What Linux can learn from Solaris performance and vice-versa

This is a topic that I would love to see brought up more, and I think there is a lot Linux can learn from Solaris. As someone who was only exposed to Solaris in the last 4 years (using Linux since &#x27;96), I have become increasingly interested in the seemingly unimportant features which have been incredibly useful.<p>Zones have a distinct maturity and robustness over LxC (to be expected), ZFS is the filesystem I wish we could have, dtrace isn&#x27;t a bolt-on etc.<p>It would be nice to see it fully open-sourced again as I think the one thing it has working against it is a smaller community and it lacks the same size army of driver authors.

&#x27;Linux might get DTrace-like capabilities via SystemTap&#x27;<p>Might? SystemTap&#x27;s been stable &amp; out of the box on RHEL 5 for years. The extensive list of default tap points are supported on production by RH. When I was doing systems stuff 5 years ago we used it for double checking TCP socket options that weren&#x27;t normally exposed to userspace tools.<p>Dtrace can do some awesome stuff stap can&#x27;t, like trace something from userspace down to kernel space. But systemtap does provide live instrumentation on running kernels and has for years.<p>PS: Just saw p93. Sun got in trouble for the obvious &quot;Setting up SystemTap is difficult on distros that don&#x27;t maintain, support, use or like SystemTap&quot; years ago. This is repeated on p 93. Stop it, this makes Joyent look stupid, you&#x27;re better than this.<p>And p100. Re: &#x27;several million dollar E10K&#x27; performance? Red Hat were replacing them with Xeon&#x27;s by 2003 (with Sun&#x27;s old sales staff) and crushing them. Though that was SPARC&#x27;s fault not Solaris&#x27;s.

The sad part is that both dtrace and ZFS originally did not end up in the kernel purely because of licensing reasons :-(

One thing I noticed about Solaris - it handles low-memory situations (like 15.5G out of 16GB being used) and swapping, very very well.<p>If Linux has enough RAM, it will outperform Solaris, but, it is quicker to get bogged down if there is swapping.<p>(These observations are from about Centos 5.x , so, perhaps they are no longer valid, however.)

What surprised me most is that SPARC is only ~2x slower after all these years (3.6ghz T5 &#x2F; Sol11) ;)<p><pre><code> $ time perl -e &#x27;for ($i = 0; $i &lt; 100_000_000; $i++) { $s = &quot;SCaLE12x&quot; }&#x27; real 0m33.59s user 0m33.57s sys 0m0.00s</code></pre>

How can you talk about Solaris performance without mentioning dispadmin?

It seems like futexes are really just an alternative interface made to build pthread mutexes on top of. In addition, they may only be faster on Linux because of implementation issues. It doesn&#x27;t seem worth including for comparison.<p>Also, I&#x27;m confused by the claim that Solaris doesn&#x27;t have the vfsstat utility; yes, it doesn&#x27;t have that utility, but it does have &quot;fsstat&quot; which provides VFS-level statistics. So it&#x27;d be helpful to see a more detailed comparison.

I detest slideshare. The way they try to monetize and track me by making me log in to download the PDF. The dumb way they show the slides on a third of the screen and fill the rest with crud.<p>So if you really don&#x27;t want your slides read, put them on slideshare.

Video now available: <a href="http://www.joyent.com/blog/what-linux-can-learn-from-solaris-performance-and-vice-versa" rel="nofollow">http:&#x2F;&#x2F;www.joyent.com&#x2F;blog&#x2F;what-linux-can-learn-from-solaris...</a>

Sure yeah, Solaris is full of great technologies, it is undeniable, and DTrace is an awesome and unique one.<p>Now there&#x27;s one thing those guys can learn from Linux: modesty.

Looking forward to the video!

The last bullet in slide 83 isn&#x27;t exactly a selling point.

Just yesterday Perl has once again been declared dead on Hacker News, and here we have it happily strutting along in a keynote about a bleeding edge topic. :)