
Chapter 1: HP Clustered File System Commands 24
Copyright © 1999-2005 PolyServe, Inc. All rights reserved.
12... Per-target I/O statistics in tuples, or groups of two numbers. (The
number of targets is indicated in field 4.) Each tuple consists of the
following fields for each target:
• SCSI I/Os queued
• Transient failures
Note that the “SCSI I/Os queued” numbers are for the underlying
disk, not the partition. PSD devices that share the same underlying
disk will share the same numbers here.
12+$4*2... I/O statistics in quads, or groups of four numbers. (The number
of quads appears in field 6, “Number of I/O sizes”). Each quad consists of
the following fields for each I/O size:
• Minimum latency
•Maximum latency
• Count of I/Os
• Total latency for all I/Os
The minimum and maximum latency are reset every interval. Latencies
are in microseconds.
mxnlmconfig – enable or disable
Synopsis
/opt/hpcfs/mxnlmconfig -q|-e|-d
Description
NLM is the locking protocol used by NFS. By default, it is disabled in
CFS-Linux. If necessary, NLM can be enabled; however, you should be
aware of the following caveat:
• File locks granted by the NFS server are cluster-coherent. When a
failover occurs, the locks are released by the original server and the
client automatically reclaims them on the new server (the backup
node). However, during the period after the lock is released, another
client or application may compete for and win the lock.
Commentaires sur ces manuels