<!-- 
RSS generated by JIRA (9.4.14#940014-sha1:734e6822bbf0d45eff9af51f82432957f73aa32c) at Sat Feb 10 01:30:20 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-3027] Failure on test suite parallel-scale test_write_disjoint: invalid file size 140329 instead of 160376 = 20047 * 8</title>
                <link>https://jira.whamcloud.com/browse/LU-3027</link>
                <project id="10000" key="LU">Lustre</project>
                    <description>&lt;p&gt;This issue was created by maloo for sarah &amp;lt;sarah@whamcloud.com&amp;gt;&lt;/p&gt;

&lt;p&gt;This issue relates to the following test suite run: &lt;a href=&quot;https://maloo.whamcloud.com/test_sets/2ed1fef2-94bd-11e2-93c6-52540035b04c&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://maloo.whamcloud.com/test_sets/2ed1fef2-94bd-11e2-93c6-52540035b04c&lt;/a&gt;.&lt;/p&gt;

&lt;p&gt;The sub-test test_write_disjoint failed with the following error:&lt;/p&gt;
&lt;blockquote&gt;
&lt;p&gt;write_disjoint failed! 1&lt;/p&gt;&lt;/blockquote&gt;

&lt;p&gt;test log shows:&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;librdmacm: Fatal: no RDMA devices found
librdmacm: Fatal: no RDMA devices found
librdmacm: Fatal: no RDMA devices found
librdmacm: Fatal: no RDMA devices found
librdmacm: Fatal: no RDMA devices found
librdmacm: Fatal: no RDMA devices found
librdmacm: Fatal: no RDMA devices found
loop 0: chunk_size 103399
[client-27vm6.lab.whamcloud.com:00935] 7 more processes have sent help message help-mpi-btl-base.txt / btl:no-nics
[client-27vm6.lab.whamcloud.com:00935] Set MCA parameter &quot;orte_base_help_aggregate&quot; to 0 to see all help / error messages
loop 79: chunk_size 71702, file size was 573616
rank 2, loop 80: invalid file size 140329 instead of 160376 = 20047 * 8
loop 79: chunk_size 71702, file size was 573616
rank 4, loop 80: invalid file size 140329 instead of 160376 = 20047 * 8
loop 79: chunk_size 71702, file size was 573616
rank 6, loop 80: invalid file size 140329 instead of 160376 = 20047 * 8
loop 79: chunk_size 71702, file size was 573616
rank 0, loop 80: invalid file size 140329 instead of 160376 = 20047 * 8
--------------------------------------------------------------------------
MPI_ABORT was invoked on rank 4 in communicator MPI_COMM_WORLD 
with errorcode -1.
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;

&lt;p&gt;Looks like &lt;a href=&quot;https://jira.whamcloud.com/browse/LU-2453&quot; title=&quot;parallel-scale test_write_disjoint: invalid file size 723793 instead of 827192 = 103399 * 8&quot; class=&quot;issue-link&quot; data-issue-key=&quot;LU-2453&quot;&gt;&lt;del&gt;LU-2453&lt;/del&gt;&lt;/a&gt; is a similar issue seen in b2_1 branch&lt;/p&gt;</description>
                <environment></environment>
        <key id="18086">LU-3027</key>
            <summary>Failure on test suite parallel-scale test_write_disjoint: invalid file size 140329 instead of 160376 = 20047 * 8</summary>
                <type id="1" iconUrl="https://jira.whamcloud.com/secure/viewavatar?size=xsmall&amp;avatarId=11303&amp;avatarType=issuetype">Bug</type>
                                            <priority id="1" iconUrl="https://jira.whamcloud.com/images/icons/priorities/blocker.svg">Blocker</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="1">Fixed</resolution>
                                        <assignee username="green">Oleg Drokin</assignee>
                                    <reporter username="maloo">Maloo</reporter>
                        <labels>
                    </labels>
                <created>Mon, 25 Mar 2013 17:48:35 +0000</created>
                <updated>Fri, 8 Nov 2013 15:56:13 +0000</updated>
                            <resolved>Fri, 11 Oct 2013 18:06:33 +0000</resolved>
                                    <version>Lustre 2.4.0</version>
                    <version>Lustre 2.4.1</version>
                    <version>Lustre 2.5.0</version>
                                    <fixVersion>Lustre 2.4.2</fixVersion>
                                        <due></due>
                            <votes>0</votes>
                                    <watches>11</watches>
                                                                            <comments>
                            <comment id="63958" author="yujian" created="Fri, 9 Aug 2013 12:43:41 +0000"  >&lt;p&gt;The failure occurred regularly on Lustre b2_4 branch:&lt;br/&gt;
&lt;a href=&quot;https://maloo.whamcloud.com/test_sets/b571c2f0-fdac-11e2-9fd5-52540035b04c&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://maloo.whamcloud.com/test_sets/b571c2f0-fdac-11e2-9fd5-52540035b04c&lt;/a&gt;&lt;br/&gt;
&lt;a href=&quot;https://maloo.whamcloud.com/test_sets/d70a40f0-fcd9-11e2-b90c-52540035b04c&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://maloo.whamcloud.com/test_sets/d70a40f0-fcd9-11e2-b90c-52540035b04c&lt;/a&gt;&lt;br/&gt;
&lt;a href=&quot;https://maloo.whamcloud.com/test_sets/dc877024-fcc1-11e2-9fdb-52540035b04c&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://maloo.whamcloud.com/test_sets/dc877024-fcc1-11e2-9fdb-52540035b04c&lt;/a&gt;&lt;br/&gt;
&lt;a href=&quot;https://maloo.whamcloud.com/test_sets/1bec6152-fcb8-11e2-9222-52540035b04c&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://maloo.whamcloud.com/test_sets/1bec6152-fcb8-11e2-9222-52540035b04c&lt;/a&gt;&lt;/p&gt;</comment>
                            <comment id="64110" author="pjones" created="Mon, 12 Aug 2013 18:35:57 +0000"  >&lt;p&gt;Lai&lt;/p&gt;

&lt;p&gt;Could you please look at this failure on b2_4?&lt;/p&gt;

&lt;p&gt;Thanks&lt;/p&gt;

&lt;p&gt;Peter&lt;/p&gt;</comment>
                            <comment id="64303" author="laisiyao" created="Thu, 15 Aug 2013 03:06:55 +0000"  >&lt;p&gt;I couldn&apos;t reproduce on my local test environment with 2.4 and master code, will look more into maloo logs.&lt;/p&gt;</comment>
                            <comment id="64397" author="yujian" created="Fri, 16 Aug 2013 13:52:54 +0000"  >&lt;p&gt;Hi Lai,&lt;/p&gt;

&lt;p&gt;I can manually reproduce this failure on Rosso cluster:&lt;/p&gt;

&lt;p&gt;Lustre build: &lt;a href=&quot;http://build.whamcloud.com/job/lustre-b2_4/32/&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;http://build.whamcloud.com/job/lustre-b2_4/32/&lt;/a&gt;&lt;br/&gt;
Maloo report: &lt;a href=&quot;https://maloo.whamcloud.com/test_sets/0d0b5720-0676-11e3-87de-52540035b04c&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://maloo.whamcloud.com/test_sets/0d0b5720-0676-11e3-87de-52540035b04c&lt;/a&gt; &lt;/p&gt;</comment>
                            <comment id="64432" author="laisiyao" created="Sat, 17 Aug 2013 01:49:17 +0000"  >&lt;p&gt;ahh, yes, after increasing wdisjoint_REP, I can reproduce it now, and I&apos;m looking into debug logs.&lt;/p&gt;</comment>
                            <comment id="64892" author="green" created="Thu, 22 Aug 2013 21:06:55 +0000"  >&lt;p&gt;This issue is also present in master:&lt;br/&gt;
&lt;a href=&quot;https://maloo.whamcloud.com/sub_tests/query?commit=Update+results&amp;amp;page=1&amp;amp;sub_test[query_bugs]=&amp;amp;sub_test[status]=FAIL&amp;amp;sub_test[sub_test_script_id]=6c1d247c-55d0-11e0-bb3d-52540025f9af&amp;amp;test_node[architecture_type_id]=&amp;amp;test_node[distribution_type_id]=&amp;amp;test_node[file_system_type_id]=&amp;amp;test_node[lustre_branch_id]=&amp;amp;test_node[os_type_id]=&amp;amp;test_node_network[network_type_id]=&amp;amp;test_session[query_date]=&amp;amp;test_session[query_recent_period]=&amp;amp;test_session[test_group]=&amp;amp;test_session[test_host]=&amp;amp;test_session[user_id]=&amp;amp;test_set[test_set_script_id]=b10ed7ea-55b4-11e0-bb3d-52540025f9af&amp;amp;utf8=%E2%9C%93&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://maloo.whamcloud.com/sub_tests/query?commit=Update+results&amp;amp;page=1&amp;amp;sub_test[query_bugs]=&amp;amp;sub_test[status]=FAIL&amp;amp;sub_test[sub_test_script_id]=6c1d247c-55d0-11e0-bb3d-52540025f9af&amp;amp;test_node[architecture_type_id]=&amp;amp;test_node[distribution_type_id]=&amp;amp;test_node[file_system_type_id]=&amp;amp;test_node[lustre_branch_id]=&amp;amp;test_node[os_type_id]=&amp;amp;test_node_network[network_type_id]=&amp;amp;test_session[query_date]=&amp;amp;test_session[query_recent_period]=&amp;amp;test_session[test_group]=&amp;amp;test_session[test_host]=&amp;amp;test_session[user_id]=&amp;amp;test_set[test_set_script_id]=b10ed7ea-55b4-11e0-bb3d-52540025f9af&amp;amp;utf8=%E2%9C%93&lt;/a&gt;&lt;/p&gt;</comment>
                            <comment id="65038" author="green" created="Mon, 26 Aug 2013 02:19:50 +0000"  >&lt;p&gt;So, after some digging, the reason for the failure is a lock that somehow survived truncate to 0 on the client with rank 0 process.&lt;br/&gt;
So later one when a glimpse is done, this lock happens to have the highest offset and is consluted, yet it&apos;s on the wrong node.&lt;/p&gt;

&lt;p&gt;Eg. in this test run: &lt;a href=&quot;https://maloo.whamcloud.com/test_sets/1bec6152-fcb8-11e2-9222-52540035b04c&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://maloo.whamcloud.com/test_sets/1bec6152-fcb8-11e2-9222-52540035b04c&lt;/a&gt;&lt;br/&gt;
We can see that the latest client to write had a lock ffff88006a606000/0xab2c500485c68cac with offsets covering &lt;span class=&quot;error&quot;&gt;&amp;#91;20480-&amp;gt;184319&amp;#93;&lt;/span&gt; with highest file size at 63248&lt;br/&gt;
But when the other (rank 0) client does glimpse to determine file size, there&apos;s another lock covering &lt;span class=&quot;error&quot;&gt;&amp;#91;184320-EOF&amp;#93;&lt;/span&gt; with handle 0x39ce525e4ad00966 that is a left over from previous iteration. This is a higher offset lock, so it gets the glimpse, but this client only has highest write at offset 55342.&lt;/p&gt;

&lt;p&gt;Sadly the maloo report for this failure has a hole in lustre debug log right around where truncate have happened, so I cannot see why this lock did not get cancelled. And maloo is down ATM, so I cannot try my luck with a different report.&lt;/p&gt;</comment>
                            <comment id="65043" author="green" created="Mon, 26 Aug 2013 03:20:41 +0000"  >&lt;p&gt;Actually I just found that the lock in question is created after truncate.&lt;br/&gt;
Apparently the bug is such that we match some wrong lock:&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;00020000:00200000:0.0:1377200002.830736:0:29294:0:(lov_io.c:415:lov_io_iter_init()) shrink: 0 [26754, 40131)
00000080:00200000:0.0:1377200002.830740:0:29294:0:(lcommon_cl.c:728:ccc_io_one_lock_index()) lock: 2 [6, 9]
00020000:00010000:0.0:1377200002.830743:0:29294:0:(lov_lock.c:1057:lov_lock_fits_into()) W(2):[41, 61]/W(2):[0, 18446744073709551615] 0 1/1: 1
00000020:00010000:0.0:1377200002.830744:0:29294:0:(cl_lock.c:514:cl_lock_lookup()) has: W(2):[0, 18446744073709551615](5) need: W(2):[6, 9]: 1
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;

&lt;p&gt;So we matched a lok that was originally for pages 41-61, but was granted as whole file, or so it seems.&lt;/p&gt;

&lt;p&gt;But as we have decided this, there&apos;s a parallel process that cancels this lock (in fact the cancel was already happening) when we did the match:&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;00000008:00010000:0.0:1377200002.838156:0:28077:0:(osc_lock.c:1288:osc_lock_flush()) ### lock ffff8800411caa98: 4 pages were written.
 ns: lustre-OST0003-osc-ffff88005b040000 lock: ffff880042609740/0x695594a2b763446f lrc: 3/0,0 mode: PW/PW res: [0x65f71:0x0:0x0].0 rrc: 1 type: EXT [0-&amp;gt;18446744073709551615] (req 167936-&amp;gt;253951) flags: 0x420400020000 nid: local remote: 0x433a6203c6e8086c expref: -99 pid: 29295 timeout: 0 lvb_type: 1
...
00010000:00010000:0.0:1377200002.838194:0:28077:0:(ldlm_request.c:1117:ldlm_cli_cancel_local()) ### client-side cancel ns: lustre-OST0003-osc-ffff88005b040000 lock: ffff880042609740/0x695594a2b763446f lrc: 4/0,0 mode: PW/PW res: [0x65f71:0x0:0x0].0 rrc: 1 type: EXT [0-&amp;gt;18446744073709551615] (req 167936-&amp;gt;253951) flags: 0x428400020000 nid: local remote: 0x433a6203c6e8086c expref: -99 pid: 29295 timeout: 0 lvb_type: 1
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;

&lt;p&gt;Now the original process continues to ask for the actual dlm lock:&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;00000008:00010000:0.0:1377200002.838278:0:29294:0:(osc_lock.c:1674:osc_lock_init()) ### lock ffff8800411caa98, osc lock ffff880042618a98, flags 40000000
...
00010000:00010000:0.0:1377200002.838296:0:29294:0:(ldlm_request.c:916:ldlm_cli_enqueue()) ### client-side enqueue START, flags 40000000
 ns: lustre-OST0003-osc-ffff88005b040000 lock: ffff880042609540/0x695594a2b7634476 lrc: 3/0,1 mode: --/PW res: [0x65f71:0x0:0x0].0 rrc: 1 type: EXT [167936-&amp;gt;253951] (req 167936-&amp;gt;253951) flags: 0x0 nid: local remote: 0x0 expref: -99 pid: 29294 timeout: 0 lvb_type: 1
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;
&lt;p&gt;And here we requested wrong lock!&lt;/p&gt;

&lt;p&gt;(This log snipped is from a different log file than above, but you can see the same picture with the previous log too just search for that stray lock handle)&lt;/p&gt;</comment>
                            <comment id="65232" author="bobijam" created="Wed, 28 Aug 2013 10:08:32 +0000"  >&lt;p&gt;patch tracking at &lt;a href=&quot;http://review.whamcloud.com/7477&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;http://review.whamcloud.com/7477&lt;/a&gt; &lt;/p&gt;

&lt;div class=&quot;preformatted panel&quot; style=&quot;border-width: 1px;&quot;&gt;&lt;div class=&quot;preformattedHeader panelHeader&quot; style=&quot;border-bottom-width: 1px;&quot;&gt;&lt;b&gt;commit message&lt;/b&gt;&lt;/div&gt;&lt;div class=&quot;preformattedContent panelContent&quot;&gt;
&lt;pre&gt;Change subject: LU-3027 clio: properly expand lov parent lock descr
...................................................................... 

LU-3027 clio: properly expand lov orig lock descr 

* If a client request a cl_lock with original ext region [A, B], 
its lov-&amp;gt;lls_orig saves the [A, B] pair, while its cl_lock&apos;s 
cll_descr has been modified to what it get from osc_lock, such 
as [C, D]. 

When new ext lock request [E, F] from the same client, it uses 
existing cl_lock&apos;s cll_descr to match the request, even though 
[E, F] is not contained by [A, B], but it could be contianed by 
[C, D], and this cl_lock could be returned. 

When ldlm_lock [C, D] is canceled, the second lock request would 
enqueue a ldlm_lock using the returned cl_lock&apos;s original ext, i.e 
[A, B], that&apos;s wrong. 

* Put -machinefile option ahead of other mpiexec options, since some 
version of mpiexec request global options be put before its local 
options, and -machinefile is a global options. 
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;</comment>
                            <comment id="65285" author="green" created="Wed, 28 Aug 2013 17:43:57 +0000"  >&lt;p&gt;After discussing with Jinshan I have these two alternative approaches for a fix:&lt;/p&gt;

&lt;p&gt;&lt;a href=&quot;http://review.whamcloud.com/7481&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;http://review.whamcloud.com/7481&lt;/a&gt; - I like this one more&lt;/p&gt;

&lt;p&gt;&lt;a href=&quot;http://review.whamcloud.com/7482&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;http://review.whamcloud.com/7482&lt;/a&gt; - this one has a potential to waste more memory for sublocks, I fear so I don&apos;t like it as such.&lt;/p&gt;</comment>
                            <comment id="65346" author="yujian" created="Thu, 29 Aug 2013 09:00:44 +0000"  >&lt;p&gt;Hi Bobi and Oleg,&lt;/p&gt;

&lt;p&gt;While creating/updating the patches, could you please add the following test parameters into commit message so as to verify write_disjoint test automatically?&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;Test-Parameters: envdefinitions=SLOW=yes,ONLY=write_disjoint \
clientdistro=el6 serverdistro=el6 clientarch=x86_64 \
serverarch=x86_64 testlist=parallel-scale
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;</comment>
                            <comment id="65419" author="green" created="Fri, 30 Aug 2013 04:16:26 +0000"  >&lt;p&gt;patch landed to master.&lt;/p&gt;</comment>
                            <comment id="65423" author="yujian" created="Fri, 30 Aug 2013 06:24:28 +0000"  >&lt;p&gt;Hi Oleg,&lt;/p&gt;

&lt;p&gt;The patch &lt;a href=&quot;http://review.whamcloud.com/7481&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;http://review.whamcloud.com/7481&lt;/a&gt; can be applied to Lustre b2_4 branch without conflict. Could you please cherry-pick it to Lustre b2_4 branch? Thanks.&lt;/p&gt;</comment>
                            <comment id="65459" author="pjones" created="Fri, 30 Aug 2013 17:38:28 +0000"  >&lt;p&gt;Landed for 2.5&lt;/p&gt;</comment>
                            <comment id="66035" author="yujian" created="Mon, 9 Sep 2013 06:46:14 +0000"  >&lt;p&gt;Lustre build: &lt;a href=&quot;http://build.whamcloud.com/job/lustre-b2_4/45/&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;http://build.whamcloud.com/job/lustre-b2_4/45/&lt;/a&gt; (2.4.1 RC2)&lt;/p&gt;

&lt;p&gt;Since patch &lt;a href=&quot;http://review.whamcloud.com/7481&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;http://review.whamcloud.com/7481&lt;/a&gt; was reverted from Lustre b2_4 branch, the failure occurred again:&lt;br/&gt;
&lt;a href=&quot;https://maloo.whamcloud.com/test_sets/51ed9046-1919-11e3-aa6c-52540035b04c&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://maloo.whamcloud.com/test_sets/51ed9046-1919-11e3-aa6c-52540035b04c&lt;/a&gt;&lt;/p&gt;</comment>
                            <comment id="66214" author="green" created="Tue, 10 Sep 2013 17:05:49 +0000"  >&lt;p&gt;There&apos;s a different patch from Jinshan here: &lt;a href=&quot;http://review.whamcloud.com/7569&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;http://review.whamcloud.com/7569&lt;/a&gt;&lt;br/&gt;
This works well in my testing, but would be great if somebody can do nfs testing of it (note it requires the other 3027 patch reverted which is already true for b2_4, but not true for master).&lt;/p&gt;</comment>
                            <comment id="67142" author="sarah" created="Fri, 20 Sep 2013 17:30:13 +0000"  >&lt;p&gt;I will work on the NFS testing&lt;br/&gt;
Here is the patch including 7569 and revert 3027 &lt;a href=&quot;http://review.whamcloud.com/#/c/7733/&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;http://review.whamcloud.com/#/c/7733/&lt;/a&gt;&lt;/p&gt;

&lt;p&gt;parallel-scale-nfsv3 failed as &lt;/p&gt;

&lt;p&gt;suite log shows&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;== parallel-scale-nfsv3 test iorssf: iorssf == 20:53:59 (1380167639)
+ 6 * 1024 * 1024 * 4
+ 26722304 * 9/10 / 1024 / 1024 / 2 / 2
free space=26722304, Need: 2 x 2 x 3 GB
(blockSize reduced to 3 Gb)
OPTIONS:
IOR=/usr/bin/IOR
ior_THREADS=2
ior_DURATION=30
MACHINEFILE=/tmp/parallel-scale-nfs.machines
wtm-75
wtm-76
mkdir: cannot create directory `/mnt/lustre/d0.ior.ssf&apos;: Permission denied
chmod: cannot access `/mnt/lustre/d0.ior.ssf&apos;: No such file or director
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;

&lt;p&gt;test log shows:&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;** error **
ERROR in aiori-POSIX.c (line 105): cannot open file.
ERROR: Not a directory
** exiting **
** error **
ERROR in aiori-POSIX.c (line 105): cannot open file.
ERROR: Not a directory
** exiting **
** error **
ERROR in aiori-POSIX.c (line 105): cannot open file.
ERROR: Not a directory
** exiting **
** error **
ERROR in aiori-POSIX.c (line 105): cannot open file.
ERROR: Not a directory
** exiting **
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;</comment>
                            <comment id="67438" author="pjones" created="Tue, 24 Sep 2013 19:02:49 +0000"  >&lt;p&gt;Patch landed for 2.5.0&lt;/p&gt;</comment>
                            <comment id="68110" author="sarah" created="Tue, 1 Oct 2013 20:38:41 +0000"  >&lt;p&gt;hmm for &lt;a href=&quot;https://jira.whamcloud.com/browse/LU-3027&quot; title=&quot;Failure on test suite parallel-scale test_write_disjoint: invalid file size 140329 instead of 160376 = 20047 * 8&quot; class=&quot;issue-link&quot; data-issue-key=&quot;LU-3027&quot;&gt;&lt;del&gt;LU-3027&lt;/del&gt;&lt;/a&gt;, tag-2.4.93 (&lt;a href=&quot;http://build.whamcloud.com/job/lustre-master/1687/&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;http://build.whamcloud.com/job/lustre-master/1687/&lt;/a&gt;) should have the fix but I still hit this error:&lt;/p&gt;

&lt;p&gt;&lt;a href=&quot;https://maloo.whamcloud.com/test_sets/9a628942-272b-11e3-88c6-52540035b04c&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://maloo.whamcloud.com/test_sets/9a628942-272b-11e3-88c6-52540035b04c&lt;/a&gt;&lt;/p&gt;</comment>
                            <comment id="68316" author="jay" created="Thu, 3 Oct 2013 20:34:11 +0000"  >&lt;p&gt;patch is at: &lt;a href=&quot;http://review.whamcloud.com/7841&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;http://review.whamcloud.com/7841&lt;/a&gt;, please give it a try.&lt;/p&gt;</comment>
                            <comment id="68616" author="sarah" created="Tue, 8 Oct 2013 18:15:59 +0000"  >&lt;p&gt;Here is the result of parallel-scale test_write_disjoint:&lt;/p&gt;

&lt;p&gt;&lt;a href=&quot;https://maloo.whamcloud.com/test_sessions/5602b272-303b-11e3-b28a-52540035b04c&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://maloo.whamcloud.com/test_sessions/5602b272-303b-11e3-b28a-52540035b04c&lt;/a&gt;&lt;/p&gt;</comment>
                            <comment id="68850" author="pjones" created="Fri, 11 Oct 2013 18:06:33 +0000"  >&lt;p&gt;Landed for 2.5&lt;/p&gt;</comment>
                            <comment id="70567" author="yujian" created="Sat, 2 Nov 2013 15:00:23 +0000"  >&lt;p&gt;Lustre build: &lt;a href=&quot;http://build.whamcloud.com/job/lustre-b2_4/47/&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;http://build.whamcloud.com/job/lustre-b2_4/47/&lt;/a&gt;&lt;/p&gt;

&lt;p&gt;The failure still occurred regularly on Lustre b2_4 branch:&lt;br/&gt;
&lt;a href=&quot;https://maloo.whamcloud.com/test_sets/0039b106-4332-11e3-9490-52540035b04c&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://maloo.whamcloud.com/test_sets/0039b106-4332-11e3-9490-52540035b04c&lt;/a&gt;&lt;br/&gt;
&lt;a href=&quot;https://maloo.whamcloud.com/test_sets/762409ba-4333-11e3-8676-52540035b04c&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://maloo.whamcloud.com/test_sets/762409ba-4333-11e3-8676-52540035b04c&lt;/a&gt;&lt;/p&gt;</comment>
                            <comment id="70685" author="yujian" created="Tue, 5 Nov 2013 02:15:26 +0000"  >&lt;p&gt;Patches &lt;a href=&quot;http://review.whamcloud.com/7569&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;http://review.whamcloud.com/7569&lt;/a&gt; and &lt;a href=&quot;http://review.whamcloud.com/7841&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;http://review.whamcloud.com/7841&lt;/a&gt; landed on Lustre b2_4 branch. The failure was fixed.&lt;/p&gt;</comment>
                            <comment id="71020" author="paf" created="Thu, 7 Nov 2013 21:31:53 +0000"  >&lt;p&gt;Jian - Are you saying that when you added 7569 and 7841 to b2_4 you no longer see the failure?&lt;/p&gt;

&lt;p&gt;I do not see those patches as landed to b2_4 in Gerrit, and Cray is still seeing the closely related &lt;a href=&quot;https://jira.whamcloud.com/browse/LU-3889&quot; title=&quot; LBUG: (osc_lock.c:497:osc_lock_upcall()) ASSERTION( lock-&amp;gt;cll_state &amp;gt;= CLS_QUEUING ) &quot; class=&quot;issue-link&quot; data-issue-key=&quot;LU-3889&quot;&gt;&lt;del&gt;LU-3889&lt;/del&gt;&lt;/a&gt; with both patches landed in 2.4.&lt;/p&gt;</comment>
                            <comment id="71126" author="yujian" created="Fri, 8 Nov 2013 15:52:27 +0000"  >&lt;p&gt;Hi Patrick,&lt;/p&gt;

&lt;p&gt;Lustre b2_4 build #48 contains those two patches: &lt;a href=&quot;http://build.whamcloud.com/job/lustre-b2_4/48/&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;http://build.whamcloud.com/job/lustre-b2_4/48/&lt;/a&gt;. And since that build, parallel-scale test write_disjoint has passed:&lt;br/&gt;
&lt;a href=&quot;https://maloo.whamcloud.com/test_sets/35b41124-45a7-11e3-b22a-52540035b04c&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://maloo.whamcloud.com/test_sets/35b41124-45a7-11e3-b22a-52540035b04c&lt;/a&gt;&lt;br/&gt;
&lt;a href=&quot;https://maloo.whamcloud.com/test_sets/484f9162-4590-11e3-8713-52540035b04c&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://maloo.whamcloud.com/test_sets/484f9162-4590-11e3-8713-52540035b04c&lt;/a&gt;&lt;br/&gt;
&lt;a href=&quot;https://maloo.whamcloud.com/test_sets/c5f43484-4602-11e3-b5e8-52540035b04c&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://maloo.whamcloud.com/test_sets/c5f43484-4602-11e3-b5e8-52540035b04c&lt;/a&gt;&lt;br/&gt;
&lt;a href=&quot;https://maloo.whamcloud.com/test_sets/1c537816-47f3-11e3-bc81-52540035b04c&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://maloo.whamcloud.com/test_sets/1c537816-47f3-11e3-bc81-52540035b04c&lt;/a&gt;&lt;/p&gt;</comment>
                            <comment id="71127" author="paf" created="Fri, 8 Nov 2013 15:56:13 +0000"  >&lt;p&gt;Interesting - Thanks, Jian.&lt;/p&gt;</comment>
                    </comments>
                <issuelinks>
                            <issuelinktype id="10010">
                    <name>Duplicate</name>
                                                                <inwardlinks description="is duplicated by">
                                        <issuelink>
            <issuekey id="11875">LU-701</issuekey>
        </issuelink>
                            </inwardlinks>
                                    </issuelinktype>
                            <issuelinktype id="10011">
                    <name>Related</name>
                                            <outwardlinks description="is related to ">
                                        <issuelink>
            <issuekey id="20796">LU-3889</issuekey>
        </issuelink>
                            </outwardlinks>
                                                                <inwardlinks description="is related to">
                                        <issuelink>
            <issuekey id="20796">LU-3889</issuekey>
        </issuelink>
            <issuelink>
            <issuekey id="20755">LU-3874</issuekey>
        </issuelink>
                            </inwardlinks>
                                    </issuelinktype>
                    </issuelinks>
                <attachments>
                    </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|hzvm93:</customfieldvalue>

                        </customfieldvalues>
                    </customfield>
                                                                <customfield id="customfield_10090" key="com.pyxis.greenhopper.jira:gh-global-rank">
                        <customfieldname>Rank (Obsolete)</customfieldname>
                        <customfieldvalues>
                            <customfieldvalue>7390</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>