… with CentOS 5.2 and ext3 filesystem we get 1060 transactions/sec with single thread and sync_binlog=1 while with 2 threads… XFS instead of EXT3 gives expected results – we get 2350 transactions/sec with sync_binlog=1 and 2550 transactions/sec with sync-binlog=0 which is about 10% overhead. EXT2 filesystem also behaves similar to XFS so it seems to be EXT3 specific…
Comment: Drop table performance
April 21, 2011 By 22 Comments
… also know performance issues with ext3 and sync_binlog http://www.mysqlperformanceblog.com/2009/01/21/beware-ext3-and-sync-binlog-do-not-play-well-together/ And in general XFS shows better and stable performance than ext3. ext4 looks better than ext3…
Comment: Drop table performance
April 20, 2011 By 22 Comments
… also know performance issues with ext3 and sync_binloghttp://www.mysqlperformanceblog.com/2009/01/21/beware-ext3-and-sync-binlog-do-not-play-well-together/ And in general XFS shows better and stable performance than ext3. ext4 looks better than ext3…
Comment: Maximal write througput in MySQL
March 5, 2010 By 10 Comments
… here ? I remember EXT3 performs surprisingly bad with sync_binlog=1 http://www.mysqlperformanceblog.com/2009/01/21/beware-ext3-and-sync-binlog-do-not-play-well-together/ In any case it looks like sync_binlog has very bad overhead… fsync per commit in single client (because of XA) with binlog it should be 3 as I understand – the fact performance…
Comment: Jeremy Cole on MySQL Replication
May 27, 2006 By 12 Comments
… a few points. You’re right abuot sync_binlog. I am mainly discussing setting it to sync_binlog=1, but I neglected to mention… with regard to using replication for failover/disaster recovery, where sync_binlog=1 is basically a requirement. Regarding transaction rates, in a… small binary log events constantly or near constantly, to an ext3 filesystem set with data=journal, I think that’s nearly…
Comment: Performance problem with Innodb and DROP TABLE
February 3, 2011 By 23 Comments
Patrick, Ext3 has slow deletes and not just slow but impacting performance … explained here http://www.mysqlperformanceblog.com/2009/01/21/beware-ext3-and-sync-binlog-do-not-play-well-together/ ext4 looks promising in…
Comment: Beware: ext3 and sync-binlog do not play well together
April 6, 2009 By 19 Comments
… ran several sysbench tests with ext3, ext2, and XFS. I noticed a huge performance hit with ext3 and sync_binlog=1 and only a…
Comment: Linux schedulers in tpcc like benchmark
January 31, 2009 By 19 Comments
…/2009/01/21/beware-ext3-and-sync-binlog-do-not-play-well-together/ The problem is most people run on EXT3 and it is…
Comment: Beware: ext3 and sync-binlog do not play well together
January 21, 2009 By 19 Comments
… this today. We were getting 3500 qps replicating only with sync_binlog=1 and innodb_flush_at_trx_commit = 1. This is… 2 respectively increased this to almost 11k qps. All on ext3. Moving to xfs, we got almost identical values with the…
Comment: Is your server's performance about to degrade?
May 19, 2010 By 13 Comments
… flush the data to disk as often as ext3 does, but when you explicitly sync data to disk, it might have to… 1GB binlog from memory to disk at the moment MySQL issued the sync. And that sync is by default only issued inside the binlog… was caused by the very long sync-call. Obviously with faster syncs (i.e. because you sync your binlog more often or with another…
