December 2010
10 posts
configuration management
a sysadmin that doesn’t use configuration management is like a programmer who doesn’t use source control.
Dec 31st
hup ur phone
Getting messages like these in your console trying to sync up your phone with iTunes? iTunes[(pid)] _connect_to_port (thread blahblah): Could not connect to USB mux port for device N: Connection refused iTunes[(pid)] _MobileDeviceConnect_locked (thread blahblah): Could not connect to lockdown port on device blahblahblahblah Before you waste any more time googling for the answer, try...
Dec 31st
Dec 30th
waah
virtualization is the answer but I can’t use it :(
Dec 29th
signals and ulimit
I think a user got slapped by a ulimit I put in for the head node… In /etc/security/limits.conf (which is a PAM facility, btw - doing it here avoids having to throw this stuff into the various shell profiles…) * hard cpu 5 root hard cpu unlimited named hard cpu unlimited nobody hard cpu unlimited This sets the max anything can run for a total of 5 minutes of cpu time, which is a...
Dec 29th
router maxout
grabbing stuff from usenet @ 5MB/s is already tasking my alix 2d2’s cpu to the max. polling is already enabled. :/
Dec 28th
Dec 27th
let's calculate pi and do stuff with it
Fun exercises: 1. how does one parallelize pi estimations to n digits?  What’s the fastest way that’s accurate, and is there a really fast way that’s going to generate correctable errors? 2. *really* fast substring matching 3. tree structure for manipulating pi digits? 4. unique array of indicies? 5. parallelize everything (shm and mpi)
Dec 27th
the volume storage solution
Application: So this is for a development video encoding platform. Reads can be really slow (specifically, the product of the peak number of simultaneous clients * the max bitrate of blu-ray 1080p MPEG-2’s, which is 40Mbps)*[http://www.blu-ray.com/faq/] (And, not sure if seeking bumps this number up significantly).  Realistically, we’re streaming h264 content, so reads aren’t...
Dec 26th
1 note
HPC Multithreading
Turned off odd numbered cores on all 64 nodes of the HPC on Friday afternoon. Principle Investigator emails me on Sunday morning telling me everything runs 42% slower. I proceed to turn all the cores back on (I’ve got zero political leverage here). Need to look into why; possible reasons: 1. I turned off hard-cores instead of soft-cores (very possible that it’s not as simple as...
Dec 26th