<!-- 
RSS generated by JIRA (9.4.14#940014-sha1:734e6822bbf0d45eff9af51f82432957f73aa32c) at Sat Feb 10 02:27:51 UTC 2024

It is possible to restrict the fields that are returned in this document by specifying the 'field' parameter in your request.
For example, to request only the issue key and summary append 'field=key&field=summary' to the URL of your request.
-->
<rss version="0.92" >
<channel>
    <title>Whamcloud Community JIRA</title>
    <link>https://jira.whamcloud.com</link>
    <description>This file is an XML representation of an issue</description>
    <language>en-us</language>    <build-info>
        <version>9.4.14</version>
        <build-number>940014</build-number>
        <build-date>05-12-2023</build-date>
    </build-info>


<item>
            <title>[LU-9628] LBUG (niobuf.c:773:ptl_send_rpc()) ASSERTION( (at_max == 0) || imp-&gt;imp_state != LUSTRE_IMP_FULL || (imp-&gt;imp_msghdr_flags &amp; 0x1) || !(imp-&gt;imp_connect_data.ocd_connect_flags &amp; 0x1000000ULL) ) failed:</title>
                <link>https://jira.whamcloud.com/browse/LU-9628</link>
                <project id="10000" key="LU">Lustre</project>
                    <description>&lt;p&gt;Soak client running soak test&lt;/p&gt;
&lt;div class=&quot;code panel&quot; style=&quot;border-width: 1px;&quot;&gt;&lt;div class=&quot;codeContent panelContent&quot;&gt;
&lt;pre class=&quot;code-java&quot;&gt;Jun  9 12:08:56 soak-16 systemd-logind: Removed session 1396.
Jun  9 12:09:24 soak-16 kernel: Lustre: soaked-MDT0000-mdc-ffff880828cb2000: Connection restored to 192.168.1.108@o2ib10 (at 192.168.1.108@o2ib10)
Jun  9 12:09:24 soak-16 kernel: LustreError: 11-0: soaked-OST0003-osc-ffff880828cb2000: operation ldlm_enqueue to node 192.168.1.104@o2ib10 failed: rc = -19
Jun  9 12:09:24 soak-16 kernel: LustreError: 2947:0:(&lt;span class=&quot;code-keyword&quot;&gt;import&lt;/span&gt;.c:671:ptlrpc_connect_import()) already connecting
Jun  9 12:09:25 soak-16 kernel: LustreError: 11-0: soaked-OST0003-osc-ffff880828cb2000: operation ldlm_enqueue to node 192.168.1.104@o2ib10 failed: rc = -107
Jun  9 12:09:25 soak-16 kernel: LustreError: Skipped 12826 previous similar messages
Jun  9 12:09:25 soak-16 kernel: LustreError: 2947:0:(&lt;span class=&quot;code-keyword&quot;&gt;import&lt;/span&gt;.c:671:ptlrpc_connect_import()) already connecting
Jun  9 12:09:25 soak-16 kernel: LustreError: 2947:0:(&lt;span class=&quot;code-keyword&quot;&gt;import&lt;/span&gt;.c:671:ptlrpc_connect_import()) Skipped 13048 previous similar messages
Jun  9 12:09:26 soak-16 kernel: LustreError: 167-0: soaked-OST0003-osc-ffff880828cb2000: This client was evicted by soaked-OST0003; in progress operations using &lt;span class=&quot;code-keyword&quot;&gt;this&lt;/span&gt; service will fail.
Jun  9 12:09:26 soak-16 kernel: LustreError: 2960:0:(client.c:1189:ptlrpc_import_delay_req()) @@@ invalidate in flight  req@ffff8805e1cf3900 x1569656575292352/t0(0) o101-&amp;gt;soaked-OST0003-osc-ffff880828cb2000@192.168.1.104@o2ib10:28/4 lens 328/400 e 0 to 1 dl 1497009748 ref 1 fl Rpc:X/0/ffffffff rc 0/-1
Jun  9 12:09:26 soak-16 kernel: LustreError: 2947:0:(client.c:1176:ptlrpc_import_delay_req()) @@@ invalidate in flight  req@ffff880624b19800 x1569656617848704/t0(0) o8-&amp;gt;soaked-OST0003-osc-ffff880828cb2000@192.168.1.104@o2ib10:28/4 lens 520/544 e 0 to 0 dl 0 ref 1 fl Rpc:N/0/ffffffff rc 0/-1
Jun  9 12:09:56 soak-16 kernel: LustreError: 2960:0:(niobuf.c:773:ptl_send_rpc()) ASSERTION( (at_max == 0) || imp-&amp;gt;imp_state != LUSTRE_IMP_FULL || (imp-&amp;gt;imp_msghdr_flags &amp;amp; 0x1) || !(imp-&amp;gt;imp_connect_data.ocd_connect_flags &amp;amp; 0x1000000ULL) ) failed:
Jun  9 12:09:56 soak-16 kernel: LustreError: 2960:0:(niobuf.c:773:ptl_send_rpc()) LBUG
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;
&lt;div class=&quot;code panel&quot; style=&quot;border-width: 1px;&quot;&gt;&lt;div class=&quot;codeContent panelContent&quot;&gt;
&lt;pre class=&quot;code-java&quot;&gt;[74364.267656] LustreError: 217188:0:(niobuf.c:773:ptl_send_rpc()) ASSERTION( (at_max == 0) || imp-&amp;gt;imp_state != LUSTRE_IMP_FULL || (imp-&amp;gt;imp_msghdr_flags &amp;amp; 0x1) || !(imp-&amp;gt;imp_connect_data.ocd_connect_flags &amp;amp; 0x1000000ULL) ) failed:
[74364.267659] LustreError: 217188:0:(niobuf.c:773:ptl_send_rpc()) LBUG
[74364.267661] Pid: 217188, comm: df
[74364.267661]
Call Trace:
[74364.267685]  [&amp;lt;ffffffffa08287ee&amp;gt;] libcfs_call_trace+0x4e/0x60 [libcfs]
[74364.267695]  [&amp;lt;ffffffffa082887c&amp;gt;] lbug_with_loc+0x4c/0xb0 [libcfs]
[74364.267747]  [&amp;lt;ffffffffa0b61c4f&amp;gt;] ptl_send_rpc+0xb1f/0xe60 [ptlrpc]
[74364.267815]  [&amp;lt;ffffffffa0b95203&amp;gt;] ? sptlrpc_req_refresh_ctx+0x153/0x900 [ptlrpc]
[74364.267856]  [&amp;lt;ffffffffa0b570f0&amp;gt;] ptlrpc_send_new_req+0x460/0xa60 [ptlrpc]
[74364.267894]  [&amp;lt;ffffffffa0b5bcc1&amp;gt;] ptlrpc_set_wait+0x3d1/0x900 [ptlrpc]
[74364.267906]  [&amp;lt;ffffffffa0e1a45d&amp;gt;] ? osc_statfs_async+0xfd/0x1e0 [osc]
[74364.267919]  [&amp;lt;ffffffffa0cd5e67&amp;gt;] ? lov_statfs_async+0xe7/0x730 [lov]
[74364.267928]  [&amp;lt;ffffffff811dd065&amp;gt;] ? kmem_cache_alloc_node_trace+0x125/0x220
[74364.267955]  [&amp;lt;ffffffffa0d7800d&amp;gt;] ll_statfs_internal+0x35d/0xf30 [lustre]
[74364.267959]  [&amp;lt;ffffffff812094ac&amp;gt;] ? lookup_fast+0xcc/0x2e0 
[74364.267963]  [&amp;lt;ffffffff8120bd83&amp;gt;] ? path_lookupat+0x83/0x7a0
[74364.267966]  [&amp;lt;ffffffff8120be16&amp;gt;] ? path_lookupat+0x116/0x7a0
[74364.267979]  [&amp;lt;ffffffffa0ebb798&amp;gt;] ? _nfs4_proc_statfs+0xc8/0xf0 [nfsv4]
[74364.268023]  [&amp;lt;ffffffffa0968519&amp;gt;] ? lprocfs_counter_add+0xf9/0x160 [obdclass]
[74364.268044]  [&amp;lt;ffffffffa0d78c64&amp;gt;] ll_statfs+0x84/0x180 [lustre]
[74364.268047]  [&amp;lt;ffffffff8120ed4d&amp;gt;] ? putname+0x3d/0x60
[74364.268052]  [&amp;lt;ffffffff812312b1&amp;gt;] statfs_by_dentry+0xa1/0x140
[74364.268054]  [&amp;lt;ffffffff8123136b&amp;gt;] vfs_statfs+0x1b/0xb0
[74364.268056]  [&amp;lt;ffffffff81231455&amp;gt;] user_statfs+0x55/0xa0
[74364.268059]  [&amp;lt;ffffffff812314c7&amp;gt;] SYSC_statfs+0x27/0x60
[74364.268062]  [&amp;lt;ffffffff812316ce&amp;gt;] SyS_statfs+0xe/0x10
[74364.268068]  [&amp;lt;ffffffff81696b09&amp;gt;] system_call_fastpath+0x16/0x1b
[74364.268069]
[74364.268070] Kernel panic - not syncing: LBUG
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;

&lt;p&gt;Crash dump is available on soak at /scratch/dumps/soak-16&lt;br/&gt;
vmcore-dmesg attached&lt;/p&gt;</description>
                <environment>Soak cluster&lt;br/&gt;
</environment>
        <key id="46607">LU-9628</key>
            <summary>LBUG (niobuf.c:773:ptl_send_rpc()) ASSERTION( (at_max == 0) || imp-&gt;imp_state != LUSTRE_IMP_FULL || (imp-&gt;imp_msghdr_flags &amp; 0x1) || !(imp-&gt;imp_connect_data.ocd_connect_flags &amp; 0x1000000ULL) ) failed:</summary>
                <type id="1" iconUrl="https://jira.whamcloud.com/secure/viewavatar?size=xsmall&amp;avatarId=11303&amp;avatarType=issuetype">Bug</type>
                                            <priority id="2" iconUrl="https://jira.whamcloud.com/images/icons/priorities/critical.svg">Critical</priority>
                        <status id="5" iconUrl="https://jira.whamcloud.com/images/icons/statuses/resolved.png" description="A resolution has been taken, and it is awaiting verification by reporter. From here issues are either reopened, or are closed.">Resolved</status>
                    <statusCategory id="3" key="done" colorName="success"/>
                                    <resolution id="3">Duplicate</resolution>
                                        <assignee username="wc-triage">WC Triage</assignee>
                                    <reporter username="cliffw">Cliff White</reporter>
                        <labels>
                            <label>soak</label>
                    </labels>
                <created>Fri, 9 Jun 2017 17:38:20 +0000</created>
                <updated>Thu, 1 Aug 2019 20:47:15 +0000</updated>
                            <resolved>Sat, 23 Feb 2019 22:40:41 +0000</resolved>
                                    <version>Lustre 2.10.0</version>
                    <version>Lustre 2.12.0</version>
                                                        <due></due>
                            <votes>0</votes>
                                    <watches>4</watches>
                                                                            <comments>
                            <comment id="206223" author="green" created="Thu, 24 Aug 2017 02:32:15 +0000"  >&lt;p&gt;I jut hit this assertion on my testbed, but the stacktrace is a bit different.&lt;/p&gt;

&lt;div class=&quot;preformatted panel&quot; style=&quot;border-width: 1px;&quot;&gt;&lt;div class=&quot;preformattedContent panelContent&quot;&gt;
&lt;pre&gt;[39956.774374] Lustre: DEBUG MARKER: == recovery-small test 29a: error adding new clients doesn&apos;t cause LBUG (bug 22273) ================== 22:11:33 (1503540693)
[39957.040948] Lustre: Failing over lustre-MDT0000
[39957.630050] Lustre: server umount lustre-MDT0000 complete
[39961.483178] LustreError: 166-1: MGC192.168.123.166@tcp: Connection to MGS (at 192.168.123.166@tcp) was lost; in progress operations using this service will fail
[39961.495128] Lustre: Evicted from MGS (at 192.168.123.166@tcp) after server handle changed from 0xaf506984f6812737 to 0xaf506984f6812967
[39961.508960] LustreError: 29451:0:(niobuf.c:776:ptl_send_rpc()) ASSERTION( (at_max == 0) || imp-&amp;gt;imp_state != LUSTRE_IMP_FULL || (imp-&amp;gt;imp_msghdr_flags &amp;amp; 0x1) || !(imp-&amp;gt;imp_connect_data.ocd_connect_flags &amp;amp; 0x1000000ULL) ) failed: 
[39961.511060] LustreError: 29451:0:(niobuf.c:776:ptl_send_rpc()) LBUG
[39961.511718] Pid: 29451, comm: ll_cfg_requeue
[39961.513004] 
Call Trace:
[39961.514239]  [&amp;lt;ffffffffa02187ce&amp;gt;] libcfs_call_trace+0x4e/0x60 [libcfs]
[39961.514937]  [&amp;lt;ffffffffa021885c&amp;gt;] lbug_with_loc+0x4c/0xb0 [libcfs]
[39961.515774]  [&amp;lt;ffffffffa05f8a82&amp;gt;] ptl_send_rpc+0xb82/0xec0 [ptlrpc]
[39961.516456]  [&amp;lt;ffffffff81383cf9&amp;gt;] ? snprintf+0x49/0x70
[39961.517160]  [&amp;lt;ffffffffa0223cb7&amp;gt;] ? libcfs_debug_msg+0x57/0x80 [libcfs]
[39961.517716]  [&amp;lt;ffffffffa05ed030&amp;gt;] ptlrpc_send_new_req+0x480/0xa90 [ptlrpc]
[39961.518300]  [&amp;lt;ffffffffa05f1d41&amp;gt;] ptlrpc_set_wait+0x3d1/0x900 [ptlrpc]
[39961.519663]  [&amp;lt;ffffffffa03a3255&amp;gt;] ? lustre_get_jobid+0x215/0x4d0 [obdclass]
[39961.520556]  [&amp;lt;ffffffffa05fe0b5&amp;gt;] ? lustre_msg_set_jobid+0x95/0x100 [ptlrpc]
[39961.521426]  [&amp;lt;ffffffffa05f22f7&amp;gt;] ptlrpc_queue_wait+0x87/0x230 [ptlrpc]
[39961.522688]  [&amp;lt;ffffffffa05ce426&amp;gt;] ldlm_cli_enqueue+0x686/0x810 [ptlrpc]
[39961.523845]  [&amp;lt;ffffffffa05c9200&amp;gt;] ? ldlm_completion_ast+0x0/0x920 [ptlrpc]
[39961.524621]  [&amp;lt;ffffffffa0595a10&amp;gt;] ? mgc_blocking_ast+0x0/0x7e0 [mgc]
[39961.525315]  [&amp;lt;ffffffffa059160a&amp;gt;] mgc_enqueue.isra.7.constprop.17+0x19a/0x320 [mgc]
[39961.526531]  [&amp;lt;ffffffffa0595a10&amp;gt;] ? mgc_blocking_ast+0x0/0x7e0 [mgc]
[39961.530457]  [&amp;lt;ffffffffa05c9200&amp;gt;] ? ldlm_completion_ast+0x0/0x920 [ptlrpc]
[39961.531168]  [&amp;lt;ffffffffa05973a3&amp;gt;] mgc_process_log+0x183/0x890 [mgc]
[39961.531866]  [&amp;lt;ffffffff810b7cc0&amp;gt;] ? default_wake_function+0x0/0x20
[39961.532519]  [&amp;lt;ffffffffa05999e0&amp;gt;] mgc_requeue_thread+0x2c0/0x870 [mgc]
[39961.533296]  [&amp;lt;ffffffff810b7cc0&amp;gt;] ? default_wake_function+0x0/0x20
[39961.534927]  [&amp;lt;ffffffffa0599720&amp;gt;] ? mgc_requeue_thread+0x0/0x870 [mgc]
[39961.535738]  [&amp;lt;ffffffff810a2eba&amp;gt;] kthread+0xea/0xf0
[39961.536395]  [&amp;lt;ffffffff810a2dd0&amp;gt;] ? kthread+0x0/0xf0
[39961.537054]  [&amp;lt;ffffffff8170fb98&amp;gt;] ret_from_fork+0x58/0x90
[39961.537702]  [&amp;lt;ffffffff810a2dd0&amp;gt;] ? kthread+0x0/0xf0
[39961.538352] 
[39961.539261] Kernel panic - not syncing: LBUG
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;

&lt;p&gt;this is on current lustre-master, crashdump is available&lt;/p&gt;</comment>
                            <comment id="231878" author="jamesanunez" created="Mon, 13 Aug 2018 19:32:29 +0000"  >&lt;p&gt;replay-single test_121 crash. Same assertion, stack trace is a bit different; &lt;a href=&quot;https://testing.whamcloud.com/test_sets/084a0e64-9d95-11e8-8ee3-52540065bddc&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://testing.whamcloud.com/test_sets/084a0e64-9d95-11e8-8ee3-52540065bddc&lt;/a&gt;. Core file can be found in /scratch/dumps/trevis-10vm1.trevis.whamcloud.com/10.9.4.107-2018-08-11-00:59:14 .&lt;/p&gt;

&lt;p&gt;From kernel-crash log&lt;/p&gt;
&lt;div class=&quot;preformatted panel&quot; style=&quot;border-width: 1px;&quot;&gt;&lt;div class=&quot;preformattedContent panelContent&quot;&gt;
&lt;pre&gt;[52958.205573] Lustre: DEBUG MARKER: == replay-single test 121: lock replay timed out and race ============================================ 00:55:47 (1533948947)
[52976.888014] LustreError: 4047:0:(import.c:673:ptlrpc_connect_import()) already connecting
[53155.279068] LustreError: 4047:0:(client.c:1179:ptlrpc_import_delay_req()) @@@ invalidate in flight  req@ffff8aa5771b3000 x1608454336137216/t0(0) o38-&amp;gt;lustre-MDT0000-mdc-ffff8aa59f230000@10.9.4.110@tcp:12/10 lens 520/544 e 0 to 0 dl 0 ref 1 fl Rpc:N/0/ffffffff rc 0/-1
[53156.576261] LustreError: 18862:0:(niobuf.c:782:ptl_send_rpc()) ASSERTION( (at_max == 0) || imp-&amp;gt;imp_state != LUSTRE_IMP_FULL || (imp-&amp;gt;imp_msghdr_flags &amp;amp; MSGHDR_AT_SUPPORT) || !(imp-&amp;gt;imp_connect_data.ocd_connect_flags &amp;amp; 0x1000000ULL) ) failed: 
[53156.578612] LustreError: 18862:0:(niobuf.c:782:ptl_send_rpc()) LBUG
[53156.579251] CPU: 0 PID: 18862 Comm: lfs Kdump: loaded Tainted: G           OE  ------------   3.10.0-862.9.1.el7.x86_64 #1
[53156.580457] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
[53156.581117] Call Trace:
[53156.581472]  [&amp;lt;ffffffffb690e84e&amp;gt;] dump_stack+0x19/0x1b
[53156.582040]  [&amp;lt;ffffffffc07657b2&amp;gt;] libcfs_call_trace+0x72/0x80 [libcfs]
[53156.582744]  [&amp;lt;ffffffffc076583c&amp;gt;] lbug_with_loc+0x4c/0xb0 [libcfs]
[53156.583491]  [&amp;lt;ffffffffc0ab225b&amp;gt;] ptl_send_rpc+0xb6b/0xe70 [ptlrpc]
[53156.585442]  [&amp;lt;ffffffffc0aa7730&amp;gt;] ptlrpc_send_new_req+0x460/0xa70 [ptlrpc]
[53156.586206]  [&amp;lt;ffffffffc0aac211&amp;gt;] ptlrpc_set_wait+0x291/0x790 [ptlrpc]
[53156.588327]  [&amp;lt;ffffffffc0aac78d&amp;gt;] ptlrpc_queue_wait+0x7d/0x220 [ptlrpc]
[53156.589081]  [&amp;lt;ffffffffc0a916f2&amp;gt;] ldlm_cli_enqueue+0x3d2/0x920 [ptlrpc]
[53156.592174]  [&amp;lt;ffffffffc0bed71a&amp;gt;] mdc_enqueue_base+0x30a/0x1c10 [mdc]
[53156.592825]  [&amp;lt;ffffffffc0bef77f&amp;gt;] mdc_intent_lock+0x12f/0x560 [mdc]
[53156.595867]  [&amp;lt;ffffffffc0a49bc9&amp;gt;] lmv_intent_lock+0x589/0x1980 [lmv]
[53156.599678]  [&amp;lt;ffffffffc0d46de9&amp;gt;] ll_inode_revalidate+0x169/0x800 [lustre]
[53156.600388]  [&amp;lt;ffffffffc0d474df&amp;gt;] ll_getattr+0x5f/0x700 [lustre]
[53156.602227]  [&amp;lt;ffffffffb6420e09&amp;gt;] vfs_getattr+0x49/0x80
[53156.602835]  [&amp;lt;ffffffffb6420f35&amp;gt;] vfs_fstatat+0x75/0xc0
[53156.603367]  [&amp;lt;ffffffffb64214f1&amp;gt;] SYSC_newlstat+0x31/0x60
[53156.611484]  [&amp;lt;ffffffffb642177e&amp;gt;] SyS_newlstat+0xe/0x10
[53156.612068]  [&amp;lt;ffffffffb6920795&amp;gt;] system_call_fastpath+0x1c/0x21
[53156.613337] Kernel panic - not syncing: LBUG
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;</comment>
                    </comments>
                <issuelinks>
                            <issuelinktype id="10010">
                    <name>Duplicate</name>
                                            <outwardlinks description="duplicates">
                                        <issuelink>
            <issuekey id="33707">LU-7558</issuekey>
        </issuelink>
                            </outwardlinks>
                                                        </issuelinktype>
                            <issuelinktype id="10011">
                    <name>Related</name>
                                                                <inwardlinks description="is related to">
                                                        </inwardlinks>
                                    </issuelinktype>
                    </issuelinks>
                <attachments>
                            <attachment id="26952" name="vmcore-dmesg.txt" size="256333" author="cliffw" created="Fri, 9 Jun 2017 17:38:17 +0000"/>
                    </attachments>
                <subtasks>
                    </subtasks>
                <customfields>
                                                                                                                                                                                            <customfield id="customfield_10890" key="com.atlassian.jira.plugins.jira-development-integration-plugin:devsummary">
                        <customfieldname>Development</customfieldname>
                        <customfieldvalues>
                            
                        </customfieldvalues>
                    </customfield>
                                                                                                                                                                                                                                                                                                                                                        <customfield id="customfield_10390" key="com.pyxis.greenhopper.jira:gh-lexo-rank">
                        <customfieldname>Rank</customfieldname>
                        <customfieldvalues>
                            <customfieldvalue>1|hzzenr:</customfieldvalue>

                        </customfieldvalues>
                    </customfield>
                                                                <customfield id="customfield_10090" key="com.pyxis.greenhopper.jira:gh-global-rank">
                        <customfieldname>Rank (Obsolete)</customfieldname>
                        <customfieldvalues>
                            <customfieldvalue>9223372036854775807</customfieldvalue>
                        </customfieldvalues>
                    </customfield>
                                                                                            <customfield id="customfield_10060" key="com.atlassian.jira.plugin.system.customfieldtypes:select">
                        <customfieldname>Severity</customfieldname>
                        <customfieldvalues>
                                <customfieldvalue key="10022"><![CDATA[3]]></customfieldvalue>

                        </customfieldvalues>
                    </customfield>
                                                                                                                                                                                                                                                                                                                                                        </customfields>
    </item>
</channel>
</rss>