Server Fault is a question and answer site for system and network administrators. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

I'm in a confusing situation right now: I have 2 MS Server 2008, hosting a WCF-Webservice which is basically reading data from an SQL-Server and forwarding it to the client.

We use NLB to loadbalance those two applicationservers.

During Loadtests there is now a strange reading in the performance-logs: the CPU and MEM Load is quite even throughout those server, but only one server is building up write-queues on the HD, the other isn't.

Is there any relation between those readings and the NLB?

(The servers are only hosting this application: nothing else and are configured the same way)

share|improve this question
Same servers? Same discs? Same configuration? Can it be one disc subsystem is faster, thus not queueing up, while the other is overloaded? ;) – TomTom Aug 29 '11 at 14:41
This was an idea: but the servers were newly bought to do only this job: and they are identical in any way. – MADMap Aug 29 '11 at 14:51

It really depends on what the WCF application is doing to know if those counters will matter. You need to work with your dev team to see if it is a problem.

share|improve this answer
I'm also a dev and have insights in the service: there is no writing to the disk from the service itself (except logging which was deactivated for the loadtest). So I can exclude that. But basically my question was wheter NLB has to write something on the HD to perform? – MADMap Aug 29 '11 at 14:45
It has not. NLB does no writing. – TomTom Aug 30 '11 at 3:44
NLB doesn't touch the disk. – mrdenny Aug 31 '11 at 0:25

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.