30/11/09 18:40:13, <tho...@equinox.homelinux.org>:
Hi all,
this some kind of Off-Topic since it has nothing to do with LFS at all. I
send this to this list because I know that there are quite a lot geeks and
experienced people out there who may have a hint for me.
Have you ever seen a machine which has too much RAM installed? We have a
brand new HP (DL380G6) server here with 48G RAM installed. It has an p410i
and a p800 SAS controller connected to a MSA70 with 1TB usable disk space.
There are 2 Quad-Core-Xeon (X5560) with hyperthreading (a total of 16 CPUs).
As an OS there is s SuSE SLES10 installed and as DB-Software (because of
which we have this machine) Oracle10g.
The problem:
When we create a file which is 32GByte large (for instance using dd
if=/dev/null of=test.dat...) the copy process runs very fast up to round
about 29-30GB slows down quite immediatly and the workload increases up to
loadavg=35 or so. It finally results in a non-responding machine where we
can only press the reset-button.
What we did:
Adding the mentioned 30GB plus the rest what the OS itself is using it
adds up to quite exact 32GB. We removed 6 of the 12 RAM modules (every has
4GB) so that the machine now has less that 32GB RAM (exact 24GB). The dd
command runs quite fast until the file was created and nothing special is
seen on the machine - everything worked as expected.
Do you have an idea what the 32GB-limit could be? Or what could make the
machine to behave the way it does?
Our next step will be to test that all with the 64-bit stuff but it should
work on 32bit too, isn't it?
Any ideas?
Thank you!
Thomas
Could as well have something to do with the type of memory used (RDIMM or UDIMM memory)
--
http://linuxfromscratch.org/mailman/listinfo/lfs-dev
FAQ: http://www.linuxfromscratch.org/faq/
Unsubscribe: See the above information page
-- http://linuxfromscratch.org/mailman/listinfo/lfs-dev FAQ: http://www.linuxfromscratch.org/faq/ Unsubscribe: See the above information page
