[sheepdog-users] Many vdi snapshots may block the network
sirio81 at gmail.com
Mon Dec 9 16:26:49 CET 2013
Hi, I was doing a stress test on my testing cluster: a cylcle that creates
a snapshot for each one of my vdi and then remove them.
While the script was running may colleagues complained about frozen
As soon as the script stopped, they also stopped complaining.
I tried again to run the script, and the connection went off.
Does the action of taking snapshot generate lots of broadcast?
May this be related to corosync more than sheepdog?
Note: my 4 nodes are using dedicated nic and switch for syncing.
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the sheepdog-users