In and around vacuum and PostgreSQL at low level

We are happy to schedule our next meetup on Thursday, September 26th. Adjust will host it and we are going to have two wonderful speakers this time, Rafia Sabih and Dmitrii Dolgov.

“In and around Vacuum!” By Rafia Sabih

Even after numerous blog posts and talks on vacuum utility of PostgreSQL, it still manages to make people wonder, this talk is yet another attempt on demystifying its different aspects. We will start with the basics as to why vacuum is required, when is autovacuum not enough and how its different parameters can optimize the performance of database. Next, we will also uncover the details of things around it like visibility maps, free space maps etc. Finally, we will delve ourselves into the deeper details of vacuum and autovacuum by going through the internals of these utilities. So, the next time something about vacuum makes you wonder you will be confident as to which routines to attack or get ready to just play around the many wonderful aspects of this utility.

Rafia Sabih is currently working in Zalando SE as a part of the team devoted to run and maintain the highly available PostgreSQL clusters on Kubernetes. One of the many responsibilities of this role is the development of postgres-operator, which is an open-sourced solution for maintaining PostgreSQL clusters. Prior to that she was part of the development team for an upcoming storage format for PostgreSQL namely zheap that supports in-place updates. She was also actively involved in the development of intra-query parallelism in PostgreSQL.

“PostgreSQL at low level: stay curious!” by Dmitrii Dolgov

Have you ever encountered a transient performance issue, that was hard to investigate only from the database point of view? On top of how many layers of abstraction your database is working? What is the difference between running your database on a bare metal, VM or inside a container? PostgreSQL does not work in the vacuum, it heavily relies on functionality provided by an underlying platform. And sometimes to answer these questions above one needs to step back and look at a problem not only from a database point of view. In this talk we will discuss how to achieve that, how to tame such tools as strace, perf or eBPF to troubleshoot intricate issues (e.g. lock preemption problem on VM, shared memory segments limitations or memory reclaim process within a container) and stay curious.

Dmitrii Dolgov is a PostgreSQL Contributor and is currently working as a Software Engineer at Zalando SE.

Doors will open at 18:30 with the talks starting at 19:00.

If you want to propose a talk for one of the next meetups: https://forms.gle/RDLyuD5f2AJnZEW4A

If you want to host a PostgreSQL Meetup in Berlin: https://forms.gle/K4n6gM1uo8sAenuw8