SWSWC · Interviews
Community homeHot discussions Latest posts Best of Knowledge base Resources About

SWC · Interviews · Newbie question: how should a swc-interview config file be organised?

74
SWr/swc-interview·posted by swoole_lee·5 minutes agoTutorial

Newbie question: how should a swc-interview config file be organised?

Some background first. Our setup is swc-interview plus three downstream services, seven figures of daily requests, peaking around nine in the evening.

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.

We also fixed monitoring along the way: replaced average-based alerts with percentiles and split them per endpoint. False alerts dropped by about seventy percent and the on-call rotation visibly cheered up.

Mmysqlserverteam.comExternal link · opens in a new tab
38 comments

38 comments

M
Oops_wang·2 days ago

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.

501
Wwinter·3 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.

405
Ttang_hao·28 minutes 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.

393
Zzhu_zong·2 days 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
Cchen_devOP·1 hour agoedited

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.

286
Sswoole_lee·2 days ago

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

344
Kkernel_panic·just nowedited

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

336
Zzhu_zong·5 hours ago

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

185
KkiteOP·just now

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

99
Nnikic·5 hours ago

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.

16
Zzhou_yi·2 hours ago

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

11
Hhuang_ke·yesterday

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.

10
Rran_boMod·12 minutes agoedited

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

243
Kkernel_panic·5 hours ago

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

198
Wwinter·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.

194
Sswoole_lee·28 minutes ago

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

421
Bbob_chen·5 hours ago

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

257
Ddev_zhou·2 hours 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.

374
Hhuang_ke·2 days ago

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

129
Rran_bo·2 days ago

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

3
Cchen_dev·2 days agoLevel 6

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

400
Zzhu_zongOP·1 hour 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.

50
LlinlinMod·28 minutes ago

Agreeing with the above. One addition: with this option enabled the GC count in your metrics doubles, so adjust the alert threshold at the same time or it will keep firing.

477
Ttang_hao·12 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.

234
Kkernel_panic·2 days ago

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

11
Lli_ming·just now

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.

30
Hhuang_ke·just now

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

8
Aalice_dev·2 days 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.

5
Rran_bo·3 minutes ago

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

136
Wwinter·1 hour ago

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

67
Sslow_query·1 hour ago

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

46
Oops_wang·28 minutes ago

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

512
WwinterOP·1 hour agoedited

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.

347
Rran_bo·2 days ago

Agreeing with the above. One addition: with this option enabled the GC count in your metrics doubles, so adjust the alert threshold at the same time or it will keep firing.

267
Ddev_zhou·2 days ago

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

10
Sslow_queryMod·2 days 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.

2
Sslow_query·just now

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

80
Wwinter·2 days ago

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

26

This is the post detail page /en/c/swc-interview/post/p8. 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 →