magic-trace
pyroscope
magic-trace | pyroscope | |
---|---|---|
29 | 56 | |
4,465 | 7,382 | |
1.1% | - | |
6.8 | 9.6 | |
24 days ago | about 1 year ago | |
OCaml | Go | |
MIT License | GNU Affero General Public License v3.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
magic-trace
-
When Optimising Code, Measure
I really like magic-trace [0].
https://github.com/janestreet/magic-trace
Not that the exact tracing relies on Intel PT - support for AMD was added recently but uses perf so suffers from the same sampling/skew issues, but is still very useful.
-
Grafana Phlare, open source database for continuous profiling at scale
Would love to see this integrate with magic trace [1]. I'll need to look at the code for the flamegraph plugin, because handling nanosecond timestamps in flamegraphs seems to break most tools due to float precision.
(1) https://github.com/janestreet/magic-trace
-
How to break into Hudson River Trading?
As for inner workings, have you looked into magic trace? I want to play around with it but last I checked, it doesn't work on macs.
-
Brendan Intel.com
I really hope he can work with cloud vendors and Intel to make Processor Trace a more popular and easier to use capability.
It's unfortunate how https://github.com/janestreet/magic-trace and PMUs in general can't be used by lots of people using cloud VMs.
- GitHub - janestreet/magic-trace: magic-trace collects and displays high-resolution traces of what a process is doing
-
Hacker News top posts: Apr 23, 2022
Magic-trace – High-resolution traces of what a process is doing\ (133 comments)
- Magic-trace – High-resolution traces of what a process is doing
- Magic-trace - 高分辨率跟踪一个进程正在做什么 (Magic-trace – High-resolution traces of what a process is doing)
pyroscope
- Grafana Phlare, open source database for continuous profiling at scale
-
The pros and cons of eBPF profiling in K8s
What do you mean? pyroscope.io was slow for you? or the blog?
- Go garbage collector doesn't release memory
- Pyroscope - Continuous profiling platform
-
Ask HN: What are some 'cool' but obscure data structures you know about?
Tries (or prefix trees).
We use them a lot at Pyroscope for compressing strings that have common prefixes. They are also used in databases (e.g indexes in Mongo) or file formats (e.g debug symbols in macOS/iOS Mach-O format are compressed using tries).
We have an article with some animations that go into details about tries in case anyone's interested [0].
[0] https://github.com/pyroscope-io/pyroscope/blob/main/docs/sto...
- How to add dynamic tags/labels to Java profiles (example)
-
Question: How do you handle oversized heap analysis?
You could use continuous profiling with Pyroscope which uses async-profiler under the hood, but with the added functionality that you can add relevant tags to your VMs (example).
-
JFR (Java Flight Recorder) Parser written in Go
Java Flight Recorder (JFR) is a format for collecting diagnostic and profiling data from Java applications. A while back someone created an issue for Pyroscope , an open source continuous profiler written in Go, to support ingesting profiles in JFR format, but there were no existing parsers that were also written in Go.
-
flamegraph.com - a new website for uploading, analyzing, and sharing pprof profiles
This cloud version is actually a slimmed-down version of Pyroscope which is open source and so you can run it locally.
-
We created flamegraph.com - A website for uploading, analyzing, and sharing flamegraphs
At Pyroscope (open source continuous profiling) we use flamegraphs extensively to visualize and analyze profiling data. However, one of the worst parts about using flamegraphs for analysis is that they are kind of annoying to share.
What are some alternatives?
viztracer - VizTracer is a low-overhead logging/debugging/profiling tool that can trace and visualize your python code execution.
parca - Continuous profiling for analysis of CPU and memory usage, down to the line number and throughout time. Saving infrastructure cost, improving performance, and increasing reliability.
perspective - A data visualization and analytics component, especially well-suited for large and/or streaming datasets.
profefe - Continuous profiling for long-term postmortem analysis
perfetto - Frontend for magic-trace; forks https://ui.perfetto.dev
barrier - Open-source KVM software
linux - Linux kernel source tree
Grafana - The open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more.
scalene - Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals
SheetJS js-xlsx - 📗 SheetJS Spreadsheet Data Toolkit -- New home https://git.sheetjs.com/SheetJS/sheetjs
memray - Memray is a memory profiler for Python
Oat++ - 🌱Light and powerful C++ web framework for highly scalable and resource-efficient web application. It's zero-dependency and easy-portable.