Viewing profile — super_ar

Good question. I wouldn’t say this replaces Flink in general. If you already run Flink and are comfortable with it, it’s a very powerful system. Where we saw friction with Flink wa…

Hi HN! We are Ashish and Armend, founders of GlassFlow. Over the last year, we worked with teams running high-throughput pipelines into self-hosted ClickHouse. Mostly for observabi…

I am seeing this pattern a lot lately. Teams start with a simple flow: logs/metrics → Vector → ClickHouse Works well as long as they run simple transformations via Vector. When the…

Really cool!

Looks cool! Do you have any idea who "good" it is at detecting AI-generated text?

This is interesting. Just wondering about your traffic volume and how long you have been running lcoalpdf? For us, it is more like 5% of the traffic from GEO, but we have been runn…

Yes, same machine.

There is another test that we published on our docs page. You can check it out here: Setup: https://docs.glassflow.dev/load-test/setup Results: https://docs.glassflow.dev/load-test…

Fair point. Thanks for calling it out! To clarify, we’re focused on a specific use case: Kafka to ClickHouse pipelines with exactly-once guarantees. Kafka can’t provide exactly-onc…

Totally fair point. For stable, known workloads, you can get really far with something lightweight on a single machine. The challenge comes when you need fault tolerance, scaling, …

Hi HN, A few weeks ago, we shared GlassFlow: Open Source streaming ETL to dedup and join streams from Kafka for ClickHouse ( https://news.ycombinator.com/item?id=43953722 ). One of…

Great question! RMT can work well when eventual consistency is acceptable and real-time accuracy isn't critical. But in use cases where results need to be correct immediately (dash…

Thanks for asking those questions. Duplicates often come from how systems interact with Kafka, not from Kafka itself. For example, if a service retries sending a message after a ti…

Great to hear that you are considering it for zenskar. We don't have a publicly available load test, but in internal checks it was able to handle 15k requests per second (locally o…

Good question! RMT does deduplication, but its dependency on background merges that you can't control can lead to incorrect results in queries until the merge is complete. We wante…