…some batch jobs, reports and other non response time critical activities are overloading the system causing …doing work from 32 processes is faster than just having one process. This is true if …Sometimes even single process overloads system too much in this case throttling by having relatively short …
Comment: Testing STEC SSD MACH16 200GB SLC
April 26, 2012 By 7 Comments
… is second case as having slowdown for longer interval of time would make dips very different depending on overlap with measurement…% response time (which sysbench provides) for each of 10 second intervals too. This would show differently if it is just uniform slowdown – 95% should be just couple of times higher than normal or stall in which case 95% should…
Comment: Benchmarking single-row insert performance on Amazon EC2
May 16, 2012 By 11 Comments
…. Basically you fill in 100 million rows, then start a new partition and fill that in. During the time that you are modifying a partition it fits in main memory (and would have… on the first 100M rows). The minimum performance troughs occur just as the partition switches. So performance gets worse and worse…
Post: Testing Intel SSD 520
May 1, 2012 By 7 Comments
… random write asynchronous 8 threads IO, the test is done just after a secure erase operation on the card. The card…, with some strange small periodic drops. To better understand response time ranges, we need to switch to synchronous IO and vary… times: We still see small hiccups in throughput and response times even for small amount of threads. For 8 threads the 95% response time…
Comment: Testing Virident FlashMAX 1400
May 8, 2012 By 3 Comments
Austin, I am not aware that Turbo=1 affects life time by itself. It is just that wit turbo=1 you will be able to perform more writes per second, and if you do, then physical time of life may be shorter, because you will use all 15PB of writes in shorter period of time.
Comment: ext4 vs xfs on SSD
May 3, 2012 By 23 Comments
… and his feedback was that some recent developments in the XFS world have greatly enhanced the metadata…with regards to metadata fragmentation), so maybe it’s time to do another benchmark. What I found with…Dave was referring to above. Disclaimer: I’m just someone who runs their own benchmarks, and am…
Comment: ext4 vs xfs on SSD
April 25, 2012 By 23 Comments
… considered solved for developers and for ops. For developer – push in source code tree – problem solved. For ops – it should be… long as 6 months. Following your logic, it seems I just should go ahead and recommend to use btrfs to everyone…. It still free product and all problems will be fixed in 3-5 years, so everybody will be prepared by that time.
Post: Joining many tables in MySQL - optimizer_search_depth
April 20, 2012 By 6 Comments
… keys just in case) which would take 5 seconds even though in the read less than 1000 rows and doing it completely in memory… this change I could bring optimization, and full query execution time to less than 50ms. Low values, such as 3,4… this further I found the following explanation from Timour Katchaounov in MySQL mailing list archives I have some recollection that there…
Comment: Looking for RAID Controller without Battery Learning problems ?
March 1, 2012 By 7 Comments
… to bad data write-backs are very hard to zero in and fix. I had this 3ware BBU card which was…-ups focussing on cards/hardware too, real help just in time. — Help stop Net censorship in India Censorship of Google, Yahoo, Facebook and Twitter…
Post: Join Optimizations in MySQL 5.6 and MariaDB 5.5
April 4, 2012 By 2 Comments
… MRR uses appropriately. In my tests I noticed that with just the join_buffer_size increased to 6M, the query time was ~300s… Join and Key-ordered Scan disabled, and the only difference in query time is 48.78s vs 48.91s, so I don… did not make much of a difference in the query times. Conclusion BKA improves the query time by a huge margin for IO…
