… spikes and produces a very constant and predictable result. vCache vs. FlashCache – the basics Once I’d determined that configuration C… within acceptable bounds. This is, however, only a hypothesis. vCache vs. FlashCache – dirty page threshold Finally, we examine the impact of… way. The following graph shows sysbench OLTP performance for FlashCache vs. vCache with a 10% dirty threshold versus the same metrics…
Post: Benchmarking Percona Server TokuDB vs InnoDB
May 7, 2013 By 32 Comments
… with TokuDB, of course I wanted to compare InnoDB performance vs TokuDB. I have a particular workload I’m interested in…
Post: Testing the Virident FlashMAX II
March 21, 2013 By 1 Comment
… 6.3, and the filesystem used for the test was XFS, mounted with both the noatime,nodiratime options. The card was… II: we see a read throughput of approximately 2580MiB/sec vs. 1450MiB/sec with the previous generation of hardware, an improvement…
Post: Virident vCache vs. FlashCache: Part 1
May 16, 2013 By 3 Comments
(This is part one of a two part series) Over the past few weeks I have been looking at a preview release of Virident’s vCache software, which is a kernel module and set of utilities designed to provide functionality similar to that of FlashCache. In particular, Virident engaged Percona to do a …
Comment: Benchmarking Percona Server TokuDB vs InnoDB
May 7, 2013 By 32 Comments
The point at 685 sec when InnoDB performance drops, is that when data doesn’t fit all in RAM anymore? I would in general expect to see benefits from TokuDB when workload is diskbound. You could artificially reduce InnoDB buffer pool (and corresponding Tokutek setting) to have more SSD vs RAM.
Post: More on MySQL transaction descriptors optimization
April 26, 2013 By Leave a Comment
… a results comparison on a single-node (on the left) vs. two-node (on the right) configuration. No surprises here, the…
Post: Rotating MySQL slow logs safely
April 18, 2013 By 7 Comments
… particularly evident when using the ext3 file system (instead of xfs). Use FLUSH LOGS instead of sending SIGHUP When copytruncate is…
Post: Disconnecting a replication slave is easier with MySQL 5.5+ (RESET SLAVE vs. RESET SLAVE ALL)
April 17, 2013 By 2 Comments
It’s not uncommon to promote a server from slave to master. One of the key things to protect your data integrity is to make sure that the promoted slave is permanently disconnected from its old master. If not, it may get writes from the old master, which can cause all kinds of data corruption. …
Comment: Testing the Micron P320h
April 17, 2013 By 7 Comments
… lot on your kernel. There was a performance regression in XFS in the pre-CentOS 6.4 kernels which made EXT4… into a couple of situations where the latest version of XFS (on CentOS 6.4) crashes the box with a kernel…
Comment: Testing the Micron P320h
April 16, 2013 By 7 Comments
Vadim, indeed the difference between XFS and EXT4 is pretty surprising.. – did you monitor by chance … that EXT4 still cached data even under O_DIRECT, while XFS not at all. This may also probably explain why there… x3 times more I/O ops on EXT4 than on XFS (as it should be fully IO-read-bound here (I…
