Hi Jørn, >> I would say that this sort of performance drop is not typical. Some >> users have reported a smaller performance loss in single threaded >> workloads in 5.6. > > But dropping from an average of 1800 jobs per minute down to 300? I don't > think that should be expected.
I would agree with you here. > A few weeks ago I stopped the test and restored the initial database starting > the test over again. Now the performance was back to 1700 jobs per minute, > but it slowly went down as the test ran. Yesterday it was down to 300 per > minutes and still (but very slowly) dropped. > > Yesterday I did the following: > > * stopped the test > * dumped all databases > * stopped the mysql server 5.6 > * Downloaded 5.5.33-log source and installed it > * Removed all inodb* and ib_log* files > * Removed all databases > * Started and initialized mysql > * Restored all databases > * Started the test where I left it. > > After a few hours I could see that the performance was back to normal - 1800 > - > 2000 jobs per minute. There is no sign of drop in performace so far. > > Please explain. I want to suspect that there might be a specific query regression (where 5.6 has introduced a new feature, and you fall in an edge case where it is being optimized incorrectly). The way to deduce this is to run EXPLAIN for key queries in MySQL 5.6 and 5.5, and compare for differences: https://dev.mysql.com/doc/refman/5.6/en/explain.html When you have one, there are a lot of people on the list that would be happy to pair this down to a test case, and file a bug. There is also a switch to disable specific optimizations, so you may have an easy work around that would allow you to restore back on 5.6: https://dev.mysql.com/doc/refman/5.6/en/switchable-optimizations.html - Morgan -- MySQL General Mailing List For list archives: http://lists.mysql.com/mysql To unsubscribe: http://lists.mysql.com/mysql
