magic-trace VS viztracer

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.

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

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.

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.

Magic-trace – High-resolution traces of what a process is doing\ (133 comments)

* https://github.com/gaogaotiantian/viztracer get a timeline of execution vs call-stack (great to discover what's happening deep inside pandas)

Do not use bad instrumenting profilers. A good modern tracing-based instrumenting profiler provides so much more actionable information and insights into where problems are than a sampling profiler it is ridiculous.

As a example consider viztracer [1] for Python. By using a aggregate visualizer such as a flame graph you can figure out what is taking the most time then you can use a tracing visualizer to figure out the exact call stacks and system execution and state that caused it. Not only that, a tracing visualizer lets you diagnose whole system performance and makes it trivial to identify 1 in 1000 anomalous execution patterns (with a 4k screen a anomalous execution pattern stands out like a 4 pixel dead spot). In addition you also get vastly less biased information for parallel execution and get easy insights into parallel execution slowdowns, interference, contention, and blocking behaviors.

The only advantages highlighted in your video that still apply to a good instrumenting profiler are:

1. Multi-language support.

2. Performance counters (though that is solved by doing manual tracking after you know the hotspots and causes).

3. Overhead (if you are using low sampling frequency). Even then a good tracing instrumentation implementation should only incur low double-digit percent overhead and maybe 100% overhead in truly pathological cases involving only small functions where the majority of the execution time is literally spent in function call overhead.

4. No need for recompilation, but you are already looking to make performance changes and test so you already intend to rebuild frequently to test those experiments. In addition, the relative difference in information is so humongous that this is not even worth contemplating unless it is a hard requirement like evaluating something in the field.

[1] https://github.com/gaogaotiantian/viztracer

Actually it has explicit support for async task based reporting:

https://github.com/gaogaotiantian/viztracer#async-support

Let us run perf on this, similarly to what we did to example0.py. However, we add the argument -k CLOCK_MONOTONIC so that we use the same clock as VizTracer and ask VizTracer to generate a JSON, instead of an HTML file: