Postgres is half as fast in Linux 7.0
The Backend Engineering Show with Hussein Nasser

Postgres is half as fast in Linux 7.0

B2Upper-intermediateJune 17, 202634 min

An aws engineer discovered a 50% regression in postgres throughput while testing the new Linux 7.0 kernel. The cause turns out to be massive TLB and page faults exacerbated by Postgres process-based design. In this backend engineering show episode I dive deep into how this was discovered, the root cause and the possible fixes and workarounds. Intermediate and Advanced Backend Engineering Course Bundlehttps://courses.husseinnasser.com/bundleMy Book, Root Cause: Stories and Lessons from Two Decades of Backend Engineering Bugs https://amzn.to/4cKfZhe 0:00 Intro2:30 The Discovery6:30 Spinlocks9:25 Preemption 13:00 Root Cause17:00 How Postgres Processes exacerbated the problem 22:30 Is the fix easy?25:50...

Play episode

Opens the player: the full transcript, every word clickable, with translation and flashcards.

Try it: tap any word

Real sentences from the start of this episode. Every word is marked with its level.

Sentence 1 of 12 · 0:00

% .

and that is mainly due to a change in some default configurations that the Linux

Tap a word to see its meaning in your language.

Do you know these words?

8 harder words from this episode. Tap one to see what it means, then mark it.

Mark a few words and we'll tell you how this episode fits your level.

Is this episode right for you?

B2

B2 · Upper-intermediate

Comfortable if you already follow TV news

A1 34%A2 32%B1 15%B2 13%C1 6%
  • 81% of the words are B1 or easier.
  • 130 words a minute: a natural pace.
  • 106 harder words (B2 and up) in the whole episode.

Transcript

The opening of the episode. The whole transcript is in the player.

0:00

Amazon engineer discovered that Postgres SQL is 50% slower in the new to be released Linux kernel 7.0 and that is mainly due to a change in some default configurations that the Linux kernel decided to change these changes specifically target something called preemption in kernel code. Now of course the Postgres maintainers were all over this, this

0:32

happened two months ago and they were all over this and the problem is understood and there is a workaround, not a code workaround, it's just a configuration workaround to enable it, to enable Postgres to perform normally. but I wanted to make this video to illustrate the fundamental design choice

0:57

that Postgres made that actually led to this issue and that is the choice of mainly processes versus threads in my opinion. So let's do a deep dive of this topic we'll talk about what happened how this was discovered fantastic troubleshooting by the way from the Italian this is coming from Amazon

That was the opening. The rest of the episode (33 min) is in the player: every word clickable, with translation, saved words and flashcards.

Continue in the player

Automatically generated from the audio. May contain errors. Audio belongs to its publisher and is played from their feed. Rights holders can request removal — copyright & takedown policy