[Gluster-users] Status of the SAMBA module
Vijay Bellur
vbellur at redhat.com
Tue Aug 6 18:41:32 UTC 2013
On 08/06/2013 05:09 PM, haiwei.xie-soulinfo wrote:
> Hi,
>
> Unfortunately, add the two params into smb.conf, nfs client OS will core dump with dd testing.
> I reconfigure gluster vol, without any new params in smb.conf, performance looks good. Maybe
> former low performance result from error config.
>
> [root at infi131 cifs]# dd if=/dev/zero of=t1 bs=64k count=100000
> 记录了100000+0 的读入
> 记录了100000+0 的写出
> 6553600000字节(6.6 GB)已复制,21.3123 秒,308 MB/秒
>
>
> bugs:
> 1, dd bs > 128K, glusterfs brick log shows client disconnect, I guess api caller crash.
> in /var/log/samba/cores, may core files.
Can you please provide backtrace from any of the cores if possible?
>
> 2, some times, nfs client OS core dump.
>
> crash kernel log like:
> Aug 6 11:06:36 infi131 kernel: INFO: task dd:3146 blocked for more than 120 seconds.
> Aug 6 11:06:36 infi131 kernel: "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
> Aug 6 11:06:36 infi131 kernel: dd D 0000000000000000 0 3146 2754 0x00000084
> Aug 6 11:06:36 infi131 kernel: ffff880125b55cd8 0000000000000082 0000000000000000 fff880123fc0<>ff802b5f ffff065fff802117 ff813fc3<>ff803c4f ff8155f8000000f8 ff819b58<>alTae
> Aug 6 11:10:36 infi131 kernel: "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
> Aug 6 11:10:36 infi131 kernel: dd D 0000000000000000 0 3146 2754 0x00000084
> Aug 6 11:10:36 infi131 kernel: ffff880125b55cd8 0000000000000082 0000000000000000 ffff8801231f1c10
> Aug 6 11:10:36 infi131 kernel: ffff880125b55cf8 ffffffffa046c50f ffff8801231f1c72 ffff8801231f1c73
> Aug 6 11:10:36 infi131 kernel: ffff880139cb45f8 ffff880125b55fd8 000000000000fb88 ffff880139cb45f8
> Aug 6 11:10:36 infi131 kernel: Call Trace:
> Aug 6 11:10:36 infi131 kernel: [<ffffffffa046c50f>]? ciswieae+x2/x8 cf]<>[ffff819d> ycpg+x/x0<>[ffff85d7> oshdl+x30c
> Aug 6 11:14:21 infi131 kernel: ipmi device interface
>
Is this a nfs client mounting gluster nfs server?
Thanks,
Vijay
More information about the Gluster-users
mailing list