MariaDB 11.0 – new optimizer, new major version series

With MariaDB 10.0.0 having been released over ten years ago (12 Nov 2012), you may ask yourself when there will be MariaDB 11.0.0. If so, I can answer you: Today.

You can now download MariaDB Server 11.0 Alpha preview from our dedicated download page and check out the release notes.

Time has passed …

Of course, we have a better reason for going with a new first number in a release other than ten years having passed. Significant new features. Significant incompatibilities with earlier versions.

This one trick can make MariaDB 30x faster!

Yes, it is a bit of a click-bait title, but in this case running one SQL command did improve a community user’s performance by that much. It could help you too.

The story

A community user posted in a couple of places that when migrating a large WordPress installation to MariaDB that they were seeing a certain query performing terribly. The query was taking 1.5 seconds to execute and it was clear from the explain plan that the optimizer was not making an ideal decision about the join order.

The query was generated by WordPress so it would not be easy to force an index, or rewrite the query.

ARM improvements in 2020

2020 has seen quite a few developments with the ARM architecture. For MariaDB things are no different. First we have expanded our testing infrastructure to cover more Linux distributions (Debian, Ubuntu, Fedora, CentOS, RedHat) on ARM and we are now building packages for all of them. The next MariaDB release will include additional binary tarballs for ARM distributions, in addition to the already existing RPM and DEB packages.

All this could not be accomplished without the help of Huawei, who have donated several ARM builders to our effort. We strongly believe that only by testing on as many different platforms as possible, with as many different compilers as possible we can guarantee MariaDB’s performance and stability.

Improved MariaDB performance using Shannon Systems PCIe and atomic writes

We recently had a chance to test how the Shannon Direct-IO PCIe Flash G3i devices improves the performance of MariaDB. Anybody who cares about I/O performance has noticed that PCIe drives have become readily available in recent years and that they are significantly faster than normal SSD drives connected to the traditional SATA port (not to mention hard disk drives). In addition to being great hardware, the Shannon drives offer an extra boost by having a device driver that supports atomic writes. This means the device guarantees that a write made to it reaches the drive, and thus the MariaDB server does not have to run extra checks like it does on normal hardware.

MyISAM and KPTI – Performance Implications From The Meltdown Fix

Recently we had a report from a user who had seen a stunning 90% performance regression after upgrading his server to a Linux kernel with KPTI (kernel page-table isolation – a remedy for the Meltdown vulnerability). (more…)

MariaDB 10.1 and MySQL 5.7 performance on commodity hardware

When you have read my previous blog post about MariaDB 10.1 GA performance, you have probably wondered why I didn’t include any numbers for MySQL 5.7. There are two reasons: first MySQL wasn’t GA at that time and secondly MySQL is not running stable on Power8.

Today I will come up with a comparison benchmark. I have chosen some more down-to-earth hardware for that because that is what the majority of our users will be running. Specifically it’s a SP-64 cloud machine from OVH. It has a 4-core Intel CPU and 64G of RAM. Disks aren’t fancy, but the benchmark is again a simplified read-only OLTP workload that runs from memory. …

MariaDB 10.1 can do 1 million queries per second

MariaDB 10.1 not only contains tons of new features, it has also been polished to deliver top performance. The biggest improvement has been achieved for scalability on massively multithreaded hardware.
(more…)

A few interesting findings on MariaDB and MySQL scalability, multi-table OLTP RO

It’s been almost a year since I benchmarked MariaDB and MySQL on our good old 4 CPU / 32 Cores / 64 Threads Sandy Bridge server. There seem to be a few interesting things happened since that time.

  • MySQL 5.6.23 peak throughput dropped by ~8% compared to 5.6.14. Looks like this regression appeared in MySQL 5.6.21.
  • 10.0.18 (git snapshot) peak threads increased by ~20% compared to 10.0.9 and reached parity with 5.6.23 (not with 5.6.20 though).
  • 10.1.4 (git snapshot) and 5.7.5 are the champions (though 10.1.4 was usually 1-5% faster). Both have similar peaks @ 64 threads.