You could return to v108 and watch performance again.
El 29/03/16 a les 22:19, Karl Johnson ha escrit: > Disks are fine and RAID is optimal. It doesn't happen only when backups > run but it's easier to see during this time. What's strange is that > there were no issue on <108 kernels. > > It could have been this following patch from RedHat but 113 isn't based > on 2.6.32-573.22.1, 114 will be I think. > > /* Due to prematurely decremented calc_load_task, the calculated load > average was off by up to the number of CPUs in the machine. (BZ#1300349)/ > > Karl > > On Tue, Mar 29, 2016 at 3:35 PM, Gena Makhomed <g...@csdoc.com > <mailto:g...@csdoc.com>> wrote: > > On 29.03.2016 21:03, Karl Johnson wrote: > > Every weekend I do backups of all CT which take a lot of IO. It > didn't > affect much load average before 108 but as soon as I upgraded to > 113, load > got very high and nodes became sluggish during backups. It might be > something else but I was looking for feedback if someone else > had the same > issue. I will continue to troubleshoot this issue. Meanwhile, I will > upgrade them from 113.12 to 113.21 and see how it goes even if > there's > nothing related to this in the changelog. > > > See smartctl - temperature of HDDs and seek/read errors. > > Reason of "nodes became sluggish during backups" > can be high HDD temp and high seek/read errors rate. > > Also see free space on backup partition - if free space > low it will be very fragmented and write will be slow > - need many IOPS for write many small file chunks. > > -- > Best regards, > Gena > > _______________________________________________ > Users mailing list > Users@openvz.org <mailto:Users@openvz.org> > https://lists.openvz.org/mailman/listinfo/users > > > > > _______________________________________________ > Users mailing list > Users@openvz.org > https://lists.openvz.org/mailman/listinfo/users > _______________________________________________ Users mailing list Users@openvz.org https://lists.openvz.org/mailman/listinfo/users
