Looks like it's running with a high cpu-level again.... it's currently not impacting the site performance it seems, so I'll leave it running for a bit if that might help trace where the problem might be.
thread_id: 3 date_now: 1556706076.018998 loops: 246336607 172211047 246343444 300853502 230819619 195445612 263889138 194968394 wake_cache: 105064005 103218494 128285292 108769792 106103198 100259938 103680891 88192964 wake_tasks: 75086490 25141922 102567287 131951431 67591528 47537756 108661002 45316125 wake_signal: 0 0 0 0 0 0 0 0 poll_exp: 180150495 128360416 230852580 240721223 173694726 147797694 212341893 133509089 poll_drop: 3482151 2091662 3331142 3261047 2840128 2274358 2521993 3149966 poll_dead: 0 0 0 0 0 0 0 0 poll_skip: 0 0 0 0 0 0 0 0 fd_skip: 0 0 0 0 0 0 0 0 fd_lock: 6129490 11461998 7893033 7900711 8577433 10106993 9788556 3012407 fd_del: 0 0 0 0 0 0 0 0 conn_dead: 0 0 0 0 0 0 0 0 stream: 55741017 33505282 53565283 52407020 46031445 37059793 41244820 49874155 empty_rq: 44638490 67387609 37452856 50370558 55838595 59929139 57700911 34436393 long_rq: 66107108 17951324 177726917 127643664 59754161 40347246 103056053 36018697 cpust_ms_tot: 151395 48182 32775 98606 69228 49291 57636 201601 cpust_ms_1s: 9 0 0 11 3 0 0 14 cpust_ms_15s: 21 18 1 63 5 20 13 34 avg_loop_us: 34 10 30 13 34 6 7 56 On Thu, Mar 14, 2019 at 10:47 AM Willy Tarreau <w...@1wt.eu> wrote: > On Thu, Mar 14, 2019 at 10:34:46AM +0100, Mark Janssen wrote: > > This was the 'show activity' info > > > > Show activity: > > thread_id: 7 > > date_now: 1552497125.537000 > > loops: 1876310231 2198499593 29388065 2234235968 2189969792 23322503 > 11681489 1867345227 > > wake_cache: 4699089 4475087 5332367 4386659 4870234 5108383 5693172 > 4044835 > > wake_tasks: 1868654965 2192153566 21290780 2227958941 2182536918 > 15400586 2497632 1860594634 > > Thank you, so from here it already appears that some threads are much more > loaded than other ones, which means it's not the global run queue which is > the culprit but a local one. This helps a lot. I'll have a look at the > scheduler code to see if I can spot anything related to this. > > > I've since restarted haproxy, so I can't query it currently for new info, > > but wheh it happens again, i'll try to keep it running on the slave node > ;) > > OK thank you! > > Willy > -- Mark Janssen -- m...@sig-io.nl Unix / Linux Open-Source and Internet Consultant
