thank you very much, "leap second" was the translation i missed for our german word "Schaltsekunde"
so i will reboot our infrastrcuture and rollout a kernel update within which was timed for tomorrow after my vacation which is now supsended :-) P.S.: named DNS showas also interesting CPU spikes, but not permamently.... Am 01.07.2012 12:52, schrieb Raghavendra D Prabhu: > * On Sun, Jul 01, 2012 at 12:44:42PM +0200, Reindl Harald > <h.rei...@thelounge.net> wrote: >> i notice since this night all mysqld instances >> suing innodb are running at very high CPU, there >> is nothing in the mysqld-log and after restarting >> the service the same again >> >> i do not think this has to to with the reason taking >> back 5.5.25 becasue no disk-IO, i more doubt this >> has to do with the time-correction-second (not sure >> how to translate "Schaltsekunde" to english) because >> it started late at night >> ______________________ >> >> http://dev.mysql.com/doc/refman/5.5/en/news-5-5-25a.html >> >> BTW: since there are announcements of new versions of >> mysqld it is very rude take them back without any >> announcement and put after weeks some lines in the old >> changelog which nobody reads after rollout >> >> however, as said, i doubt this is not the problem >> > > It has to do with http://bugs.mysql.com/bug.php?id=65778 > More analysis here: > > > http://blog.mozilla.org/it/2012/06/30/mysql-and-the-leap-second-high-cpu-and-the-fix/ > http://serverfault.com/questions/403732/anyone-else-experiencing-high-rates-of-linux-server-crashes-during-a-leap-second > > > It is more of a linux kernel bug (affecting RHEL >=6 in the enterprise > kernels category)
signature.asc
Description: OpenPGP digital signature