02/28/85 traffic_control_meters, tcm Syntax as a command: tcm {-control_args} Function: prints out the values of various traffic control meters. Control arguments: -counters, -ct prints out the number and frequency of certain paths through the traffic controller. -gen prints out general traffic control information. -queue, -qu prints out certain resource usage as a function of depth in the eligible queue. -report_reset, -rr generates a full report and then performs the reset operation. -reset, -rs resets the metering interval for the invoking process so that the interval begins at the last call with -reset specified. If -reset has never been given in a process, it is equivalent to having been specified at system initialization time. Access required: This command requires access to phcs_ or metering_gate_. Notes: If the traffic_control_meters command is given with no control arguments, it prints a full report. The following meters reflect activity of the traffic controller, and some constants used therein. They are printed if the -gen control argument is specified. Ave queue length is the average number of processes in the eligible and priority queues. This is the average number of ready, waiting, or running processes. Ave eligible is a recent average of the number of eligible processes. Response time is the average time between a process' receiving an interactive wakeup and the awarding of eligibility to the process. The response time seen by the user is larger than this meter. The following meters pertain to the number and frequency of certain paths through the traffic controller. They are printed if the -ct control argument is specified. Interactions is a count of, and the average time between, terminal interactions. Loadings is a count of, the average time between, and the number per interaction of process loadings. Blocks is a count of, and the average time between, calls to "block" to block some process. Wakeups is a count of, and the average time between, wakeup signals being sent. Schedulings is a count of, the average time between, and the number per interaction of trips through the scheduler/rescheduler function that caused priorities to be changed. Lost priority is the number of times the alarm clock went off indicating a priority process that had been running lost its eligibility because it had used up its eligible time; i.e., its eligible time exceeded the CPU quantum that the process remains in the queue. The process reenters the traffic controller to be rescheduled. Priority boosts is the number of times the alarm clock went off indicating a priority scheduling process on the ready list should be granted high priority; i.e., have its waiting time before rescheduling set to 0. The process is then resorted into the ready list with its new, higher priority. Wait Page is a count of, the average time between, and the number per interaction of calls to force some process to a wait state in order to wait for page transfer. Wait PTL is a count of, the average time between, and the number per interaction of calls to force some process to a wait state in order to wait for the page table lock. Wait Other is a count of, the average time between, and the number per interaction of calls to force some process to a wait state in order to wait for events other than page control events. Total Waits is a count of, the average time between, and the number per interaction of calls to force some process to a wait state. Notify Page is the number of, and average time between, calls to notify processes waiting for page transfer events. Notify PTL is the number of, and average time between, calls to notify processes waiting for page table unlockings. Notify Other is the number of, and average time between, calls to notify processes waiting for all other events. Total Notifies is the number of, and the average time between, notify calls (i.e., returning a waiting process to the ready state). Get Processor is the number of, and average time between, calls to get_processor. Get_processor is called at notify time to find a CPU on which to run the notified process. An idle process or lower priority running process is preempted. Pre-empts is a count of, average time between, and the number per interaction of process preemptions and timer runout faults. Getwork is the number of, and average time between, calls to getwork. Getwork is the dispatcher portion of the scheduler; it finds a process to run on the executing CPU. Retry getwork is the number of, and average time between, retries of the getwork function. Extra notifies is the number of, and average time between, notify calls that found no process waiting on the notified event. Last EN event is the last notified event for which no process was waiting. Notify timeout is the number of times a notify was not received by a waiting process within notify_timeout_interval (a tuning parameter). This is printed only if the count is nonzero. Last NTO event is the last event on which a notify timeout occurred. The following meters pertain to the eligible queue. They are printed if the -qu control argument is specified. Depth is the depth of the process within the eligible queue. A process deep in the eligible queue is run only if processes above it cannot run. %PF is the percentage of page faults that occurred from processes at this depth. TBPF is the average time between page faults at this depth. %GTW is the percentage of getwork calls being made when a member of this priority relinquishes control. TBS is the average time between getwork calls at this priority level. %CPU is the percentage of CPU time consumed by members of this priority. ----------------------------------------------------------- Historical Background This edition of the Multics software materials and documentation is provided and donated to Massachusetts Institute of Technology by Group BULL including BULL HN Information Systems Inc. as a contribution to computer science knowledge. This donation is made also to give evidence of the common contributions of Massachusetts Institute of Technology, Bell Laboratories, General Electric, Honeywell Information Systems Inc., Honeywell BULL Inc., Groupe BULL and BULL HN Information Systems Inc. to the development of this operating system. Multics development was initiated by Massachusetts Institute of Technology Project MAC (1963-1970), renamed the MIT Laboratory for Computer Science and Artificial Intelligence in the mid 1970s, under the leadership of Professor Fernando Jose Corbato. Users consider that Multics provided the best software architecture for managing computer hardware properly and for executing programs. Many subsequent operating systems incorporated Multics principles. Multics was distributed in 1975 to 2000 by Group Bull in Europe , and in the U.S. by Bull HN Information Systems Inc., as successor in interest by change in name only to Honeywell Bull Inc. and Honeywell Information Systems Inc. . ----------------------------------------------------------- Permission to use, copy, modify, and distribute these programs and their documentation for any purpose and without fee is hereby granted,provided that the below copyright notice and historical background appear in all copies and that both the copyright notice and historical background and this permission notice appear in supporting documentation, and that the names of MIT, HIS, BULL or BULL HN not be used in advertising or publicity pertaining to distribution of the programs without specific prior written permission. Copyright 1972 by Massachusetts Institute of Technology and Honeywell Information Systems Inc. Copyright 2006 by BULL HN Information Systems Inc. Copyright 2006 by Bull SAS All Rights Reserved