LILinux Community
Community homeHot discussions Latest posts Best of Knowledge base Resources About

Linux Community · After reading the linux core source I finally understand the trade-offs

71
LIr/linux·posted by huang_ke·yesterdayOpen source

After reading the linux core source I finally understand the trade-offs

Short version: linux needs almost no tuning at small and medium scale — the point where it starts to hurt is much further out than most people assume. Full measurements below.

Order of investigation, by return on effort: 1. Check downstream latency first — usually it is not your problem 2. Then pool hit rate and wait-queue length 3. Only then GC and allocation 4. Suspect the framework last

The first thing was to collapse the variables. We were changing config and upgrading the version at the same time, and afterwards nobody could say which change caused what. We rolled back to moving one variable at a time, re-ran three times, and only then did the curve settle. Tedious, but not skippable.

One last trap: in container environments remember to adjust the memory-related parameters in step. Otherwise the host limit and the process expectation disagree, and the symptom is intermittent, unreproducible failure.

What genuinely surprised me was the tail. The average looked great while P99 jumped by an order of magnitude past some threshold. The cause was not linux itself but our upstream connection reuse — the load test traffic was too clean and hid the long-tail requests.

17 comments

17 comments

M
Sswoole_lee·5 hours ago

Can you give a minimal reproduction? I ran it locally for ten minutes and could not reproduce on macOS with the latest version.

196
Kkite·28 minutes ago

Has anyone run a controlled experiment? I did, reducing it to a single variable, and the difference was 4% — within noise. So I suspect the main cause is something else.

69
Nnikic·1 hour ago

Worth learning from this debugging approach. We went straight at the logs and took a much longer route.

333
Ttang_hao·12 minutes ago

There is actually a simpler fix that needs no architecture change: move this check up to the gateway and the problem disappears. The cost is one extra lookup at the gateway.

53
Wwinter·28 minutes ago

This is not a linux problem, it is a usage problem. The docs say this API is not thread-safe and you must lock around it yourself.

111
Kkite·3 minutes ago

A question: what changes in a container with a 512Mi memory limit? That is how we run it in production.

44
Kkite·12 minutes ago

We have run this in production for two years without hitting it. That said, we never reached this scale, so our experience is not really evidence here.

33
Sslow_queryOP·2 hours ago

Saved. I am reworking this area this week — this saves a lot of wrong turns.

14
Kkernel_panic·28 minutes ago

This is not a linux problem, it is a usage problem. The docs say this API is not thread-safe and you must lock around it yourself.

22
Rrase·1 hour ago

Has anyone run a controlled experiment? I did, reducing it to a single variable, and the difference was 4% — within noise. So I suspect the main cause is something else.

315
Kkernel_panic·3 minutes ago

This matches what we see in production. We only hit it past 3k QPS; the earlier load tests showed nothing — the test traffic was too clean, with no long-tail requests.

225
Aalice_dev·1 hour ago

I see point 3 differently. The trade-off depends on your read/write ratio: read-heavy with little writing means caching actually widens the inconsistency window.

377
Nnikic·5 hours ago

I just read the linux source — the author actually explains the reasoning in a comment, roughly "so that it degrades into predictable behaviour in extreme cases".

299
Sslow_query·2 hours ago

One counter-example: below linux 7.4 the semantics of that code are different, so do not copy it verbatim. We got burned in staging and rolled back once.

30
Cchen_dev·2 hours agoedited

Sharing our numbers, 8 cores 16GB, same scenario:

| Concurrency | P50 | P99 |
|---|---|---|
| 200 | 12ms | 88ms |
| 500 | 31ms | 340ms |

P99 clearly collapses at 500 concurrency, which lines up with your knee point.

64
Kkite·yesterday

Can you give a minimal reproduction? I ran it locally for ten minutes and could not reproduce on macOS with the latest version.

89
Cchen_dev·yesterday

Thanks for sharing real numbers — far more useful than the articles that only cover concepts.

4

This is the post detail page /en/c/linux/post/p5. Posts and comments are generated deterministically from a seeded PRNG, so the same post always renders the same content and the link can be shared, reloaded and indexed. In production this page reads MySQL for the post, Redis for hot-post caching, and fetches the whole comment tree in a single query on the path column.

See the database schema →