… designed to look solely at vCache performance under some different sets of MySQL configuration parameters. For example, given that the front-end… vCache performance results were obtained with the default vCache configuration, I think vCache can be declared the clear winner. Base MySQL & Benchmark…
Post: Benchmarking Percona Server TokuDB vs InnoDB
May 7, 2013 By 32 Comments
… for InnoDB. So let’s see what results we have. The results are in TPS (more is better)… myisam_repair_threads = 1 myisam_recover socket=/var/lib/mysql/mysql.sock user=root skip-grant-tables TokuDB-related…as I understand from documentation TokuDB comes with good settings out-of-box, but I am ready to…
Post: How to recover table structure from InnoDB dictionary
April 22, 2013 By 4 Comments
…by a byte and thus will spoil the result. That’s why I prefer the structure from… tables into some MySQL server. Use LOAD DATA INFILE constraints_parser generates mysql>LOAD DATA INFILE ‘/…UNSIGNED NOT NULL, `first_name` VARCHAR(45) CHARACTER SET ‘utf8′ COLLATE ‘utf8_general_ci’ NOT NULL, `last…
Comment: MySQL 5.6 - InnoDB Memcached Plugin as a caching layer
March 30, 2013 By 10 Comments
… to http://dev.mysql.com/doc/refman/5.6/en/innodb-memcached-internals.html there are some caching settings to play with… in an InnoDB table.” I’d like to see the results with all settings.
Comment: MySQL and Percona Server in LinkBench benchmark
May 8, 2013 By 18 Comments
… signal but URLs for bugs.mysql.com really aren’t spam. For 5.6 you need to set innodb_lru_scan_depth…_free_block you are not going to have good performance results. Prior to 5.6 foreground threads were responsible for moving… them. http://bugs.mysql.com/bug.php?id=68658 http://bugs.mysql.com/bug.php?id=68588 http://bugs.mysql.com/bug.php…
Comment: MySQL and Percona Server in LinkBench benchmark
May 8, 2013 By 18 Comments
… 5.6 you need to set innodb_lru_scan_depth to a value similar to innodb…free_block you are not going to have good performance results. Prior to 5.6 foreground threads were responsible for …them. http://bugs.mysql.com/bug.php?id=68658 http://bugs.mysql.com/bug.php?id=68588 http://bugs.mysql.com/bug….
Comment: MySQL and Percona Server in LinkBench benchmark
May 11, 2013 By 18 Comments
… doublewrite) 64 around 13000 16 around 12000 4 around 6000 — mysql-5.6-dev (doublewrite) 64 around 16000 16 around 12000 4 around 5500 mysql-5.6-dev (wo doublewrite) 64 around 20000 16 around 14000 4 around 6000 These result numbers might not be so accurate. But should not has so much error (such as 2x times 
) * I added these settings…
Post: Testing the Micron P320h
April 16, 2013 By 7 Comments
… well does it perform with MySQL? Exact results vary, depending upon the usual factors (read/write ratio, working set size, buffer pool size… compare the performance of the P320h on a standard TPCC-MySQL test to the original FusionIO and the Intel i910 with…
Comment: MySQL Partitioning - can save you or kill you
April 30, 2013 By 45 Comments
…Insert’ part. 1. With a standard numeric key id, set as a Primary Key, it will probably be quicker…where probably only recently read records will be cached, resulting in more disc reads. 2. If you need …could easily be quicker on a partitioned table, as Mysql can fire off one thread per partition (at …
Post: PHP Large result sets and summary tables.
July 6, 2007 By 8 Comments
… crazy. Why ? Because by default mysql_query uses mysql_store_result C library call and buffers all result set in the process memory. Not good… which does not apply to MySQL result set. OK there is “easy” fix for this problem, you can use mysql_unbuffered_query instead and… similar behavior. This call users underlying mysql_use_result API call which does not store all result set in memory but instead streams it…
