HP File Server Optimization Tips

I have Hyper-V running on a powerful server and I have one of the virtual machines mounted to an ISO hosted on a fileshare on an HP DL380 G4, lets call it fileserver1. The bottleneck in the whole setup is fileserver1.

Fileserver1 is setup with a RAID5 array that we've been using for about 4 years i guess. Its been a great fileserver to about 40 staff members. Running Windows Server 2003 Standard with 2x Xeons @3.4GHz and 1GB RAM. All servers have 1GB NICs connected to GB switch. It is a really underutilized server averaging about 5% in every performance counter in perfmon. With the iso file mounted to the virtual machine on the other server, fileserver1's Pages/sec counter maxes out which is apparently the bottle neck.

My questions
1. How can I reduce this bottlleneck? I'm not sure if I should add more RAM becuase i've heard fileserving is not RAM intensive and this is the only time pages/sec even gets close to maxing out.
2. Is there a set of best practices or suggestions that will allow me to optimize the performance of fileserver1?
LVL 5
twcadminAsked:
Who is Participating?
 
SysExpertConnect With a Mentor Commented:
Well the problem is that your peak is over 1 GB, which means that at some point you were doing a lot of paging which drastically slows things down.

You should run perfmon in log mode to see when this is happening or simply add 1 Gb more RAM

 
I hope this helps !
0
 
Nuno MartinsCommented:
Hi,
I notice one thing a little wile ago if you disable receive side scaling on the network card your network will work faster.
this teak was made in a DL380 G5. But you can try it and test it.

NM
0
 
twcadminAuthor Commented:
Thanks for the tip but the network doesnt seem to be maxing out at all
0
Free Tool: ZipGrep

ZipGrep is a utility that can list and search zip (.war, .ear, .jar, etc) archives for text patterns, without the need to extract the archive's contents.

One of a set of tools we're offering as a way to say thank you for being a part of the community.

 
SysExpertCommented:
1) Check task manager and see if All the RAM is being used in the commit charge Section.

If total or peak is > 1 GB then you need more RAM

You should use perfmon to monitor more counters to see the exact issue

I hope this helps !
0
 
twcadminAuthor Commented:
Under commit charge total is bouncing around 366,000 and peak is 1,169,504 so if theres a 1GB ram already in there, and commit is only around 360MB, doesnt that mean theres plenty of RAM?

Physical ram says 570MB available
0
 
twcadminAuthor Commented:
Any suggestions for improving this bottleneck or best practices as I requested?
0
Question has a verified solution.

Are you are experiencing a similar issue? Get a personalized answer when you ask a related question.

Have a better answer? Share it in a comment.

All Courses

From novice to tech pro — start learning today.