HP 3000 Manuals HP 3000 Manuals
Application Measurements
Application graphs reflect performance measurements summarized by
application. An application is a user-definable group of related
processes.
You can define up to 15 applications on MPE V systems and 31 applications
on MPE XL systems.
HP LaserRX/MPE predefines one application called OTHER. All processes
that do not belong to a user-defined application are summarized into the
OTHER application.
For more information on application definition, see HP LaserRX/MPE User's
Manual: Analysis Software.
Six sets of application measurements can be selected:
* Application Bottlenecks.
* Application Transaction Response.
* Application CPU Utilization.
* Application Response States.
* Application Queue Depth.
* Application Resource Usage.
For each set of application measurements, you can display two graphs
using the same graph window. Use the vertical scroll bar at the right
side of the graph:
* When the scroll box is at the top of the scroll bar, Graph 1 (a
ranked application summary) is displayed.
Summary graphs list the five busiest applications in the display
period. The criteria for "busiest" varies according to the type
of graph. The application labels on the top of the graph are in
ranked order. The busiest application for the period is on the
left.
* When the scroll box is not at the top of the scroll bar, Graph 2
(an application-by-application detail) is displayed.
Individual application graphs display variables for one
application at a time.
The following pages list variables for all application graphs.
Table A-19. Application Bottlenecks--Variables
------------------------------------------------------------------------------------------
| |
| Use the Application Bottlenecks graphs to display the CPU utilization and physical |
| disc I/Os for each application defined to HP LaserRX/MPE. Two Application Bottlenecks |
| graphs exist: |
| * Busiest Applications. This graph displays first when you select Application |
| Bottlenecks. |
| * Individual Applications. This graph displays when you scroll down on the |
| vertical scroll bar. |
| |
------------------------------------------------------------------------------------------
Table A-20. Application Bottlenecks Graph 1--Variables
---------------------------------------------------------------------------------------------
| |
| The initial graph when Application Bottlenecks is drawn shows the five busiest |
| applications (in terms of CPU used) in the display period. The application names on |
| the graph are displayed in decreasing order by average percent of CPU used. The |
| measurement presented is CPU Utilization for each application. |
| |
| Y-Axis: Percent of CPU utilized (up to 100). |
| |
| X-Axis: Choose the scale using X-Axis options. |
| |
---------------------------------------------------------------------------------------------
| | |
| Busiest | Application with the highest utilization of the CPU for the period |
| Application | displayed. The measurement reflected in the graph is CPU utilization. A |
| | second graph is displayed when you scroll down on the vertical scroll bar. |
| | |
---------------------------------------------------------------------------------------------
| | |
| Second | Application with the second highest utilization of the CPU for the period |
| Busiest | displayed. The measurement reflected in the graph is CPU Utilization. |
| Application | |
| | |
---------------------------------------------------------------------------------------------
| | |
| Third | Application with the third highest utilization of the CPU for the period |
| Busiest | displayed. The measurement reflected in the graph is CPU Utilization. |
| Application | |
| | |
---------------------------------------------------------------------------------------------
| | |
| Fourth | Application with the fourth highest utilization of the CPU for the period |
| Busiest | displayed. The measurement reflected in the graph is CPU Utilization. |
| Application | |
| | |
---------------------------------------------------------------------------------------------
| | |
| Fifth | Application with the fifth highest utilization of the CPU for the period |
| Busiest | displayed. The measurement reflected in the graph is CPU Utilization. |
| Application | |
| | |
---------------------------------------------------------------------------------------------
Table A-21. Application Bottlenecks Graph 2--Variables
---------------------------------------------------------------------------------------------
| |
| The second Application Bottlenecks graph displays CPU and disc activity for up to 32 |
| applications (31 are user-defined; 1 is HP LaserRX-defined, called OTHER). |
| |
| Note: MPE V systems are limited to 16 applications (15 user-defined). |
| |
| Measurements displayed are: CPU Util, Phys Disc. You can display these metrics for |
| individual applications by using the vertical scroll bar. |
| |
| Y-Axis: I/Os per second (0 to 100) for Phys Disc. Percent of time (0 to 100) for |
| CPU. |
| |
| X-Axis: Choose the scale using X-Axis options. |
| |
---------------------------------------------------------------------------------------------
| | |
| Application | Indicates which application's data is being displayed on the graph. |
| | |
---------------------------------------------------------------------------------------------
| | |
| CPU Util | The percentage of elapsed time that the CPU is busy executing instructions |
| | on behalf of processes in this application. On MPE V systems, it does not |
| | include CPU spent in managing main memory. On MPE XL systems, it includes |
| | CPU time spent in managing main memory for processes that belong to this |
| | application. |
| | |
---------------------------------------------------------------------------------------------
| | |
| Phys Disc | The number of transfers per second made to or from the disc drives on |
| | behalf of user programs in this application. Does not include transfers |
| | used in managing memory. On MPE V systems, it does not include transfers |
| | used in managing memory. On MPE XL systems, memory management transfers |
| | are included in the application disc transfer value. |
| | |
---------------------------------------------------------------------------------------------
Table A-22. Application Transaction Response--Variables
------------------------------------------------------------------------------------------
| |
| Use the Application Transaction Response graphs to display terminal transaction |
| activity and response time for each application defined to HP LaserRX/MPE. Two |
| Application Transaction Response graphs exist: |
| * Busiest Applications--This graph displays first when you select Application |
| Transaction Response. |
| * Individual Applications--This graph displays when you scroll down on the |
| vertical scroll bar. |
| |
------------------------------------------------------------------------------------------
Table A-23.
----------------------------------------------------------------------------------------------------------------
| CSI243sIX897CSI32s |
| |
| The initial graph when Application Transaction Response is drawn shows the five |
| busiest applications in the display period. The application names on the graph are |
| displayed in decreasing order by average terminal transaction rate. |
| |
| The measurement presented is the Rate (x1000) for each application. |
| |
| Y-Axis: Number of transactions per hour (up to 20,000 on a linear scale; up to |
| 1,000,000 on a logarithmic scale). Each unit represents 1000 transactions. |
| |
| X-Axis: Choose the scale using X-Axis options. |
| |
----------------------------------------------------------------------------------------------------------------
| | |
| Highest | Application with the highest number of terminal transactions per hour. |
| Trans Rate | The measurement reflected in the graph is Rate (x1000). |
| | |
----------------------------------------------------------------------------------------------------------------
| | |
| Second | Application with the second highest number of terminal transactions per |
| Highest | hour. The measurement reflected in the graph is Rate (x1000). |
| Trans Rate | |
| | |
----------------------------------------------------------------------------------------------------------------
| | |
| Third | Application with the third highest number of terminal transactions per |
| Highest | hour. The measurement reflected in the graph is Rate (x1000). |
| Trans Rate | |
| | |
----------------------------------------------------------------------------------------------------------------
| | |
| Fourth | Application with the fourth highest number of terminal transactions per |
| Highest | hour. The measurement reflected in the graph is Rate (x1000). |
| Trans Rate | |
| | |
----------------------------------------------------------------------------------------------------------------
| | |
| Fifth | Application with the fifth highest number of terminal transactions per |
| Highest | hour. The measurement reflected in the graph is Rate (x1000). |
| Trans Rate | |
| | |
----------------------------------------------------------------------------------------------------------------
Table A-24.
----------------------------------------------------------------------------------------------------------------
| CSI243sIX898CSI32s |
| |
| The second Application Transaction Response graph displays terminal transaction rates |
| and response times for up to 32 applications (31 user-defined; 1 HP LaserRX-defined, |
| called OTHER). Note: MPE V systems are limited to 16 applications (15 user-defined). |
| Metrics displayed: First Response, Prompt, Rate (x1000), Think. You can display |
| these metrics for individual applications by using the vertical scroll bar. Y-Axis: |
| Number of seconds (up to 20 in linear scaling; up to 100 on a logarithmic scale), or |
| number of transactions (up to 20,000 on a linear scale; up to 100,000 on a logarithmic |
| scale). Each unit represents 1000 transactions. X-Axis: Choose the scale using |
| X-Axis options. |
| |
----------------------------------------------------------------------------------------------------------------
| | |
| Application | Indicates which application's data is being displayed on the graph. |
| | |
----------------------------------------------------------------------------------------------------------------
| | |
| First | The average time between pressing return-enter on the keyboard and the |
| Response | time the first line is written to the terminal screen. |
| | |
----------------------------------------------------------------------------------------------------------------
| | |
| Prompt | The average time between pressing return-enter and the next prompt to the |
| | user. |
| | |
----------------------------------------------------------------------------------------------------------------
| | |
| Rate (x1000) | The number of terminal transactions per hour. (Each unit on the graph |
| | represents 1000 transactions.) A terminal transaction is the activity |
| | that occurs between reads issued to a terminal. Interactive and batch |
| | processes (but not system processes) that read and write to a terminal can |
| | generate terminal transactions. |
| | |
----------------------------------------------------------------------------------------------------------------
| | |
| Think | The average time between receiving a prompt at the terminal and the next |
| | carriage return. |
| | |
----------------------------------------------------------------------------------------------------------------
NOTE On MPE XL systems before A.40.00 (2.1), the values displayed on
this graph are approximations.
Table A-25. Application CPU Utilization--Variables
------------------------------------------------------------------------------------------
| |
| Use the Application CPU Utilization graphs to display CPU Utilization for each |
| application defined to HP LaserRX/MPE in each of the four CPU scheduling queues. Two |
| Application CPU Utilization graphs exist: |
| 1. Busiest Applications--This graph displays first when you select Application CPU |
| Utilization. |
| 2. Individual Applications--This graph displays when you scroll down on the |
| vertical scroll bar. |
| |
------------------------------------------------------------------------------------------
Table A-26.
----------------------------------------------------------------------------------------------------------------
| CSI243sIX903CSI32s |
| |
| The initial graph when Application CPU Utilization is drawn shows the five busiest |
| applications (in terms of CPU used) in the display period. The application names on |
| the graph are displayed in decreasing order by average percent of CPU used. The |
| measurement presented is CPU Utilization for each application. |
| |
| Y-Axis: Percent of CPU utilized (up to 100). |
| |
| X-Axis: Choose the scale using X-Axis options. |
| |
----------------------------------------------------------------------------------------------------------------
| | |
| Busiest | Application with the highest utilization of the CPU for the period |
| Application | displayed. The measurement reflected in the graph is CPU utilization. |
| | |
----------------------------------------------------------------------------------------------------------------
| | |
| Second | Application with the second highest utilization of the CPU for the period |
| Busiest | displayed. The measurement reflected in the graph is CPU Utilization. |
| Application | |
| | |
----------------------------------------------------------------------------------------------------------------
| | |
| Third | Application with the third highest utilization of the CPU for the period |
| Busiest | displayed. The measurement reflected in the graph is CPU Utilization. |
| Application | |
| | |
----------------------------------------------------------------------------------------------------------------
| | |
| Fourth | Application with the fourth highest utilization of the CPU for the period |
| Busiest | displayed. The measurement reflected in the graph is CPU Utilization. |
| Application | |
| | |
----------------------------------------------------------------------------------------------------------------
| | |
| Fifth | Application with the fifth highest utilization of the CPU for the period |
| Busiest | displayed. The measurement reflected in the graph is CPU Utilization. |
| Application | |
| | |
----------------------------------------------------------------------------------------------------------------
Table A-27. Application CPU Utilization Graph 2--Variables
---------------------------------------------------------------------------------------------
| |
| The second Application CPU Utilization graph displays individual activity for up to 32 |
| applications (31 user-defined; 1 HP LaserRX-defined, called OTHER). Note: MPE V |
| systems are limited to 16 applications (15 user-defined). Individual application CPU |
| utilization is shown by queue. CS DS ES LL. You can display these metrics for |
| individual applications by using the vertical scroll bar. |
| |
| Y-Axis: Percent of CPU utilized (up to 100). |
| |
| X-Axis: Choose the scale using X-Axis options. |
| |
---------------------------------------------------------------------------------------------
| | |
| Application | Indicates which application's data is being displayed on the graph. |
| | |
---------------------------------------------------------------------------------------------
| | |
| CS | The percentage of elapsed time the CPU is busy executing instructions for |
| | all processes in the selected application whose scheduling queue is CS. CS |
| | queue assignment can be by default or changed by the GETPRIORITY |
| | intrinsic. |
| | |
---------------------------------------------------------------------------------------------
| | |
| DS | The percentage of elapsed time the CPU is busy executing instructions for |
| | all processes in the selected application whose scheduling queue is DS. DS |
| | queue assignment can be by default or changed by the GETPRIORITY |
| | intrinsic. |
| | |
---------------------------------------------------------------------------------------------
| | |
| ES | The percentage of elapsed time the CPU is busy executing instructions for |
| | all processes in the selected application whose scheduling queue is ES. ES |
| | queue assignment can be by default or changed by the GETPRIORITY |
| | intrinsic. |
| | |
---------------------------------------------------------------------------------------------
| | |
| LL | The percentage of elapsed time the CPU is busy executing instructions for |
| | all processes in the selected application whose scheduling queue is LL. |
| | (Linear queue, AS, or BS). LL queue assignment can be by default or |
| | changed by the GETPRIORITY intrinsic. |
| | |
---------------------------------------------------------------------------------------------
Table A-28. Application Response States Variables
------------------------------------------------------------------------------------------
| |
| Use the Application Response States graphs to display application response states |
| ranked by CPU usage. Two Application Response States graphs exist: |
| |
| 1. Busiest Applications--This graph displays first when you select Application |
| Response States. |
| 2. Individual Applications--This graph displays when you scroll down on the |
| vertical scroll bar. |
| |
------------------------------------------------------------------------------------------
Table A-29. Application Response States Graph 1--Variables
---------------------------------------------------------------------------------------------
| |
| The initial graph when Application Response States is drawn shows the five busiest |
| applications in the display period. Application labels on the graph are ranked from |
| high to low utilization. The measurement presented is CPU usage for each application. |
| |
| |
| Y-Axis: Percent of CPU utilized (up to 100). |
| |
| X-Axis: Choose the scale using X-Axis options. |
| |
---------------------------------------------------------------------------------------------
| | |
| Busiest | Application with the highest utilization of the CPU for the period |
| Application | displayed. The measurement reflected in the graph is CPU utilization. |
| | |
---------------------------------------------------------------------------------------------
| | |
| Second | Application with the second highest utilization of the CPU for the period |
| Busiest | displayed. The measurement reflected in the graph is CPU Utilization. |
| Application | |
| | |
---------------------------------------------------------------------------------------------
| | |
| Third | Application with the third highest utilization of the CPU for the period |
| Busiest | displayed. The measurement reflected in the graph is CPU Utilization. |
| Application | |
| | |
---------------------------------------------------------------------------------------------
| | |
| Fourth | Application with the fourth highest utilization of the CPU for the period |
| Busiest | displayed. The measurement reflected in the graph is CPU Utilization. |
| Application | |
| | |
---------------------------------------------------------------------------------------------
| | |
| Fifth | Application with the fifth highest utilization of the CPU for the period |
| Busiest | displayed. The measurement reflected in the graph is CPU Utilization. |
| Application | |
| | |
---------------------------------------------------------------------------------------------
Table A-30. Application Response States Graph 2--Variables
---------------------------------------------------------------------------------------------
| |
| The second Application Response States graph displays the average amount of time a |
| process in the application spent using or waiting on system resources. Individual |
| response states are displayed for up to 32 applications (31 user-defined; 1 HP |
| LaserRX-defined, called OTHER). |
| |
| Note: MPE V systems are limited to 16 applications (15 user-defined). |
| |
| Measurements displayed are: CPU, Wait CPU, Wait Disc, Wait Mem, Impeded. |
| |
| The area between Impeded and 100% is OtherIO, which can include such things as waiting |
| for tape transfers. You can display these metrics for individual applications by |
| using the vertical scroll bar. |
| |
| Y-Axis: Percentage of response time (0-100). 100% equals the average time processes |
| in the application spent waiting on short-term events (using CPU, waiting on CPU, |
| waiting on disc, waiting on memory, waiting on impedes, waiting on other I/O), but not |
| including time spent waiting on terminal input or other long-duration reasons. |
| X-Axis: Choose the scale using X-Axis options. |
| |
---------------------------------------------------------------------------------------------
| | |
| Application | Indicates which application's data is being displayed on the graph. |
| | |
---------------------------------------------------------------------------------------------
| | |
| CPU | The percent of the overall application response (including jobs) using the |
| | CPU. |
| | |
---------------------------------------------------------------------------------------------
| | |
| Wait CPU | The percent of the overall application response (including jobs) waiting |
| | to use the CPU. |
| | |
---------------------------------------------------------------------------------------------
| | |
| Wait Disc | The percent of the overall application response (including jobs) waiting |
| | for disc transfers to complete. |
| | |
---------------------------------------------------------------------------------------------
| | |
| Wait Mem | The percent of the overall application response (including jobs) waiting |
| | for memory. |
| | |
---------------------------------------------------------------------------------------------
| | |
| Impeded | The percent of the overall application response (including jobs) impeded. |
| | A process may be impeded when it is waiting on a software lock or |
| | synchronization mechanism. It is not uncommon for file and database locks |
| | to cause a process to become impeded, although this is by no means the |
| | only way they so become. |
| | |
---------------------------------------------------------------------------------------------
Table A-31. Application Queue Depth--Variables
------------------------------------------------------------------------------------------
| |
| Use the Application Queue Depth graphs to display queue depth in terms of CPU, disc, |
| memory, and impede for each application defined to HP LaserRX/MPE. Two Application |
| Queue Depth graphs exist: |
| 1. Busiest Applications--This graph displays first when you select Application |
| Queue Depth. |
| 2. Individual Applications--This graph displays when you scroll down on the |
| vertical scroll bar. |
| |
------------------------------------------------------------------------------------------
Table A-32. Application Queue Depth Graph 1--Variables
---------------------------------------------------------------------------------------------
| |
| The initial graph when Application Queue Depth is drawn shows the five busiest |
| applications in the display period. For each application, measurements represent |
| total queue depth (the number of processes queued on CPU, disc, memory, and impede). |
| Application labels on the graph are ranked from high to low queue depth. |
| |
| Y-Axis: Average number of processes (up to 10 on a linear scale; up to 100 on a |
| logarithmic scale). |
| |
| X-Axis: Choose the scale using X-Axis options. |
| |
---------------------------------------------------------------------------------------------
| | |
| Highest | Application with the highest queue depth. |
| Queue Depth | |
| | |
---------------------------------------------------------------------------------------------
| | |
| Second | Application with the second highest queue depth for the period displayed. |
| Highest | |
| Queue Depth | |
| | |
---------------------------------------------------------------------------------------------
| | |
| Third | Application with the third highest queue depth for the period displayed. |
| Highest | |
| Queue Depth | |
| | |
---------------------------------------------------------------------------------------------
| | |
| Fourth | Application with the fourth highest queue depth for the period displayed. |
| Highest | |
| Queue Depth | |
| | |
---------------------------------------------------------------------------------------------
| | |
| Fifth | Application with the fifth highest queue depth for the period displayed. |
| Highest | |
| Queue Depth | |
| | |
---------------------------------------------------------------------------------------------
Table A-33. Application Queue Depth Graph 2--Variables
---------------------------------------------------------------------------------------------
| |
| The second Application Queue Depth graph displays individual queue depths for up to 32 |
| applications (31 user- defined; 1 HP LaserRX-defined, called OTHER). Note: MPE V |
| systems are limited to 16 applications (15 user-defined). Measurements displayed are |
| the average number of processes belonging to the application that are queued waiting |
| for: CPU, disc, memory, impede. You can display these metrics for individual |
| applications by using the vertical scroll bar. |
| |
| Y-Axis: Average number of processes in the queue (up to 10 on a linear scale; up to |
| 100 on a logarithmic scale). |
| |
| X-Axis: Choose the scale using X-Axis options. |
| |
---------------------------------------------------------------------------------------------
| | |
| Application | Indicates which application's data is being displayed on the graph. |
| | |
---------------------------------------------------------------------------------------------
| | |
| CPU | The average number of processes waiting on or using the CPU. This is an |
| | indication of CPU load. |
| | |
---------------------------------------------------------------------------------------------
| | |
| Disc | The average number of processes blocked, waiting on a disc resource. This |
| | is an indication of disc I/O load. |
| | |
---------------------------------------------------------------------------------------------
| | |
| Memory | The average number of processes blocked, waiting on memory. This is an |
| | indication of memory load. |
| | |
---------------------------------------------------------------------------------------------
| | |
| Impede | The average number of processes blocked, waiting on impedes. This is an |
| | indication of impede load. |
| | |
---------------------------------------------------------------------------------------------
Table A-34. Application Resource Usage--Variables
------------------------------------------------------------------------------------------
| |
| Use the Application Resource Usage graphs to display the resources used per terminal |
| transaction for each application defined to HP LaserRX/MPE. |
| |
| These graphs are useful only for applications that complete most of their activity as |
| a result of terminal transactions. |
| |
| Two Application Resource Usage graphs exist: |
| 1. Busiest Applications--This graph displays first when you select Application |
| Resource Usage. |
| 2. Individual Applications--This graph displays when you scroll down on the |
| vertical scroll bar. |
| |
------------------------------------------------------------------------------------------
Table A-35. Application Resource Usage Graph 1--Variables
---------------------------------------------------------------------------------------------
| |
| The initial graph when Application Resource Usage is drawn shows the five busiest |
| applications in the display period. |
| |
| For each application, measurements represent transaction rate per hour (x1000). |
| Application labels on the graph are ranked from high to low rate. |
| |
| Y-Axis: Number of transactions per hour (up to 20,000 linear; up to 100,000 on a |
| logarithmic scale). Each unit represents 1,000 transactions per hour. |
| |
| X-Axis: Choose the scale using X-Axis options. |
| |
---------------------------------------------------------------------------------------------
| | |
| Highest | Application with the highest number of terminal transactions per hour. |
| Trans Rate | The measurement reflected in the graph is Rate (x1000). |
| | |
---------------------------------------------------------------------------------------------
| | |
| Second | Application with the second highest number of terminal transactions per |
| Highest | hour. The measurement reflected in the graph is Rate (x1000). |
| Trans Rate | |
| | |
---------------------------------------------------------------------------------------------
| | |
| Third | Application with the third highest number of terminal transactions per |
| Highest | hour. The measurement reflected in the graph is Rate (x1000). |
| Trans Rate | |
| | |
---------------------------------------------------------------------------------------------
| | |
| Fourth | Application with the fourth highest number of terminal transactions per |
| Highest | hour. The measurement reflected in the graph is Rate (x1000). |
| Trans Rate | |
| | |
---------------------------------------------------------------------------------------------
| | |
| Fifth | Application with the fifth highest number of terminal transactions per |
| Highest | hour. The measurement reflected in the graph is Rate (x1000). |
| Trans Rate | |
| | |
---------------------------------------------------------------------------------------------
Table A-36. Application Resource Usage Graph 2--Variables
---------------------------------------------------------------------------------------------
| |
| The second Application Resource Usage graph displays resource usage for up to 32 |
| individual applications (31 are user- defined; 1 is HP LaserRX-defined, called OTHER). |
| |
| |
| Note: MPE V systems are limited to 16 applications (15 user-defined). |
| |
| Measurements displayed are: Rate (x1000), CPU/Tran, Disc I/O /Tran. You can display |
| these metrics for individual applications by using the vertical scroll bar. |
| |
| Y-Axis: Transaction rate (1,000 transactions per hour) or CPU milliseconds per |
| transaction, or disc I/Os per transaction (up to 1,000 on a linear scale; up to 10,000 |
| on a logarithmic scale). |
| |
| X-Axis: Choose the scale using X-Axis options. |
| |
---------------------------------------------------------------------------------------------
| | |
| Application | Indicates which application's data is being displayed on the graph. |
| | |
---------------------------------------------------------------------------------------------
| | |
| Rate (x1000) | The number of terminal transactions per hour. (Each unit on the graph |
| | represents 1000 transactions.) A terminal transaction is the activity |
| | that occurs between reads issued to a terminal. Interactive and batch |
| | processes (but not system processes) that read and write to a terminal can |
| | generate terminal transactions. |
| | |
---------------------------------------------------------------------------------------------
| | |
| CPU/Tran | The number of CPU milliseconds used per transaction. The CPU for this |
| | application (in all queues) is divided by the number of interactive |
| | transactions unless no terminal transactions were completed in the time |
| | interval. If no transactions were completed, then this value is missing. |
| | |
---------------------------------------------------------------------------------------------
| | |
| Disc/Tran | The number of physical disc transfers per transaction. The sum of the |
| | physical disc transfers is divided by the number of interactive |
| | transactions unless no terminal transactions were completed in the time |
| | interval. If no transactions were completed, then this value is missing.. |
| | |
---------------------------------------------------------------------------------------------