… better understand response time ranges, we need to switch to synchronous IO and vary amount of threads. Throughput: And response times: We still see small hiccups in throughput and response times even… 95% response time is 0.69ms. Now let me get back to random write case. I will try synchronous IO varying amount…
Post: Testing Virident FlashMAX 1400
May 4, 2012 By 3 Comments
… still continue to run benchmarks of different SSD cards. This time I show numbers for Virident FlashMAX 1400. This is a… in my benchmarks. To see distribution of response time, the results for random read synchronous IO. There we can see that 1450… sync mode, and only 64 threads are getting close. Response time: In the conclusion, from all tested cards, Virident FlashMAX shows…
Post: Testing Fusion-io ioDrive
May 3, 2012 By 1 Comment
… to read sync IO, with 1-64 threads. Throughput: Response time: For same cases (i.e. 4 threads) we see some interesting patterns. As for response time, actually it does not seem much better than for Intel… – 0.69 ms). To better understand patterns in the read synchronous case, let me unfold results and show them in timeline…
Post: Testing Fusion-io ioDrive2 Duo
May 10, 2012 By 12 Comments
… with separation per thread for random read synchronous IO: There is also excellent response time characteristics. 0.25ms and 0.19ms for…
Post: Announcement of Percona XtraDB Cluster 5.5.20 GA release
April 3, 2012 By 10 Comments
… Cluster is and how does it work, you still have time to register today. I expect XtraDB Cluster and Galera will… Percona XtraDB Cluster: New HA solution. Percona XtraDB Cluster provides: Synchronous replication. Transaction either commited on all nodes or none. Multi…. It uses the Galera library, version 2.x, a generic Synchronous Multi-Master replication plugin for transactional applications. The Galera library…
Comment: How FLUSH TABLES WITH READ LOCK works with Innodb Tables
March 24, 2012 By 20 Comments
… read lock, LVM snapshot should be recoverable 100% of the time. You might have found recovery bug but there have been… having log files and data on the same partition or synchronization of binary log and innodb snapshot. In certain versions FLUSH…
Post: State of the art: Galera - synchronous replication for InnoDB
October 27, 2009 By 13 Comments
First time I heard about Galera on Percona Performance Conference 2009, Seppo Jaakola was presenting “Galera: Multi-Master Synchronous MySQL Replication Clusters… remember synchronous replication was announced for SolidDB on MySQL UC 2007, but later the product was killed by IBM. So long time…
Post: What time 18446744073709550.000 means
May 17, 2009 By 25 Comments
… appeared and I noticed sysbench getting crazy showing query execution time 18446744073709550.000 or like this. Obviously this is unsigned integer… … end_time = clock_gettime(CLOCK_THREAD_CPUTIME_ID, &tp); total_time = end_time – start_time; How we can get query executed in negative time ? It… these generators synchronized. That is if in your server you have 4 CPU, each of them lives on its own time. Usually…
Comment: What time 18446744073709550.000 means
May 18, 2009 By 25 Comments
… bad idea. Or precisely changing time is a bad idea. Use only “time shifting”, so that time is not changed in step (possible negative), but kernel makes the time go slower/faster which will adjust the time without making any gap. Or the best solution – configure NTP daemon to have constantly synchronized time.
Post: How Does Semisynchronous MySQL Replication Work?
January 19, 2012 By 23 Comments
… to understand is that despite the name, semi-synchronous replication is still asynchronous. Semi-synchronous is actually a pretty bad name, because… understand why, let’s look at what truly synchronous replication means. In truly synchronous replication, when you commit a transaction, the commit… apply this transaction to its own data, and during that time, it will be delayed relative to the master. However, other…
