« MySQL Performance: InnoDB Dirty Pages & Log Size Impact | Main | PostgreSQL Performance: VARCHAR and FX Class scheduler impact @dbSTRESS benchmark »

Tuesday, 02 June, 2009

MySQL Performance: Some results comparing InnoDB log size impact @dbSTRESS benchmark

Following my previous post (where I've also told about a significant performance gain by using a bigger InnoDB log size ), I'd like to present you some results obtained on the Read+Write workload and log size equal to 1024MB. I've labeled it on graphs as "FF" (Fast & Furious :-)) as within a such configuration MySQL server may go very fast until it'll meet a "furious flushing" to free some space within a log file... :-)

However, the speed-up is quite important, so if you don't worry too much if time to time your production activity may have a short drop on performance - you have to consider this option as one of the first to test to improve your throughput! :-)

As you may see from the following graphs, most of engines performing with 1024M redo log even better than previously tested MySQL 5.4 with 128M log. But with a bigger redo log MySQL 5.4 is also going more far. And perf version build5 performs even better.

On the same time the test is not long enough to present a real avg TPS when each engine is running on its full power (all results should be better). But you still may recognize the moment when each engine met its "furious flushing" - throughput is shortly dropped on one moment or another...

As usually, X-axis represents the number of concurrent clients (sessions), and Y-axis the obtained TPS level.

Read+Write @8cores

Read+Write @16cores

Any comments are welcome! :-)

Posted by Dimitri at 10:41
Categories: MySQL, Solaris, Tools/ dbSTRESS