Wed, 25 Apr 2012 20:48:58 UTC - Dave Pacheco - Uncategorized

It's incredibly easy to visualize where your Node program spends its time using DTrace and node-stackvis (a Node port of Brendan Gregg's FlameGraph tool):

  1. Run your Node.js program as usual.
  2. In another terminal, run:
    $ dtrace -n 'profile-97/execname == "node" && arg1/{
        @[jstack(150, 8000)] = count(); } tick-60s { exit(0); }' > stacks.out
    This will sample about 100 times per second for 60 seconds and emit results to stacks.out. Note that this will sample all running programs called "node". If you want a specific process, replace execname == "node" with pid == 12345 (the process id).
  3. Use the "stackvis" tool to transform this directly into a flame graph. First, install it:
    $ npm install -g stackvis
    then use stackvis to convert the DTrace output to a flamegraph:
    $ stackvis dtrace flamegraph-svg < stacks.out > stacks.svg
  4. Open stacks.svg in your favorite browser.

You'll be looking at something like this:

This is a visualization of all of the profiled call stacks. This example is from the "hello world" HTTP server on the Node.js home page under load. Start at the bottom, where you have "main", which is present in most Node stacks because Node spends most on-CPU time in the main thread. Above each row, you have the functions called by the frame beneath it. As you move up, you'll see actual JavaScript function names. The boxes in each row are not in chronological order, but their width indicates how much time was spent there. When you hover over each box, you can see exactly what percentage of time is spent in each function. This lets you see at a glance where your program spends its time.

That's the summary. There are a few prerequisites:

  • You must gather data on a system that supports DTrace with the Node.js ustack helper. For now, this pretty much means illumos-based systems like SmartOS, including the Joyent Cloud. MacOS users: OS X supports DTrace, but not ustack helpers. The way to get this changed is to contact your Apple developer liaison (if you're lucky enough to have one) or file a bug report at bugreport.apple.com. I'd suggest referencing existing bugs 5273057 and 11206497. More bugs filed (even if closed as dups) show more interest and make it more likely Apple will choose to fix this.
  • You must be on 32-bit Node.js 0.6.7 or later, built --with-dtrace. The helper doesn't work with 64-bit Node yet. On illumos (including SmartOS), development releases (the 0.7.x train) include DTrace support by default.

There are a few other notes:

  • You can absolutely profile apps in production, not just development, since compiling with DTrace support has very minimal overhead. You can start and stop profiling without restarting your program.
  • You may want to run the stacks.out output through c++filt to demangle C++ symbols. Be sure to use the c++filt that came with the compiler you used to build Node. For example:
    c++filt < stacks.out > demangled.out
    then you can use demangled.out to create the flamegraph.
  • If you want, you can filter stacks containing a particular function. The best way to do this is to first collapse the original DTrace output, then grep out what you want:
    $ stackvis dtrace collapsed < stacks.out | grep SomeFunction > collapsed.out
    $ stackvis collapsed flamegraph-svg < collapsed.out > stacks.svg
  • If you've used Brendan's FlameGraph tools, you'll notice the coloring is a little different in the above flamegraph. I ported his tools to Node first so I could incorporate it more easily into other Node programs, but I've also been playing with different coloring options. The current default uses hue to denote stack depth and saturation to indicate time spent. (These are also indicated by position and size.) Other ideas include coloring by module (so V8, JavaScript, libc, etc. show up as different colors.)

For more on the underlying pieces, see my previous post on Node.js profiling and Brendan's post on Flame Graphs.

Dave Pacheco blogs at dtrace.org

Thu, 15 Dec 2011 19:59:15 UTC - ryandahl - Uncategorized

This week Microsoft announced support for Node in Windows Azure, their cloud computing platform. For the Node core team and the community, this is an important milestone. We've worked hard over the past six months reworking Node's machinery to support IO completion ports and Visual Studio to provide a good native port to Windows. The overarching goal of the port was to expand our user base to the largest number of developers. Happily, this has paid off in the form of being a first class citizen on Azure. Many users who would have never used Node as a pure unix tool are now up and running on the Windows platform. More users translates into a deeper and better ecosystem of modules, which makes for a better experience for everyone.

We also redesigned our website - something that we've put off for a long time because we felt that Node was too nascent to dedicate marketing to it. But now that we have binary distributions for Macintosh and Windows, have bundled npm, and are serving millions of users at various companies, we felt ready to indulge in a new website and share of a few of our success stories on the home page.

Work is on-going. We continue to improve the software, making performance improvements and adding isolate support, but Node is growing up.

Tue, 25 Oct 2011 22:26:23 UTC - ryandahl - Uncategorized

Version 0.6.0 will be released next week. Please spend some time this week upgrading your code to v0.5.10. Report any API differences at a href="https://github.com/joyent/node/wiki/API-changes-between-v0.4-and-v0.6"https://github.com/joyent/node/wiki/API-changes-between-v0.4-and-v0.6 or report a bug to us at a href="http://github.com/joyent/node/issues"http://github.com/joyent/node/issues if you hit problems.

The API changes between v0.4.12 and v0.5.10 are 99% cosmetic, minor, and easy to fix. Most people are able to migrate their code in 10 minutes. Don't fear.

Once you've ported your code to v0.5.10 please help out by testing third party modules. Make bug reports. Encourage authors to publish new versions of their modules. Go through the list of modules at a href="http://npmjs.org/"http://npmjs.org/ and try out random ones. This is especially encouraged of Windows users!

Tue, 04 Oct 2011 22:39:56 UTC - ryandahl - Uncategorized

Suppose you're writing a web server which does video encoding on each file upload. Video encoding is very much compute bound. Some recent blog posts suggest that Node.js would fail miserably at this.

Using Node does not mean that you have to write a video encoding algorithm in JavaScript (a language without even 64 bit integers) and crunch away in the main server event loop. The suggested approach is to separate the I/O bound task of receiving uploads and serving downloads from the compute bound task of video encoding. In the case of video encoding this is accomplished by forking out to ffmpeg. Node provides advanced means of asynchronously controlling subprocesses for work like this.

It has also been suggested that Node does not take advantage of multicore machines. Node has long supported load-balancing connections over multiple processes in just a few lines of code - in this way a Node server will use the available cores. In coming releases we'll make it even easier: just pass --balance on the command line and Node will manage the cluster of processes.

Node has a clear purpose: provide an easy way to build scalable network programs. It is not a tool for every problem. Do not write a ray tracer with Node. Do not write a web browser with Node. Do however reach for Node if tasked with writing a DNS server, DHCP server, or even a video encoding server.

By relying on the kernel to schedule and preempt computationally expensive tasks and to load balance incoming connections, Node appears less magical than server platforms that employ userland scheduling. So far, our focus on simplicity and transparency has paid off: the number of success stories from developers and corporations who are adopting the technology continues to grow.

Page 2 →