DTracing in Anger
My Macbook has becomeso sluggish that it feels like I’m typing ove a 9600 baud modem aagn. Or 2400. It’s alo droping keystokes – which is irritatng as hll – so please forgive theapparent tyos and mistakes. It comes and goes each minute, so thiswhole post isn’t too bad. Usually I cn see what’s wrng [...]
Read more...In: DTrace, macosx, performance
ZFS trivia: metaslabs and growing vdevs
Lately, I’ve been rooting around in the bowels of ZFS as we’ve explored some long-standing performance pathologies. To that end I’ve been fortunate to learn at the feet of Matt Ahrens who was half of the ZFS founding team and George Wilson who has forgotten more about ZFS than most people will ever know. I wanted to [...]
Read more...In: GeorgeWilson, MattAhrens, metaslab, spacemap, ZFS
Active Benchmarking
Benchmarking is often done badly: tools are run ad-hoc, without understanding what they are testing or checking that the results are valid. This can lead to poor architectural choices that haunt you later on. I previously summarized this situation as: casual benchmarking: you benchmark A, but actually measure B, and conclude you’ve measured C. In [...]
Read more...In: benchmarking, performance
illumos hackathon 2012: user-land types for DTrace
At the illumos hackathon last week, Robert Mustacchi and I prototyped better support for manipulating user-land structures. As anyone who’s used it knows, DTrace is currently very kernel-centric — this both reflects the reality of how operating systems and DTrace are constructed, and the origins of DTrace itself in the Solaris Kernel Group. Discussions at [...]
Read more...In: DTrace, hackathon, illumos, pid, user-land
A systems software double-header: Surge and GOTO
I recently returned from a systems software double-header, presenting at two of the industry’s best conferences: Surge in Baltimore and GOTO in Aarhus, Denmark. These conferences have much in common: they are both expertly run; they both seek out top technical content; they both attract top technologists; and (it must be said) they both take [...]
Read more...In: Uncategorized
Upcoming Talk
Next Tuesday, October 2nd I’ll be talking at ZFS Day on how Joyent deploys its cloud services on top of ZFS. One of the main design principles of ZFS is merging the management of physical volumes with individual filesystems. Instead of relying on an underlying volume manager, ZFS manages disks directly and aggregates them into [...]
Read more...In: ZFS
Upcoming Talks
I have a busy few days coming up: On Friday, September 28th, I’m speaking at Surge’12 in Baltimore with Bryan Cantrill on The Real-Time Web in the Real World: DIRT in Production. On Monday, October 1st, I’ll speak at illumos day on DTracing the Cloud, in San Francisco. On Tuesday, October 2nd, at the same [...]
Read more...In: talks
FISL13: The USE Method
In July, Bryan Cantrill, Deirdré Straughan and I spoke at FISL, one of the world’s largest open software conferences, in Porto Alegre, Brazil. I had a great time. My talk introduced the USE Method: a simple strategy for performing a complete check of system performance health, identifying common bottlenecks and errors. This methodology can be [...]
Read more...In: performance, slides, usemethod, video
Debugging dynamic library dependencies on illumos
In this short follow-up to my post on illumos process tools, I’ll expand a bit on ldd and pldd, which print the dynamic linking dependencies of binaries and processes, respectively, and crle, which prints out the runtime linker configuration. These tools are available in most illumos distributions including SmartOS. Understanding builds (and broken builds in [...]
Read more...In: smartos
Webex utilities
I wish that none of our customers encountered problems with our product, but they do, and when they do our means for remotely accessing their systems is often via a Webex shared screen. We remotely control their Delphix server to collect data (often using DTrace). While investigating a customer issue recently I developed a couple [...]
Read more...In: Delphix, Mac OS X, Webex