… – the LRU for cache management is classics and there are scalable algorithms to deal with it. I would expect Monty to…_cache_ values indeed can cause significant performance problems. Interesting enough Innodb has a very similar task of managing its own cache of file descriptors (set by innodb_open_files) As the time allows I should test if…
Post: InnoDB thread concurrency
June 5, 2006 By 4 Comments
…_innodb–; ENTER; } retry: if (entered_thread < innodb_thread_concurrency) { entered_threads++; thread->n_tickets_to_enter_innodb = innodb_concurrency_tickets; ENTER; } if (innodb_…might end up sleeping waiting to enter the queue. The scalability problems with multiple CPUs is well known bug 15815 …
Post: kernel_mutex problem cont. Or triple your throughput
December 2, 2011 By 10 Comments
… a complex fate. Once it was one solution for poor InnoDB scalability, then it changed default value, then it even was named…= 0 vs 8 for all range of threads: Threads innodb concurrency=0 innodb concurrency=8 1 11178.34 2 27741.06 4….51 1024 22166.94 183524.16 So innodb_thread_concurrency is even more helpful innodb_sync_spin_loops, and allows to get…
Post: My Innodb Feature wishes
May 4, 2006 By 30 Comments
… times space compression. Insert buffer for delete. For Insert operation Innodb uses nice tecnique called Insert Buffer which speeds up inserts… key and promoting real one to unique. Tablespaces. To call “innodb_file_per_table” option tablespaces is a joke. It is… is well possible Scalability It is actually bug but it is so bad I will list it. Basically Innodb has problems scaling…
Post: InnoDB benchmarks
January 3, 2007 By 15 Comments
…-innodb and next startup options were used: libexec/mysqld –no-defaults –user=root –innodb-buffer-pool-size=1500M –innodb-log-file-size=100M –innodb… or on our page http://www.mysqlperformanceblog.com/files/benchmarks/innodb_scale.html (Note: This benchmark is synthetic micro benchmarks focusing… did not show the scalability problem, but the main goal was the comparison of overall performance of InnoDB before fix (in 5…
Post: Internals of InnoDB mutexes
September 7, 2006 By 4 Comments
… problems. Let’s look on InnoDB mutex (schematic for simplification): spin_loop: for (i=0; i< innodb_spin_locks;i++) if (mutex… on condition_variable in reserved cell; innodb_spin_locks is configurable via system variable innodb_sync_spin_loops (default value is 20… array. We have reports from partners that this patch increase scalability on Solaris/Opteron boxes dramatically – so you can test it…
Post: Great work Innodb Team
November 30, 2009 By 8 Comments
… in the area of our interest which is Performance And Scalability. Innodb Plugin 1.0.4 had a lot of great performance… cache. The Group Commit bug is also finally fixed now. Innodb plugin documentation now seems to be merged with MySQL Documentation… public release and probably 4 years since the work on Innodb plugin features such as compression or Online index creation has…
Post: MySQL 5.0, 5.1 and Innodb Plugin CPU Efficiency
December 3, 2008 By 15 Comments
… 2% slower with 8 cores, thus showing a bit better scalability. MySQL 5.1 plugin (compiled in) is further 3% slower… execution path. Another thing to note – if you’re using Innodb Plugin consider using new Barracuda format, though do this only… testing as this format will not be recognized by older Innodb versions. Note: These are completely CPU bound test conditions, data…
Post: Improved InnoDB rw_lock patch
October 20, 2008 By 3 Comments
… performance , but for some workloads it showed for us reverse scalability. E.g. update_key benchmark from sysbench. There are also…. That is was main reason why we did not include InnoDB smp fixes in our build yet. Fortunately we get fixed… results comparable with Google’s smpfix, so we will include innodb_rw_lock into our next -percona-highperf release
Post: InnoDB compression woes
May 20, 2011 By 14 Comments
InnoDB compression is getting some traction, and I see quite contradictory … 7%. Obviously we have some mutex serialization problem. Analyzing SHOW INNODB STATUS (SEMAPHORES) for workload with compression tables we can see… main benefit), but for in-memory load it shows significant scalability problem.
