May 21, 2012

Post: ext4 vs xfs on SSD

…thread: 87 MiB/sec ext4 4 threads: 74 MiB/sec xfs 4 threads: 97 MiB/sec Dropping performance in case…to another question I was asked, namely: “If MySQL 5.5 uses async IO, is innodb_write_io_threads …-num=1 –file-extra-flags=direct –file-fsync-freq=0 –file-io-mode=sync –file-block-size=16384 –…

Post: Too many connections? No problem!

… that ever happen to you in production? [percona@sandbox msb_5_0_87]$ ./use ERROR 1040 (00000): Too many connections Just happened to… msb_5_0_87]$ ./use Welcome to the MySQL monitor. Commands end with ; or \g. Your MySQL connection id is 8 Server version: 5.0.87-percona-highperf-log MySQL Percona High Performance Edition, Revision 61 (GPL) Type ‘help;’ or…

Comment: Disaster: LVM Performance in Snapshot Mode

….1 0.1 0.1 0.7 0.0 1693.7 | 1357.2 0.1 73.6 1480.5 87.1 | 336.5 0.1 0.1 2.1 0.0 1696.2 | 1355.7 0… indirect address blocks are cached and ext3 resumes the “raw” performance. But once the snapshot is created it plummets again. It…

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

… bound. That said, benchmark was running on a Percona Server 5.0.92-87 with the following my.cnf configuration: [mysqld] datadir=/data… single-thread performance by 5-10%. Sequential write results were a bit more interesting. With WT (write-through) cache enabled, performance was really…_prg {925} dm-0 462.1 34.1 7.7 0% 3.8 8.2 12.1 87.0 0.5 0% 0.0 0.7 93% 0 While number of…

Post: MySQL 6.0 vs 5.1 in TPC-H queries

… but in batches reads. So let us see how perform 5.1 and 6.0 in cold mode (I dropped OS caches by… KEY (li_shp_dt_idx) (full table scan will be performed in this case) then we got: 1 min 39.14….27 4.87 247.70 0.27 0.52 0.52 27.22 dm-0 0.00 0.00 542.60 0.61 130724.54 4.87 65362.27 2.43 240.66 0

Post: Using flow control functions for performance monitoring queries

0))/count(*) poor, sum(if(wtime>5,1,0))/count(*) fatal from performance_log_080523; +———+——————+——–+——–+——–+ | cnt | avw | soso | poor | fatal | +———+——————+——–+——–+——–+ | 4412134 | 0.18669403011609 | 0.1280 | 0.0396 | 0

Post: Which adaptive should we use?

performance of adaptive_flushing with doublewrite… So, instead of that, estimate is adjusted more. case1: “innodb_doublewrite = false” [0

Post: Improved InnoDB fast index creation

5.1.56 and 5.50.000008 | | freeing items | 0.000021 | | cleaning up | 0.000003 | +——————————+———–+ 18 rows in set (0.00 sec) Now let’s see how performance87 sec) Records: 4194304 Duplicates: 0 Warnings: 0 mysql> SHOW PROFILE; +——————————+————+ |…

Post: Multi Column indexes vs Index Merge

…. If where clause from first column selects 5% of the rows and applying where clause … affected (6 min 47.87 sec) Rows matched: 11010048 Changed: 10900996 Warnings: 0 Lets see what happens …where clause. Index merge does helps performance but it is far from performance of combined index in this…

Post: InnoDB vs MyISAM vs Falcon benchmarks - part 1

… NULL default ”, `country_id` smallint(5) unsigned NOT NULL default ‘0‘, PRIMARY KEY (`id`), UNIQUE KEY `email…that is why we see bad performance. We hope the performance of LIMIT queries will …5 The previous query but with LIMIT. Again the LIMIT is bad for Falcon. InnoDB is better than MyISAM by 87