<!-- 
RSS generated by JIRA (9.4.14#940014-sha1:734e6822bbf0d45eff9af51f82432957f73aa32c) at Sat Feb 10 02:44:50 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-11549] Unattached inodes after 3 min racer run.</title>
                <link>https://jira.whamcloud.com/browse/LU-11549</link>
                <project id="10000" key="LU">Lustre</project>
                    <description>&lt;p&gt;An attempt to run racer.sh on a DNE system with rpms built from wc master branch:&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;[root@cslmodev100 racer]# sh racer.sh  -t 180 -T 7 -f 20 -c -d /mnt/testfs/racer-dir/
Directory:     /mnt/testfs/racer-dir/
Time Limit:    180
Lustre Tests:  1
Max Files:     20
Threads:       7
Running Tests: lustre_file_create dir_create file_rm file_rename file_link file_symlink file_list file_concat file_exec dir_remote
MDS Count:     3
Running racer.sh for 180 seconds. CTRL-C to exit
file_create: FILE=/mnt/testfs/racer-dir//10 SIZE=207136
file_create: FILE=/mnt/testfs/racer-dir//17 SIZE=4800
file_create: FILE=/mnt/testfs/racer-dir//5 SIZE=73416
file_create: FILE=/mnt/testfs/racer-dir//19 SIZE=116024
...
file_create: FILE=/mnt/testfs/racer-dir//0 SIZE=234400
file_create: FILE=/mnt/testfs/racer-dir//2 SIZE=136432
file_create: FILE=/mnt/testfs/racer-dir//8 SIZE=53296
file_create: FILE=/mnt/testfs/racer-dir//12 SIZE=233528
racer cleanup
sleeping 5 sec ...
lustre_file_create.sh: no process found
dir_create.sh: no process found
file_rm.sh: no process found
file_rename.sh: no process found
file_link.sh: no process found
file_symlink.sh: no process found
file_list.sh: no process found
file_concat.sh: no process found
file_exec.sh: no process found
dir_remote.sh: no process found
there should be NO racer processes:
root     201964  0.0  0.0 112660   988 pts/24   S+   11:03   0:00 grep -E lustre_file_create|dir_create|file_rm|file_rename|file_link|file_symlink|file_list|file_concat|file_exec|dir_remote
Filesystem                                   1K-blocks    Used    Available Use% Mounted on
172.18.1.3@o2ib1,172.18.1.4@o2ib1:/testfs 240559470792 4289196 238129624412   1% /mnt/testfs
We survived racer.sh for 180 seconds.
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;
&lt;p&gt;&#160;&lt;br/&gt;
e2fsck on the MDT0 device:&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;[root@cslmodev103 ~]# umount /dev/md66
[root@cslmodev103 ~]# e2fsck -fvn /dev/md66
e2fsck 1.42.13.x6 (01-Mar-2018)
Pass 1: Checking inodes, blocks, and sizes
Pass 2: Checking directory structure
Pass 3: Checking directory connectivity
Pass 4: Checking reference counts
Inode 2061541938 ref count is 3, should be 2.  Fix? no

Unattached inode 2061541970
Connect to /lost+found? no

Inode 2061541986 ref count is 2, should be 1.  Fix? no

Unattached inode 2061542181
Connect to /lost+found? no

Inode 2061542575 ref count is 10, should be 9.  Fix? no

Inode 2061542583 ref count is 6, should be 5.  Fix? no

Pass 5: Checking group summary information
[QUOTA WARNING] Usage inconsistent for ID 0:actual (1248931840, 1295) != expected (1248919552, 1295)
Update quota info for quota type 0? no

[QUOTA WARNING] Usage inconsistent for ID 0:actual (1248931840, 1295) != expected (1248919552, 1295)
Update quota info for quota type 1? no


testfs-MDT0000: ********** WARNING: Filesystem still has errors **********


        1304 inodes used (0.00%, out of 3042005760)
          85 non-contiguous files (6.5%)
           2 non-contiguous directories (0.2%)
             # of inodes with ind/dind/tind blocks: 72/64/0
   381833025 blocks used (25.10%, out of 1520996090)
           0 bad blocks
           2 large files

         555 regular files
         491 directories
           0 character device files
           0 block device files
           0 fifos
         107 links
         249 symbolic links (249 fast symbolic links)
           0 sockets
------------
        1400 files
[root@cslmodev103 ~]#

[root@cslmodev103 ~]# dumpe2fs -h /dev/md66 | grep -i state
dumpe2fs 1.42.13.x6 (01-Mar-2018)
Filesystem state:         clean
[root@cslmodev103 ~]#

&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;

&lt;p&gt;Invalid symlink inodes are due to &lt;a href=&quot;https://jira.whamcloud.com/browse/LU-11130&quot; title=&quot;cross-target rename creates invalid symlink inodes&quot; class=&quot;issue-link&quot; data-issue-key=&quot;LU-11130&quot;&gt;&lt;del&gt;LU-11130&lt;/del&gt;&lt;/a&gt;, wrong nlinks are due to &lt;a href=&quot;https://jira.whamcloud.com/browse/LU-11446&quot; title=&quot;ldiskfs inodes nlink mismatch with DNE&quot; class=&quot;issue-link&quot; data-issue-key=&quot;LU-11446&quot;&gt;LU-11446&lt;/a&gt;,&lt;br/&gt;
unattached inodes are what this ticket is about.&lt;/p&gt;

&lt;p&gt;The racer test script doesn&apos;t use migrate or striped dirs,&lt;br/&gt;
just &quot;lustre_file_create dir_create file_rm file_rename file_link file_symlink file_list file_concat file_exec dir_remote&quot;. Also there is no failovers.&lt;/p&gt;

&lt;p&gt;Lustre is built from the tip of the wc master branch:&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;$ git log --oneline wc/master
fe7c13bd48 (wc/master) LU-11329 utils: create tests maintainers list
70a01a6c9c LU-11276 ldlm: don&apos;t apply ELC to converting and DOM locks
72372486a5 LU-11347 osd: do not use pagecache for I/O
8b9105d828 LU-11199 mdt: Attempt lookup lock on open
697e8fe6f3 LU-11473 doc: add lfs-getsom man page
ed0c19d250 LU-1095 misc: quiet console messages at startup
....
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&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;[root@cslmodev103 ~]# rpm -q lustre_ib
lustre_ib-2.11.56_16_gfe7c13b-1.el7.centos.x86_64
[root@cslmodev103 ~]#
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;</description>
                <environment></environment>
        <key id="53673">LU-11549</key>
            <summary>Unattached inodes after 3 min racer run.</summary>
                <type id="1" iconUrl="https://jira.whamcloud.com/secure/viewavatar?size=xsmall&amp;avatarId=11303&amp;avatarType=issuetype">Bug</type>
                                            <priority id="3" iconUrl="https://jira.whamcloud.com/images/icons/priorities/major.svg">Major</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="zam">Alexander Zarochentsev</assignee>
                                    <reporter username="zam">Alexander Zarochentsev</reporter>
                        <labels>
                    </labels>
                <created>Fri, 19 Oct 2018 16:55:53 +0000</created>
                <updated>Thu, 12 Mar 2020 11:43:52 +0000</updated>
                            <resolved>Fri, 11 Oct 2019 18:02:37 +0000</resolved>
                                    <version>Lustre 2.11.0</version>
                    <version>Lustre 2.12.0</version>
                                    <fixVersion>Lustre 2.13.0</fixVersion>
                                        <due></due>
                            <votes>0</votes>
                                    <watches>9</watches>
                                                                            <comments>
                            <comment id="235455" author="pjones" created="Thu, 25 Oct 2018 00:30:31 +0000"  >&lt;p&gt;Zam&lt;/p&gt;

&lt;p&gt;Have you confirmed whether the situation improves with your proposed fix for &lt;a href=&quot;https://jira.whamcloud.com/browse/LU-11130&quot; title=&quot;cross-target rename creates invalid symlink inodes&quot; class=&quot;issue-link&quot; data-issue-key=&quot;LU-11130&quot;&gt;&lt;del&gt;LU-11130&lt;/del&gt;&lt;/a&gt;?&lt;/p&gt;

&lt;p&gt;Peter&lt;/p&gt;</comment>
                            <comment id="235516" author="spitzcor" created="Thu, 25 Oct 2018 20:44:14 +0000"  >&lt;p&gt;The bug still exists with patch from &lt;a href=&quot;https://jira.whamcloud.com/browse/LU-11130&quot; title=&quot;cross-target rename creates invalid symlink inodes&quot; class=&quot;issue-link&quot; data-issue-key=&quot;LU-11130&quot;&gt;&lt;del&gt;LU-11130&lt;/del&gt;&lt;/a&gt;.&lt;/p&gt;

&lt;p&gt;However, we&apos;ve found that the problem is no longer reproducible after disabling the cross-MDT capability provided with &lt;a href=&quot;https://jira.whamcloud.com/browse/LU-3537&quot; title=&quot;allow cross-MDT for all metadata operations &quot; class=&quot;issue-link&quot; data-issue-key=&quot;LU-3537&quot;&gt;&lt;del&gt;LU-3537&lt;/del&gt;&lt;/a&gt; (but leaving the async update capability from &lt;a href=&quot;https://jira.whamcloud.com/browse/LU-3534&quot; title=&quot;async update cross-MDTs&quot; class=&quot;issue-link&quot; data-issue-key=&quot;LU-3534&quot;&gt;&lt;del&gt;LU-3534&lt;/del&gt;&lt;/a&gt;).&lt;/p&gt;</comment>
                            <comment id="236941" author="zam" created="Tue, 13 Nov 2018 18:41:57 +0000"  >&lt;p&gt;Peter,&lt;br/&gt;
&amp;gt;Have you confirmed whether the situation improves with your proposed fix for &lt;a href=&quot;https://jira.whamcloud.com/browse/LU-11130&quot; title=&quot;cross-target rename creates invalid symlink inodes&quot; class=&quot;issue-link&quot; data-issue-key=&quot;LU-11130&quot;&gt;&lt;del&gt;LU-11130&lt;/del&gt;&lt;/a&gt;&lt;/p&gt;

&lt;p&gt;no, the unattached inodes have nothing to do with &lt;a href=&quot;https://jira.whamcloud.com/browse/LU-11130&quot; title=&quot;cross-target rename creates invalid symlink inodes&quot; class=&quot;issue-link&quot; data-issue-key=&quot;LU-11130&quot;&gt;&lt;del&gt;LU-11130&lt;/del&gt;&lt;/a&gt;. We have &lt;a href=&quot;https://jira.whamcloud.com/browse/LU-11130&quot; title=&quot;cross-target rename creates invalid symlink inodes&quot; class=&quot;issue-link&quot; data-issue-key=&quot;LU-11130&quot;&gt;&lt;del&gt;LU-11130&lt;/del&gt;&lt;/a&gt; landed for some time already, it doesn&apos;t have any effect on this bug.&lt;/p&gt;

&lt;p&gt;This issue is about regular files ,  racer.sh test (attached) without stiped dirs or migrate, no failovers, no e2fsck runs expept the final e2fsck run after racer.sh completes.  Actually it was harder to reproduce the issue on master b/c it just hangs .&lt;/p&gt;

&lt;p&gt;here the results of 10 min racer run:&lt;/p&gt;

&lt;p&gt;E2fsck after racer.  Well, it is mounted this time but nobody accesses the fs for about 30 sec since racer completes. Believe me the corruption exists when the fs is cleanly unmounted.&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;e2fsck 1.42.13.x6 (01-Mar-2018)
device /dev/md66 mounted by lustre
Warning!  /dev/md66 is mounted.
Warning: skipping journal recovery because doing a read-only filesystem check.
Pass 1: Checking inodes, blocks, and sizes
Pass 2: Checking directory structure
Pass 3: Checking directory connectivity
Pass 4: Checking reference counts
Inode 2061541921 ref count is 3, should be 2.  Fix? no

Unattached inode 2061541929
Connect to /lost+found? no
...
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;
&lt;p&gt;the inode stat:&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;[root@cslmodev103 ~]# debugfs -c -R &quot;stat &amp;lt;2061541929&amp;gt;&quot; /dev/md66
debugfs 1.42.13.x6 (01-Mar-2018)
/dev/md66: catastrophic mode - not reading inode or group bitmaps
Inode: 2061541929   Type: regular    Mode:  0644   Flags: 0x0
Generation: 2673176195    Version: 0x00000024:007990ae
User:     0   Group:     0   Project:     0   Size: 0
File ACL: 0    Directory ACL: 0
Links: 1   Blockcount: 0
Fragment:  Address: 0    Number: 0    Size: 0
ctime: 0x5bd09024:00000000 -- Wed Oct 24 10:30:44 2018
atime: 0x5bd09024:00000000 -- Wed Oct 24 10:30:44 2018
mtime: 0x5bd09024:00000000 -- Wed Oct 24 10:30:44 2018
crtime: 0x5bd0902b:51e10c54 -- Wed Oct 24 10:30:51 2018
Size of extra inode fields: 32
Extended attributes stored in inode body:
  lma = &quot;00 00 00 00 04 00 00 00 0f 50 01 00 02 00 00 00 54 58 00 00 00 00 00 00 &quot; (24)
  lma: fid=[0x20001500f:0x5854:0x0] compat=0 incompat=4

  lov = &quot;d0 0b d1 0b 01 00 00 00 54 58 00 00 00 00 00 00 0f 50 01 00 02 00 00 00 00 00 10 00 01 00 00 00 b1 b7 dc 06 01 00 00 00 00 00 00 00 00 00 00
00 00 00 00 00 01 00 00 00 &quot; (56)
  selinux = &quot;unlabeled\000&quot; (10)
  link = &quot;df f1 ea 11 02 00 00 00 3e 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 13 00 00 00 02 00 01 50 0b 00 01 85 f4 00 00 00 00 38 00 13 00 0
0 00 02 c0 01 05 d3 00 00 79 c7 00 00 00 00 38 &quot; (62)
BLOCKS:

[root@cslmodev103 ~]#
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;
&lt;p&gt;FIDs in Link EA decoded:&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;fid1 = [0x20001500b:0x185f4:0x0]
fid2 = [0x2c00105d3:0x79c7:0x0]
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;
&lt;p&gt;Those fids found on the lustre fs:&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;[root@cslmodev100 ~]# lfs path2fid /mnt/testfs/racer-dir
[0x20001500b:0x185f4:0x0]
[root@cslmodev100 ~]# lfs path2fid /mnt/testfs/racer-dir/18/11/3/8/14/0/12/19/0/6/2/9/13/12/7/9/15/0/3/10/6/5/4/6/1/4/9/10/7/19/12/10/7/3/18/15/19/8/16/5/10/18/1/6/11/5/3/1/5/11/13/9/10/6/9/15/11/17/11/5/1/0/2/6/4/3/15/8/16/17/0/13/1/14/10/18/7/10/15/2/16/19/10/7/13/4/7/8/8/8/18/15/7/3/1/0/8/10/3/15/2/5/19/10/6/18/12/1/11/9/4/2/1/9/8/11/17/14/8/15/17/9/11/8/10/17/10/9/7/0/16/2/14/4/10/1/17/3/15/5/10/14/17/6/7/19/18/14/16/6/3/1/6/10/5/9/11/0/13/1/11/13/5/9/6/10/14/2/8/13/17/13/10/5/2/4/16/3/10/12/14/11/19/8/15/12/1/7/2/7/13
[0x2c00105d3:0x79c7:0x0]
[root@cslmodev100 ~]#
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;
&lt;p&gt;Moreover, there is &quot;8&quot; file name in the second dir, but it doesn&apos;t allow file to be accessed:&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;[root@cslmodev100 ~]# ls -l /mnt/testfs/racer-dir/18/11/3/8/14/0/12/19/0/6/2/9/13/12/7/9/15/0/3/10/6/5/4/6/1/4/9/10/7/19/12/10/7/3/18/15/19/8/16/5/10/18/1/6/11/5/3/1/5/11/13/9/10/6/9/15/11/17/11/5/1/0/2/6/4/3/15/8/16/17/0/13/1/14/10/18/7/10/15/2/16/19/10/7/13/4/7/8/8/8/18/15/7/3/1/0/8/10/3/15/2/5/19/10/6/18/12/1/11/9/4/2/1/9/8/11/17/14/8/15/17/9/11/8/10/17/10/9/7/0/16/2/14/4/10/1/17/3/15/5/10/14/17/6/7/19/18/14/16/6/3/1/6/10/5/9/11/0/13/1/11/13/5/9/6/10/14/2/8/13/17/13/10/5/2/4/16/3/10/12/14/11/19/8/15/12/1/7/2/7/13/8
ls: cannot access /mnt/testfs/racer-dir/18/11/3/8/14/0/12/19/0/6/2/9/13/12/7/9/15/0/3/10/6/5/4/6/1/4/9/10/7/19/12/10/7/3/18/15/19/8/16/5/10/18/1/6/11/5/3/1/5/11/13/9/10/6/9/15/11/17/11/5/1/0/2/6/4/3/15/8/16/17/0/13/1/14/10/18/7/10/15/2/16/19/10/7/13/4/7/8/8/8/18/15/7/3/1/0/8/10/3/15/2/5/19/10/6/18/12/1/11/9/4/2/1/9/8/11/17/14/8/15/17/9/11/8/10/17/10/9/7/0/16/2/14/4/10/1/17/3/15/5/10/14/17/6/7/19/18/14/16/6/3/1/6/10/5/9/11/0/13/1/11/13/5/9/6/10/14/2/8/13/17/13/10/5/2/4/16/3/10/12/14/11/19/8/15/12/1/7/2/7/13/8: No such file or directory
[root@cslmodev100 ~]#
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;
&lt;p&gt;in further investigation I found that fid lookup for &lt;tt&gt;&lt;span class=&quot;error&quot;&gt;&amp;#91;0x20001500f:0x5854:0x0&amp;#93;&lt;/span&gt;&lt;/tt&gt; fails &lt;br/&gt;
 (return code 0 means the fid not found):&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;00000004:00000040:14.0:1540652178.108296:0:90739:0:(mdt_handler.c:5441:mdt_object_init()) object init, fid = [0x20001500f:0x5854:0x0]
00000004:00000010:14.0:1540652178.108298:0:90739:0:(mdd_object.c:282:mdd_object_alloc()) slab-alloced &apos;mdd_obj&apos;: 96 at ffff880f83b741e0.
...
00080000:00000001:14.0:1540652178.108324:0:90739:0:(osd_oi.c:543:osd_oi_iam_lookup()) Process entered
00000001:00000010:14.0:1540652178.108338:0:90739:0:(osd_dynlocks.c:109:dynlock_lock()) slab-alloced &apos;nhl&apos;: 72 at ffff88101b532ee8.
00000001:00000010:14.0:1540652178.108342:0:90739:0:(osd_dynlocks.c:193:dynlock_unlock()) slab-freed &apos;hl&apos;: 72 at ffff88101b532ee8.
00080000:00000001:14.0:1540652178.108344:0:90739:0:(osd_oi.c:565:osd_oi_iam_lookup()) Process leaving (rc=0 : 0 : 0)
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;
&lt;p&gt;Conclusions:&lt;/p&gt;
&lt;ol&gt;
	&lt;li&gt;the unattached inode on MDT0 actually has one link from MDT1 and it has a valid nlink counter value of 1&lt;/li&gt;
	&lt;li&gt;the link from MDT1 doesn&apos;t work b/c FID lookup finds no inode on MDT0.&lt;/li&gt;
	&lt;li&gt;the inode has no name on MDT0 which is a format violation, at least it should be connected to /REMOTE_PARENT_DIR/&lt;/li&gt;
	&lt;li&gt;the OI on MDT0 has no record for &lt;span class=&quot;error&quot;&gt;&amp;#91;0x20001500f:0x5854:0x0&amp;#93;&lt;/span&gt; (the unattached inode FID)&lt;/li&gt;
	&lt;li&gt;one of Link EA records is valid (corresponding forward link exists) another one is not vaild (there is no link  &quot;racer-dir/8&quot;).&lt;/li&gt;
&lt;/ol&gt;

</comment>
                            <comment id="236943" author="zam" created="Tue, 13 Nov 2018 19:13:10 +0000"  >&lt;p&gt;More info from another run where I managed to get lustre logs with almost full debug (trace , inode, info, other) and I added debug code to OUT code :&lt;/p&gt;

&lt;p&gt;the unattached inode  FID is &lt;tt&gt;0x20001ec49:0xab67:0x0&lt;/tt&gt; now. Below is a grep for 0x20001ec49:0xab67:0x0 through the lustre 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;00000004:00000002:16.0:1541058276.560428:0:61806:0:(mdt_reint.c:72:mdt_obj_version_get()) FID [0x20001ec49:0xab67:0x0] version is 0x37000634a7
00080000:00000002:16.0:1541058276.560531:0:61806:0:(osd_handler.c:312:osd_idc_find_and_init()) testfs-MDT0000: FID [0x20001ec49:0xab67:0x0] not in the id map cache
00080000:00000002:16.0:1541058276.560677:0:61806:0:(osd_handler.c:3971:osd_ref_del()) [0x20001ec49:0xab67:0x0] decrease nlink 1
00080000:00000002:16.0:1541058276.560691:0:61806:0:(osd_handler.c:5864:osd_index_ea_insert()) parent 1985033217 insert 0x20001ec49:0xab67:0x0:2061542000 rc = 0
00080000:00000002:16.0:1541058276.560694:0:61806:0:(osd_handler.c:3882:osd_ref_add()) [0x20001ec49:0xab67:0x0] increase nlink 0
00000004:00000002:16.0:1541058276.560734:0:61806:0:(mdt_handler.c:736:mdt_pack_attr2body()) [0x20001ec49:0xab67:0x0]: nlink=1, mode=100644, valid=0x100000000002f8f
00010000:00000040:34.0:1541058276.561254:0:26965:0:(ldlm_resource.c:1701:ldlm_resource_dump()) --- Resource: [0x20001ec49:0xab67:0x0].0x0 (ffff8810196f4f00) refcount = 1
00000020:00001000:6.0:1541058276.561752:0:61820:0:(out_handler.c:1085:out_handle()) ... testfs-MDT0000: buf 0, update 0, opc = 6 [0x20001ec49:0xab67:0x0]
00010000:00000040:13.0:1541058276.570670:0:26966:0:(ldlm_resource.c:1701:ldlm_resource_dump()) --- Resource: [0x20001ec49:0xab67:0x0].0x0 (ffff8810196f4f00) refcount = 2
00000020:00001000:6.0:1541058276.571050:0:61820:0:(out_handler.c:1085:out_handle()) ... testfs-MDT0000: buf 0, update 0, opc = 8 [0x20001ec49:0xab67:0x0]
00000020:00000040:6.0:1541058276.571056:0:61820:0:(out_handler.c:295:out_xattr_get()) testfs-MDT0000: [0x20001ec49:0xab67:0x0] get xattr trusted.link len 43: rc = 43
00000020:00001000:6.0:1541058276.571722:0:61820:0:(out_handler.c:1085:out_handle()) ... testfs-MDT0000: buf 0, update 0, opc = 3 [0x20001ec49:0xab67:0x0]
00080000:00000002:6.0:1541058276.571726:0:61820:0:(osd_handler.c:312:osd_idc_find_and_init()) testfs-MDT0000: FID [0x20001ec49:0xab67:0x0] not in the id map cache
00000020:00001000:6.0:1541058276.571728:0:61820:0:(out_handler.c:1085:out_handle()) ... testfs-MDT0000: buf 0, update 1, opc = 7 [0x20001ec49:0xab67:0x0]
00080000:00000002:6.0:1541058276.571774:0:61820:0:(osd_handler.c:3882:osd_ref_add()) [0x20001ec49:0xab67:0x0] increase nlink 1
00080000:00000002:6.0:1541058276.571782:0:61820:0:(osd_handler.c:4382:osd_xattr_set()) [0x20001ec49:0xab67:0x0] set xattr &apos;trusted.link&apos; with size 62
00080000:00000002:6.0:1541058276.571791:0:61820:0:(osd_compat.c:264:osd_add_to_remote_parent()) md66: add agent entry [0x20001ec49:0xab67:0x0]
00080000:00000002:6.0:1541058276.571799:0:61820:0:(osd_compat.c:296:osd_add_to_remote_parent()) testfs-MDT0000: create agent entry for 0x20001ec49:0xab67:0x0: rc = 0
00000004:00000002:13.0:1541058276.615091:0:61817:0:(mdt_open.c:2214:mdt_mfd_close()) testfs-MDT0000: close file [0x20001ec49:0xab67:0x0] with intent: 0
00000004:00000002:13.0:1541058276.615095:0:61817:0:(mdd_object.c:1155:mdd_attr_set()) testfs-MDD0000: no valid attribute on [0x20001ec49:0xab67:0x0], previousvalid is 0x1
00080000:00000002:13.0:1541058276.615139:0:61817:0:(osd_handler.c:312:osd_idc_find_and_init()) testfs-MDT0000: FID [0x20001ec49:0xab67:0x0] not in the id map cache
00080000:00000002:13.0:1541058276.615239:0:61817:0:(osd_handler.c:3971:osd_ref_del()) [0x20001ec49:0xab67:0x0] decrease nlink 2
00080000:00000002:13.0:1541058276.615246:0:61817:0:(osd_compat.c:318:osd_delete_from_remote_parent()) md66: remove agent direntry [0x20001ec49:0xab67:0x0]
00080000:00000002:13.0:1541058276.615253:0:61817:0:(osd_compat.c:340:osd_delete_from_remote_parent()) testfs-MDT0000: remove agent entry for 0x20001ec49:0xab67:0x0: rc = 0
00080000:00000002:13.0:1541058276.615255:0:61817:0:(osd_oi.c:817:osd_oi_delete()) md66: delete [0x20001ec49:0xab67:0x0]
00010000:00000040:13.0:1541058276.615329:0:61817:0:(ldlm_resource.c:1701:ldlm_resource_dump()) --- Resource: [0x20001ec49:0xab67:0x0].0x0 (ffff8810196f4f00) refcount = 2
00010000:00000040:13.0:1541058276.615332:0:61817:0:(ldlm_resource.c:1707:ldlm_resource_dump()) ### ### ns: mdt-testfs-MDT0000_UUID lock: ffff88078a251680/0x94311686d2f0ef67 lrc: 2/0,0 mode: EX/EX res: [0x20001ec49:0xab67:0x0].0x0 bits 0x2/0x0 rrc: 3 type: IBT flags: 0x40000001000000 nid: 172.18.1.8@o2ib1 remote: 0x54fc01ada1ff65c1 expref: 9 pid: 61820 timeout: 0 lvb_type: 0
00000004:00000040:13.0:1541058276.615373:0:61817:0:(mdt_handler.c:5461:mdt_object_free()) object free, fid = [0x20001ec49:0xab67:0x0]
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;

&lt;p&gt;For a moment, nlink counter dropped to zero:&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;00080000:00000002:16.0:1541058276.560694:0:61806:0:(osd_handler.c:3882:osd_ref_add()) [0x20001ec49:0xab67:0x0] increase nlink 0
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;

&lt;p&gt;I think it is not a valid situation, VFS warns about such cases, but Lustre avoids nlinks increase from zero (&lt;a href=&quot;https://jira.whamcloud.com/browse/LU-4416&quot; title=&quot;support for 3.12 linux kernel&quot; class=&quot;issue-link&quot; data-issue-key=&quot;LU-4416&quot;&gt;&lt;del&gt;LU-4416&lt;/del&gt;&lt;/a&gt; &lt;a href=&quot;http://review.whamcloud.com/11571&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;http://review.whamcloud.com/11571&lt;/a&gt; ).&lt;/p&gt;

&lt;p&gt;almost at the same time thread 61817 closes the file, it sees nlink = 0 (my guess) and continue with osd_delete_from_remote_parent() and osd_oi_delete() , it causes the corruption explained in the previous comment.&lt;/p&gt;</comment>
                            <comment id="236979" author="zam" created="Wed, 14 Nov 2018 10:17:40 +0000"  >&lt;p&gt;Attaching&#160;&lt;span class=&quot;nobr&quot;&gt;&lt;a href=&quot;https://jira.whamcloud.com/secure/attachment/31461/31461_unconnected.txt.gz&quot; title=&quot;unconnected.txt.gz attached to LU-11549&quot;&gt;unconnected.txt.gz&lt;sup&gt;&lt;img class=&quot;rendericon&quot; src=&quot;https://jira.whamcloud.com/images/icons/link_attachment_7.gif&quot; height=&quot;7&quot; width=&quot;7&quot; align=&quot;absmiddle&quot; alt=&quot;&quot; border=&quot;0&quot;/&gt;&lt;/sup&gt;&lt;/a&gt;&lt;/span&gt; &amp;#8211; lustre log from MDT0 with dropping nlink to zero and destroying the file.&lt;/p&gt;</comment>
                            <comment id="238681" author="zam" created="Mon, 17 Dec 2018 14:11:50 +0000"  >&lt;p&gt;more debugging showed the following scenario of the fs corruption:&lt;/p&gt;

&lt;p&gt;1. client opens file &lt;tt&gt;&lt;span class=&quot;error&quot;&gt;&amp;#91;0x20001500b:0x185f4:0x0&amp;#93;&lt;/span&gt;/9&lt;/tt&gt; , FID=&lt;tt&gt;&lt;span class=&quot;error&quot;&gt;&amp;#91;0x200020b8a:0x1c3d:0x0&amp;#93;&lt;/span&gt;&lt;/tt&gt; and keeps fd open:&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;00000004:00000002:10.0:1544282653.825766:0:105088:0:(mdt_open.c:1319:mdt_reint_open()) I am going to open [0x20001500b:0x185f4:0x0]/(9-&amp;gt;[0x200020b8a:0x1c3d:0x0]) cr_flag=02102 mode=0100
666 msg_flag=0x0
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;
&lt;p&gt;2. rename &lt;tt&gt;&lt;span class=&quot;error&quot;&gt;&amp;#91;0x20001500b:0x185f4:0x0&amp;#93;&lt;/span&gt;/4 to &lt;span class=&quot;error&quot;&gt;&amp;#91;0x20001500b:0x185f4:0x0&amp;#93;&lt;/span&gt;/9&lt;/tt&gt; unlinks target file:&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;0000004:00000002:16.0:1544282653.939918:0:105058:0:(mdt_reint.c:1880:mdt_reint_rename_internal()) @@@ rename [0x20001500b:0x185f4:0x0]/4 to [0x20001500b:0x185f4:0x0]/9  req@ffff880cf46

00000004:00000001:16.0:1544282653.942415:0:105058:0:(mdd_dir.c:3039:mdd_rename()) Process entered
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;
&lt;p&gt;and puts the object into the orpan list b/c the file is still open:&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;00000004:00080000:16.0:1544282653.942707:0:105058:0:(mdd_dir.c:1663:mdd_finish_unlink()) Object [0x200020b8a:0x1c3d:0x0] is inserted into orphan list, open count = 1
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;
&lt;p&gt;3. somehow in parallel with (2), a cross-mdt transaction adds a reference to &lt;tt&gt;&lt;span class=&quot;error&quot;&gt;&amp;#91;0x200020b8a:0x1c3d:0x0&amp;#93;&lt;/span&gt;&lt;/tt&gt; (increases nlink count):&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;00080000:00000002:17.0:1544282653.996839:0:105655:0:(osd_handler.c:3882:osd_ref_add()) [0x200020b8a:0x1c3d:0x0] increase nlink 1
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;
&lt;p&gt;it is a part of compound &quot;out&quot; update :&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;00000020:00001000:17.0:1544282653.996777:0:105655:0:(out_handler.c:997:out_handle()) testfs-MDT0000: out update request, 1 buffers
...
00000020:00001000:17.0:1544282653.996782:0:105655:0:(out_handler.c:1085:out_handle()) ... testfs-MDT0000: buf 0, update 0, opc = 3 [0x200020b8a:0x1c3d:0x0]
...
00000020:00001000:17.0:1544282653.996789:0:105655:0:(out_handler.c:1085:out_handle()) ... testfs-MDT0000: buf 0, update 1, opc = 7 [0x200020b8a:0x1c3d:0x0]
...
00000020:00001000:17.0:1544282653.996792:0:105655:0:(out_handler.c:1085:out_handle()) ... testfs-MDT0000: buf 0, update 2, opc = 12 [0x20001fbeb:0x4:0x0]
...
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;
&lt;p&gt;I think the cross-target update is a link() operation, creating a file name on another MDT.&lt;/p&gt;

&lt;p&gt;4. finally, file close removes the object from orphan list and from OI (b/c it has ORPHAN_OBJ and DEAD_OBJ flags set),&#160; creating a fs corruption reported by e2fsck as &quot;unattached inode&quot;.&lt;/p&gt;

&lt;p&gt;I do not know what exactly is broken yet, suspecting cross-target link not checking properly for ORPAN_OBJ | DEAD_OBJ flags.&lt;/p&gt;

&lt;p&gt;&#160;&lt;/p&gt;</comment>
                            <comment id="248135" author="gerrit" created="Fri, 31 May 2019 18:18:40 +0000"  >&lt;p&gt;Alexander Zarochentsev (c17826@cray.com) uploaded a new patch: &lt;a href=&quot;https://review.whamcloud.com/35021&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://review.whamcloud.com/35021&lt;/a&gt;&lt;br/&gt;
Subject: &lt;a href=&quot;https://jira.whamcloud.com/browse/LU-11549&quot; title=&quot;Unattached inodes after 3 min racer run.&quot; class=&quot;issue-link&quot; data-issue-key=&quot;LU-11549&quot;&gt;&lt;del&gt;LU-11549&lt;/del&gt;&lt;/a&gt; mdt: take UPDATE lock for rename target&lt;br/&gt;
Project: fs/lustre-release&lt;br/&gt;
Branch: master&lt;br/&gt;
Current Patch Set: 1&lt;br/&gt;
Commit: 4ff2700af396e63fd9ac90d5f51f1129465c8df7&lt;/p&gt;</comment>
                            <comment id="250007" author="cfaber" created="Tue, 25 Jun 2019 18:22:26 +0000"  >&lt;p&gt;Peter Jones - any chance we can get someone to review this?&lt;/p&gt;</comment>
                            <comment id="251739" author="zam" created="Sat, 20 Jul 2019 10:04:49 +0000"  >&lt;p&gt;Root cause update:&lt;/p&gt;

&lt;p&gt;0. Locks are OK.&lt;/p&gt;

&lt;p&gt;1. the mdt_reint_link operation over a remote object cannot perform a reliable check for the remote object, We want to check the mdd object for DEAD_OBJ flag but can&apos;t do that, because DEAD_OBJ is an mdd object flag, it exists on the remote MDT and not seen through OSP/OUT interface where out_attr_get() checks only dt object state. So the mdd_link_sanity_check() is passed successfully and illegal link operation is done.&lt;/p&gt;

&lt;p&gt;2. A solution could be in moving DEAD_OBJ flag to lu_object level .&lt;/p&gt;</comment>
                            <comment id="252502" author="gerrit" created="Fri, 2 Aug 2019 19:39:27 +0000"  >&lt;p&gt;Alexander Zarochentsev (c17826@cray.com) uploaded a new patch: &lt;a href=&quot;https://review.whamcloud.com/35683&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://review.whamcloud.com/35683&lt;/a&gt;&lt;br/&gt;
Subject: &lt;a href=&quot;https://jira.whamcloud.com/browse/LU-11549&quot; title=&quot;Unattached inodes after 3 min racer run.&quot; class=&quot;issue-link&quot; data-issue-key=&quot;LU-11549&quot;&gt;&lt;del&gt;LU-11549&lt;/del&gt;&lt;/a&gt; tests: link succeded to an ophan remote object&lt;br/&gt;
Project: fs/lustre-release&lt;br/&gt;
Branch: master&lt;br/&gt;
Current Patch Set: 1&lt;br/&gt;
Commit: 14ab193c6aa78ca95b85fa5c940af62fbb815abb&lt;/p&gt;</comment>
                            <comment id="252503" author="zam" created="Fri, 2 Aug 2019 19:46:35 +0000"  >&lt;p&gt;Reproducer: &lt;a href=&quot;https://review.whamcloud.com/35683&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://review.whamcloud.com/35683&lt;/a&gt; :&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;== sanityn test 104: Link to an orphan remote object should not succeed ============================== 22:38:41 (1564774721)
fail_loc=0x8000018a
sanityn.sh: line 4738: 23639 Terminated              $MULTIOP $DIR2/$tdir/mdt0dir/foodir/file2 Ow4096_c
 sanityn test_104: @@@@@@ FAIL: Link to an orphan object succeeded 
  Trace dump:
  = ./../tests/test-framework.sh:6114:error()
  = sanityn.sh:4739:test_104()
  = ./../tests/test-framework.sh:6416:run_one()
  = ./../tests/test-framework.sh:6455:run_one_logged()
  = ./../tests/test-framework.sh:6286:run_test()
  = sanityn.sh:4741:main()
Dumping lctl log to /tmp/test_logs/1564774698/sanityn.test_104.*.1564774724.log
Dumping logs only on local client.
Resetting fail_loc on all nodes...done.
FAIL 104 (3s)
cleanup: ======================================================
sh: fuser: command not found
sh: fuser: command not found
== sanityn test complete, duration 26 sec ============================================================ 22:38:44 (1564774724)
sanityn: FAIL: test_104 Link to an orphan object succeeded
rm: cannot remove &apos;/mnt/lustre/d104.sanityn/mdt1dir&apos;: Directory not empty
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;


&lt;p&gt;the wrong link causes a cross-mdt link corruption, &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;[root@devvm1 tests]# stat /mnt/lustre/d104.sanityn/mdt1dir/file2x 
stat: cannot stat &#8216;/mnt/lustre/d104.sanityn/mdt1dir/file2x&#8217;: No such file or directory
[root@devvm1 tests]# 
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;

&lt;p&gt;file2x is a name which cannot be deleted, it points to a remote object already removed from OI, but its inode (unconnected) still exists.&lt;/p&gt;</comment>
                            <comment id="252972" author="gerrit" created="Mon, 12 Aug 2019 20:29:50 +0000"  >&lt;p&gt;Alexander Zarochentsev (c17826@cray.com) uploaded a new patch: &lt;a href=&quot;https://review.whamcloud.com/35776&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://review.whamcloud.com/35776&lt;/a&gt;&lt;br/&gt;
Subject: &lt;a href=&quot;https://jira.whamcloud.com/browse/LU-11549&quot; title=&quot;Unattached inodes after 3 min racer run.&quot; class=&quot;issue-link&quot; data-issue-key=&quot;LU-11549&quot;&gt;&lt;del&gt;LU-11549&lt;/del&gt;&lt;/a&gt; mdd: set LUSTRE_ORPHAN_FL for non-dirs&lt;br/&gt;
Project: fs/lustre-release&lt;br/&gt;
Branch: master&lt;br/&gt;
Current Patch Set: 1&lt;br/&gt;
Commit: fd759510de938a3556eddf3b5798ce95135e1dbc&lt;/p&gt;</comment>
                            <comment id="252974" author="zam" created="Mon, 12 Aug 2019 20:36:52 +0000"  >&lt;p&gt;The above patch &lt;a href=&quot;https://review.whamcloud.com/35776&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://review.whamcloud.com/35776&lt;/a&gt; fixes the issue, my reproducer doesn&apos;t show any fs corruption .  Unfortunately it reports an incorrect link creation even with the fix b/c the test was not ready that client repeats the link() operation  after getting ESTALE error, so second attempt to create the link works.&lt;/p&gt;

&lt;p&gt;the fix is one-liner:&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;
diff --git a/lustre/mdd/mdd_dir.c b/lustre/mdd/mdd_dir.c
index 17613d6..260dd7a 100644
--- a/lustre/mdd/mdd_dir.c
+++ b/lustre/mdd/mdd_dir.c
@@ -1456,7 +1456,7 @@ &lt;span class=&quot;code-keyword&quot;&gt;static&lt;/span&gt; &lt;span class=&quot;code-object&quot;&gt;int&lt;/span&gt; mdd_mark_orphan_object(&lt;span class=&quot;code-keyword&quot;&gt;const&lt;/span&gt; struct lu_env *env,
        struct lu_attr *attr = MDD_ENV_VAR(env, la_for_start);
        &lt;span class=&quot;code-object&quot;&gt;int&lt;/span&gt; rc;
 
-       &lt;span class=&quot;code-keyword&quot;&gt;if&lt;/span&gt; (!S_ISDIR(mdd_object_type(obj)))
+       &lt;span class=&quot;code-keyword&quot;&gt;if&lt;/span&gt; (S_ISDIR(mdd_object_type(obj)))
                &lt;span class=&quot;code-keyword&quot;&gt;return&lt;/span&gt; 0;
 
        attr-&amp;gt;la_valid = LA_FLAGS;
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;</comment>
                            <comment id="253852" author="gerrit" created="Thu, 29 Aug 2019 12:05:32 +0000"  >&lt;p&gt;Alexander Zarochentsev (c17826@cray.com) uploaded a new patch: &lt;a href=&quot;https://review.whamcloud.com/35991&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://review.whamcloud.com/35991&lt;/a&gt;&lt;br/&gt;
Subject: &lt;a href=&quot;https://jira.whamcloud.com/browse/LU-11549&quot; title=&quot;Unattached inodes after 3 min racer run.&quot; class=&quot;issue-link&quot; data-issue-key=&quot;LU-11549&quot;&gt;&lt;del&gt;LU-11549&lt;/del&gt;&lt;/a&gt; tests: link succeded to an ophan remote object&lt;br/&gt;
Project: fs/lustre-release&lt;br/&gt;
Branch: master&lt;br/&gt;
Current Patch Set: 1&lt;br/&gt;
Commit: 3e6574997f82407c98b90318448400bb3a1ca5e0&lt;/p&gt;</comment>
                            <comment id="254311" author="gerrit" created="Sat, 7 Sep 2019 01:49:30 +0000"  >&lt;p&gt;Oleg Drokin (green@whamcloud.com) merged in patch &lt;a href=&quot;https://review.whamcloud.com/35776/&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://review.whamcloud.com/35776/&lt;/a&gt;&lt;br/&gt;
Subject: &lt;a href=&quot;https://jira.whamcloud.com/browse/LU-11549&quot; title=&quot;Unattached inodes after 3 min racer run.&quot; class=&quot;issue-link&quot; data-issue-key=&quot;LU-11549&quot;&gt;&lt;del&gt;LU-11549&lt;/del&gt;&lt;/a&gt; mdd: set LUSTRE_ORPHAN_FL for non-dirs&lt;br/&gt;
Project: fs/lustre-release&lt;br/&gt;
Branch: master&lt;br/&gt;
Current Patch Set: &lt;br/&gt;
Commit: 8d27c92a66d63aaf8b8fbe1fc73e49263b5bed1e&lt;/p&gt;</comment>
                            <comment id="256250" author="adilger" created="Fri, 11 Oct 2019 18:02:37 +0000"  >&lt;p&gt;The fix for this problem has been landed for 2.13.0 so this ticket should be closed so that it can be tracked properly for the release.  Since the test patch is not currently passing testing I&apos;ve opened a separate ticket to track that landing.&lt;/p&gt;</comment>
                    </comments>
                <issuelinks>
                            <issuelinktype id="10011">
                    <name>Related</name>
                                            <outwardlinks description="is related to ">
                                        <issuelink>
            <issuekey id="53452">LU-11446</issuekey>
        </issuelink>
            <issuelink>
            <issuekey id="52665">LU-11130</issuekey>
        </issuelink>
            <issuelink>
            <issuekey id="19633">LU-3537</issuekey>
        </issuelink>
                            </outwardlinks>
                                                                <inwardlinks description="is related to">
                                        <issuelink>
            <issuekey id="57135">LU-12848</issuekey>
        </issuelink>
            <issuelink>
            <issuekey id="58317">LU-13346</issuekey>
        </issuelink>
            <issuelink>
            <issuekey id="54125">LU-11706</issuekey>
        </issuelink>
                            </inwardlinks>
                                    </issuelinktype>
                    </issuelinks>
                <attachments>
                            <attachment id="31462" name="racer-mod.tar.gz" size="3680" author="zam" created="Wed, 14 Nov 2018 13:22:08 +0000"/>
                            <attachment id="31461" name="unconnected.txt.gz" size="7710597" author="zam" created="Wed, 14 Nov 2018 10:15:46 +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|i004nj:</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>