[Bugs] [Bug 1192971] Disperse volume: 1x(4+2) config doesn't sustain 2 brick failures

[bugzilla at redhat.com]

https://bugzilla.redhat.com/show_bug.cgi?id=1192971



--- Comment #6 from Paul Cuzner <pcuzner at redhat.com> ---
Quick update

I updated glusterfs to glusterfs-server-3.7.0beta2-0.2.gitc1cd4fa.el7 on nodes
and client, and reran the test scenario

Result - beta2 is not hanging the client anymore when the nodes disapper -
which is great.

But...

self heal is not clearing, and is showing errors (attached)
Also the workload generator was running throughout the nodes being killed and
restarted saw I/O errors

5242880 bytes (5.2 MB) copied, 0.408578 s, 12.8 MB/s
File created, pausing for 2 seconds
Creating file number 226
dd: failed to open ‘/mnt/glusterfs/test-files/test_file_226’: Input/output
error
File created, pausing for 2 seconds
Creating file number 227
dd: failed to open ‘/mnt/glusterfs/test-files/test_file_227’: Input/output
error
File created, pausing for 2 seconds
Creating file number 228
dd: failed to open ‘/mnt/glusterfs/test-files/test_file_228’: Input/output
error
File created, pausing for 2 seconds
Creating file number 229
80+0 records in
80+0 records out
5242880 bytes (5.2 MB) copied, 0.868086 s, 6.0 MB/s
File created, pausing for 2 seconds
Creating file number 230
80+0 records in
80+0 records out
5242880 bytes (5.2 MB) copied, 0.368102 s, 14.2 MB/s
File created, pausing for 2 seconds


Also, I tried a full self heal manually 

[root at gfs-ec2 glusterfs]# gluster vol heal ec_volume full 
Commit failed on ebc870ff-6149-4f2d-bd83-ece1f82b839d. Please check log file
for details.

-- 
You are receiving this mail because:
You are on the CC list for the bug.
Unsubscribe from this bug https://bugzilla.redhat.com/token.cgi?t=rRIslMnNe3&a=cc_unsubscribe