On Fri, Jun 11, 2021 at 04:49:44PM +0100, Anton Ivanov wrote:
> 
> On 10/06/2021 23:01, Ben Pfaff wrote:
> > On Tue, Jun 08, 2021 at 10:27:08AM +0100, [email protected] 
> > wrote:
> > > From: Anton Ivanov <[email protected]>
> > > 
> > > Set a soft time limit of "raft election timer"/2 on ovsdb
> > > processing.
> > > 
> > > This improves behaviour in large heavily loaded clusters.
> > > While it cannot fully eliminate spurious raft elections
> > > under heavy load, it significantly decreases their number.
> > > 
> > > TODO: randomize session processing order to ensure individual
> > > sessions towards the end of the remotes list are not starved
> > > 
> > > Signed-off-by: Anton Ivanov <[email protected]>
> > Personally I'd consider a random or round-robin processing order to be
> > pretty critical here.
> 
> I have pushed an updated version which implements a "restart where you 
> stopped" approach. This should be mostly identical to the current master in 
> terms of "session starvation" while having "raft at higher priority".

That seems fine, then.
_______________________________________________
dev mailing list
[email protected]
https://mail.openvswitch.org/mailman/listinfo/ovs-dev

Reply via email to