… that the slaves can execute all events and be in sync with the master Change configuration for all servers and restart…: 2013-05-17 13:21:26 3130 [ERROR] Slave I/O: The slave IO thread stops because the master has GTID…: 2013-05-17 13:32:08 2563 [ERROR] Slave I/O: The slave IO thread stops because the master has GTID…
Post: MySQL and Percona Server in LinkBench benchmark
May 8, 2013 By 18 Comments
… port=3306 innodb_buffer_pool_size = 30G innodb_flush_method = O_DIRECT innodb_log_file_size = 2000M innodb_log_files_in… = 8 innodb_write_io_threads = 8 innodb_io_capacity = 5000 sync_binlog=0 max_connections=5000 table_open_cache=5000 table…
Comment: What I'm looking forward to at Percona Live (MySQL Users Conference)
April 7, 2013 By 1 Comment
Hmm, Is your statement below actually in sync with what O‘Reily thinks about who actually started the MySQL Conference – at the MySQL Users Conference (as the Percona Live MySQL Conference and Expo was originally called back in 2003)
Comment: Is there room for more MySQL IO Optimization?
January 10, 2013 By 11 Comments
… often you’re calling fsync() within your code, the real sync to the disk will be involved not more frequent than….) so, O_DIRECT is giving a workaround here from all these problems (and again, should be used combined with O_SYNC flag to… in most cases you’ll be more *safe* when using O_DIRECT, while may still go faster with buffered I…
Post: Beware: ext3 and sync-binlog do not play well together
January 21, 2009 By 19 Comments
… reported strange problem with MySQL having extremely poor performance when sync-binlog=1 is enabled, even though the system with RAID… – we get 2350 transactions/sec with sync_binlog=1 and 2550 transactions/sec with sync-binlog=0 which is about 10% overhead… on MySQL side – may be opening binlog with O_DSYNC flag if sync_binlog=1 instead of using fsync will help ? Or…
Post: Testing FusionIO: strict_sync is too strict...
June 15, 2009 By 8 Comments
… kernel, so I was decided to test it in strict_sync mode. As I understand FusionIO in default mode, like Intel… internal memory, not to final media. And FusionIO has “strict_sync” mode to guarantee fsync is trustworthy. So let’s benchmark… benchmark on 100W (9GB data) with 3GB buffer_pool in O_DIRECT access. The raw number are here and graph is…
Comment: Evaluating IO subsystem performance for MySQL Needs
March 5, 2008 By 23 Comments
… anyway. If you’re speaking about unbuffered IO to device (O_SYNC, O_DIRECT) they must not be lost after call returns. If… system cache is removed from equation because of use of O_DIRECT which bypasses OS cache for reads and writes. 256MB…
Comment: Innodb usability and ease of use.
September 28, 2007 By 14 Comments
… it better if I could use O_DIRECT for my data files to prevent FS caching, and O_SYNC for my trx logs.
Comment: SSD, XFS, LVM, fsync, write cache, barrier and lost transactions
March 10, 2009 By 32 Comments
… on the log commit, and thus also for the data. O_SYNC might be different though. Basically you specified the “please go…
Comment: Beware: ext3 and sync-binlog do not play well together
January 23, 2009 By 19 Comments
Steward, You’re saying FSYNC == O_SYNC for opening files ? Speaking about NDB I assume you mean besides Innodb which has fixed sized logs…. BTW even for tablespaces Innodb uses background pre-allocation.
