Monitoring The Disk Subsystem In Netware - HP ML570 - ProLiant - G2 Tuning Manual

Novell NetWare 6 performance tuning guidelines for ProLiant servers
monitoring the disk
subsystem in
NetWare 6
For example, the theoretical maximum achievable throughput on a 66 MHz PCI when a
32-bit bus master bursting with a 32-bit target would be:
4 bytes per data phase x 66 million data phases per second = 264 MB / second
Utility tools such as Monitor, NetWare Remote Manager (NRM), and SET parameters can
be used to gauge disk subsystem performance in NetWare 6. These utilities provide clues
as to whether there is a performance bottleneck in the disk subsystem. The following are
parameters to monitor:
dirty cache buffers – Number of cache buffers containing updated data that has not
been written to the disk. The operating system writes the data to the disk either as
soon as the cache buffer is filled or when the dirty cache delay time elapses (default
3.3 seconds).
current disk requests – Number of pending disk I/O requests that are queued for
service.
least recently used (LRU) settings – measures the length of time it takes for a cache
buffer at the head of the list to make its way down to the tail, where it becomes the
LRU buffer.
Novell Storage Services (NSS) cache buffers – Check the cache buffers used by the
NSS. To view the statistics shown in table 4, type the following at the console prompt:
table 4. buffer cache statistics
statistics
num cache buffer
num hash buckets
min OS free cache buffers
num cache pages allocated
cache hit percentage
cache hit
cache miss
percent of buckets used
max entries in a bucket
total entries
Check the values for the Cache hit percentage and the Percent of buckets used on the
displayed result.
Cache hit percentage provides a percentage of how the cache is performing. A
percentage value of > 75 is desirable.
Percent of buckets used provides a percentage of the total cache currently in use.
NSS / Cachestats
cache
512
524288
256
233106
76
69803
21624
0%
1
1286
8