[Gluster-users] Transport Endpoint Not connected while running sysbench on Gluster Volume

[Julio Guevara]

Also, this is the profile output of this Volume:

gluster> volume profile mariadb_gluster_volume info cumulative
Brick: laeft-dccdb01p.core.epay.us.loc:/export/mariadb_backup/brick
-------------------------------------------------------------------
Cumulative Stats:
   Block Size:              16384b+               32768b+
65536b+
 No. of Reads:                    0                     0
  0
No. of Writes:                83391                465750
 102911

   Block Size:             131072b+
 No. of Reads:                   33
No. of Writes:                 8551
 %-latency   Avg-latency   Min-Latency   Max-Latency   No. of calls
Fop
 ---------   -----------   -----------   -----------   ------------
 ----
      0.00       0.00 us       0.00 us       0.00 us             26
 FORGET
      0.00       0.00 us       0.00 us       0.00 us             33
RELEASE
      0.00       0.00 us       0.00 us       0.00 us             92
 RELEASEDIR
      0.00     102.25 us      70.00 us     155.00 us              4
 SETXATTR
      0.00     159.80 us      97.00 us     207.00 us              5
RMDIR
      0.00     266.75 us     121.00 us     675.00 us              4
SETATTR
      0.00     100.62 us      29.00 us     700.00 us             16
INODELK
      0.00      84.33 us      29.00 us     477.00 us             33
FLUSH
      0.00      68.16 us      34.00 us     165.00 us             92
OPENDIR
      0.01      88.35 us      21.00 us     608.00 us             92
 STAT
      0.01     754.04 us     262.00 us   10104.00 us             25
 CREATE
      0.02     169.04 us      27.00 us     997.00 us            179
 READDIRP
      0.04     150.90 us      43.00 us    1867.00 us            365
 LOOKUP
      0.04   16330.75 us     297.00 us   46360.00 us              4
MKDIR
      0.18    7896.70 us      71.00 us  256814.00 us             33
 READ
      0.68     466.93 us      19.00 us    1848.00 us           2119
 STATFS
      2.39  151339.17 us     227.00 us  540998.00 us             23
 UNLINK
      5.49  320155.28 us    2035.00 us 1273394.00 us             25
FSYNC
     31.28      69.00 us      30.00 us   11447.00 us         660603
WRITE
     59.84 10899586.88 us 5827342.00 us 13921169.00 us              8
 OPEN

    Duration: 71425 seconds
   Data Read: 4325376 bytes
Data Written: 29195534336 bytes


As you can see OPEN Fop take the most amount of time and they normally
timeout, even with default value for networking.frame-timeout

Thanks

On Tue, Jun 13, 2017 at 3:43 PM, Julio Guevara <julioguevara150 at gmail.com>
wrote:

> I'm having a hard time trying to get a gluster volume up and running. I
> have setup other gluster volumes on other systems without much problems but
> this one is killing me.
>
> The gluster vol was created with the command:
> gluster volume create mariadb_gluster_volume laeft-dccdb01p:/export/
> mariadb/brick
>
> I had to lower frame-timeout since the system would become unresponsive
> until the frame failed by timeout:
> gluster volume set mariadb_gluster_volume networking.frame-timeout 5
>
> running gluster version: glusterfs 3.8.12
>
> The workload i'm using is: sysbench --test=fileio --file-total-size=4G
> --file-num=64 prepare
>
> sysbench version: sysbench 0.4.12-5.el6
>
> kernel version: 2.6.32-696.1.1.el6
>
> centos: 6.8
>
> Issue: Whenever I run the sysbench over the mount /var/lib/mysql_backups I
> get the error that is shown on the log output.
>
> It is a constant issue, I can reproduce it when I start increasing the
> --file-num for sysbench above 3.
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.gluster.org/pipermail/gluster-users/attachments/20170614/c0b377d0/attachment.html>