…_join: No Tmp_table: No Tmp_table_on_disk: No # Filesort: No Filesort_on_disk: No Merge_passes: 0 # No InnoDB statistics… queries are being executed. This is where Jeremy’s SHOW PROFILE patch – which is included in all Community tree based Percona… digging deeper. On the other hand, this way of manual profiling you can’t really see real time stats, for example…
Post: Ultimate MySQL variable and status reference list
….commanual core_fileblogpercona.commanual Created_tmp_disk_tablesblogpercona.commanual Created_tmp_filesblogpercona.commanual ….commanual print_defaultsblogpercona.commanual profilingblogpercona.commanual profiling_history_sizeblogpercona.commanual protocol_versionblogpercona.commanual …
Post: Identifying the load with the help of pt-query-digest and Percona Server
Overview Profiling, analyzing and then fixing queries is likely the most oft-…_join: No Tmp_table: No Tmp_table_on_disk: No # Filesort: No Filesort_on_disk: No Merge_passes: 0 # InnoDB_IO_r… nearly 40 pages from disk. Let’s analyze next part of the output produced by pt-query-digest. # Profile # Rank Query ID…
Post: Improved InnoDB fast index creation
…Records: 4194304 Duplicates: 0 Warnings: 0 mysql> SHOW PROFILE; +——————————+————+ | Status | Duration | +——————————+————+ . . . | copy to tmp table | 184.694432 | . . …. it does not have to do random disk seeks to fetch secondary index pages to…
Post: Write contentions on the query cache
… I used commands you’re probably familiar with: EXPLAIN, SHOW PROFILE, SHOW STATUS LIKE ‘Handler%’. EXPLAIN and Handler counters only confirmed… same, I got around 200 lines of output from SHOW PROFILE instead of the 15 lines above. Particularly interesting, a sequence… suspect either some change in data access pattern (reads on disk vs reads in memory, execution plan instability) or contention somewhere…
Post: To find the bottleneck, stop guessing and start measuring
… at 25% CPU usage and was writing some files to disk, but not waiting on I/O. What’s going on… improve your performance is build profiling into your application, or run the application under a profiler (Google for “profiling
Post: Why you should ignore MySQL's key cache hit ratio
… slow and is a problem for my application. I have profiled it with SHOW STATUS and I know it causes a… “mostly factual” above, because Key_reads actually aren’t physical disk reads at all. If the requested block of data isn… randomly positioned, which is a worst-case scenario for spinning disks. This is also very hard to prove, but seems reasonable…
Post: Percona-XtraDB-9.1: released and new coming features
… for each query: # Bytes_sent: 4973 Tmp_tables: 1 Tmp_disk_tables: 1 Tmp_table_sizes: 7808 That is you can… used, was it disk table or in-memory, and how big was temporary table. Also you can profile each individual query from… replication Show internal InnoDB data dictionary Show InnoDB locking/io profiling in slow.log I hope you enjoy our work!
Post: Using LoadAvg for Performance Optimization
…” state or in “uninterruptable sleep” state which typically corresponds to disk IO. You can also map LoadAvg to VMSTAT output – it… you can’t use another drive instead), and the fact disks can optimize multiple outstanding requests a bit better compared to… always available unlike other metrics. It is best to have profiling information so you can see as response time for your…

