System Shutdown
System Failure
I/O Devices
If the VM/SP Monitor data collection to a spool file is taking place, a system shut­
down causes closing of the file and termination of monitoring. If data collection is
to tape, a system shutdown implies a MONITOR STOP TAPE command. Normal
command processing for the MONITOR STOP TAPE function is performed by the
system.
If the VM/SP system fails and data collection to a spool file is active, the spool file
is closed and preserved, except for the last buffer. If the VM/SP system fails and
data collection is active on tape, an attempt is made to write two tape marks,
rewind, and unload the tape. If the tape drive fails to rewind and unload, be sure to
write a tape mark before rewinding and unloading the tape. VM/SP Monitor data
collection is terminated by the system failure.
If VM/SP monitor data collection is active using tape, a supported tape drive must
be dedicated to the system for the duration of the monitoring. For accounting pur­
poses, all I/O is charged to the system.
Performance Observation and Analysis 57

VM/SP Monitor Data Volume and Overhead Use of the VM/SP Monitor usually requires that three pages be locked in storage
for the entire time the VM/SP Monitor is active; however, only two pages are
required if the single buffer option is used with only the PERFORM class of data
collection enabled. This reduces by three the number of page frames available for
paging. This significantly affects the performance of the rest of the system when
there is a limited number of page frames available for paging. PERFORM This class of data collection is activated once every 60 seconds (or as
defined by the MONITOR INTERVAL command), and records sys­
tem counters relevant to performance statistics. It is, therefore, a very
low overhead data collection option. RESPONSE This class collects terminal interaction data and, because of the human
factor, has a very low rate of occurrence relative to processor speeds.
Consequently, this class causes negligible overhead and produces a
low volume of data. SCHEDULE This class records the queue manipulation activity of the scheduler
and generates a record every time a user is added to the eligible list,
added to queue 1 or queue2, or removed from queue. The recording
overhead is very low. USER This class of data collection is active once every 60 seconds (or as
defined by the MONITOR INTERVAL command). Data is extracted
from each user's VMBLOK, including the system VMBLOK. The
overhead incurred is comparable with that of the statistical data of the PERFORM class; however, it increases with the number of users
logged onto the system. INSTSIM This class of data collection can give rise to large volumes of data
because of the frequency of privileged instructions in some virtual
machines. This may incur significant overhead. It should be activated
for short periods of time and preferably, though not necessarily, when
other classes of data collection are inactive. If the Virtual Machine
Assist feature is active for the virtual machine, the data volume and,
consequently, the CP overhead may be reduced. DAST AP This class of data collection samples device activity counts once every 60 seconds (or as defined by the MONITOR INTERVAL command)
and is a very low source of overhead, similar to the PERFORM and USER classes. SEEKS This class of data collection can give rise to large volumes of data
because every start I/O request to DASD is recorded via a MONI­ TOR CALL. SYSPROF This class of data collection is complementary to the SCHEDULE and DAST AP classes and results in a small amount of additional overhead.
It obtains more refined data on DASD resource usage.
58 VM/SP System Programmer's Guide