scalene
bcc
scalene | bcc | |
---|---|---|
32 | 71 | |
11,174 | 19,450 | |
1.4% | 1.0% | |
9.2 | 9.2 | |
5 days ago | 7 days ago | |
Python | C | |
Apache License 2.0 | Apache License 2.0 |
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.
scalene
-
Memray – A Memory Profiler for Python
I collected a list of profilers (also memory profilers, also specifically for Python) here: https://github.com/albertz/wiki/blob/master/profiling.md
Currently I actually need a Python memory profiler, because I want to figure out whether there is some memory leak in my application (PyTorch based training script), and where exactly (in this case, it's not a problem of GPU memory, but CPU memory).
I tried Scalene (https://github.com/plasma-umass/scalene), which seems to be powerful, but somehow the output it gives me is not useful at all? It doesn't really give me a flamegraph, or a list of the top lines with memory allocations, but instead it gives me a listing of all source code lines, and prints some (very sparse) information on each line. So I need to search through that listing now by hand to find the spots? Maybe I just don't know how to use it properly.
I tried Memray, but first ran into an issue (https://github.com/bloomberg/memray/issues/212), but after using some workaround, it worked now. I get a flamegraph out, but it doesn't really seem accurate? After a while, there don't seem to be any new memory allocations at all anymore, and I don't quite trust that this is correct.
There is also Austin (https://github.com/P403n1x87/austin), which I also wanted to try (have not yet).
Somehow this experience so far was very disappointing.
(Side node, I debugged some very strange memory allocation behavior of Python before, where all local variables were kept around after an exception, even though I made sure there is no reference anymore to the exception object, to the traceback, etc, and I even called frame.clear() for all frames to really clear it. It turns out, frame.f_locals will create another copy of all the local variables, and the exception object and all the locals in the other frame still stay alive until you access frame.f_locals again. At that point, it will sync the f_locals again with the real (fast) locals, and then it can finally free everything. It was quite annoying to find the source of this problem and to find workarounds for it. https://github.com/python/cpython/issues/113939)
- Scalene: A high-performance CPU GPU and memory profiler for Python
- Scalene: A high-performance, CPU, GPU, and memory profiler for Python
-
How can I find out why my python is so slow?
Use this my fren: https://github.com/plasma-umass/scalene
-
Making Python 100x faster with less than 100 lines of Rust
You should take a look at Scalene - it's even better.
https://github.com/plasma-umass/scalene
-
Blog Post: Making Python 100x faster with less than 100 lines of Rust
I like seeing another Python profiler. The one I've been playing with is Scalene (GitHub). It does some fun things related to letting you see how much things are moving across the system Python memory boundary.
-
Cum as putea sa imbunatatesc timpul de rulare al pitonului?
Ai vazut "Python Performance Matters" by Emery Berger (Strange Loop 2022)? E in principiu o prezentare si demo cu Scalene.
- Scalene - A Python CPU/GPU/memory profiler with optimization proposals
- Scalene: A Python CPU/GPU/memory profiler with optimization proposals
-
OpenAI might be training its AI technology to replace some software engineers, report says
I tried out some features of machine learning models suggesting optimisations on code profiled by scalene and pretty much all of them would make the code less efficient, both time and memory wise. I am not worried. The devil is in the details and ML will not replace all of us anytime soon
bcc
-
eBPF: Unleashing Kernel Magic for Modern Infrastructure
But wait, there's more! Enter the BCC toolkit and library, your trusty sidekick in simplifying the arcane art of writing eBPF applications. With BCC by your side, you'll be wielding eBPF like a seasoned pro in no time.
-
Linux: Easy Keylogger with eBPF (2018)
Nice - I normally use [bash-readline](https://github.com/iovisor/bcc/blob/master/tools/bashreadlin...) when coworking/co-inhabiting a server or training someone.
-
eBPF Documentary
One of the big wins is not so much “build and run your own stuff” but there are very nice low-cost (in terms of compute) performance utilities built on eBPF
https://github.com/iovisor/bcc
There are so many utilities in that list; there’s a diagram midway down the readme which tries to help show their uses. bcc-tools should be available in any distro.
Also, Brendan Gregg does a ton of performance stuff that is worth knowing about if you check out his other work. Not eBPF only. Flame graphs are useful.
- Bpftop: Streamlining eBPF performance optimization
-
eBPF Tutorial by Example 16: Monitoring Memory Leaks
Reference: https://github.com/iovisor/bcc/blob/master/libbpf-tools/memleak.c
- eBPF Tutorial by Example 9: Capturing Scheduling Latency and Recording as Histogram
-
Uprobes Siblings - Capturing HTTPS Traffic: A Rust and eBPF Odyssey
In this article, we'll build a basic version of an HTTPS sniffer, inspired by bcc-sslsniff.py, but we'll use Rust and Aya. We're going to demonstrate the capabilities of uprobes by employing uprobe and uretprobe along with familiar maps like PerCpuArray, HashMap, and PerEventArray. This will be a straightforward example to help us explore how uprobes function.
-
Issue XDP_REDIRECT on other interface in the same namespace
As xpd program I am using the BCC example xdp_redirect_map.py in skb mode as my NIC does not support native mode, attaching the program to veth2 and a dummy function to veth3
-
Linux runtime security agent powered by eBPF
https://github.com/iovisor/bcc/blob/master/docs/reference_gu...
- eBPF Practical Tutorial: Capturing SSL/TLS Plain Text Data Using uprobe
What are some alternatives?
flask-profiler - a flask profiler which watches endpoint calls and tries to make some analysis.
libbpf - Automated upstream mirror for libbpf stand-alone build.
palanteer - Visual Python and C++ nanosecond profiler, logger, tests enabler
bpftrace - High-level tracing language for Linux eBPF [Moved to: https://github.com/bpftrace/bpftrace]
pytest-austin - Python Performance Testing with Austin
ebpf-for-windows - eBPF implementation that runs on top of Windows
memray - Memray is a memory profiler for Python
zfs - OpenZFS on Linux and FreeBSD
pyshader - Write modern GPU shaders in Python!
linux - Linux kernel source tree
viztracer - VizTracer is a low-overhead logging/debugging/profiling tool that can trace and visualize your python code execution.
nokogiri-rust - Ruby FFI wrapper around scraper crate to be used instead of Nokogiri. Status: proof of concept.