begin quoting Mike Marion as of Fri, Oct 12, 2007 at 10:44:21AM -0700: > Quoting Andrew Lentvorski <[EMAIL PROTECTED]>: [snip] > >B) Linux is just a touch unstable when pushed hard > > We've found that it handles the cpu load just fine, it's when it's run > into OOM situations too far and too fast that it falls over sometimes. > This seems to be alleviated with more swap space, which seems to > give the OS more time/room to react and recover. I've still seen > buggy apps knock over even a 128Gig machine though.. that was one > process. That was a seriously screwed up bug that just ate memory at > an insanely fast rate. I've seen similar bugs take down solaris hosts > too though.
My current (desktop) box is running Solaris 2.8, has an uptime of almost 500 days, and has been run to the ragged edge of collapse a half-dozen times in this span. Out of memory and swap; process rabbits; fork-bombs; runaway cpu-bound processes... Of course, recovering from some of those was a tad difficult, in the 1-character-per-minute typing speeds sense. Back in the 2.5.1 days on U1s, things weren't nearly this stable. > >If you do Solaris x86, suddenly these two things go away. Ah... this is a sparc box. -- I really did mean to shut this box down once a quarter for cleaning. Stewart Stremler -- [email protected] http://www.kernel-panic.org/cgi-bin/mailman/listinfo/kplug-list
