Hello Lukas, On 4/4/2016 8:56 PM, Lukas Tribus wrote: > Hi Nenad, > > >> I suggest you try reverting commit 7610073a. I have exhibited very >> similar issues and everything points to this commit (which was Willy's >> first suspect). > > So I assume this affects 1.6 and 1.7-dev as well, the bug is not > specific to the > 1.5 backport, right?
I am not sure, as I haven't even be able to reliably reproduce it on 1.5 (though we are running with some backports from 1.6) as it seems to be traffic-pattern related. On one workload I exhibit instant and constant jump in CPU usage (from 40% to 80-100%, about 50:50 sys:usr), but on other, there are just some very short spikes to 100%. That being said, I haven't been able to devote any time to debugging this. There are specific workloads where this commit improves performance, so I don't think simply reverting that is an option (although the gain on those is 15-20%, while the loss here is much more). Regards, Nenad