Next month, I'll be hosting a discussion of a talk by Andy Pavlo, given for his Intro to Database Systems course at CMU. The title of the talk is "Memory & Disk I/O Management and the video link is https://www.youtube.com/watch?v=aoewwZwVmv4. As usual, we have will have three sessions, and you can sign up to participate in one of them using this form.
This will be our first time discussing a talk that is not specifically about PostgreSQL. However, the material is pretty directly applicable to PostgreSQL, and we can discuss similarities and differences between what is presented here and how PostgreSQL does it on the calls. My expectation is that Andy probably won't be able to join us, although I have let him know that he is more than welcome, but I hope to be joined by at least one other PostgreSQL committer on each of the calls.
Much of the talk is about how the buffer cache -- which we called shared_buffers -- is managed. I believe that should be important to us, as PostgreSQL hackers or aspiring hackers, for two reasons. First, it's pretty common to need to write code that interacts with the PostgreSQL buffer cache, and knowing how it works makes that easier. Second, PostgreSQL has some known weak points in this area, so there is probably some way we could improve things, if only we could figure out what to do exactly.
In any case, I hope you find the talk interesting if you choose to watch it, and please do sign up for one of the discussion sections if you're interested.
No comments:
Post a Comment