[Gluster-users] Cluster not healing

[Gambit15]

Have you verified that Gluster has marked the files as split-brain?

gluster volume heal <vol> info split-brain

If you're fairly confident about which files are correct, you can automate
the split-brain healing procedure.

>From the manual...

>         volume heal <VOLNAME> split-brain bigger-file <FILE>
>               Performs healing of <FILE> which is in split-brain by
> choosing the bigger file in the replica as source.
>
>         volume heal <VOLNAME> split-brain source-brick <HOSTNAME:BRICKNAME>
>               Selects <HOSTNAME:BRICKNAME> as the source for all the files
> that are in split-brain in that replica and heals them.
>
>         volume heal <VOLNAME> split-brain source-brick
> <HOSTNAME:BRICKNAME> <FILE>
>               Selects the split-brained <FILE> present in
> <HOSTNAME:BRICKNAME> as source and completes heal.
>

D

On 23 January 2017 at 16:28, James Wilkins <nebulai at gmail.com> wrote:

> Hello,
>
> I have a couple of gluster clusters - setup with distributed/replicated
> volumes that have starting incrementing the heal-count from statistics -
> and for some files returning input/output error when attempting to access
> said files from a fuse mount.
>
> If i take one volume, from one cluster as an example:
>
> gluster volume heal storage01 statistics info
> <snip>
> Brick storage02.<redacted>:/storage/sdc/brick_storage01
> Number of entries: 595
> </snip>
>
> And then proceed to look at one of these files (have found 2 copies - one
> on each server / brick)
>
> First brick:
>
> # getfattr -m . -d -e hex  /storage/sdc/brick_storage01/
> projects/183-57c559ea4d60e-canary-test--node02/wordpress285-data/html/wp-
> content/themes/twentyfourteen/single.php
> getfattr: Removing leading '/' from absolute path names
> # file: storage/sdc/brick_storage01/projects/183-57c559ea4d60e-
> canary-test--node02/wordpress285-data/html/wp-
> content/themes/twentyfourteen/single.php
> security.selinux=0x73797374656d5f753a6f626a6563
> 745f723a676c7573746572645f627269636b5f743a733000
> trusted.afr.dirty=0x000000000000000000000000
> trusted.afr.storage01-client-0=0x000000020000000100000000
> trusted.bit-rot.version=0x02000000000000005874e2cd0000459d
> trusted.gfid=0xda4253be1c2647b7b6ec5c045d61d216
> trusted.glusterfs.quota.c9764826-596a-4886-9bc0-60ee9b3fce44.contri.1=
> 0x00000000000006000000000000000001
> trusted.pgfid.c9764826-596a-4886-9bc0-60ee9b3fce44=0x00000001
>
> Second Brick:
>
> # getfattr -m . -d -e hex /storage/sdc/brick_storage01/
> projects/183-57c559ea4d60e-canary-test--node02/wordpress285-data/html/wp-
> content/themes/twentyfourteen/single.php
> getfattr: Removing leading '/' from absolute path names
> # file: storage/sdc/brick_storage01/projects/183-57c559ea4d60e-
> canary-test--node02/wordpress285-data/html/wp-
> content/themes/twentyfourteen/single.php
> security.selinux=0x73797374656d5f753a6f626a6563
> 745f723a676c7573746572645f627269636b5f743a733000
> trusted.afr.dirty=0x000000000000000000000000
> trusted.bit-rot.version=0x020000000000000057868423000d6332
> trusted.gfid=0x14f74b04679345289dbd3290a3665cbc
> trusted.glusterfs.quota.47e007ee-6f91-4187-81f8-90a393deba2b.contri.1=
> 0x00000000000006000000000000000001
> trusted.pgfid.47e007ee-6f91-4187-81f8-90a393deba2b=0x00000001
>
>
>
> I can see the only the first brick has the appropiate trusted.afr.<client>
> tag - e.g in this case
>
> trusted.afr.storage01-client-0=0x000000020000000100000000
>
> Files are same size under stat - just the access/modify/change dates are
> different.
>
> My first question is - reading https://gluster.readthedocs.io/en/latest/
> Troubleshooting/split-brain/ this suggests that i should have this field
> on both copies of the files - or am I mis-reading?
>
> Secondly - am I correct that each one of these entries will require manual
> fixing?  (I have approx 6K files/directories in this state over two
> clusters - which appears like an awful lot of manual fixing)
>
> I've checked gluster volume info <vol> and all appropiate
> services/self-heal daemon are running.  We've even tried a full heal/heal
> and iterating over parts of the filesystem in question with find / stat /
> md5sum.
>
> Any input appreciated.
>
> Cheers,
>
>
>
>
>
> _______________________________________________
> Gluster-users mailing list
> Gluster-users at gluster.org
> http://lists.gluster.org/mailman/listinfo/gluster-users
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.gluster.org/pipermail/gluster-users/attachments/20170123/12b5c8e7/attachment.html>