Open Source Search Server
Being a sponsor of the MySQL Percona Live Conference & Expo – April 10-12 in Santa Clara, has its perks. We have a booth in the conference hall, our logo is displayed everywhere, and we have the opportunity to connect with the greater MySQL eco-system. So you must be wondering, what’s in it for me?
I’m glad you asked!
Read the rest of this entry »
We are extremely proud to announce Sphinx Search Day 2012! The first U.S. opportunity for the Sphinx community to come together and showcase the performance, scalability, and flexibility that users world-wide have come to love and rely upon.
Seattle MySQL Meetup: “When to adopt a Sphinx (for Search)”
We will be speaking at the Seattle MySQL Meetup on the 5th of March 2012. If you are in the Seattle area and interest in learning about when or or more importantly why one should adopt a Sphinx, this is your opportunity!
Slides for my “How to offload MySQL server with Sphinx” FOSDEM’s talk is available here along with the others. Also we’ve participated in Sphinx user stories (by SkySQL and Sphinx).
Thanks for everyone who organized and attend FOSDEM 2012! It was pleasure to speak there at MySQL & Friends track (special thanks to Frederic Descamps for organizing it)!
If you want us to speak on the conferences or in Sphinx meetup in your location – please feel free to ping me!
See you!
Sincerely yours, Vlad.
If you want to know more about Sphinx performance or looking to offload your heavy loaded production DB from Full-text and non-full-text queries we are welcome you to meet Sphinx at FOSDEM conference in Brussels, Belgium on the first weekend this February!
Vladimir Fedorkov, Director of Professional Services at Sphinx will present talks in MySQL and Friends Devroom and will open Sphinx Performance Top Secrets.
For our European users this is also a good time to arrange onsite performance and tuning – we will not charge you for most travel expenses around these dates. Please contact us for details and mention promotional code FOSDEMSPH for the discount.
Looking forward to meet you in Brussels!
Things break, servers crash, software has bugs, water is wet, so to keep the sky blue and clear we need backups. While backing up a disk index in Sphinx is basically a matter of copying files around, properly backing up RT is a little bit more complicated. (But only a little bit.) Read on to find out how binlogs, periodic flushes, and two newly added 2.0.2-beta features (FLUSH RTINDEX and ATTACH INDEX) can all work together for backup/recovery.
Read the rest of this entry »
Let me step back from sphinx performance and highlight first how Sphinx uses memory.
There are two different ways to store data in Sphinx (we call it indexes): on-disk and Real-Time index. Lets start with good old on-disk indexes.
Basically Sphinx on-disk index is simply a set of files generated by indexer during indexing process. All of them, except .spd and .spp are kept in memory for performance reasons. Read the rest of this entry »
As you might know Sphinx team are focused not only on full-text search improvements like blended characters support we introduced in 2.0.1-beta, we also cares about performance improvements. And one of the main questions on performance – how do you measure single query speed especially in scalable, distributed environment.
Read the rest of this entry »
One of the application of distributed indexes in Sphinx is parallelizing queries across many CPU cores even when running on a single server. There’s a well known trick to have an agent line (or three) pointing to the very same master searchd instance. Only problem with that approach is, every query entails a bunch of one-off TCP connections, extra forks, and other redundant internal work. Which is okay when you’re serving a few heavy queries but might spin over 50% of your CPU in system time doing those works when you’re doing many quick ones.
Now that’s a problem, but starting with 1.10-beta, there is a solution, called dist_threads directive. So if you’re still doing that agent=localhost trick, and suffering from TCP stack pressure and/or seeing way too much system time in top(1) or vmstat(8), do read on, you are eligible. (As a collateral, if you’re still on anything pre-2.0.1, you should seriously consider upgrading, too.)
Read the rest of this entry »
Sphinx Road Show: Announcement/Questionnaire
As a result of positive response we received from our 2010 Sphinx Conference in Moscow, we decided to take the show on road! Thus the Sphinx Road Show scheduled for Europe in late November 2011.
Read the rest of this entry »
