Llamaindex · Toolchain · This llamaindex-tools bug hid for three years before anyone reported it

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.

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

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.

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.

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

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.

One counter-example: below llamaindex-tools 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.

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

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

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.

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.

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.

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

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

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.

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

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

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.

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

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.

One counter-example: below llamaindex-tools 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.

One counter-example: below llamaindex-tools 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.

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

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

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

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.

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

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.

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 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.

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

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.

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.

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

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 llamaindex-tools source — the author actually explains the reasoning in a comment, roughly "so that it degrades into predictable behaviour in extreme cases".

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.

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.

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

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.

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.