* Page Faults/sec
This counter contains the average number of page faults that occur in the system per second.
Remember that a page fault occurs
when a requested code or data page is not in working or standby memory.
* Cache Faults/sec
This counter contains the average number of cache faults that occur in the system per second.
Remember that cache faults occur
whenever the Cache Manager does not find a file's page in the immediate cache.
* Pages/sec
This counter contains the average number of pages
read from the disk or written to the disk by the system per second.
This value is the sum of two other counters—Pages Input/sec and Pages Output/sec.
The count includes paging traffic on behalf of the system cache
to access file data for applications and pages read to and from noncached mapped memory files.
Use this counter if you are concerned
about excessive memory pressure (also known as thrashing) and the excessive paging that may result.
* Available Memory
This counter indicates the amount of unused memory remaining in the system.
This memory can be used as additional memory for database or system usage.
Available Memory is the most important counter for memory planning.
Source:
Microsoft SQL Server 2000 Administrator's Companion eBook