Now that flash storage is becoming more popular, IO alignment question keeps popping up more often than it used to when all we had were rotating hard disk drives. I think the reason is very simple – when systems only had one bearing hard disk drive (HDD) as in RAID1 or one disk drive at [...]
InnoDB Flushing: a lot of memory and slow disk
March 31, 2011 By 57 Comments
You may have seen in the last couple of weekly news posts that Baron mentioned we are working on a new adaptive flushing algorithm in InnoDB. In fact, we already have three such algorithms in Percona Server (reflex, estimate, keep_average). Why do we need one more? Okay, first let me start by showing the current [...]
MySQL on Amazon RDS part 2: Determining Peak Throughput
March 28, 2011 By 4 Comments
This is a continuation of my series of benchmark posts comparing Amazon RDS to a server running on Amazon EC2. Upcoming posts (probably 6 or 8 in total) will extend the scope of the benchmark to include data on our Dell r900 with traditional hard drives in RAID10, and a server in the Joyent cloud. [...]
Virtualization and IO Modes = Extra Complexity
March 21, 2011 By 12 Comments
It has taken a years to get a proper integration between operating system kernel, device driver and hardware to get behavior with caches and IO modes correctly. I remember us having a lot of troubles with fsync() not flushing hard drive write cache and so potential hard drives can be lost on power failure. Happily [...]
Death match! EBS versus SSD price, performance, and QoS
February 21, 2011 By 55 Comments
Is it a good idea to deploy your database into the cloud? It depends. I have seen it work well many times, and cause trouble at other times. In this blog post I want to examine cloud-based I/O. I/O matters a lot when a) the database’s working set is bigger than the server’s memory, or [...]
White Paper: “Scaling MySQL Deployments Efficiently” from Percona and Virident
February 7, 2011 By 2 Comments
Percona was working closely with Virident on evaluating tachIOn as solution for MySQL, and as result you can find whitepaper “Scaling MySQL Deployments Efficiently Using Virident tachIOn Drives”, available from Virident website. It was done as part of our consulting practice, but all results and numbers are certified by Percona. I personally really enjoyed performance [...]
Effect from innodb log block size 4096 bytes
January 3, 2011 By 19 Comments
In my post MySQL 5.5.8 and Percona Server: being adaptive I mentioned that I used innodb-log-block-size=4096 in Percona Server to get better throughput, but later Dimitri in his article MySQL Performance: Analyzing Percona’s TPCC-like Workload on MySQL 5.5 sounded doubt that it really makes sense. Here us quote from his article: “Question: what is a [...]
Write performance on Virident tachIOn card
December 13, 2010 By 10 Comments
This is crosspost from http://www.ssdperformanceblog.com/. Disclaimer: The benchmarks were done as part of our consulting practice, but this post is totally independent and fully reflects our opinion. One of the biggest problems with solid state drives is that write performance may drop significantly with decreasing free space. I wrote about this before (http://www.ssdperformanceblog.com/2010/07/free-space-and-write-performance/), using a [...]
The perils of uniform hardware and RAID auto-learn cycles
November 16, 2010 By 16 Comments
Last night a customer had an emergency in selected machines on a large cluster of quite uniform database servers. Some of the servers were slowing down in a very puzzling way over a short time span (a couple of hours). Queries were taking multiple seconds to execute instead of being practically instantaneous. But nothing seemed [...]
Cache Miss Storm
September 10, 2010 By 30 Comments
I worked on the problem recently which showed itself as rather low MySQL load (probably 5% CPU usage and close to zero IO) would spike to have hundreds instances of threads running at the same time, causing intense utilization spike and server very unresponsive for anywhere from half a minute to ten minutes until everything [...]
