ESESP32 · Code review
Community homeHot discussions Latest posts Best of Knowledge base Resources About

ESP32 · Code review · Two weeks with esp32-review: what feels right and what drives me up the wall

91
ESr/esp32-review·posted by zhu_zong·3 hours agoReview

Two weeks with esp32-review: what feels right and what drives me up the wall

Short version: esp32-review 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.

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.

Image placeholder · object storage in production
POST /api/uploads → CDN origin pull
33 comments

33 comments

M
Mmike_xu·5 hours agoedited

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.

283
Mmike_xu·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.

5
Wwinter·28 minutes ago

I just read the esp32-review source — the author actually explains the reasoning in a comment, roughly "so that it degrades into predictable behaviour in extreme cases".

154
Nnikic·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.

241
Kkernel_panic·3 minutes ago

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

116
NnikicOP·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.

47
Ddev_zhou·5 hours ago

This is not a esp32-review problem, it is a usage problem. The docs say this API is not thread-safe and you must lock around it yourself.

385
Aalice_dev·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.

21
Zzhou_yi·2 days agoedited

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.

104
Aalice_dev·2 days ago

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

55
Sswoole_lee·2 days agoedited

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.

47
Nnikic·2 days ago

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

266
Nnikic·28 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.

18
Llinlin·2 hours ago

This is not a esp32-review problem, it is a usage problem. The docs say this API is not thread-safe and you must lock around it yourself.

144
Llinlin·5 hours ago

One counter-example: below esp32-review 7.4 the semantics of that code are different, so do not copy it verbatim. We got burned in staging and rolled back once.

340
Llinlin·2 days 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.

45
Hhuang_ke·28 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.

6
Llinlin·2 days ago

One counter-example: below esp32-review 7.4 the semantics of that code are different, so do not copy it verbatim. We got burned in staging and rolled back once.

10
Zzhu_zong·2 days agoedited

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

486
Llinlin·3 minutes ago

I just read the esp32-review source — the author actually explains the reasoning in a comment, roughly "so that it degrades into predictable behaviour in extreme cases".

8
Wwinter·3 minutes ago

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

1
Ddev_zhou·just now

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

3
Oops_wang·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.

53
Llinlin·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.

32
Wwinter·2 hours agoedited

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.

63
Cchen_dev·1 hour ago

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

4
Kkite·just now

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

155
Sswoole_leeOP·2 hours ago

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

359
Bbob_chen·2 days 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.

400
Nnikic·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.

5
Oops_wang·5 hours 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.

39
Zzhou_yi·2 days agoedited

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

485
Cchen_dev·just now

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.

1

This is the post detail page /en/c/esp32-review/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 →