… use sysbench fileio, 16KiB block size (to match workload from InnoDB, as this is primary usage for me), and recently I… reasons for that. First, MySQL/InnoDB uses async writes, so this will emulate database load, and second, async mode allows to see…=direct –file-fsync-freq=0 –file-block-size=16384 –report-interval=10 run You may see I gather metrics every 10 sec…
Post: Testing Samsung SSD SATA 256GB 830 - not all SSD created equal
April 25, 2012 By 10 Comments
… use sysbench fileio, 16KiB block size (to match workload from InnoDB, as this is primary usage for me), and recently I… reasons for that. First, MySQL/InnoDB uses async writes, so this will emulate database load, and second, async mode allows to see…=direct –file-fsync-freq=0 –file-block-size=16384 –report-interval=10 run You may see I gather metrics every 10 sec…
Post: Optimizing InnoDB for creating 30,000 tables (and nothing else)
December 22, 2011 By 5 Comments
… noticed that I was only creating about 10-15 tables every second which means we’d take a very long time to… innodb-adaptive-checkpoint=0 and flush-neighbor-pages=0 in the hope of avoiding a bunch of background flushing (which called fsync… that there was an fsync() call when extending the data file, so I tried setting a higher innodb-autoextend-increment and a…
Comment: Effect from innodb log block size 4096 bytes
January 4, 2011 By 18 Comments
… not convinced 
) (sorry..) if I remember well, redo logs within InnoDB are not opened with O_DIRECT option.. – so all redo… are remaining buffered by the filesystem and then flushed by fsync() every second by InnoDB.. – means whatever block size you’re using the writes…
Comment: Effect from innodb log block size 4096 bytes
January 4, 2011 By 18 Comments
… not convinced ) (sorry..) if I remember well, redo logs within InnoDB are not opened with O_DIRECT option.. – so all redo… are remaining buffered by the filesystem and then flushed by fsync() every second by InnoDB.. – means whatever block size you’re using the writes…
Post: Heikki Tuuri Innodb answers - Part I
October 26, 2007 By 17 Comments
… known aspects of Innodb operations while I see it causing problems every so often. Q16: How Innodb decided how …innodb_flush_log_at_trx_commit=2, that is, to flush the log to the disk only once per second…With good RAID with BBU you can get 2000 fsync/sec or more which is typically enough. Q23: …
Post: Tokyo Tyrant - The Extras Part I : Is it Durable?
November 10, 2009 By 5 Comments
…) == -1){ tchdbsetecode(hdb, TCEMMAP, __FILE__, __LINE__, __func__); err = true; } if(fsync(hdb->fd) == -1){ tchdbsetecode(hdb, TCESYNC, __FILE__, __LINE__, __func__); err… a trick from Innodb: We can easily write a a script that calls a background sync every second ( i.e. like innodb_flush_log…
Post: Disaster: LVM Performance in Snapshot Mode
February 5, 2009 By 55 Comments
…/sec executed 163.50 Requests/sec executed (All were 60 second runs) As you see the performance indeed improves though there… final run I did is emulating how Innodb would do buffer pool flushes – calling fsync every 100 writes rather than after each request… going to the same locations over and over again (ie innodb circular logs) – in this case the overhead will be quickly…
Comment: PBXT benchmarks
April 10, 2007 By 14 Comments
… does not call fsync() or uses other techniques. These means it can hardly be compare to Innodb apples to apples. innodb_flush_logs_at_trx_commit=2 settings is kind of close, but not exactly because Innodb will still flush logs every second and…
Post: MySQL Limitations Part 2: The Binary Log
October 23, 2010 By 11 Comments
This is the second in a series on what’s seriously limiting MySQL in … an fsync call for every transaction. And the server performs an XA transaction between InnoDB and the binary log. This adds more fsync calls… replication through the InnoDB transaction log would work fine if a) all the data were in InnoDB, and b) InnoDB‘s data didn…
