Re: gfid entries in volume heal info that do not heal

Jim Kinney <jim.kinney@xxxxxxxxx> · Mon, 06 Nov 2017 14:04:35 -0500

That took a while!

I have the following stats:

4085169 files in both bricks
3162940 files only have a single hard link.

All of the files exist on both servers. bmidata2 (below) WAS running when bmidata1 died.

gluster volume heal clifford  statistics heal-count
Gathering count of entries to be healed on volume clifford has been successful 

Brick bmidata1:/data/glusterfs/clifford/brick/brick
Number of entries: 0

Brick bmidata2:/data/glusterfs/clifford/brick/brick
Number of entries: 296252

Brick bmidata1:/data/glusterfs/clifford3/brick/brick
Number of entries: 1

Brick bmidata2:/data/glusterfs/clifford3/brick/brick
Number of entries: 182407

Why those numbers are so much smaller than the data from a stat run through the entire brick, I have no idea.

The 20TB of space for this mount point is composed of 4 10TB brick in a 2x2.

As this is all from a large copy in from a backup source, I'm thinking of rerunning rsync to overwrite files with same create/modify times on the mount to realign things (maybe?)

I ran a giant ls/stat on the mount but nothing changed. Ran it again with no changes.

gluster-health-report 

Loaded reports: glusterd-op-version, georep, gfid-mismatch-dht-report, glusterd-peer-disconnect, disk_usage, errors_in_logs, coredump, glusterd, glusterd_volume_version_cksum_errors, kernel_issues, errors_in_logs, ifconfig, nic-health, process_status

[     OK] Disk used percentage  path=/  percentage=7
[     OK] Disk used percentage  path=/var  percentage=7
[     OK] Disk used percentage  path=/tmp  percentage=7
[  ERROR] Report failure  report=report_check_errors_in_glusterd_log
[     OK] All peers are in connected state  connected_count=1  total_peer_count=1
[     OK] no gfid mismatch
[ NOT OK] Failed to check op-version
[ NOT OK] The maximum size of core files created is NOT set to unlimited.
[  ERROR] Report failure  report=report_check_worker_restarts
[  ERROR] Report failure  report=report_non_participating_bricks
[     OK] Glusterd is running  uptime_sec=5177509
[  ERROR] Report failure  report=report_check_version_or_cksum_errors_in_glusterd_log
[  ERROR] Report failure  report=report_check_errors_in_glusterd_log
[ NOT OK] Recieve errors in "ifconfig enp131s0" output
[ NOT OK] Recieve errors in "ifconfig eth0" output
[ NOT OK] Recieve errors in "ifconfig eth3" output
[ NOT OK] Recieve errors in "ifconfig mlx_ib0" output
[ NOT OK] Transmission errors in "ifconfig mlx_ib0" output
[ NOT OK] Errors seen in "cat /proc/net/dev -- eth0" output
[ NOT OK] Errors seen in "cat /proc/net/dev -- eth3" output
[ NOT OK] Errors seen in "cat /proc/net/dev -- mlx_ib0" output
[ NOT OK] Errors seen in "cat /proc/net/dev -- enp131s0" output
High CPU usage by Self-heal

NOTE: Bmidata2 up for over 300 days. due for reboot. 

On Tue, 2017-10-24 at 12:35 +0530, Karthik Subrahmanya wrote:
Hi Jim,

Can you check whether the same hardlinks are present on both the bricks & both of them have the link count 2?
If the link count is 2 then  "find <brickpath> -samefile <brickpath/.glusterfs/<first two
 bits of gfid>/<next 2 bits of gfid>/<full gfid>"
should give you the file path.

Regards,
Karthik

On Tue, Oct 24, 2017 at 3:28 AM, Jim Kinney <jim.kinney@xxxxxxxxx> wrote:

I'm not so lucky. ALL of mine show 2 links and none have the attr data that supplies the path to the original.

I have the inode from stat. Looking now to dig out the path/filename from  xfs_db on the specific inodes individually.

Is the hash of the filename or <path>/filename and if so relative to where? /, <path from top of brick>, ?

On Mon, 2017-10-23 at 18:54 +0000, Matt Waymack wrote:

In my case I was able to delete the hard links in the .glusterfs folders of the bricks and it seems to have done the trick, thanks!

From: Karthik Subrahmanya [mailto:ksubrahm@xxxxxxxxxx]

Sent: Monday, October 23, 2017 1:52 AM

To: Jim Kinney <jim.kinney@xxxxxxxxx>; Matt Waymack <mwaymack@xxxxxxxxx>

Cc: gluster-users <Gluster-users@xxxxxxxxxxx>

Subject: Re:  gfid entries in volume heal info that do not heal

Hi Jim & Matt,

Can you also check for the link count in the stat output of those hardlink entries in the .glusterfs folder on the bricks.

If the link count is 1 on all the bricks for those entries, then they are orphaned entries and you can delete those hardlinks.

To be on the safer side have a backup before deleting any of the entries.

Regards,

Karthik

On Fri, Oct 20, 2017 at 3:18 AM, Jim Kinney <jim.kinney@xxxxxxxxx> wrote:

I've been following this particular thread as I have a similar issue (RAID6 array failed out with 3 dead drives at once while a 12 TB load was being copied into one mounted space - what a mess)

I have >700K GFID entries that have no path data:

Example:

getfattr -d -e hex -m . .glusterfs/00/00/0000a5ef-5af7-401b-84b5-ff2a51c10421

# file: .glusterfs/00/00/0000a5ef-5af7-401b-84b5-ff2a51c10421

security.selinux=0x73797374656d5f753a6f626a6563745f723a756e6c6162656c65645f743a733000

trusted.bit-rot.version=0x020000000000000059b1b316000270e7

trusted.gfid=0x0000a5ef5af7401b84b5ff2a51c10421

[root@bmidata1 brick]# getfattr -d -n trusted.glusterfs.pathinfo -e hex -m . .glusterfs/00/00/0000a5ef-5af7-401b-84b5-ff2a51c10421

.glusterfs/00/00/0000a5ef-5af7-401b-84b5-ff2a51c10421: trusted.glusterfs.pathinfo: No such attribute

I had to totally rebuild the dead RAID array and did a copy from the live one before activating gluster on the rebuilt system. I accidentally copied over the .glusterfs folder from the working side

(replica 2 only for now - adding arbiter node as soon as I can get this one cleaned up).

I've run the methods from "http://docs.gluster.org/en/latest/Troubleshooting/gfid-to-path/" with no results using random GFIDs. A full systemic
 run using the script from method 3 crashes with "too many nested links" error (or something similar).

When I run gluster volume heal volname info, I get 700K+ GFIDs. Oh. gluster 3.8.4 on Centos 7.3

Should I just remove the contents of the .glusterfs folder on both and restart gluster and run a ls/stat on every file?

When I run a heal, it no longer has a decreasing number of files to heal so that's an improvement over the last 2-3 weeks :-)

On Tue, 2017-10-17 at 14:34 +0000, Matt Waymack wrote:

Attached is the heal log for the volume as well as the shd log. 

Run these commands on all the bricks of the replica pair to get the attrs set on the backend.

[root@tpc-cent-glus1-081017 ~]# getfattr -d -e hex -m . /exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2
getfattr: Removing leading '/' from absolute path names
# file: exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2
security.selinux=0x73797374656d5f753a6f626a6563745f723a756e6c6162656c65645f743a733000
trusted.afr.dirty=0x000000000000000000000000
trusted.afr.gv0-client-2=0x000000000000000100000000
trusted.gfid=0x108694dbc0394b7cbd3dad6a15d811a2
trusted.gfid2path.9a2f5ada22eb9c45=0x38633262623330322d323466332d346463622d393630322d3839356136396461363131662f435f564f4c2d623030312d693637342d63642d63772e6d6435

[root@tpc-cent-glus2-081017 ~]# getfattr -d -e hex -m . /exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2
getfattr: Removing leading '/' from absolute path names
# file: exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2
security.selinux=0x73797374656d5f753a6f626a6563745f723a756e6c6162656c65645f743a733000
trusted.afr.dirty=0x000000000000000000000000
trusted.afr.gv0-client-2=0x000000000000000100000000
trusted.gfid=0x108694dbc0394b7cbd3dad6a15d811a2
trusted.gfid2path.9a2f5ada22eb9c45=0x38633262623330322d323466332d346463622d393630322d3839356136396461363131662f435f564f4c2d623030312d693637342d63642d63772e6d6435

[root@tpc-arbiter1-100617 ~]# getfattr -d -e hex -m . /exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2
getfattr: /exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2: No such file or directory

[root@tpc-cent-glus1-081017 ~]# getfattr -d -e hex -m . /exp/b4/gv0/.glusterfs/e0/c5/e0c56bf7-8bfe-46ca-bde1-e46b92d33df3
getfattr: Removing leading '/' from absolute path names
# file: exp/b4/gv0/.glusterfs/e0/c5/e0c56bf7-8bfe-46ca-bde1-e46b92d33df3
security.selinux=0x73797374656d5f753a6f626a6563745f723a756e6c6162656c65645f743a733000
trusted.afr.dirty=0x000000000000000000000000
trusted.afr.gv0-client-11=0x000000000000000100000000
trusted.gfid=0xe0c56bf78bfe46cabde1e46b92d33df3
trusted.gfid2path.be3ba24c3ef95ff2=0x63323366353834652d353566652d343033382d393131622d3866373063656334616136662f435f564f4c2d623030332d69313331342d63642d636d2d63722e6d6435

[root@tpc-cent-glus2-081017 ~]# getfattr -d -e hex -m . /exp/b4/gv0/.glusterfs/e0/c5/e0c56bf7-8bfe-46ca-bde1-e46b92d33df3
getfattr: Removing leading '/' from absolute path names
# file: exp/b4/gv0/.glusterfs/e0/c5/e0c56bf7-8bfe-46ca-bde1-e46b92d33df3
security.selinux=0x73797374656d5f753a6f626a6563745f723a756e6c6162656c65645f743a733000
trusted.afr.dirty=0x000000000000000000000000
trusted.afr.gv0-client-11=0x000000000000000100000000
trusted.gfid=0xe0c56bf78bfe46cabde1e46b92d33df3
trusted.gfid2path.be3ba24c3ef95ff2=0x63323366353834652d353566652d343033382d393131622d3866373063656334616136662f435f564f4c2d623030332d69313331342d63642d636d2d63722e6d6435

[root@tpc-arbiter1-100617 ~]# getfattr -d -e hex -m . /exp/b4/gv0/.glusterfs/e0/c5/e0c56bf7-8bfe-46ca-bde1-e46b92d33df3
getfattr: /exp/b4/gv0/.glusterfs/e0/c5/e0c56bf7-8bfe-46ca-bde1-e46b92d33df3: No such file or directory

And the output of "gluster volume heal <volname> info split-brain"

[root@tpc-cent-glus1-081017 ~]# gluster volume heal gv0 info split-brain
Brick tpc-cent-glus1-081017:/exp/b1/gv0
Status: Connected
Number of entries in split-brain: 0

Brick tpc-cent-glus2-081017:/exp/b1/gv0
Status: Connected
Number of entries in split-brain: 0

Brick tpc-arbiter1-100617:/exp/b1/gv0
Status: Connected
Number of entries in split-brain: 0

Brick tpc-cent-glus1-081017:/exp/b2/gv0
Status: Connected
Number of entries in split-brain: 0

Brick tpc-cent-glus2-081017:/exp/b2/gv0
Status: Connected
Number of entries in split-brain: 0

Brick tpc-arbiter1-100617:/exp/b2/gv0
Status: Connected
Number of entries in split-brain: 0

Brick tpc-cent-glus1-081017:/exp/b3/gv0
Status: Connected
Number of entries in split-brain: 0

Brick tpc-cent-glus2-081017:/exp/b3/gv0
Status: Connected
Number of entries in split-brain: 0

Brick tpc-arbiter1-100617:/exp/b3/gv0
Status: Connected
Number of entries in split-brain: 0

Brick tpc-cent-glus1-081017:/exp/b4/gv0
Status: Connected
Number of entries in split-brain: 0

Brick tpc-cent-glus2-081017:/exp/b4/gv0
Status: Connected
Number of entries in split-brain: 0

Brick tpc-arbiter1-100617:/exp/b4/gv0
Status: Connected
Number of entries in split-brain: 0

-Matt

From: Karthik Subrahmanya [mailto:ksubrahm@xxxxxxxxxx] 
Sent: Tuesday, October 17, 2017 1:26 AM
To: Matt Waymack <mwaymack@xxxxxxxxx>
Cc: gluster-users <Gluster-users@xxxxxxxxxxx>
Subject: Re:  gfid entries in volume heal info that do not heal

Hi Matt,

Run these commands on all the bricks of the replica pair to get the attrs set on the backend.

On the bricks of first replica set:
getfattr -d -e hex -m . <brick path>/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2
On the fourth replica set:
getfattr -d -e hex -m . <brick path>/.glusterfs/e0/c5/e0c56bf7-8bfe-46ca-bde1-e46b92d33df3
Also run the "gluster volume heal <volname>" once and send the shd log.
And the output of "gluster volume heal <volname> info split-brain"
Regards,
Karthik

On Mon, Oct 16, 2017 at 9:51 PM, Matt Waymack <mailto:mwaymack@xxxxxxxxx> wrote:
OK, so here’s my output of the volume info and the heal info. I have not yet tracked down physical location of these files, any tips to finding them would be appreciated, but I’m definitely just wanting them gone.  I forgot to mention earlier that the cluster is running 3.12 and was upgraded from 3.10; these files were likely stuck like this when it was on 3.10.

[root@tpc-cent-glus1-081017 ~]# gluster volume info gv0

Volume Name: gv0
Type: Distributed-Replicate
Volume ID: 8f07894d-e3ab-4a65-bda1-9d9dd46db007
Status: Started
Snapshot Count: 0
Number of Bricks: 4 x (2 + 1) = 12
Transport-type: tcp
Bricks:
Brick1: tpc-cent-glus1-081017:/exp/b1/gv0
Brick2: tpc-cent-glus2-081017:/exp/b1/gv0
Brick3: tpc-arbiter1-100617:/exp/b1/gv0 (arbiter)
Brick4: tpc-cent-glus1-081017:/exp/b2/gv0
Brick5: tpc-cent-glus2-081017:/exp/b2/gv0
Brick6: tpc-arbiter1-100617:/exp/b2/gv0 (arbiter)
Brick7: tpc-cent-glus1-081017:/exp/b3/gv0
Brick8: tpc-cent-glus2-081017:/exp/b3/gv0
Brick9: tpc-arbiter1-100617:/exp/b3/gv0 (arbiter)
Brick10: tpc-cent-glus1-081017:/exp/b4/gv0
Brick11: tpc-cent-glus2-081017:/exp/b4/gv0
Brick12: tpc-arbiter1-100617:/exp/b4/gv0 (arbiter)
Options Reconfigured:
nfs.disable: on
transport.address-family: inet

[root@tpc-cent-glus1-081017 ~]# gluster volume heal gv0 info
Brick tpc-cent-glus1-081017:/exp/b1/gv0
<gfid:108694db-c039-4b7c-bd3d-ad6a15d811a2>
<gfid:6d5ade20-8996-4de2-95d5-20ef98004742>
<gfid:bc6cdc3d-5c46-4597-a7eb-282b21e9bdd5>
<gfid:3c2ff4d1-3662-4214-8f21-f8f47dbdbf06>
<gfid:053e2fb1-bc89-476e-a529-90dffa39963c>

<removed to save scrolling>

Status: Connected
Number of entries: 118

Brick tpc-cent-glus2-081017:/exp/b1/gv0
<gfid:108694db-c039-4b7c-bd3d-ad6a15d811a2>
<gfid:6d5ade20-8996-4de2-95d5-20ef98004742>
<gfid:bc6cdc3d-5c46-4597-a7eb-282b21e9bdd5>
<gfid:3c2ff4d1-3662-4214-8f21-f8f47dbdbf06>
<gfid:053e2fb1-bc89-476e-a529-90dffa39963c>

<removed to save scrolling>

Status: Connected
Number of entries: 118

Brick tpc-arbiter1-100617:/exp/b1/gv0
Status: Connected
Number of entries: 0

Brick tpc-cent-glus1-081017:/exp/b2/gv0
Status: Connected
Number of entries: 0

Brick tpc-cent-glus2-081017:/exp/b2/gv0
Status: Connected
Number of entries: 0

Brick tpc-arbiter1-100617:/exp/b2/gv0
Status: Connected
Number of entries: 0

Brick tpc-cent-glus1-081017:/exp/b3/gv0
Status: Connected
Number of entries: 0

Brick tpc-cent-glus2-081017:/exp/b3/gv0
Status: Connected
Number of entries: 0

Brick tpc-arbiter1-100617:/exp/b3/gv0
Status: Connected
Number of entries: 0

Brick tpc-cent-glus1-081017:/exp/b4/gv0
<gfid:e0c56bf7-8bfe-46ca-bde1-e46b92d33df3>
<gfid:6f0a0549-8669-46de-8823-d6677fdca8e3>
<gfid:d0e2fb2a-21b5-4ea8-a578-0801280b2530>
<gfid:48bff79c-7bc2-4dc5-8b7f-4401b27fdf5a>
<gfid:5902593d-a059-4ec7-b18b-7a2ab5c49a50>
<gfid:cb821178-4621-4fcf-90f3-5b5c2ad7f756>
<gfid:6aea0805-8dd1-437c-b922-52c9d11e488a>
<gfid:f4076a37-2e2f-4d7a-90dd-0a3560a4bdff>
<gfid:51ff7386-a550-4971-957c-b42c4d915e9f>
<gfid:4309f7b8-3a9d-4bc8-ba2b-799f8a02611b>
<gfid:b76746ec-6d7d-4ea3-a001-c96672a4d47e>
<gfid:f8de26e7-d17d-41e0-adcd-e7d24ed74ac8>
<gfid:8e2c4540-e0b4-4006-bb5d-aacd57f8f21b>
<gfid:183ebefb-b827-4cbc-b42b-bfd136d5cabb>
<gfid:88d492fe-bfbd-4463-ba55-0582d0ad671b>
<gfid:e3a6c068-d48b-44b5-9480-245a69648a9b>
<gfid:4aab9c6a-22d2-469a-a688-7b0a8784f4b1>
<gfid:c6d182f2-7e46-4502-a0d2-b92824caa4de>
<gfid:eb546f93-e9d6-4a59-ac35-6139b5c40919>
<gfid:6043e381-7edf-4569-bc37-e27dd13549d2>
<gfid:52090dc7-7a3c-40f9-9c54-3395f5158eab>
<gfid:ecceee46-4310-421e-b56e-5fe46bd5263c>
<gfid:354aea57-4b40-47fc-8ede-1d7e3b7501b4>
<gfid:d43284d4-86aa-42ff-98b8-f6340b407d9d>
Status: Connected
Number of entries: 24

Brick tpc-cent-glus2-081017:/exp/b4/gv0
<gfid:e0c56bf7-8bfe-46ca-bde1-e46b92d33df3>
<gfid:6f0a0549-8669-46de-8823-d6677fdca8e3>
<gfid:d0e2fb2a-21b5-4ea8-a578-0801280b2530>
<gfid:48bff79c-7bc2-4dc5-8b7f-4401b27fdf5a>
<gfid:5902593d-a059-4ec7-b18b-7a2ab5c49a50>
<gfid:cb821178-4621-4fcf-90f3-5b5c2ad7f756>
<gfid:6aea0805-8dd1-437c-b922-52c9d11e488a>
<gfid:f4076a37-2e2f-4d7a-90dd-0a3560a4bdff>
<gfid:51ff7386-a550-4971-957c-b42c4d915e9f>
<gfid:4309f7b8-3a9d-4bc8-ba2b-799f8a02611b>
<gfid:b76746ec-6d7d-4ea3-a001-c96672a4d47e>
<gfid:f8de26e7-d17d-41e0-adcd-e7d24ed74ac8>
<gfid:8e2c4540-e0b4-4006-bb5d-aacd57f8f21b>
<gfid:183ebefb-b827-4cbc-b42b-bfd136d5cabb>
<gfid:88d492fe-bfbd-4463-ba55-0582d0ad671b>
<gfid:e3a6c068-d48b-44b5-9480-245a69648a9b>
<gfid:4aab9c6a-22d2-469a-a688-7b0a8784f4b1>
<gfid:c6d182f2-7e46-4502-a0d2-b92824caa4de>
<gfid:eb546f93-e9d6-4a59-ac35-6139b5c40919>
<gfid:6043e381-7edf-4569-bc37-e27dd13549d2>
<gfid:52090dc7-7a3c-40f9-9c54-3395f5158eab>
<gfid:ecceee46-4310-421e-b56e-5fe46bd5263c>
<gfid:354aea57-4b40-47fc-8ede-1d7e3b7501b4>
<gfid:d43284d4-86aa-42ff-98b8-f6340b407d9d>
Status: Connected
Number of entries: 24

Brick tpc-arbiter1-100617:/exp/b4/gv0
Status: Connected
Number of entries: 0

Thank you for your help!

From: Karthik Subrahmanya [mailto:mailto:ksubrahm@redhat.com] 
Sent: Monday, October 16, 2017 10:27 AM
To: Matt Waymack <mailto:mwaymack@xxxxxxxxx>
Cc: gluster-users <mailto:Gluster-users@gluster.org>
Subject: Re:  gfid entries in volume heal info that do not heal

Hi Matt, 

The files might be in split brain. Could you please send the outputs of these? 
gluster volume info <volname>
gluster volume heal <volname> info
And also the getfattr output of the files which are in the heal info output from all the bricks of that replica pair.
getfattr -d -e hex -m . <file path on brick>

Thanks &  Regards
Karthik

On 16-Oct-2017 8:16 PM, "Matt Waymack" <mailto:mwaymack@xxxxxxxxx> wrote:
Hi all,

I have a volume where the output of volume heal info shows several gfid entries to be healed, but they’ve been there for weeks and have not healed.  Any normal file that shows up on the heal info does get healed as expected, but these gfid entries do not.  Is there any way to remove these orphaned entries from the volume so they are no longer stuck in the heal process?

Thank you!

_______________________________________________
Gluster-users mailing list
mailto:Gluster-users@gluster.org
http://lists.gluster.org/mailman/listinfo/gluster-users

_______________________________________________
Gluster-users mailing list
Gluster-users@xxxxxxxxxxx
http://lists.gluster.org/mailman/listinfo/gluster-users

_______________________________________________
Gluster-users mailing list
Gluster-users@xxxxxxxxxxx
http://lists.gluster.org/mailman/listinfo/gluster-users