Adrian, ----- Original Message ----- From: ""Adrian Liang"" <[EMAIL PROTECTED]> Newsgroups: mailing.database.mysql Sent: Saturday, September 21, 2002 6:48 AM Subject: Interesting innodb activity with 3.23.52
> > Hi, > > We experienced some interesting things when we upgraded to Mysql-Max > 3.23.52 (Red Hat 7.1, 2.4.7-10enterprise). It looked like after a > sustained amount of large disk activity, the whole system would slow to > a crawl and CPU idle % would go down to 0 for about 30 seconds before it > popped back. We tried fiddling around with the configuration files and > even tried another kernel (2.4.9-34enterprise) but without any luck. > What did work was downgrading our MySQL version to 3.23.49a . Once we > downgraded, everything worked fine. > > Has anyone seen anything like this before? Ideally we'd like to take > advantage of all the changes made between .49a and .52. this sounds like the well-known 'thread thrashing' problem in Linux. It also occurs with MyISAM tables. CPU usage increases 100-fold to normal. Small changes in glibc seem to affect this. Some users have got a good version by compiling themselves and linking with the glibc on their own computer. The new Linux O(1) thread schedulers may solve this problem. > Adrian Liang > Em: [EMAIL PROTECTED] Best regards, Heikki Tuuri Innobase Oy --- Order technical MySQL/InnoDB support at https://order.mysql.com/ See http://www.innodb.com for the online manual and latest news on InnoDB sql query --------------------------------------------------------------------- Before posting, please check: http://www.mysql.com/manual.php (the manual) http://lists.mysql.com/ (the list archive) To request this thread, e-mail <[EMAIL PROTECTED]> To unsubscribe, e-mail <[EMAIL PROTECTED]> Trouble unsubscribing? Try: http://lists.mysql.com/php/unsubscribe.php