I think this only pertains to Linux distros. Yesterday I saw my machine almost grind to a halt. I thought it was due to some testing I was doing with Cassandra, but nothing changed even after killing the Cassandra nodes I was running. I did notice several ksoftirqd processes.  I wound up rebooting this morning. Looks like the issue is caused by a leap second. Just wanted to pass this along in case anyone else notices an unusual, expected load on your machine.

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