Mike Marion wrote:
Quoting Andrew Lentvorski <[EMAIL PROTECTED]>:
B) Linux is just a touch unstable when pushed hard
We've heard this for years from people who can't point to any reason
(line of code) why.
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.
You can't go too far into "OOM". When you are out of memory you are out.
What do you expect it to do when OOM? It must be something which does
not require the allocation of any more memory. There is no perfect
solution. The current policy is to kill off the process which most
recently tried to malloc as this is probably the one likely to be using
up most of the memory.
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.
Swap space is many orders of magnitude slower than memory. The machine
certainly will appear to lock up if you get too far down that path due
to the working set being constantly swapped back and forth. Solaris
boxes usually have far more robust disk systems in them which is why
they appear to perform better under high swapping load. Anything the cpu
does, no matter the algorithm, is going to be insignificant compared to
the time required seeking around the disk.
If you do Solaris x86, suddenly these two things go away.
I find that hard to believe. When swapping the disk is going to be the
bottleneck regardless of OS.
--
Tracy R Reed Read my blog at http://ultraviolet.org
Key fingerprint = D4A8 4860 535C ABF8 BA97 25A6 F4F2 1829 9615 02AD
Non-GPG signed mail gets read only if I can find it among the spam.
--
[email protected]
http://www.kernel-panic.org/cgi-bin/mailman/listinfo/kplug-list
