Adam Leventhal's blog

Month: October 2011

On Monday, the Delphix systems crew is rolling down the 101 to the illumos hackathon in San Jose. Anyone who’s working on illumos, developing illumos-derived technologies like ZFS or DTrace, or who wants to cut some OS code, should drop by. Here’s the sign up.

What’s a hackathon? Not exactly sure, but we’re hoping to cut a bunch of code, and hopefully build some neat stuff in a short period of time. The basic plan is that we’ll meet at the Wyndam at 10am — if you can’t track us down, message me on twitter. Bring your ideas for cool, fun projects, that a few people might be able to bang out in a marathon day. At Delphix, we’ve been thinking about time-correlated DTrace, libzfs v2, tab-completion for mdb, some build system improvements, and something goofy we call tarfs. We’ll throw the ideas at the whiteboard, break into project teams, and hack them up until we have something to demo (and Joyent has offered up build servers if you need one).

For now, think about what you’d want to build (think fun but small — we only have the day), pull down the illumos source, and hoard your favorite source of caffeine. Got a good idea? Post it in the comments. And I hope to see you Monday.

It’s my pleasure to welcome Matt Amdur to Delphix, to the world of DTrace, and — just today — to the blogosphere. Matt joined Delphix about two months after 10 years of software engineering, most recently at VMware. Matt and I met in at Brown University in 1997 where we worked together closely for all four years. We’ve had in the back of our minds that our professional lives would converge at some point; I couldn’t be happier to have my good friend onboard.

Matt’s first blog post is a great war story, describing his first use of DTrace on a customer system. It was vindicating to witness first hand, both in how productive an industry vet could be with DTrace after a short period, and in what a great hire Matt was for Delphix. Working with him has been evocative of our collaboration in college — while making all the more apparent the significant distance we’ve both come. Welcome, Matt!

After writing about Oracle’s port of DTrace to OEL, I wanted to take it for a spin. Following the directions that Wim Coekaerts spelled out, I installed and configured a VM to run OEL with Oracle’s nascent DTrace port. Setting up the system was relatively painless.

Here’s my first DTrace invocation on OEL:

[root@screven ~]# uname -a
Linux screven 2.6.32-201.0.4.el6uek.x86_64 #1 SMP Tue Oct 4 16:47:00 EDT 2011 x86_64 x86_64 x86_64 GNU/Linux
[root@screven ~]# dtrace -n 'BEGIN{ trace("howdy from linux"); }'
dtrace: description 'BEGIN' matched 1 probe
CPU     ID                    FUNCTION:NAME
0      1                           :BEGIN   howdy from linux

Then I wanted to see what was on the system:

[root@screven ~]# dtrace -l | wc -l
Are you kidding me? For comparison, my Mac has 154,918 probe available and our illumos-derived Delphix OS has 77,320 (Mac OS X has many probes pre-created for each process). It looks like this beta only has the syscall provider, but digging around I can see that Wim didn’t mention that the profile provider is also there:
[root@screven ~]# modprobe profile
[root@screven ~]# dtrace -l | wc -l
[root@screven ~]# dtrace -n profile:::profile-997
dtrace: failed to enable 'profile:::profile-997': Failed to enable probe
Not that sweet.
At least I can run my favorite DTrace script:
[root@screven ~]# dtrace -n syscall:::entry'{ @[execname] = count(); }'
dtrace: description 'syscall:::entry' matched 285 probes
pickup                                                            9
abrtd                                                            11
qmgr                                                             17
rsyslogd                                                         25
rs:main Q:Reg                                                    35
master                                                           52
tty                                                              60
dircolors                                                        80
hostname                                                         92
tput                                                             92
id                                                              198
unix_chkpwd                                                     550
auditd                                                          599
dtrace                                                          760
bash                                                           1515
sshd                                                           8327
I wanted to trace activity when I connected to the system using ssh… but ssh logins fail with all probes enabled. To repeat: ssh logins fail with DTrace probes enabled. I’d try to debug it, but I’m too dejected.


While I’d like to give this obviously nascent port the benefit of the doubt, its current state is frankly embarrassing. It’s very clear now why Oracle wasn’t demonstrating this at OpenWorld last week: it doesn’t stand up to the mildest level of scrutiny. It’s fine that Oracle has embarked on a port of DTrace to the so-called unbreakable kernel, but this is months away from being usable. Announcing a product of this low quality and value calls into question Oracle’s credibility as a technology provider. Further, this was entirely avoidable; there were other DTrace ports to Linux that Oracle could have used as a starting point to produce something much closer to functional.

This is not DTrace

So, OEL users, know that this is not DTrace. This is no better than one of the DTrace knockoffs and in many ways much worse. What Oracle released is worse than worthless by violating perhaps the most fundamental tenet of DTrace: don’t damage the system. And, to the OEL folks, I’m sure you’ll get there, but how about you take down your beta until it’s ready? As it is, people might get the wrong impression about what DTrace is.

Yesterday (October 4, 2011) Oracle made the surprising announcement that they would be porting some key Solaris features, DTrace and Zones, to Oracle Enterprise Linux. As one of the original authors, the news about DTrace was particularly interesting to me, so I started digging.

I should note that this isn’t the first time I’ve written about DTrace for Linux. Back in 2005, I worked on Linux-branded Zones, Solaris containers that contained a Linux user environment. I wrote a coyly-titled blog post about examining Linux applications using DTrace. The subject was honest — we used precisely the same techniques to bring the benefits of DTrace to Linux applications — but the title wasn’t completely accurate. That wasn’t exactly “DTrace for Linux”, it was more precisely “The Linux user-land for Solaris where users can reap the benefits of DTrace”; I chose the snappier title.

I also wrote about DTrace knockoffs in 2007 to examine the Linux counter-effort. While the project is still in development, it hasn’t achieved the functionality or traction of DTrace. Suggesting that Linux was inferior brought out the usual NIH reactions which led me to write a subsequent blog post about a theoretical port of DTrace to Linux. While a year later Paul Fox started exactly such a port, my assumption at the time was that the primary copyright holder of DTrace wouldn’t be the one porting DTrace to Linux. Now that Oracle is claiming a port, the calculus may change a bit.

What is Oracle doing?

Even among Oracle employees, there’s uncertainty about what was announced. Ed Screven gave us just a couple of bullet points in his keynote; Sergio Leunissen, the product manager for OEL, didn’t have further details in his OpenWorld talk beyond it being a beta of limited functionality; and the entire Solaris team seemed completely taken by surprise.

What is in the port?

Leunissen stated that only the kernel components of DTrace are part of the port. It’s unclear whether that means just fbt or includes sdt and the related providers. It sounds certain, though, that it won’t pass the DTrace test suite which is the deciding criterion between a DTrace port and some sort of work in progress.

What is the license?

While I abhor GPL v. CDDL discussions, this is a pretty interesting case. According to the release manager for OEL, some small kernel components and header files will be dual-licensed while the bulk of DTrace — the kernel modules, libraries, and commands — will use the CDDL as they had under (the now defunct) OpenSolaris (and to the consernation of Linux die-hards I’m sure). Oracle already faces an interesting conundum with their CDDL-licensed files: they can’t take the fixes that others have made to, for example, ZFS without needing to release their own fixes. The DTrace port to Linux is interesting in that Oracle apparently thinks that the CDDL license will make DTrace too toxic for other Linux vendors to touch.


Regardless of how Oracle brings DTrace to Linux, it will be good for DTrace and good for its users — and perhaps best of all for the author of the DTrace book. I’m cautiously optimistic about what this means for the DTrace development community if Oracle does, in fact, release DTrace under the CDDL. While this won’t mean much for the broader Linux community, we in the illumos community will happily accept anything of value Oracle adds. The Solaris lover in me was worried when it appeared that OEL was raiding the Solaris pantry, but if this is Oracle’s model for porting, then I — and the entire illumos community I’m sure — hope that more and more of Solaris is open sourced under the aegis of OEL differentiation.

10/10/2011 follow-up post, Oracle’s port: this is not DTrace.

Recent Posts

February 12, 2017
December 18, 2016
August 9, 2016
August 2, 2016