets/d5e5b064-e426-11e1-93f8-52540035b04c" class="external-link" target="_blank" rel="nofollow noopener">https://maloo.whamcloud.com/test_sets/d5e5b064-e426-11e1-93f8-52540035b04c</a></p> <p>This coincides with the change to 1GB MDT filesystem size, though I'm not quite sure how that would have caused the problem. We'll see whether this test starts passing now that the MDT size has been increased to 2GB.</p> <p>Not sure whether it is related with this problem, but it is a clear mistake here</p> <p>: CMD: client-22vm3 /usr/sbin/mkfs.lustre --mgs --fsname=lustre --mdt --index=0 --param=sys.timeout=20 --param=lov.stripesize=1048576 --param=lov.stripecount=0 --param=mdt.identity_upcall=/usr/sbin/l_getidentity --backfstype=ldiskfs --device-size=1073741824 --mkfsoptions=\"-E lazy_itable_init\" --mountfsoptions=errors=remount-ro,iopen_nopriv,user_xattr,acl --reformat /dev/lvm-MDS/P1</p> <p> Permanent disk data:<br/> Target: lustre-MDT0000<br/> Index: 0<br/> Lustre FS: lustre<br/> Mount type: ldiskfs<br/> Flags: 0x65<br/> (MDT MGS first_time update )<br/> Persistent mount opts: errors=remount-ro,iopen_nopriv,user_xattr,acl<br/> Parameters: sys.timeout=20 lov.stripesize=1048576 lov.stripecount=0 mdt.identity_upcall=/usr/sbin/l_getidentity</p> <p>device size = 1024MB<br/> formatting backing filesystem ldiskfs on /dev/lvm-MDS/P1</p> <p>--device-size=1073741824, I guess it intend to set MDSSIZE to 1GB, instead of 1TB, though the max device_size of /dev/lvm-MDS-P1 might be just 1GB. But I am afraid some test script might based on this MDSSIZE? </p> <p>Chris, could you please fix this?</p> <p>another instance: <a href="https://maloo.whamcloud.com/test_sets/48c94224-5792-11e2-8772-52540035b04c" class="external-link" target="_blank" rel="nofollow noopener">https://maloo.whamcloud.com/test_sets/48c94224-5792-11e2-8772-52540035b04c</a></p> <p>The following instance:</p> <p><a href="https://maloo.whamcloud.com/test_sets/b532ff50-f953-11e2-8917-52540035b04c" class="external-link" target="_blank" rel="nofollow noopener">https://maloo.whamcloud.com/test_sets/b532ff50-f953-11e2-8917-52540035b04c</a></p> <p>clearly shows that one OST was not ready while setstripe was running, so function lod_qos_parse_config():</p> <div class="code panel" style="border-width: 1px;"><div class="codeContent panelContent"> <pre class="code-java"> <span class="code-keyword">if</span> ((v1-&gt;lmm_stripe_offset &gt;= d-&gt;lod_desc.ld_tgt_count) &amp;&amp; (v1-&gt;lmm_stripe_offset != (typeof(v1-&gt;lmm_stripe_offset))(-1))) { CERROR(<span class="code-quote">"invalid offset: %x\n"</span>, v1-&gt;lmm_stripe_offset); RETURN(-EINVAL); } </pre> </div></div> <p>returned EINVAL because stripe_offset equaled to ld_tgt_count which was 1. I didn't look further to figure out why ost2 was not up yet but probably it was due to previous recovery.</p> <p>Close old ticket.</p> Duplicate LU-6036 Related LU-1741 Development Rank 1|hzv3rz: Rank (Obsolete) 4135 Severity