… my Fosdem 2013 slides for information about discarded designs and benchmarks.) First, we set long_query_time to 0 in order… –session-init-query command-line option, we set the option innodb_fake_changes to prevent INSERTs, UPDATEs, and DELETEs from corrupting… is necessary when running a large stream of queries. Benchmarks We benchmarked with slow query logs captured from our production systems. We…
Comment: Benchmarking Percona Server TokuDB vs InnoDB
May 9, 2013 By 32 Comments
… upsert part did not work in this benchmark, so it was mostly INSERT benchmark What did you mean by that? In your… upsert, no? TokuDB seems to work pretty well (better than InnoDB in the 2nd test) for these upsert queries. So why… you say the upsert part did not work in this benchmark?
Post: Percona Server 5.5.30-30.2 rerelease fixes non-restart issue
April 24, 2013 By Leave a Comment
… for MySQL will now be shipped with the libjemalloc library. Benchmark showing the impact of memory allocators on MySQL performance can… upstream bug #49169. This also provides much better scalability in InnoDB high-concurrent workloads. Bugs fixed #1131189 (Alexey Kopytov). In the… #1041981 (Alexey Bychko). Fixed the upstream bug #68197 that caused InnoDB to misclassify internal read operations as synchronous when they were…
Post: Percona Server for MySQL 5.5.30-30.2 now available
April 10, 2013 By 10 Comments
… for MySQL will now be shipped with the libjemalloc library. Benchmark showing the impact of memory allocators on MySQL performance can… upstream bug #49169. This also provides much better scalability in InnoDB high-concurrent workloads. Bugs fixed #1131189 (Alexey Kopytov). In the… #1041981 (Alexey Bychko). Fixed the upstream bug #68197 that caused InnoDB to misclassify internal read operations as synchronous when they were…
Post: Percona Live MySQL Conference and Expo 2013: It feels like 2007 again
March 21, 2013 By Leave a Comment
… actually traded my other talk, “MySQL 5.6 improvements from InnoDB internals prospective,” with Oracle’s Sunny Bains and his talk, MySQL 5.6: What’s New in InnoDB. Sunny honestly knows more about InnoDB internals than I do. There are going to… forward to another lengthy discussion with Dimitri Kravtchuk on how benchmarks should be run, what the next bottleneck in MySQL will…
Comment: Why MySQL Performance at Low Concurrency is Important
March 31, 2013 By 8 Comments
… conclusions assume a benchmark with fast (100 to 200 usecs) queries: * performance_schema overhead is too high for benchmarks * innodb_checksum_algorithm=CRC32…
Post: Percona XtraDB Cluster 5.5.30-23.7.4 for MySQL now available
April 17, 2013 By 2 Comments
…, this library will be available for download from our repositories. Benchmark showing the impact of memory allocators on MySQL performance can… fixed #1154095 (Alex Yurchenko). If variable innodb_thread_concurrency has been defined to throttle InnoDB access, and work load contained DDL statements…
Comment: MySQL 5.6 - InnoDB Memcached Plugin as a caching layer
April 2, 2013 By 10 Comments
… for two distinctly different modes of operation and use cases. ‘innodb_only’ appears to be handlersocket like, where it’s simply a nosql protocol that accesses existing innodb buffer pool and real time data (good for quick simple… default is ‘innodb_only’ which is something to keep in mind. Mike, what setting did you use for your benchmark? based on…
Comment: MySQL 5.6 - InnoDB Memcached Plugin as a caching layer
March 29, 2013 By 10 Comments
1) What about SQL INSERT? How does it compare to InnoDB Memcache storing? 2) The gain in performance from SQL SELECT to InnoDB Memcache fetching seems very small. Bypassing SQL parsing and opening… times faster than the SQL interface. 3) Can you also benchmark Handlersocket and see how it compares to Innodb memcache plugin?
Comment: Benchmarking Percona Server TokuDB vs InnoDB
May 8, 2013 By 32 Comments
… if TokuDB handle concurrent workload as well as InnoDB 2) Can you also run benchmark on SELECT by PK or some range query by a secondary index? I heard that TokuDB is slower than InnoDB…
