Finding a Bottleneck

AndreL

I'm trying to find the limit of what all the points I'm about to list below are. As in does the hardware need to be replaced when it starts to be a bottle neck.

PhysicalDsk/% Dsk Time
Memory|Page/sec
Memory/Avilible Bytes
Network Secment/ Net Utilization
Processor/% Process Time
System Procesor Queue Length

Devilsbane

AndreL wrote: »

I'm trying to find the limit of what all the points I'm about to list below are. As in does the hardware need to be replaced when it starts to be a bottle neck.

PhysicalDsk/% Dsk Time
Memory|Page/sec
Memory/Avilible Bytes
Network Secment/ Net Utilization
Processor/% Process Time
System Procesor Queue Length

I believe queue is like 10, but before saying that and looking dumb I did some research and found this. Observing Processor Queue Length Apparently what is acceptable can vary.

pennystrader

The Average Disk Queue Length counter can reveal whether the drive is keeping up with the demand of running processes. The most frequently cited threshold is two items in the queue. If the average is greater than 2, a drive bottleneck might be occurring. This counter should also be compared with the baseline. If the baseline shows an average of 2.3 items in the disk queue and performance was perceived as acceptable, there’s no reason to suggest that performance is unacceptable—at a later time—if the average is the same or lower. Remember, performance is measurable with statistics, but whether performance is “good” or “bad” is a relative issue.

Devilsbane

pennystrader wrote: »

The Average Disk Queue Length counter can reveal whether the drive is keeping up with the demand of running processes. The most frequently cited threshold is two items in the queue. If the average is greater than 2, a drive bottleneck might be occurring. This counter should also be compared with the baseline. If the baseline shows an average of 2.3 items in the disk queue and performance was perceived as acceptable, there’s no reason to suggest that performance is unacceptable—at a later time—if the average is the same or lower. Remember, performance is measurable with statistics, but whether performance is “good” or “bad” is a relative issue.

You are correct, it is all relative to what you are used to. (Which is why the first task of a new system is to create a baseline.) However, I have taken various practice questions, and they will give you some values in the question and then ask you what to do. (Whether it be add ram, processor, or even moving the page file to a different disk).

Ahriakin

I've always been a fan of Disk Q Length for HDD perf monitoring. Most of the others require knowledge of the actual stats of the arrays/drives, this is a fairly simple overview of whether the drive is overloaded or no.