…you can get each index query down to one disk seek.) I claim that this…of the advantages of the newer version of iiBench (the python version that Mark wrote http://bazaar.launchpad.net/~mdcallag/mysql…

This benchmark doesn’t test the IO performance of EBS though as you‘re not flushing to disks on each commit. What numbers do you get when you set innodb_flush_log_at_trx_commit to 1?

Aaron, No particular reasons, it doesn’t matter if you have 4 1G or 2 2GB log files, as they are all concatenated together by InnoDB and written to in a circular fashion.

Mark, Probably what you are referring to is provided by the configuration option “innodb_ibuf_accel_rate” available in Percona (as mentioned by Justin). Increasing/decreasing the value of innodb_ibuf_accel_rate, you will increase/decrease the insert buffer activity.

… requirements are not that stringent and I can afford to loose 1 second worth of data, hence I did not test with innodb_flush_log_at_trx_commit=1. I would also not recommend running…

Interesting results, and well presented. Would you mind sharing the command line you used for your iiBench clients? Also, did you run a test with innodb_flush_log_at_trx_commit = 1?

… purchases_index should be interesting. You are seeing periodic drops in performance which might be the result of the insert buffer filling up… on insertion rate when increased insert buffer flushing was enabled (using the FB patch, not XtraDB but difference should be similar…