[LEAPSECS] Testing computer leap-second handling

Gerard Ashton ashtongj at comcast.net
Mon Jul 9 08:24:18 EDT 2012


I just read an explanation of what went wrong with some Linux systems:

http://serverfault.com/questions/403732/anyone-else-experiencing-high-rates-
of-linux-server-crashes-during-a-leap-second/403767#403767

I didn't understand all the details, but my take-away was that while the
impending-leap-second flag was set
during the 24 hours leading up to the leap second, various locks were being
applied by the operating system.
Locks are much more likely to have adverse effects on a heavily loaded
system than a lightly loaded system.
It would be tempting to prepare for the next leap second by running a fake
leap second into a test system
that is sitting in a lab doing nothing but keep time. But a realistic test
requires that the system under test
be running a load as similar as possible to production systems.

Gerard Ashton



More information about the LEAPSECS mailing list