Uhu... I think my message was a bit too long/boring/messy to be taken care of...
Anyway, if anyone is interested, I have a few elements of answer:


..and cannot determine if memtests exits itself because it cannot lock
pages anymore or if it is killed by the kernel because host RAM is
full?
I think the first option is the right one: it's a memtest problem,
explanation below.


By the way, I'm not sure memtest is the ideal for what I am trying to
do: fill each vserver allocated memory at its max and see what's
happening, end eventually what happens when swap is starting to be
used, but memtest locks all the pages so swap is never used... Anyone
knows about a more appropriate test software just filling RAM with
loads of data?
Effectively not, it was not appropriate. I tried executing recursively
a php loop with an incrementing array and 1) apache is not killed 2)
it just claims it is "Unable to allocate".
Doing that on 5 vservers at the same time during a few minutes shows that:
-swap is starting to be used when total rss returned by vserver-stat
equals total host RAM
-swap seems to be a host business
-rlimiting as (aka VSZ) seems to be useless because VSZ is not only
RAM, rather rlimit rss
-if total rss rlimits exceeds total host RAM, and too much vservers
are started, someting seems to happen so their individual rss is
limited?

Please tell me if I am wrong.

Best regards,

Mehdi Bennani
_______________________________________________
Vserver mailing list
[email protected]
http://list.linux-vserver.org/mailman/listinfo/vserver

Reply via email to