… for a feedback, so I do my part. Benchmark date: Oct-2012 Benchmark goal: Test how MySQL 5.6.7 performs Hardware… Version: 5.6.7-RC Benchmark specification Benchmark name: tpcc-mysql Scale factor: 2500W (~250GB of data) Benchmark length: 4000 sec but the… innodb_write_io_threads = 16 innodb_io_capacity = 20000 innodb_io_capacity_max = 40000 #not innodb options (fixed) port = 3306 back_log…
Post: Tokyo Tyrant -The Extras Part III : Write Bottleneck
November 12, 2009 By 3 Comments
… Can have only a single writer thread, bottlenecking performance When writing an application using Tokyo Cabinet only one connection can be… from multiple applications but it still single threads them when writing out to disk.  If you run several threads… distribute the data accross multiple TC database files in the back end. This should work, I just need to test…
Post: Testing the Group Commit Fix
July 13, 2011 By 13 Comments
…, automatically switching from write-back to write-through cache mode. We benchmarked the systems with sysbench multi-table and oltp read-write workload. All scripts… and sync_binlog=1 options are set and write-back cache is not enabled. Write-back cache is must-have for an environment demanding…
Post: MySQL-Memcached or NOSQL Tokyo Tyrant - part 1
October 15, 2009 By 16 Comments
… guy who blogs on bigdbahead.com and is writing this on the mysqlperformanceblog is saying you may…memcached environment. Part 3 will focus on these same benchmarks in Tokyo tyrant. All to often people force…stats for the game, be updated and stuffed back into the database. You would be surprised how…
Post: MySQL 5.5.8 - in search of stability
January 3, 2011 By 11 Comments
… for each run, I will show different graphs: benchmark throughput – This is New Order Transactions per 10 seconds…_group = 2 innodb_read_io_threads = 16 innodb_write_io_threads = 16 innodb_purge_threads=1 innodb_…=0. Okay, we are back to a stable level. Checkpoint age is also back to 3000MB, and dirty…
Post: Heikki Tuuri answers to Innodb questions, Part II
November 4, 2007 By 13 Comments
… Innodb specific and it well can affect your workload. So benchmark to be sure. In Innodb besides scalability changes in later… sequential writes, like log flushes. A question is why to use a flash memory at all, when a battery-backed disk controller write-back cache does the same thing. PZ: First Indeed writes are slower with Flash disks…
Comment: Disaster: LVM Performance in Snapshot Mode
February 9, 2009 By 55 Comments
… of the filesystem can be quite important. I run “randomio” benchmark on ext3 filesystem and compared it with xfs. The difference…. Write percentage controls the ratio of reads/writes done by each thread. My setup was 6 SAS 10K drives with 512MB write-back cache… should be a very fast write under normal circumstances (write-back cache) turns into a read and a write while holding the exclusive rwlock…
Post: Tokyo Tyrant - The Extras Part I : Is it Durable?
November 10, 2009 By 5 Comments
… write operations ( used for maintenance ). What is missing here is a scheduled call to msync. I looked and traced back… impact on my gaming benchmark from when this is running to when it is not. You can write this and cron the…. Now while I did not see a drop in my benchmark, heavy write operations will see a drop in performance… for instance…
Post: Testing Intel SSD 520
May 1, 2012 By 8 Comments
Following my previous benchmarks of SATA SSD cards I got Intel SSD 520 240GB …. The benchmark methodology I described in previous posts, so let me jump directly to results. First case is random write asynchronous 8…% response time is 0.69ms. Now let me get back to random write case. I will try synchronous IO varying amount of…
Post: dbqp and Xtrabackup testing
November 16, 2011 By Leave a Comment
… fancy, basically, we take advantage of Python’s unittest and write classes that use their code. The biggest bit dbqp does… we create a slave from the backup, replicating from the backed up server. After the initial setup, we ensure replication is… they do represent an interesting step forward. We can now write actual, honest-to-goodness Python code to test the server…
