KAKafka · English
Community homeHot discussions Latest posts Best of Knowledge base Resources About

Kafka · English · Those easily-missed type details in kafka-en

36
KAr/kafka-en·posted by rase·just nowInternals

Those easily-missed type details in kafka-en

It took me two weeks of on-and-off digging and plenty of wrong turns. Writing the process down as it happened so the next person spends less time.

Worth noting: the official docs do cover this, just in a very inconspicuous spot. I only found it reading the source comments, where the author explains the reasoning — roughly "so that it degrades into predictable behaviour in extreme cases".

Self-host — full control44%
Managed service — less work28%
Hybrid: core self-hosted17%
Not decided yet11%

61 votes total

23 comments

23 comments

M
Sswoole_leeOP·just nowedited

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.

436
Nnikic·3 minutes 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.

310
Bbob_chen·3 minutes ago

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

228
Zzhu_zong·3 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.

212
Mmike_xu·1 hour 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.

113
Oops_wang·28 minutes ago

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

91
Wwinter·2 days ago

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

26
Bbob_chen·12 minutes ago

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

446
Nnikic·2 days 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.

57
Kkite·12 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.

175
Sslow_query·1 hour ago

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

340
Ttang_hao·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.

23
Lli_ming·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.

225
Oops_wang·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.

157
Kkernel_panic·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.

9
Zzhou_yi·just nowLevel 6

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

31
Zzhou_yi·2 hours 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
Ttang_hao·yesterday

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

379
Kkite·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.

22
Sswoole_lee·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.

1
Aalice_dev·3 minutes ago

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

107
Wwinter·3 minutes ago

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

79
Sslow_query·2 days ago

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

1

This is the post detail page /en/c/kafka-en/post/p1. 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 →