LTTng Blog
lttng.org · Company blog · on HN since 2011
The LTTng project's blog covers its open-source tracing framework for Linux, with posts on latency analysis, releases, and Userspace RCU.
What HN saysHN commenters recommend LTTng for correlated kernel and userspace tracing, and one says they are very impressed by it. It is often listed among tracing tools.
20HN people shared it
11linked it in comments
16stories submitted
311story points
2 years agolast shared
2011people per year2026
Most-shared posts
- 1LTTng: An open-source tracing framework for Linux9 people · 112 points · first shared 2011 · 15 comments on HN
- 2Finding the root cause of a web request latency3 people · 30 points · first shared 2015 · discussion on HN
- 3Monitoring real-time latencies2 people · 9 points · first shared 2016 · discussion on HN
- 4Lttng-2.7-released2 people · 3 points · first shared 2015 · discussion on HN
- 5V2.132 people · first shared 2021
- 6Membarrier system call performance and the future of Userspace RCU on Linux1 people · 71 points · first shared 2018 · 4 comments on HN
- 7Tracing bare-metal systems: a multi-core story1 people · 47 points · first shared 2014 · discussion on HN
- 8Full stack system call latency profiling1 people · 17 points · first shared 2015 · discussion on HN
- 9The new dynamic user space tracing feature in LTTng1 people · 6 points · first shared 2019 · discussion on HN
- 10Preventing trace event record loss with LTTng-UST's blocking mode1 people · 6 points · first shared 2017 · discussion on HN
- 11Bringing .NET application performance analysis to Linux1 people · 4 points · first shared 2018 · discussion on HN
- 12Barectf 2: Continuous Bare-Metal Tracing on the Parallella Board1 people · 3 points · first shared 2015 · discussion on HN
- 13LTTng Scope 0.3: A basic tutorial1 people · 3 points · first shared 2018 · discussion on HN
- 14Docs1 people · first shared 2014
- 15Ust1 people · first shared 2014
What HN people wrote when they linked it
tanelpoder · 2024-07-16
The other alternative is LTTng, released in 2005 (requires loading a kernel module):
https://lttng.org/
angry_octet · 2022-11-29
This article is pretty thin but it's not wrong.
If you're interested in consistent low latency you do need to avoid TLB misses, and also page faults, cache contention, cache coherency delay (making sure no other cores are accessing your memory) from the CC protocol (MOESI/MESI(F)) and mis-prediction, and that's after you have put all your core's threads into SCHED_FIFO. Using https://lttng.org/ can be really helpful in checking what's happening.
abusque · 2018-02-15
An option for correlated kernel and userspace tracing on Linux is LTTng. [0] For a comparison of LTTng and other tracers, check out the LTTng docs. [1]
[0] http://lttng.org/
[1] http://lttng.org/docs/v2.10/#doc-lttng-alternatives
planckscnst · 2015-07-08
That's a pretty great overview. I've learned SystemTap myself because that's what's easy to get going in my environment. I was very surprised once I "got" it. It can do pretty much anything you'd ever need. I haven't needed to look at anything else yet, although I've been meaning to play with the LTTNG tools, as I like the idea of setting up the experiment just once, recording everything, then investigating afterwards. This [1] is a good walkthrough of that workflow.
[1] http://lttng.org/blog/2015/02/04/web-request-latency-root-cause/
jordigh · 2015-01-21
Ah, an article on tracing.
I am very impressed by lttng myself:
http://lttng.org/
cbab · 2014-01-31
or LTTng with both kernel and userspace tracers http://lttng.org
Disclaimer: LTTng developer :)
dsantos · 2011-04-28
the article mentions perf, valgrind, oprofile, etc. but misses the lttng tool
http://lttng.org
throwaway2001 · 2014-12-28
jgalar · 2021-08-03
To provide some context for this release announcement, the LTTng documentation has a nice intro to tracing and an explanation of how LTTng relates to other Linux tracers.
https://lttng.org/docs/v2.13/#doc-nuts-and-bolts
edwintorok · 2014-10-27
Interesting, would it make sense to store/convert the trace in the CTF format[0]? Would the viewers from LTTng[1] be useful in analyzing this trace data?
[0] https://www.efficios.com/babeltrace
[1] http://lttng.org/files/lttv-doc/user_guide/c42.html#mainwindow
jitl · 2021-11-16
I think [this documentation page][1] does a much better job than the project homepage describing why you’d use lltng over other, related tools:
> The main distinctive features of LTTng is that it produces correlated kernel and user space traces, as well as doing so with the lowest overhead amongst other solutions. It produces trace files in the CTF format, a file format optimized for the production and analyses of multi-gigabyte data.
So it has kernel hooks as well as user space libraries for a number of different programming language runtimes like Java and Python.
Compare to eBPF, which by the way is also open-source, since it’s a kernel feature. From lltng’s documentation:
> eBPF: A subsystem in the Linux kernel in which a virtual machine can execute programs passed from the user space to the kernel.
>
> You can attach such programs to tracepoints and kprobes thanks to a system call, and they can output data to the user space when executed thanks to different mechanisms (pipe, VM register values, and eBPF maps, to name a few).
[1]: https://lttng.org/docs/v2.13/#doc-lttng-alternatives