openstack team mailing list archive

[Brent Roskos <brent.roskos@xxxxxxxxxxx>]

I wouldn't think 3 replica's across 1 zone is a viable configuration.
 Given you are starting with 4 servers, you should really have 4 zones.
 Then all 3 copies of an object can still go somewhere even when aone
server is down.

When you add more servers, just add them in groups of 4 to keep it simple
and drop a new one in each of the 4 zones.

Brent


On Mon, Jun 24, 2013 at 2:42 AM, Robert van Leeuwen <
Robert.vanLeeuwen@xxxxxxxxxxxxx> wrote:

>   > load average: 24.06, 24.02, 24.00
>
> > There is something, can i do to reduce the load?
> > is it normal?
>
> I guess it depends on what is causing the load. (are there processes
> eating all cpu cycles?)
>
> What we see is that the object-auditor and object-replicator can cause
> quite a bit of load because they are crawling the filesystems and waiting
> for IO.
> You can try to turn these off for a while to see if the load is caused by
> them.
>
> > and  why is there a node storage with load 0 and 0 cpu?
> Is it properly configured in the ring files? (as in: does it have files on
> its filesystems)
> Are the object-auditor and replicator running?
>
> Cheers,
> Robert van Leeuwen
>
> _______________________________________________
> Mailing list: https://launchpad.net/~openstack
> Post to     : openstack@xxxxxxxxxxxxxxxxxxx
> Unsubscribe : https://launchpad.net/~openstack
> More help   : https://help.launchpad.net/ListHelp
>
>