Category Archives: Performance
There was a time when PostgreSQL’s own developers were far more open about the real cost of their MVCC design. Back in the 8.1 era, the documentation spelled out the resource drain, the vacuum overhead, and the “cold comfort” of wraparound risk in plain language. I first read that line in 2003, and it stuck with me for more than twenty years. I could not imagine any serious operations team wanting a database that required a separate background process to clean up transactions long after they had completed. PostgreSQL has absolutely improved vacuuming — autovacuum, visibility maps, HOT updates, parallel vacuum, better defaults, better alerts.
…
Continue reading “The Real Operational Cost of Vacuuming in PostgreSQL”
Right after the recent MariaDB Meetup in London, I had the pleasure of sitting down with Steve Shaw – founder and CEO of HammerDB, former Principal Engineer at Intel, and board member of the MariaDB Foundation. Steve delivered the keynote talk at the event and has a unique perspective on performance, open source, and the intersection between commercial and community-driven database development.
This blog post captures our conversation – a dialogue between two people passionate about open source and database performance. We talk about Steve’s transition from Intel to HammerDB, his relationship with MariaDB Corporation, the nuances of performance testing, and what lies ahead for the HammerDB and MariaDB communities.
…
Continue reading “Open Source Performance, Benchmarks and MariaDB: A Conversation with Steve Shaw”
As you have probably seen in earlier posts, the preview version of MariaDB Vector is out and ready for you to play with. We have had input from several different places during the development of this feature. This, of course, includes hardware manufacturers such as Intel.
In the background, Intel have been prototyping using AVX512 instructions for dot product and bloom filter. Both of these are functions are part of vector searches. If you haven’t heard of these terms, let me try and break them down.
AVX-512 – 512-bit extensions to the Intel Advanced Vector Extension
The AVX512 instructions themselves are CPU specific instructions that are designed to run calculations on large vectors of numbers simultaneously.
…
Continue reading “Intel improving the performance of MariaDB Vector”
Is performance important for you, along with the latest features and long-term support? Go with MariaDB 11.4. But don’t take our word for it. We asked well known benchmarking expert Mark Callaghan to check out a number of MariaDB and MySQL releases, hit them hard with a tool of his choice, and share his findings.
MariaDB’s performance is stable over the years
The outcome: On the low concurrency load (high concurrency results are being prepared), MariaDB maintained stable performance over the last 10 years and 14 releases, while MySQL performance dropped almost by a third.
…
Continue reading “How MariaDB and MySQL performance changed over releases”
With Intel QuickAssist Technology, you can see a 5x performance in your MariaBackup compression, and lower CPU usage as well. Today I’m going to show you how.
What is Intel QuickAssist?
Nearly a decade ago, Intel released a technology called QuickAssist, which started out as a PCI-e card and then became integrated in many Xeon processes starting with the Skylake generation. QuickAssist Technology (often called QAT) is a special unit that the CPU can offload compression and encryption tasks onto.
I was lucky enough to have early access to this technology back when it was new.
…
Continue reading “Accelerating MariaBackup with Intel QuickAssist”
“The only workload that matters is my production workload” (for all values of “my”). So you can manage this responsibility, SCARY is a software tool which aims to take the uncertainty out of change; software, configuration and hardware changes. This is very early in development, but projects have to start somewhere.
SCARY takes a read view of the production database query execution, and does the equivalent query on a copy of the production database, that has differences. The query speed, query plan, data result (eventually) will be recorded along with what went on in production.
…
Let’s say you are a Cloud Service Provider, with many customers – each having many MariaDB Server users and databases. What if several such customers could share a single instance of MariaDB Server? That’s what we call the catalog feature, a feature that – if implemented – could potentially save lots of resources (and thus costs!) in a number of high-end use cases.
How the idea was born
At CloudFest 2023 near Frankfurt in March, we had in-depth meetings with a number of heavy MariaDB Server users – ones that one best would describe as Cloud Service Providers (CSPs).
…
Continue reading “Multi-tenancy through catalogs in MariaDB Server”
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.
…
Continue reading “MariaDB 11.0 – new optimizer, new major version series”