Hi William, On Fri, Apr 19, 2019 at 11:05:51AM +0000, William Dauchy wrote: > Hi Willy, > > On Sat, Apr 13, 2019 at 08:01:53AM +0200, Willy Tarreau wrote: > > Did you issue one of the commands that tries to be alone, thus "show sess" > > or "show fd" ? It's possible that you were having only one thread blocked > > initially and that with the command that was waiting for all threads to > > stop, at some point they all wake up to wait and all eat your CPU. > > nice reminder for those two commands. we however don't control all the > commands which are done through the unix socket as we have our provisioner > using it every n seconds, and also another process collecting the stats. > We however don't issue "show sess" or "show fd" to my knowledge.
OK. > Thanks for the answer anyway, I was reporting this as a "warning" to > collect our possible known issues, even if it was a very partial bug > report. Note that with all the scheduling issues we've fixed over the last days, there are multiple candidates which could cause this. Another one was the lack of effect of the nice parameter which is normally set on the CLI but the lack of which could result in socat timing out during the first half second in absence of any response. Willy
