Dathan says that 128k Stripe Size is ideal for INNODB:

128K - this is really good for INNODB, you’ll see a huge boost in responsiveness by making your Stripe Size 128K. I had a 64K stripe size, and I was blown away by the improvement of 128K

I’ve only benchmarked 64k and 1M. Google is using a 1M stripe size. 1M was about 5x slower for our workload. I’m going to have to benchmark 128k.

Interesting that he recommends RAID 10. We’re using RAID 0 and just using a Redundant Array of Inexpensive Servers. If one fails we just promote another one as master.

The other day I blogged about the fact that I thought partitioning was broken in 5.1.18.

There does in fact appear a bug that was introduced somewhere between 5.1.17 and 5.1.18 which is causing MySQL to dump core.

I tried recompiling 5.1.18 from source and the problem remained. Installing a 5.1.17 source build fixed the problem and we’ve been online for almost 72 hours without a core dump. By way of comparison 5.1.18 wouldn’t stan up for more than a few hours.

I’m not sure I have a ton of time to debug the issue but I wanted to get the information out into the public.

We’ve been playing with partitioning in MySQL 5.1.18 from the MySQL AB community builds and noticed that the daemon will dump core every 5 minutes or so when under load.

Recompiling from source fixes the problem. Anyone else notice stability problems?

Apparently, there’s been an outstanding bug for nearly two years for MySQL to add support for millisecond storage in DATETIME and TIME data types.

A microseconds part is allowable in temporal values in some contexts, such as in literal values, and in the arguments to or return values from some temporal functions. Microseconds are specified as a trailing .uuuuuu part in the value. Example:

…

However, microseconds cannot be stored into a column of any temporal data type. Any microseconds part is discarded.

What’s this about? I have to admit that I’ve known about this problem for about the same amount of time (probably three years).

At Rojo we used BIGINTs as timestamps which provided millisecond …

This thought has been floating around my head for quite some time now and I finally bit the bullet and released it from the draft state it had been sitting in for too long: there are quite many similarities between Open Source Software (OSS) projects and most of today's popular Web 2.0 sites, but there is also one odd difference that I wonder about.

For both worlds, the concept of collaboration, participation and giving more power to their users is a key component. OSS projects need contributors for patches and bug reports, but also for feedback, translations, artwork, advocacy in order to be popular and healthy. The project's developers need to be open for suggestions, listening to their user base on where the project should be heading. They also usually strive for open standards …

This is a hack I’ve heard about a couple times now:

Paul wrote a script that reads from the logfile the queries that are going to be executed moments later. He parses the queries and constructs new select queries that populate the cache with the data that speeds up the upcoming writes. He claims, if I remember correctly, a three to four times speed-increase.

Here’s the problem in a nutshell. The master can write transactions in parallel but slaves can only write them in series. [1]

This means you have a lot of optimizations on the master (TCQ and NCQ being examples) that aren’t possible on the slave.

What this patch would do is precache the data so it’s already available in memory. Since you’re pre-reading the binary log you can run SELECTs in parallel on the SLAVEs so that the cache is …

Eric Bergen from Proven Scaling (which I had the pleasure to meet in person during the MySQL Conference & Expo in Santa Clara last month) was kind enough to send me a patch for the mylmbackup tool, which justifies a new release:

Attached is a patch file for mylvmbackup that adds the ability to use
lvm version 2 and perform innodb recovery on the snapshot prior to
creating a tar ball. The option is named --innodb-recover.

I've also fixed a bug with default value handling for command line
options. In version 0.4 if a config file was specified default values
in the script were all changed to blank. This means that the config
file had to supply values for every variable instead of just the
values that need to be changed from default.

This …

We’ve been doing a lot of performance analysis of MySQL and SATA disks over the last few days and I wanted to get some thoughts out in the open to see what you guys thought.

Now that Debian Etch is out we’re seriously looking at making the jump to a full 64bit OS with 8G of memory on each of our boxes.

This also involves benchmarking SATA and potentially migrating away from MyISAM which, while very trusty, is seriously showing its age for us.

First off is raw IO tuning.

XFS benchmarks show about a 20% performance boost from bonnie++ over ext3. This is pretty obvious. Tuning readahead with ‘blockdev’ didn’t seem to help performance much. SATA seems pretty tuned when compared to hdparm and IDE drives.

After fully tuning it seems we can get about 90MBps out or our disks. Not to shabby. The Linux md driver on RAID 0 didn’t seem to boost IO performance much (and I’m pretty disappointed). Even …

Baron Schwartz was nice enough to make recordings of about a dozen talks at the recent MySQL conference. The original uploaded files were in ogg format and wouldn’t work on an ipod and weren’t very portable.

With his help, I uploaded the original MP3 files and made a podcast which contains all the links to the sessions and should work fine with iTunes and an ipod.

Here’s the link to the podcast. Just add it to iTunes or your favorite podcasting software and off you go.

In two weeks from now, the MySQL Conference & Expo 2007 will take place in Santa Clara, California. Our team has been very busy with working with the conference management team from O'Reilly to prepare for this event, especially Jay who is in charge of organizing and arranging the more than 110 sessions that will be held in several parallel tracks. The conference program looks very exciting, I am impressed by the wide range of topics and quality of speakers that we have lined up.

In addition to the presentations and tutorials, there will also be an Expo, where partner companies will exhibit their products …