Hello! I have problem with slow requests on kernel 4.4.0-45 , rolled back all nodes to 4.4.0-42Ubuntu 16.04.1 LTS (Xenial Xerus) ceph version 10.2.3 (ecc23778eb545d8dd55e2e4735b53cc93f92e65b)
Оралов Алексей Отдел корпоративной сети и технологий раб. тел.: 8-831-272-88-88 (вн.244) моб. тел. 8-910-380-12-07 e-mail: oralov_as@tset.pro From: ceph-users [mailto:ceph-users-bounces@xxxxxxxxxxxxxx] On Behalf Of Nick Fisk Hi All, Just a slight note of caution. I had been running the 4.7 kernel (With Ubuntu 16.04) on the majority of my OSD Nodes, as when I installed the cluster there was that outstanding panic bug with the 4.4 kernel. I have been experiencing a lot of flapping OSD’s every time the cluster was put under heavy load. It mostly seemed to occur when the OSD was asked to delete a large number of objects, as in fstriming RBD’s, deleting snapshots or sometimes when backfilling and the PG is removed from the source OSD. I noticed that a couple of nodes which were running the 4.4 kernel from Ubuntu, never seemed to flap and so rolled back all other nodes to 4.4 as well. After this I have not seen a single OSD flap so far. Unfortunately, I couldn’t see any reason for the flapping and/or have a reason why 4.4 seems to be more stable than 4.7, but I thought I would share this in case anyone is having similar issues. Also if there is a problem with newer kernels, it may not be something that was introduced with 4.7, but perhaps maybe 4.5 or 4.6. Nick |
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
