Hi.
I'm a little confused about why we are measuring far to much page/sec on
memory seen from performance monitor.
The setup is like this:
Dell PE 1955
Dual Quadcore Xeon 2,66GHz
4GB RAM
Server 2003 Standards 32bit
40GB of indexes
400 clients
6 storage nodes
Here are the processes that use the most memory on the networker server.
dbsrv9.exe 290MB
javaw.exe 160MB
nsrjobd.exe 95MB
gstd.exe 60MB
Services.exe 45MB
nsrd.exe 32MB
Total memory commit charge is 1,2GB and has peaked at 2,5GB (4GB RAM
installd)
Page file is 2 - 4GB
Why can this server be doing a memory:pages/sec average of 80 and topping
at 260?
We also have high measurements on disk queue length, but thats probably
just because the indexes need a faster disk.
Since it's a 32bit operating system, it's not going to help adding more
memory, and the current RAM isn't used up anyway. The question is how can I
make Networker make better use of what's there? I've been reading about
memory:pages/sec, but the documentation is pretty fuzzy. It says nothing
but add more RAM.
Johannes
To sign off this list, send email to listserv AT listserv.temple DOT edu and
type "signoff networker" in the body of the email. Please write to
networker-request AT listserv.temple DOT edu if you have any problems with this
list. You can access the archives at
http://listserv.temple.edu/archives/networker.html or
via RSS at http://listserv.temple.edu/cgi-bin/wa?RSS&L=NETWORKER
|