Ted,
I can't speak to the differences between kernels, but also I am very interested
in your thread. Our SLES10 and SLES 11 experience has been that even with
VDISK as swap on a VM system that is NOT overcommitted on memory, that any
linux swapping is just kills us with the same sort of result
http://arstechnica.com/information-technology/2014/01/bitrot-and-atomic-cows-inside-next-gen-filesystems/
--
Wasn't there something about a PASCAL programmer knowing the value of
everything and the Wirth of nothing?
Maranatha! <><
John McKown
I'm not sure what you would expect VM to be able to do here. All OSes pretty
much suspend operations while this kind of "what can I do without"
decision-making is going on inside the kernel. If the Linux kernel is taking
it's time sorting out what pages are clean/dirty/pageable, the only thin
With all of the installations (100s) i've worked with using vdisk for
swap, this would be the first complaint i've heard with the exception of
some bad configuration defaults. If you had really good performance
management tools, I'd be happy to look at the data.
On 1/15/2014 5:44 AM, Veencamp,
I don't mean to hijack Ted's thread on the swap differences he's seeing between
SLES 11 SP2 and SP3. I have a different issue, and his issue is more immediate.
I'll make a different thread on my issues. I'd like to get some feedback on VM
SET REORDER OFF for large hosts...
Jon
-Original M
David:
You wrote:
Ø If backleveling the kernel makes the problem go away, then it's clearly a
kernel logic problem in the s390x port.
Thanks! That was my logic too; it's nice to have it validated by someone who
knows more about the kernel than I do.
Yours very truly,
Ted Rodriguez-Bell
Enterpr