…Oleksiy – that sounds like fun! Though if partition table is aligned properly, after you create software RAID, there’s little difference what is the physical sector size since you want to align to md chunk size right? @Roman – while this depends a… to have a relatively small stripe size as long as IO is aligned (but not smaller than your working block size – 16k…
Post: MySQL 5.5.8 and Percona Server: being adaptive
December 20, 2010 By 25 Comments
… bytes, in test with FusionIO I use 4096 bytes, to align IO with internal FusionIO size. You can see that MySQL 5… it also concurs with my previous experience, that with bigger io_capacity you rather getting worse results. For reference, here is…_flush_neighbor_pages = 0 innodb_write_io_threads=8 innodb_read_io_threads=8 innodb_io_capacity=500 max_connections=3000 query_cache…
Post: Choosing innodb_buffer_pool_size
November 3, 2007 By 39 Comments
… serve writes to these log files as IO to the log files is not aligned to the page boundary. Finally you likely… will not make Innodb to bypass OS buffering Innodb TableSpace IO will wipe out cache because it typically makes most of… example when Innodb tries to avoid holding latches while doing IO while there could be locks set while accessing pages in…
Post: The tool I've been waiting for years
March 18, 2008 By 10 Comments
… you a clue if slow down happens because of extra IO pressure or just because pages were washed out. You can… as it can’t perform direct IO to log files on Linux because it is not aligned. [root@DB01 mysql]# du -h… the file you can draw some conclusions about how much IO pressure we have on this server. P.S If you…
Comment: Innodb usability and ease of use.
October 3, 2007 By 14 Comments
Indeed. O_DIRECT can’t be used with Log (on Linux) because it requires aligned IO while log can get writes of various sizes/alignment.
Post: Performance improvements in Percona 5.0.83 and XtraDB
July 14, 2009 By 27 Comments
… time and rest time we played with performance trying to align XtraDB performance with MySQL 5.4 ® and also port all… pool mutex into several small mutexes, and ported some Google IO fixes. Here are results what we have so far. As… eventually. But this is topic for another benchmark. And now IO-bound results Again you can see that XtraDB, 5.0…
Post: XtraDB/InnoDB CPU bound benchmarks on 24cores server
December 29, 2008 By 6 Comments
… xtpr lahf_lm bogomips : 4788.59 clflush size : 64 cache_alignment : 64 address sizes : 40 bits physical, 48 bits virtual power…=0 innodb_thread_concurrency=0 innodb_io_capacity=1000 innodb_write_io_threads = 16 innodb_read_io_threads = 16 join_buffer_size=1M…
Comment: Effect from innodb log block size 4096 bytes
January 3, 2011 By 19 Comments
Then you’d want to format to 512 byte sector size. The larger IOs will be a little less efficient, but it will work fine. Also recommend using O_DIRECT file IO (which requires sector size alignment).
Comment: MySQL 5.5.8 and Percona Server: being adaptive
December 20, 2010 By 25 Comments
You set the log block size to 4K to align with FusionIO size. What about non-log IO such as IO for table and index data? Is it necessary to set block size for them too?
Comment: Aligning IO on a hard disk RAID – the Benchmarks
August 12, 2012 By 13 Comments
[...] Aligning IO on a hard disk RAID – the Benchmarks [...]
