[Gluster-users] gluster + interruptions causing high load

[Alex Florescu]

Hello again,

I am now seeking some advices regarding gluster configuration.
I have the following options:
Options Reconfigured:
nfs.disable: 1
network.ping-timeout: 1

>From my tests, I noticed that setting a low network.ping-timeout (1s)
causes gluster to declare the other node dead, and quickly allow access to
the common storage content. But in the last 4 days I have been experiencing
some weird occurrences. I am using gluster in WAN environment replication,
and I am suspecting network connectivity is sometimes timing out.
This causes gluster to stall for ~ 1 minute, like the log says:
[2012-04-21 18:11:31.758139] C
[client-handshake.c:121:rpc_client_ping_timer_expired]
0-comun-vol-client-0: server xxx.xxx.xxx.xxx:24009 has not responded in the
last 42 seconds, disconnecting.
and also causes big load on the server (100+), freezing all other
applications.

I have now reconfigured network.ping-timeout to 10.
What I would like to achieve is to have minimum "downtime" when bricks are
failing. Any other options I can set?
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://supercolony.gluster.org/pipermail/gluster-users/attachments/20120421/2bfc8fe8/attachment.html>