June 18, 2013

Post: Aligning IO on a hard disk RAID – the Benchmarks

… Size ############################# sda | [deadline] 128 # RAID Controller ############################################ Controller | LSI…innodb_flush_log_at_trx_commit = 2 innodb_flush_method = O_DIRECT innodb_log_buffer_size = 8M innodb_buffer_pool_size = 128M innodb_log_file_size = 64M innodb_log

Post: Heikki Tuuri answers to Innodb questions, Part II

… not forget you may need to increase size of your Innodb log files to be able to use a lot of memory… solid state disks for storing ib_log* files; I know that innodb writes files in the log file group in a round robin… just as RAID cache so it can handle system restarts. When putting log files on such device could give great logging performance because…

Post: Setting up XFS on Hardware RAID -- the simple edition

… say you have a server with standard hardware RAID setup running conventional HDDs. RAID setup For the sake of simplicity you create… out there that discuss RAID minutia.  Make sure you cover the following: RAID type (usually 5 or 1+0) RAID stripe size BBU…) Are there alternatives?  Yes.  Can you have separate partitions for Innodb log volumes, etc.?  Sure.  Is it work doing much more than…

Post: Aligning IO on a hard disk RAID – the Theory

…: In this case the RAID controller is using 32KB stripe unit and that can fit in 2 standard InnoDB pages (16KB in…. In first case when reading or writing a single InnoDB page RAID will only read or write to a single disk because… that page size is no bigger than stripe element; second – logs are actually written in 512 byte units (in Percona Server…

Post: Heikki Tuuri Innodb answers - Part I

… good performance is to set innodb_flush_log_at_trx_commit=2, that is, to flush the log to the disk only once… group commit being broken. Most do not have RAID with BBU. With good RAID with BBU you can get 2000 fsync/sec… so. Sergei Golubchik serialized the MySQL binlog write and the InnoDB log flush with a mutex in 5.1, to implement XA…

Post: Innodb Performance Optimization Basics

… IO Subsystem – directly attached storage with plenty of spindles and RAID with battery backed up cache is a good bet. Typically… for more details, check out detailed guide on tuning innodb buffer pool innodb_log_file_size – This depends on your recovery speed needs… good performance innodb_log_buffer_size=4M 4M is good for most cases unless you’re piping large blobs to Innodb in this…

Post: How to estimate time it takes Innodb to Recover ?

… recovery time even if logs are of reasonable size and wikipedia has 40 minutes or so with innodb_log_file_size=256MB. In other cases I know same log file time may have recovery… takes Innodb to recover. I’d recommend to crash by power cycling if possible because this makes sure all OS/RAID caches…

Post: Fix of InnoDB/XtraDB scalability of rollback segment

… (Dell PowerEdge R900, 16-way Intel Xeon, 32GB of RAM, RAID 10 on 8 disks) to compare mysql-5.1.30…:autoextend innodb_file_per_table=1 innodb_flush_log_at_trx_commit=2 innodb_log_buffer_size=8M innodb_log_files_in_group=2 innodb_log_file_size=128M innodb_thread_concurrency=0 innodb_extra…

Post: Adjusting Innodb for Memory resident workload

… or most of their database (frequently Innodb) fits into memory. If all tables fit in Innodb buffer pool the performance for reads… can be hundreds of megabytes per second even for commodity RAIDs. Sequential Checkpointing Currently fuzzy checkpoint flushes pages which have not… per 30 minutes. It should be possible to just size Innodb logs so they are not cycled through faster than flush cycle…

Post: SSD, XFS, LVM, fsync, write cache, barrier and lost transactions

…. Originally I wanted to publish some nice benchmarks where InnoDB on SSD outperforms RAID 10, but recently I faced issue which can…:autoextend innodb_file_per_table=1 innodb_log_buffer_size=8M innodb_log_files_in_group=2 innodb_log_file_size=256M innodb_thread_concurrency=0 innodb_flush_log_at…