Agent · Architecture · Interview notes: how I answered a question about the agent-design concurrency model

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.

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.

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.

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

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.

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.

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

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

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

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

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.

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.

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

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.

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.

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.

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

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.

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

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

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.

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.

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.

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

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.

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.

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.

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

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

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

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.

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.

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

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.

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.

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

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.

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.

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.

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

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.

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

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

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.

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

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.

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

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

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.

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.

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

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.

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

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

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.

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.