Hacker News: nikolay_sivko

Andy Pavlo joins ClickHouse to establish ClickHouse Labs

nikolay_sivko — Mon, 03 Aug 2026 14:09:00 +0000

Article URL: https://clickhouse.com/blog/andy-pavlo-joins-clickhouse

Comments URL: https://news.ycombinator.com/item?id=49156011

Points: 241

# Comments: 50

It was surprisingly hard to break CloudNativePG replication

nikolay_sivko — Tue, 28 Jul 2026 19:37:03 +0000

Article URL: https://coroot.com/blog/fencing-a-cnpg-replica/

Comments URL: https://news.ycombinator.com/item?id=49088840

Points: 4

# Comments: 0

Understand Pressure Stall Information (Psi) Metrics

nikolay_sivko — Tue, 28 Jul 2026 19:09:35 +0000

Article URL: https://kubernetes.io/docs/reference/instrumentation/understand-psi-metrics/

Comments URL: https://news.ycombinator.com/item?id=49088496

Points: 2

# Comments: 0

PostgreSQL Autovacuum Internals and Benchmark

nikolay_sivko — Tue, 28 Jul 2026 19:03:26 +0000

Article URL: https://percona.community/blog/2026/07/01/postgresql-autovacuum-internals-benchmark/

Comments URL: https://news.ycombinator.com/item?id=49088411

Points: 5

# Comments: 0

What matters for performance: lessons from a year of benchmarks

nikolay_sivko — Tue, 28 Jul 2026 19:01:45 +0000

Article URL: https://clickhouse.com/blog/what-really-matters-for-performance-lessons-from-a-year-of-benchmarks

Comments URL: https://news.ycombinator.com/item?id=49088387

Points: 2

# Comments: 0

Let's break autovacuum in Postgres: reproducing failures to make it observable

nikolay_sivko — Tue, 21 Jul 2026 20:18:55 +0000

Article URL: https://coroot.com/blog/lets-break-autovacuum-in-postgres/

Comments URL: https://news.ycombinator.com/item?id=48997663

Points: 4

# Comments: 0

Meta's Root Cause Analysis Platform at Scale

nikolay_sivko — Sat, 11 Jul 2026 19:54:46 +0000

Article URL: https://engineering.fb.com/2025/12/19/data-infrastructure/drp-metas-root-cause-analysis-platform-at-scale/

Comments URL: https://news.ycombinator.com/item?id=48875249

Points: 2

# Comments: 0

The hard part of AI root cause analysis is no longer the model

nikolay_sivko — Wed, 01 Jul 2026 18:16:53 +0000

Article URL: https://coroot.com/blog/hard-part-of-ai-root-cause-analysis-is-no-longer-the-model/

Comments URL: https://news.ycombinator.com/item?id=48751050

Points: 2

# Comments: 0

Tracing PostgreSQL Using eBPF and Hardware Breakpoints

nikolay_sivko — Mon, 11 May 2026 12:29:29 +0000

Article URL: https://jnidzwetzki.github.io/2026/05/08/ebpf-hw-breakpoints-postgresql.html

Comments URL: https://news.ycombinator.com/item?id=48094132

Points: 3

# Comments: 0

PgBackRest is archived, what now?

nikolay_sivko — Tue, 28 Apr 2026 15:01:00 +0000

Article URL: https://percona.community/blog/2026/04/28/pgbackrest-is-archived-what-now/

Comments URL: https://news.ycombinator.com/item?id=47935602

Points: 4

# Comments: 1

Golang heap profiling without pprof enabled or eBPF

nikolay_sivko — Tue, 28 Apr 2026 14:50:20 +0000

Article URL: https://coroot.com/blog/zero-config-go-heap-profiling/

Comments URL: https://news.ycombinator.com/item?id=47935438

Points: 2

# Comments: 0

Making encrypted Java traffic observable with eBPF

nikolay_sivko — Wed, 25 Mar 2026 10:51:32 +0000

Article URL: https://coroot.com/blog/java-tls-instrumentation-with-ebpf/

Comments URL: https://news.ycombinator.com/item?id=47515648

Points: 3

# Comments: 0

Native Threading and Multiprocessing in Go

nikolay_sivko — Tue, 23 Sep 2025 07:42:57 +0000

Article URL: https://antonz.org/multi/

Comments URL: https://news.ycombinator.com/item?id=45343968

Points: 2

# Comments: 0

New comment by nikolay_sivko in "OpenTelemetry for Go: Measuring overhead costs"

nikolay_sivko — Thu, 19 Jun 2025 12:23:26 +0000

As suggested, I measured the overhead at various sampling rates:

No instrumentation (otel is not initialized): CPU=2.0 cores

SAMPLING 0% (otel initialized): CPU=2.2 cores

SAMPLING 10%: CPU=2.5 cores

SAMPLING 50%: CPU=2.6 cores

SAMPLING 100%: CPU=2.9 cores

Even with 0% sampling, OpenTelemetry still adds overhead due to context propagation, span creation, and instrumentation hooks

New comment by nikolay_sivko in "OpenTelemetry for Go: Measuring overhead costs"

nikolay_sivko — Mon, 16 Jun 2025 18:10:15 +0000

I'm the author. I wouldn’t say the post is critical of OTEL. I just wanted to measure the overhead, that’s all. Benchmarks shouldn’t be seen as critique. Quite the opposite, we can only improve things if we’ve measured them first.

From Utilization to Psi: Rethinking Resource Starvation Monitoring in Kubernetes

nikolay_sivko — Mon, 28 Apr 2025 09:38:00 +0000

Article URL: https://blog.zmalik.dev/p/from-utilization-to-psi-rethinking

Comments URL: https://news.ycombinator.com/item?id=43819342

Points: 2

# Comments: 0

New comment by nikolay_sivko in "Show HN: Coroot – eBPF-based, open source observability with actionable insights"

nikolay_sivko — Wed, 09 Apr 2025 14:11:20 +0000

We could totally add that, but no one's asked for it so far

New comment by nikolay_sivko in "Show HN: Coroot – eBPF-based, open source observability with actionable insights"

nikolay_sivko — Wed, 09 Apr 2025 08:24:06 +0000

1. Regarding overhead — we ran a benchmark focused on performance impact rather than raw overhead [1]. TL;DR: we didn’t observe any noticeable impact at 10K RPS. CPU usage stayed around 200 millicores (about 20% of a single core).

2. Coroot’s agent captures pseudo-traces (individual spans) and sends them to a collector via OTLP. This stream can be sampled at the collector level. In high-load environments, you can disable span capturing entirely and rely solely on eBPF-based metrics for analysis.

3. We’ve built automated root cause analysis to help users explain even the slightest anomalies, whether or not SLOs are violated. Under the hood, it traverses the service dependency graph and correlates metrics — for example, linking increased service latency to CPU delay or network latency to a database. [2]

4. Currently, Coroot doesn’t support off-CPU profiling. The profiler we use under the hood is based on Grafana Pyroscope’s eBPF implementation, which focuses on CPU time.

[1]: https://docs.coroot.com/installation/performance-impact [2]: https://demo.coroot.com/p/tbuzvelk/anomalies/default:Deploym...

New comment by nikolay_sivko in "Show HN: Coroot – eBPF-based, open source observability with actionable insights"

nikolay_sivko — Wed, 09 Apr 2025 06:18:54 +0000

From a user’s perspective, it doesn’t really matter how the data is collected. What actually matters is whether the tool helps you answer questions about your system and figure out what’s going wrong.

At Coroot, we use eBPF for a couple of reasons:

1. To get the data we actually need, not just whatever happens to be exposed by the app or OS.

2. To make integration fast and automatic for users.

And let’s be real, if all the right data were already available, we wouldn’t be writing all this complicated eBPF code in the first place:)

New comment by nikolay_sivko in "Show HN: Coroot – eBPF-based, open source observability with actionable insights"

nikolay_sivko — Wed, 09 Apr 2025 05:16:57 +0000

Enterprise Edition = Community Edition + Support + AI-based Root Cause Analysis + SSO + RBAC