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-8292 Lustre <p>With ZFS backend, ioctl(fd, FS_IOC_FIEMAP, fiemap) on the client results in an obd_get_info call to the OST(s).<br/> ZFS does not support FIEMAP, and so the dt_fiemap_get() call returns -ENOTSUPP. When the RPC reply is received by the client, two LustreError messages are sent to the console:</p> <div class="preformatted panel" style="border-width: 1px;"><div class="preformattedContent panelContent"> <pre>2016-06-16 10:04:23 LustreError: 11-0: lcy-OST0004-osc-ffff88044702bc00: Communicating with 10.1.1.175@o2ib9, operation ost_get_info failed with -95. 2016-06-16 10:04:23 LustreError: 3698:0:(file.c:1900:ll_do_fiemap()) obd_get_info failed: rc = -95 </pre> </div></div> <p>Since the user is notified of the ioctl failure, and the failure does not result in any compromise of the file system or the file data, this should not produce a console message.</p> <p>The RHEL6 cp command did not use this ioctl, but the RHEL7 one does. So with RHEL7 this has become much more noticable.</p> RHEL6.7 and RHEL7.2<br/> lustre-2.5.5-7chaos_2.6.32_642.1.1.1chaos.ch5.5.x86_64.x86_64<br/> lustre-2.8.0_0.0.llnlpreview.13-1.ch6.x86_64<br/> ZFS used as backend file system LU-8292

unnecessary LustreError 17754:0:(file.c:1900:ll_do_fiemap()) obd_get_info failed: rc = -95

Bug Minor Resolved Fixed Nathaniel Clark Olaf Faaland llnl llnlfixready zfs Thu, 16 Jun 2016 17:51:13 +0000 Tue, 14 Feb 2017 18:12:22 +0000 Mon, 3 Oct 2016 18:59:02 +0000 Lustre 2.5.5 0 5 <p>Nathaniel</p> <p>Could you please assist with this one?</p> <p>Peter</p> <p>The "ll_do_fiemap" message only appears in the 2.5 code. Are you using that release on el7?</p> <p>Two notes here:</p> <ul class="alternate" type="square"> <li>the "operation ost_get_info failed" message is because the RPC reply is marked as <tt>PTL_RPC_MSG_ERR</tt> (i.e. complete RPC failure) when it should be just a <tt>PTL_RPC_MSG_REPLY</tt> with an error code in rq_status.</li> <li>in <tt>ofd_get_info_hdl()</tt> there were changes in <a href="https://jira.whamcloud.com/browse/LU-3219" title="FIEMAP does not sync data or return cached pages" class="issue-link" data-issue-key="LU-3219"><del>LU-3219</del></a> to ensure FIEMAP would flush regions of the file that are currently being written, but if the initial <tt>ofd_fiemap_get()</tt> fails then there is no point in doing the extra locking and consistency checks: <div class="code panel" style="border-width: 1px;"><div class="codeContent panelContent"> <pre class="code-java"> rc = ofd_fiemap_get(tsi-&gt;tsi_env, ofd, fid, fiemap); /* LU-3219: Lock the sparse areas to make sure dirty * flushed back from client, then call fiemap again. */ <span class="code-keyword">if</span> (fm_key-&gt;lfik_oa.o_valid &amp; OBD_MD_FLFLAGS &amp;&amp; fm_key-&gt;lfik_oa.o_flags &amp; OBD_FL_SRVLOCK) { struct list_head locked; INIT_LIST_HEAD(&amp;locked); ost_fid_build_resid(fid, &amp;fti-&gt;fti_resid); rc = lock_zero_regions(ofd-&gt;ofd_namespace, &amp;fti-&gt;fti_resid, fiemap, &amp;locked); <span class="code-keyword">if</span> (rc == 0 &amp;&amp; !list_empty(&amp;locked)) { rc = ofd_fiemap_get(tsi-&gt;tsi_env, ofd, fid, fiemap); unlock_zero_regions(ofd-&gt;ofd_namespace, &amp;locked); } } </pre> </div></div></li> </ul> <p>That should all be done only <tt>if (!rc &amp;&amp; (...)</tt>.</p> <p>Nathaniel,</p> <p>My mistake, you're right. The ll_do_fiemap console message does not occur in 2.8. 2.8 produces only the "operation ost_get_info failed" console message Andreas describes.</p> <p>thanks,<br/> Olaf</p> <p>&gt; The "ll_do_fiemap" message only appears in the 2.5 code. Are you using that release on el7?</p> <p>Yes they have el7 for clients only</p> <p>No change needed to master. 2.5.x fix is flagged for LLNL to pickup</p> Related LU-8256 Development Rank 1|hzyevb: Rank (Obsolete) 9223372036854775807 Severity