Performance Report columns

Each report includes columns of information. Look here for descriptions of that information.

>8.0

(Component) The number of times the response time was greater than 8 seconds.

%Write Cache Overruns

(Component) Percent of Write Cache Overruns during the collection interval.

---------- (pgmname)

(Transaction) The transaction totals record. For example, ---------- QUYLIST,. This report line occurs each time the job has an active-to-wait transaction. Totals are created for Rsp* (response time), CPU Secs, and I/O counts for the transaction.

A-I Wait /Tns

(Transaction) The average time, in seconds, of active-to-ineligible wait time per transaction. If this value is high, it may be because the time-slice value is set too low for many of the interactive jobs. Consider increasing the time slice-value.

Aborts Recd

(Resource Interval) The number of frames received that contained HDLC abort indicators. This indicates that the remote equipment ended frames before they were complete.

Act Jobs

(Job Interval) The number of selected jobs (interactive or noninteractive, depending on the report section) that were active during the interval.

Act Level

(Component) Initial pool activity level.

Act Lvl

(System, Pool Interval) Activity level. For the Pool Activity section of the Pool Interval Report, the activity level of the pool during the interval. For the Storage Pool Utilization section of the System Report, the activity level at the time of the first sample interval.

Act-Inel

(System, Component) Average number of active-to-ineligible job state transitions per minute.

Act-Wait

(System, Component) Number of transitions per minute from active state to wait state by processes assigned to this pool.

ACTIVE

(Job Trace) The time the job was processing.

Active Devices

(System) Average number of active devices on the line.

Active display stations (local or remote)

(System) The number of local or remote display stations entering transactions during the measurement period.

Active Jobs

(Transaction) The number of interactive jobs that were active during the interval.

Active Jobs Per Interval

(System) Average number of jobs of this type that were active per sample interval.

Active K/T /Tns

(Transaction) An average think time and keying time (or the delay time between the end of one transaction and the start of the next transaction), in seconds, for the active work stations (described under Est of AWS). Active K/T /TNS delay time differs from Key/Think /TNS delay time in that any delay time greater than 600 seconds has been rounded to 600 seconds. This technique is used to reduce the effect of very casual users (those who may do intermittent work or leave their work stations for long periods of time) on the estimate of active work stations.

Active Wrk Stn

(Resource Interval) The number of work stations with activity.

Active/Rsp

(Transaction) The time the job spends (either waiting or active) during transaction processing, while it holds an activity level.

Activity level

(System) The sum of activity levels for all interactive pools that had interactive job activity running in them.

Activity Level Time

(Transaction) A breakdown of the transaction time spent ACTIVE, waiting on a SHORT WAIT, and waiting on a SEIZE/CFT (seize conflict). The SHORT WAIT and SEIZE CFT time are included under ACTIVITY LEVEL TIME, because the activity-level slot is not given up during these times. Note that the seize conflict time is included in the active time, not added to it to get transaction/response time, as is the case for waiting time.

Arith Ovrflw

(Component, Job Interval) The number of arithmetic overflow exceptions that occurred for the selected interactive jobs during the interval.

ASP ID

(System, Resource Interval) Auxiliary storage pool identifier.

ASP Rsc Name

(System, Resource) Identifies the ASP resource name to which the disk unit was allocated at collection time.

Async

(System, Component, Transaction, Job Interval) The number of asynchronous disk I/O operations started by the selected interactive jobs during the interval. The job that starts the I/O operation may continue processing without having to wait for the I/O operation to complete. The I/O operation is completed by a background system test.

Async DIO /Tns

(Transaction) The sum of the averages of the asynchronous DB READ, DB WRITE, NDB READ, and NDB WRITE requests (the average number of asynchronous I/O requests per transaction for the job).

Async Disk I/O

(System, Component, Transaction) Number of asynchronous disk input/output operations per transaction.

Async Disk I/O per Second

(Component) Average asynchronous disk I/O operations per second.

Async Disk I/O Requests

(Transaction) The total number of asynchronous disk I/O requests for the given combination of priority, job type, and pool.

Async I/O /Sec

(Job Interval) The average number of asynchronous disk I/O operations started per second by the job during the interval. This is calculated by dividing the asynchronous disk I/O count by the elapsed time.

Async I/O Per Second

(Job Interval) The average number of asynchronous disk I/O operations started per second by the selected noninteractive jobs during the interval.

Async Max

(Transaction) Listed under Average DIO/Transaction, the maximum number of asynchronous DBR, NDBR, and WRT I/O requests encountered for any single transaction by that job. If the job is not an interactive or autostart job type, the total disk I/O for the job is listed here.

Async Sum

(Transaction) Listed under Average DIO/Transaction, the sum of the averages of the asynchronous DBR, NDBR, and WRT requests (the average number of asynchronous I/O requests per transaction for the job).

Asynchronous DBR

(System, Job Interval, Pool Interval) The average number of asynchronous database read operations on the disk per transaction for the job during the intervals. This is calculated by dividing the asynchronous database read count by the transactions processed. This field is not printed if the jobs in the system did not process any transactions. For the Resource Utilization section of the System Report, it is the number of asynchronous database read operations per second.

The asynchronous I/O operations are performed by system asynchronous I/O tasks.

Asynchronous DBW

(System, Job Interval) The average number of asynchronous database write operations on the disk per transaction for the selected jobs during the interval. This is calculated by dividing the asynchronous database write count by the transactions processed. This field is not printed if the jobs in the system did not process any transactions. For the Resource Utilization section of the System Report, it is the number of asynchronous database read operations per second.

The asynchronous I/O operations are performed by system asynchronous I/O tasks.

Asynchronous disk I/O per transaction

(System) The average number of asynchronous physical disk I/O operations per interactive transaction.

Asynchronous NDBR

(System, Job Interval, Pool Interval) The average number of asynchronous nondatabase read operations per transaction for the jobs in the system during the interval. This is calculated from the asynchronous nondatabase read count divided by the transactions processed. This field is not printed if the jobs in the system did not process any transactions. For the Resource Utilization section of the System Report, it is the asynchronous nondatabase read operations per second.

The asynchronous I/O operations are performed by system asynchronous I/O tasks.

Asynchronous NDBW

(System, Job Interval, Pool Interval) The average number of asynchronous nondatabase write operations per transaction for the jobs in the system during the interval. This is calculated from the asynchronous nondatabase write count divided by the transactions processed. This field is not printed if the jobs in the system did not process any transactions. For the Resource Utilization section of the System Report, it is the number of asynchronous nondatabase write operations per second.

The asynchronous I/O operations are performed by system asynchronous I/O tasks.

Avail Local Storage (K)

(Resource Interval) The number of kilobytes of free local storage in the IOP.

Available Storage

(Component) Available local storage (in bytes). The average number of bytes of available main storage in the IOP. The free local storage is probably not joined because it has broken into small pieces.

Average

(Transaction) The average value of the item described in the column for all transactions.

AVERAGE

(Job Trace) Averages for the fields. The entry on the AVERAGE line in the SEQUENCE column shows the number of STRTNS and ENDTNS pairs encountered. For an interactive job, this is the number of transactions entered while the trace was on if the default STRTNS and ENDTNS values were used.

Average Disk Activity Per Hour

(Component) See Disk Arm Seek Distance

Average DIO/Transaction

(Transaction) Seven columns of information about physical disk I/O counts. Physical I/O contrasts with logical I/O shown elsewhere in these reports. A logical I/O is a request sent at the program level that might result in an access to auxiliary storage (DASD). A physical I/O refers to those requests that actually result in access to auxiliary storage.

Synchronous DBR
Synchronous NDBR
Synchronous Wrt
Synchronous Sum
Synchronous Max
Async Sum
Async Max

Average K per I/O

(Resource Interval) The average number of kilobytes transferred during each disk read or write operation.

Average Phys I/O /Sec

(Resource Interval) The average number of physical disk read and write operations per second made on all disks on the system.

Average Reads/Sec

(Resource Interval) The average number of physical disk read operations per second made on all disks on the system.

Average Response

(System) Average response time (in seconds) for interactive transactions. The Total/Average interactive response time does not include transactions for DDM server jobs.

Average Response Time

(System) Average disk response time per I/O operation.

Average Response Time (seconds)

(System) The average interactive response time.

Average Service Time

(System) Average disk service time per I/O operation. This is the amount of time a request would take if there were no contention.

Average Wait Time

(System) Average disk wait time per I/O operation. Normally due to contention.

Average Writes/Sec

(Resource Interval) The average number of physical disk write operations per second made on all disks on the system.

Avg CPU /Tns

(Transaction) The average number of processing unit seconds per transaction that fell in the given category.

Avg K/T /Tns

(Transaction) The average think time and keying time (or the delay time between transaction boundaries), in seconds, for the interactive jobs.

Avg Length

(Lock) The average number of milliseconds a lock or seize was held.

Avg Rsp (Sec)

(Transaction) The average transaction response time in seconds.

Avg Rsp /Tns

(Transaction) The average response per transaction (in seconds) for the transactions that fell into the given category.

Avg Rsp Time

(Component) Average transaction response time.

Avg Sec Locks

(Transaction) The average length of a lock in seconds attributed to interactive or noninteractive waiters.

Avg Sec Seizes

(Transaction) The average length of a seize in seconds attributed to interactive or noninteractive waiters.

Avg Time per Service

(Resource Interval) The amount of time a disk arm uses to process a given request.

Avg Util

(System, Resource Interval) On the Disk Utilization Summary of the Resource Report, the average percentage of available time that disks were busy. It is a composite average for all disks on the system. On the Communications Summary of the System Report, the average percentage of line capacity used during the measured time interval.

Batch asynchronous I/O per second

(System) The average number of asynchronous physical disk I/O operations per second of batch processing.

Batch CPU seconds per I/O

(System) The average number of system processing unit seconds used by all batch jobs for each I/O performed by a batch job.

Batch CPU Utilization

(Component) Percentage of available processing unit time used by the jobs that the system considers to be batch.

For a multiple-processor system, this is the average use across all processors.

Batch impact factor

(System) Batch workload adjustment for modeling purposes.

Batch permanent writes per second

(System) The average number of permanent write operations per second of batch processing.

Batch synchronous I/O per second

(System) The average number of synchronous physical disk I/O operations per second of batch processing.

BCPU / Synchronous DIO

(Transaction) The average number of batch processor unit seconds per synchronous disk I/O operation.

Bin

(Transaction) The number of binary overflow exceptions.

Binary Overflow

(Component) Number of binary overflows per second.

BMPL - Cur and Inl

(Transaction) The number of jobs currently in the activity level (beginning current multiprogramming level), and the number of jobs on the ineligible queue (beginning ineligible multiprogramming level) for the storage pool that the job ran in when the job left the wait state (the beginning of the transaction).

Multiprogramming level (MPL) is used interchangeably with activity level.

Bundle Wait Count

(Component) Total number of times the tasks and jobs waited for journal bundles to be written to disk.

Bundle Wait Pct

(Component) Percentage of time (relative to the interval elapsed time) spent waiting for journal bundles to be written to disk.

Bundle Writes System

(Component) Number of bundle writes to internal system journals. A bundle write is a group of journal entries which are deposited together by the system.

Bundle Writes User

(Component) Number of bundle writes to user-created journals. A bundle write is a group of journal entries which are deposited together by the system.

Bytes per Second Received

(System) Average number of bytes received per second.

Bytes per Second Transmitted

(System) Average number of bytes transmitted per second.

Bytes Recd per Sec

(Resource Interval) The average number of bytes received per second.

Bytes Trnsmitd per Sec

(Resource Interval) The average number of bytes transmitted per second.

Category

(Transaction) A group of transactions categorized together. In the Analysis by Interactive Transaction Category, the transactions are categorized by the processing unit model. The boundary values that are used to separate the transactions are given in the Avg CPU /Tns column. For the Analysis by Interactive Response Time, they are categorized by their response time. For the Analysis by Interactive Key/Think Time, they are categorized by their key/think time.

Cache Hit Statistics

(Component) Statistics data about use of cache including:

The percent of Device Cache Read Hit for each arm.
The percent of Controller Cache Read Hit for each arm.
The percent of efficiency of write cache

Device read: Device Read is the number of Device Cache Read Hits (DSDCRH) divided by number of Device Read Operations (DSDROP), expressed as a percent
Controller read: Controller Read is the number Controller Cache Read Hits (DSCCRH) divided by number of Read Commands (DSRDS), expressed as a percent.
Write efficiency: Write efficiency is the difference between Write Commands (DSWRTS) and Device Write Operations (DSDWOP) divided by Write Commands (DSWRTS), expressed as a percent.
EACS Read: The percent of read hits by the Extended Adaptive Cache Simulator.
EACS Resp: The percent of response time improvement by the Extended Adaptive Cache Simulator.

Channel

(Resource Interval) The B-channel used by the IDLC line. (special condition)

Cmn

(Job Interval) The number of communications I/O operations performed by the selected interactive jobs during the interval.

Cmn I/O

(Component) Number of communications operations (Get, Put).

Cmn I/O Per Second

(Job Interval) The average number of communications I/O operations performed per second by the selected noninteractive jobs during the interval.

Collision Detect

(Resource Interval) The number of times that the terminal equipment (TE) detected that its transmitted frame had been corrupted by another TE attempting to use the same bus.

Commit Ops

(Component) Commit operations performed. Includes application and system-provided referential integrity commits.

Communications I/O Count

(System) Number of communications I/O operations.

Communications I/O Get

(System) Number of communication get operations per transaction.

Communications I/O Put

(System) Number of communication put operations per transaction.

Communications Lines

(System, Component, Job Interval, Pool Interval) For the Report Selection Criteria, the list of communications lines selected to be included (SLTLINE parameter) or excluded (OMTLINE parameter). These are the communications line names you specify.

Control Units

(System, Component, Job Interval, Pool Interval) The list of control units selected to be included (SLTCTL parameter) or excluded (OMTCTL parameter). These are the controller names you specify.

Count

(Transaction, Lock) The number of occurrences of the item in the column. For example, in a lock report, it is the number of locks or seizes that occurred.

CPU

(Transaction) The total processing unit seconds used by the jobs with a given priority.

CPU

(Job Trace) The approximation of the CPU used on this trace entry. This is a calculated value based on the time used and the CPU model being run.

CPU /Tns

(Transaction, Job Interval) The amount of available processing unit time per transaction in seconds.

CPU Model

(System) The processing unit model number.

CPU per I/O Async

(System) CPU use per asynchronous I/O.

CPU per I/O Sync

(System) CPU use per synchronous I/O.

CPU per Logical I/O

(System) Processing unit time used for each logical disk I/O operation.

CPU QM

(Transaction) The simple processing unit queuing multiplier.

CPU Sec

(Transaction) The processing unit time used by the job in this state.

CPU Sec /Sync DIO

(Transaction) The ratio of CPU seconds divided by synchronous disk I/O requests for each type of job.

CPU Sec Avg and Max

(Transaction) The average processing unit time per transaction for the job and the largest processing unit time used for a transaction in the job. If the job is not an interactive or autostart job type, then only the total processing unit time for the job is listed under the MAX column heading.

CPU Sec per Tns

(Transaction) The processing unit time per transaction.

CPU Seconds

(System, Transaction, Component) Average processing unit seconds used per transaction. For System Summary Data, it is the total available processing unit time used by the jobs during the trace period. For Priority-Jobtype-Pool Statistics, it is the total processing unit seconds used by the jobs with a given combination of priority, job type, and pool. For Batch Job Analysis, it is the amount of available processor unit time used by the job in seconds. For Concurrent Batch Job Statistics, it is the amount of available processor unit time used by the jobs in the job set in seconds.

CPU SECONDS

(Job Trace) The approximate processing unit time used for the transaction.

CPU seconds per transaction

(System) The average processing unit seconds per transaction.

CPU Util

(System, Component, Transaction, Job Interval, Pool Interval, Batch Job Trace) Percentage of available processing unit time used. For multiple-processor systems, this is the total utilization divided by the number of processors.

CPU Util per Transaction

(Component) The result of the CPU Utilization divided by the total number of transactions for the job.

CPU Utilization (Batch)

The percentage of available CPU time that is used by batch jobs. This is the average of all processors.

CPU Utilization (Interactive)

The percentage of available CPU time that is used by interactive jobs. This is the average of all processors.

CPU Utilization (Total)

The percentage of available CPU time that is used by interactive and batch jobs. This is the average of all processors.

For uncapped partitions, the Total CPU utilization might exceed 100 percent.

CPU/Async I/O

(Job Interval) The average number of milliseconds of processing unit time taken for each asynchronous disk I/O operation. This is calculated by dividing the milliseconds of the processing unit time the job used by the asynchronous disk I/O count.

CPU/Sync I/O

(Job Interval) The average number of milliseconds of processing unit time taken for each synchronous disk I/O operation. This is calculated from the milliseconds of the processing unit time used by the job divided by the synchronous disk I/O count.

CPU/Tns

(Transaction) The average number of processing seconds per transaction for the job during the interval. This is calculated from the amount of processing unit time used divided by the number of transactions processed.

Cpu/Tns (Sec)

(Transaction) The number of processing unit seconds per transaction.

Ctl

(Component) Controller identifier.

Cum CPU Util

(Transaction) The cumulative percentage of available processing unit time used by the transactions that have an average response time per transaction equal to or less than the given category. For example, in CPU by Priority for All Jobs for Total Trace Period (System Summary Data), it is the unit time used by the jobs with a priority higher or equal to the given priority.

Cum Pct Tns

(Transaction) Cumulative CPU percent per transaction. For system summary data, it is the cumulative CPU percentage of all transactions that have an average response time per transaction equal to or less than the given category. For Interactive Program Transactions Statistics, it is the cumulative CPU percentage of all transactions through the listed program. For Job Statistics section, it is the cumulative CPU percentage of total transactions through the listed job. For Interactive Program Statistics section, it is the cumulative CPU percentage of all transactions through the listed program.

Cum Util

(System) Cumulative CPU use (a running total).

This is taken from the individual jobs and may differ slightly from the total processing unit use on the workload page.

Cur Inl MPL

(Transaction) The number of jobs waiting for an activity level (ineligible) in the storage pool.

Cur MPL

(Transaction) The number of jobs holding an activity level in the storage pool.

Current User

(Job) The user under which the job was running at the end of each interval.

DASD Ops/Sec

(Component) Disk operations per second.

DASD Ops Per Sec Reads

(Resource) Number of reads per second

DASD Ops Per Sec Writes

(Resource) Number of writes per second

Datagrams Received

(Component) The total number of input datagrams received from interfaces. This number includes those that were received in error.

(Job Trace) The number of physical database reads that occurred for the entry.

DB Cpb Util

(Component) The percentage of database capability that is used to perform database processing.

DB Fault

(System, Component) Average number of database faults per second.

DB Pages

(System, Component) Average number of database pages read per second.

DB Read

(Transaction) When listed in Physical I/O Counts column, it is the number of database read requests while the job was in that state. When listed in the Sync Disk I/O Rqs/Tns column, it is the average number of synchronous database read requests per transaction.

DB READS

(Job Trace) The number of physical database reads that occurred.

DB Write

(Transaction) When listed in the Sync Disk I/O Rqs/Tns column, it is the average number of synchronous database write requests per transaction.

DB Wrt

(Transaction) When listed in the Physical I/O Counts column, it is the number of database write requests while the job was in that state. When listed in the Synchronous Disk I/O Counts column, it is the number of synchronous database write requests per transaction.

DDM I/O

(Component, Job Interval) The number of logical database I/O operations for a distributed data management (DDM) server job.

DDM Svr Wait /Tns

(Transaction) The average time, in seconds, that a source distributed data management (DDM) server job spent waiting for the target system to respond to a request for data per transaction. This value includes line time and time spent by the target system responding to the request for data.

Dec

(Transaction) The number of decimal overflow exceptions.

Decimal Data

(Component) Data exception count per second. A data exception occurs when data that is not valid is detected by arithmetic instructions. Examples are signs or digit codes that are not valid in decimal instructions, or an insufficient number of farthest left zeros in multiply instructions.

Decommit Ops

(Component) Decommit operations performed. Includes application and system-provided referential integrity decommits.

Decimal Overflow

(Component) Number of decimal overflows per second.

Description

(Component) More detailed description of the exception type.

Detected Access Transmission Error (DTSE) In

(Resource Interval) The number of times the network termination 1 (NT1) end point notified the terminal equipment (TE) of an error in data crossing the ISDN U interface from the line transmission termination (LT) to the NT1 end point. The NT1 end point reports the errors to the TE through the maintenance channel S1.

Detected Access Transmission Error (DTSE) Out

(Resource Interval) The number of times the network termination 1 (NT1) end point notified the terminal equipment (TE) of an error in data crossing the ISDN U interface from the NT1 end point to the LT. The NT1 end point reports the errors to the TE through the maintenance channel S1.

Device

(Component) Device identifier.

DIO/Sec Async

(System) Number of asynchronous I/O operations per second.

DIO/Sec Sync

(System) Number of synchronous I/O operations per second.

Disk Arm Seek Distance

(Component) Average seek distance distributions per hour:

0: Number of zero seeks
1/12: Number of seeks between 0 and 1/12 of the disk
1/6: Number of seeks between 1/12 and 1/6 of the disk
1/3: Number of seeks between 1/6 and 1/3 of the disk
2/3: Number of seeks between 1/3 and 2/3 of the disk
>2/3: Number of seeks greater than 2/3 of the disk

Disk Arms

(System) The number of disk arms for this IOP.

Disk Capacity

(Component) Average amount of disk space used or available.

MB: Millions of bytes available on the disk.
Percent: Percent of space available on the disk.

Disk Controllers

(System) The number of disk storage controllers for this IOP.

Disk Feature

(System) The type of disk (9332, 9335, and so on).

Disk I/O Async

(System, Component) Total number of asynchronous disk I/O operations.

Disk I/O Logical

(Component) The number of logical disk operations, such as gets and puts.

Disk I/O per Second

(System) Average number of physical disk I/O operations per second.

Disk I/O Reads /Sec

(Resource Interval) The average number of disk read operations per second by the disk IOP.

Disk I/O Requests

(Transaction) The total number of synchronous and asynchronous disk I/O requests issued by the jobs during the trace period.

Disk I/O Sync

(System, Component) Total number of synchronous disk I/O operations.

Disk I/O Writes /Sec

(Resource Interval) The average number of disk write operations per second by the disk IOP.

Disk IOPs

(System) The number of disk IOP controllers.

Disk mirroring

(System) Indicates whether disk mirroring is active.

Disk Space Used

(Resource Interval) The total disk space used in gigabytes for the entire system.

Disk transfer size (KB)

(System) The average number of kilobytes transferred per disk operation.

Disk utilization

(System) The fraction of the time interval that the disk arms were performing I/O operations.

Dsk CPU Util

(System, Resource Interval) The percentage of CPU used by the disk unit.

Dtgm Req Transm Dscrd

(Component) The percentage of IP datagrams that are discarded because of the following reasons:

No route was found to transmit the datagrams to their destination.
Lack of buffer space.

Dtgm Req for Transm Tot

(Component) The total number of IP datagrams that local IP user-protocols supplied to IP in requests for transmission.

Elapsed Seconds

(Transaction, Component) The elapsed time in seconds. For the Batch Job Analysis section of the Transaction Report, it is the number of seconds elapsed from when the job started to when the job ended. For the Concurrent Batch Job Statistics section of the Transaction Report, it is the total elapsed time of all jobs in that job set.

Elapsed Time

(Job Interval) The amount of time (minutes and seconds) for which the job existed during the interval. This is the same as the interval length unless the job started or ended during the interval, in which case it is less.

Elapsed Time--Seconds

(Transaction) Shows the time spent by the job, in the following columns:

Long Wait: Elapsed times in the state (such as waiting for the next transaction or lock-wait time).
Active/Rsp: During transaction processing, the time the job spends (either waiting or active) while it holds an activity level. At the end of a transaction (on the transaction totals line), this is the time the job spent processing the transaction in an activity level, for long waits caused by locks, and in the ineligible state.
Inel Wait: The time the job spent in the ineligible wait state waiting for an activity level.

EM3270 Wait /Tns

(Transaction) The average, in seconds, of the time spent waiting on the host system communications for Systems Network Architecture (SNA) and binary synchronous communications (BSC) 3270DE per transaction. Program logic is required to determine if the emulation program is communicating with the display or the host processing unit. Because there are requirements on event-wait processing, not all transition combinations can be detected.

ENTRY

(Job Trace) The instruction in the program where the program was given control.

EORn

(Transaction) Listed in the Wait Code column, End of response time for transaction n. These codes are in the wait code column, but they are not wait codes. They indicate transaction boundary trace records.

EOTn

(Transaction) Listed in the Wait Code column, End of transaction for transaction for type n. These codes are in the wait code column, but they are not wait codes. They indicate transaction boundary trace records.

Estimated Exposr AP Not Jrnld

(Component) System-estimated access path recovery time exposure in minutes if no access paths were being journaled by the system.

Estimated Exposr Curr System

(Component) System-estimated access path recovery time exposure in minutes.

Est Of AWS

(Transaction) An estimate of the number of active work stations for the trace period or interval. Any delay time greater than 600 seconds has been rounded to 600 seconds. This technique is used to reduce the effect of very casual users (those who may do intermittent work or leave their work stations for long periods of time) on the estimate of active work stations.

Event Wait /Tns

(Transaction) The average time, in seconds, of the event-wait time per transaction. Often requests made by a job that runs on the system are made to asynchronous jobs. These asynchronous jobs use an event to signal completion of the request back to the requester. The event-wait time is the time the requesting job waits for such a signal.

EVT

(Transaction) Listed in the Wait Code column, Event Wait. This is a long wait that occurs when waiting on a message queue.

Exception Type

(Component) Type of program exception that results from the internal microprogram instructions being run in internal microprogram instructions procedure. Because these exceptions are monitored at a low level within the system, it is difficult to associate these exceptions with specific end-user operations. The counts are meaningful when the processing unit time required to process them affects system performance. A variation in the counts may indicate a system change that could affect performance. For example, a large variation in seize or lock counts may indicate a job scheduling problem or indicate that contention exists between an old application and a new one that uses the same resources.

To see the seize and lock counts, you should collect the trace data by using the Start Performance Trace (STRPFRTRC) command. Run the Print Transaction Report (PRTTNSRPT) to list the objects and jobs that are holding the locks.

Exceptional wait

(System) The average exceptional wait time, in seconds, per transaction. An exceptional wait is that portion of internal response time that cannot be attributed to the use of the processor and disk. An exceptional wait is caused by contention for internal resources of the system, for example, waiting for a lock on a database record.

Constant: The portion of exceptional wait time held constant as throughput increases.
Variable: The portion of exceptional wait time that varies as throughput increases.

Excp

(Component, Transaction) For the Component Report, it is the total number of program exceptions that occurred per second. For the Transaction Report, a Y in this column means that the transaction had exceptions. The types of exceptions that are included are process access group exceptions, and decimal, binary, and floating point overflow. See the Transition Report to see which exceptions the transaction had.

Excp Wait

(Transaction) The amount of exceptional wait time for the jobs in the job set in seconds.

Excp Wait /Tns

(Transaction) The average exceptional wait time, in seconds, per transaction. This value is the sum of those waits listed under the Exceptional Wait Breakdown by Job Type part.

Excp Wait Sec

(Transaction) The total amount of exceptional wait time in seconds for the job.

Excs ACTM /Tns

(Transaction) The average time, in seconds, of the excess activity level time per transaction (for example, time spent in the active state but not using the processing unit). If enough activity levels are available and there is plenty of interactive work of higher priority to do, a job waits longer for processing unit cycles. If the value is greater than .3, look at jobs that correspond to particular applications for more information. By looking at these jobs, you might be able to determine which application's jobs are contributing most to this value. Use the Transaction and Transition Reports for these jobs for additional information. The formula for excessive activity-level time is shown below:

Active Time - [
(multiplier X CPU X Beginning Activity Level) +
(Number of synchronous disk I/O operations X .010)]

If the beginning activity level is greater than 1, the multiplier equals 0.5. If the beginning activity level is any other value, the multiplier equals 1.

EXIT

(Job Trace) The instruction number in the program where the program gave up control.

Expert Cache

(System, Component) Directs the system to determine which objects or portions of objects should remain in a shared main storage pool based on the reference patterns of data within the object. Expert cache uses a storage management tuner, which runs independently of the system dynamic tuner, to examine overall paging characteristics and history of the pool. Some values that you might see in this column are associated with the Work with Shared Pools (WRKSHRPOOL) command:

0=*FIXED, which indicates the system does not dynamically adjust the paging characteristics of the storage pool. The system uses default values.
3=*CALC, which indicates the system dynamically adjusts the paging characteristics of the storage pool for optimum performance.

Exposed AP System Journaled

(Component) The number of exposed access paths currently being journaled by the system.

Exposed AP System Not Journaled

(Component) The number of exposed access paths currently not being journaled by the system.

(System, Resource Interval) The line speed of the protocol reported as full duplex. This indicator applies to the line speeds for an Ethernet (ELAN) token-ring (TRLAN) line, or an asynchronous transfer mode line.

Far End Code Violation

(Resource Interval) The number of unintended code violations detected by the network termination 1 (NT1) end point for frames transmitted to the NT1 end point on the interface for the T reference point. The NT1 end point reports a violation to the termination equipment (TE) through the maintenance channel S1.

Faults

(System) A value that represents the total page faults that occurred for each job type or job priority during the collection. This is the same value as shown in the JBTFLT field of the QAPMJOBS or QAPMJOBL file.

File

(Transaction) The file that contains the object.

Flp

(Transaction) The number of floating point overflow exceptions.

Flp Overflow

(Component) Number of floating point overflows per second.

Frame Retry

(Resource Interval) The number of attempts to retransmit a frame to a remote controller.

Frames Received Pct Err

(Resource Interval) The percentage of frames received in error. Errors can occur when the host system has an error or cannot process received data fast enough.

Frames Received Total

(Resource Interval) The total number of frames received including frames with errors and frames that are not valid.

Frames Transmitted Pct Err

(Resource Interval) The percentage of frames retransmitted due to error.

Frames Transmitted Total

(Resource Interval) The total number of frames transmitted.

FULL CLS

(Job Trace) The number of full closes for all types of files.

FULL OPN

(Job Trace) The number of full opens for all types of files.

FUNCTION

(Job Trace) This causes the trace entry to be recorded. The possible trace entries are as follows:

Table 1.
Function ID	Description
DATA	Data trace record
CALL	Call external
XCTL	Transfer control
EVENT	Event handler invocation
EXTXHINV	External exception handler invocation
INTXHINV	Internal exception handler invocation
INTXHRET	Return from internal exception handler
INVEXIT	Invocation exit
RETURN	Return external
ITRMXRSG	Invocation ended due to resignaling exception
EXTXHRET	Return external or from a procedure instruction
PTRMTPP	Termination phase end
PTRMUNX	End process due to an unhandled exception
NOTUSED	This type is a non-valid trace type
ITERM	Invocation ended
CANCLINV	Cancel invocation instruction

Functional Areas

(System, Component, Transaction, Job Interval, Pool Interval) For Report Selection Criteria, the list of functional areas selected to be included (SLTFCNARA parameter) or excluded (OMTFCNARA parameter).

(System, Resource Interval) The line speed of the protocol reported as half duplex. This indicator applies to the line speeds for an Ethernet (ELAN) token-ring (TRLAN) line, or an asynchronous transfer mode line.

HDW

(Transaction) Listed in the Wait Code column, Hold Wait (job suspended or system request). The job released a lock it had on the object named on the next detail line of the report (OBJECT --). The job that was waiting for the object is named on this line (WAITER --) along with the amount of time the job spent waiting for the lock to be released.

High Srv Time

(Resource Interval) The highest average service time in seconds for a disk arm in the system.

High Srv Unit

The disk arm with the highest service time.

High Util

(Resource Interval) The percentage of use for the disk arm that has the highest utilization.

High Util Unit

(Component, Resource Interval) The disk arm with the highest utilization.

High Utilization Disk

(Component) Percent of utilization of the most utilized disk arm during this interval.

High Utilization Unit

(Component) Disk arm that had the most utilization during this interval.

Holder Job Name

(Transaction) The name of the job that held the object.

Holder Number

(Transaction) The number of the job that held the object.

Holder Pool

(Transaction) The pool that held the job while it was running.

Holder Pty

(Transaction) The priority of the holder's job.

Holder Type

(Transaction) The type and subtype of the holder's job.

Holder User Name

(Transaction) The name of the user that held the object.

Holder's Job Name

(Lock) The name of the job holding the lock.

I Frames Recd per Sec

(Resource Interval) The number of information frames received per second.

I Frames Trnsmitd per Sec

(Resource Interval) The number of information frames transmitted per second.

I/O Wait

(Resource Interval) The amount of time in which a given I/O request is ready to be processed, but the disk arm is not yet available to perform the request.

ICMP Messages Error

(Component) This is the number of Internet Control Message Protocol (ICMP) messages that the entity received but determined that the messages had errors or are messages that the entity did not send due to problems.

ICMP Messages Received

(Component) This is the total number of Internet Control Message Protocol (ICMP) messages that the entity received.

ICMP Messages Sent

(Component) This is the total number of Internet Control Message Protocol (ICMP) messages that the entity attempted to send.

Incoming Calls Pct Retry

(Resource Interval) The percentage of incoming calls that were rejected by the network.

Incoming Calls Total

(Resource Interval) The total number of incoming call attempts.

Inel Time A-I/W-I

(Transaction) The amount of time the job spent in the ineligible state, either coming from time slice end (active-to-ineligible) or from the wait state (wait-to-ineligible).

Inel Wait

(Transaction) Listed in the Elapsed Time--Seconds column, the time the job spent in the ineligible wait state waiting for an activity level.

Int Feat Util

(Component) The percentage of Interactive Feature that is used by all jobs.

Inter CPU Utilization

(Component) Percentage of available processing unit time used by the jobs that the system considers to be interactive.

For a multiple-processor system, this is the average use across all processors.

INV

(Job Trace) The call level of the program.

IOP

(Component) Input/output processor (IOP) Resource name and model number for each communications IOP, DASD IOP, local workstation IOP, and multifunction IOP. Communications IOP is the percent of CPU used in the IOP. The percent does not necessarily mean that the IOP is doing any data transfers. Some of the percent can be attributed to overhead of an active line.

IOP Name/Line

(System, Resource Interval) Input/output (IOP) processor resource name and model number line.

IOP Name(Model)

(Resource Interval) The input/output processor (IOP) identification and the model number in parentheses.

IOP Name

(System, Component) Input/Output processor (IOP) resource name.

IOP Name Network Interface

(Resource Interval) The IOP name of the network interface.

IOP Processor Util Comm

(Component, Resource) Utilization of IOP due to communications activity.

IOP Processor Util LWSC

(Component, Resource) Utilization of IOP due to local workstation activity.

IOP Processor Util DASD

(Component, Resource) Utilization of IOP due to DASD activity.

IOP Processor Util Total

(Component, Resource Interval) The total percent of utilization for each local workstation, disk, and communications IOP.

IOP Util

(System) For the Disk Utilization section of the System Report, it is the percentage of utilization for each input/output processor (IOP).

For the multifunction I/O processors, this is utilization due to disk activity only, not communications activity. For the System Model Parameter section it is the fraction of the time interval the disk IOP was performing I/O operations.

Itv End

(Component, Transaction, Job Interval, Pool Interval, Resource Interval) The time (hour and minute) when the data was collected. For the Exception Occurrence Summary and Interval Counts of the Component Report, it is the ending time for the sample interval in which Collection Services recorded the exception.

Job Maximum A-I

(Pool Interval) The highest number of active-state to ineligible-state transitions by a selected job in the pool or subsystem.

Job Maximum A-W

(Pool) The highest number of active-to-wait state transitions by a selected job in the pool or subsystem.

Job Maximum CPU Util

(Pool Interval) The highest percentage of available processing unit time used by a selected job in the pool or subsystem.

Job Maximum Phy I/O

(Pool Interval) The highest number of physical disk input and output operations by a selected job in the pool or subsystem.

Job Maximum Rsp

(Pool Interval) The highest response time in seconds per transaction by a selected job in the pool or subsystem. The response time is the amount of time spent waiting for and using the resources divided by the number of transactions.

Job Maximum Tns

(Pool Interval) The highest number of transactions by a selected job in the pool or subsystem.

Job Maximum W-I

(Pool Interval) The highest number of wait-state to ineligible-state transitions by a selected job in the pool or subsystem.

Job Name

(Component, Transaction, Job Interval, Batch Job Trace) Name of the job. In the Job Summary Report of the Transaction Report, a job (identical job name, user name, and job number) appears multiple times in this list if the job uses the system Reroute Job (RRTJOB) command.

Job Number

(Component, Transaction, Job Interval, Batch Job Trace) The number of the job which the summary line describes. In the Transaction Report, an asterisk (*) before the job number indicates the job signed on during the measurement period. An asterisk (*) after the job number indicates the job signed off during the measurement period.

Job Pty

(Batch Job Trace) Priority of the job.

Job Set

(Transaction) The number of job sets is the number of batch jobs that could be active at any time during the trace period. If two jobs run sequentially, they show up as two jobs in the same job set. If two jobs run concurrently, they show up in two different job sets.

Job Type

(All Reports except where noted for the Transaction Report) Job type and subtype. Possible job type values include the following:

A

Autostart

B

Batch

BD

Batch immediate (Transaction only)

The batch immediate values are shown as BCI on the Work with Active Job display and as BATCHI on the Work with Subsystem Job display.

BE

Batch evoke (Transaction only)

BJ

Batch pre-start job (Transaction only)

C

Programmable workstation application server, which includes 5250 emulation over APPC and iSeries™ Access host servers running either APPC or TCP/IP. A job is reported as a iSeries Access server if any of the following items are true:

Incoming APPC evoke requests one of the server program names. This also applies to the pre-started jobs for the QSERVER, QCMN, and QSYSWRK subsystems that are already waiting for the named program.
Incoming IP port number corresponds to one of the service name-description-port-numbers. This also applies to the pre-started jobs for the QSERVER, QCMN, and QSYSWRK subsystems that are already waiting for the assigned IP port number.
Incoming IPX socket number corresponds to one of the service name-description-port-numbers. This also applies to the pre-started jobs for the QSERVER, QCMN, and QSYSWRK subsystems that are already waiting for the assigned IPX port number.
Incoming 5250 display emulation jobs that come from APPC data streams sent by 5250 emulation under OS/2^® Communications Manager or WARP equivalent.

D

Target distributed data management (DDM) server

I

Interactive. Interactive includes twinaxial data link control (TDLC), 5250 remote workstation, and 3270 remote workstation. For the Transaction Report, this includes twinaxial data link control (TDLC), 5250 remote workstation, 3270 remote workstation, SNA pass-through, and 5250 Telnet.

L

Licensed Internal Code task

M

Subsystem monitor

P

SNA pass-through and 5250 Telnet pass-through. On the Transaction Report, these jobs appear as I (interactive).

R

Spool reader

S

System

W

Spool writer, which includes the spool write job, and if Advanced Function Printing™ (AFP™) is specified, the print driver job.

WP

Spool print driver (Transaction only)

X

Start system job

Possible job subtype values include the following:

D: Batch immediate job
E: Evoke (communications batch)
J: Pre-start job
P: Print driver job
T: Multiple requester terminal (MRT) (System/36™ environment only)
3: System/36

Noninteractive job types include:

Autostart
Batch
Evoke
iSeries Access-Bch
Server
Spool
Distributed data management (DDM) server

Special interactive job categories include:

Interactive
Multiple requester terminal (MRT)
Pass-through
System/36

Jobs

(System, Component, Transaction, Pool Interval, Job Interval) The jobs you specify. The format of the entries is jobnumber/username/jobname. For the Report Selection Criteria report, it is the list of jobs selected to be included (SLTJOB parameter) or excluded (OMTJOB parameter). This does not include jobs selected by using the STLFCNARA or OMTFCNARA parameter.

K per I/O

(System, Resource Interval) The average number of kilobytes (1024 bytes) read or written for each disk I/O operation.

K/T /Tns Sec

(Transaction) The average delay time, or time spent keying and thinking between transactions for the job, in seconds. The value represents the time interval between active-to-wait and wait-to-active or wait-to-ineligible job state transitions.

KB per I/O Read

(Resource Interval) The average number of kilobytes (1 KB equals 1024 bytes) transferred per read operation.

KB per I/O Write

(Resource Interval) The average number of kilobytes (1024 bytes) transferred per write operation.

KB Received/Second

(System, Component) The total number of kilobytes (1024) received per second on the specified interface when it was active on the selected intervals, which includes framing characters.

KB Transmitted/Second

(System, Component) The total number of kilobytes (1024) transmitted per second from the specified interface when it was active on the selected intervals, which includes framing characters.

KBytes Transmitted IOP

(Component, Resource Interval) Total kilobytes transmitted from an IOP to the system across the bus.

KBytes Transmitted System

(Component, Resource Interval) Total kilobytes transmitted to the IOP from the system across the bus.

Key/Think

(Transaction) The amount of time spent waiting for the work station user by the program.

Key/Think /Tns

(Transaction) The average think time and keying time (or the delay time between transaction boundaries), in seconds, for the interactive jobs.

(Lock) Whether this is a lock or seize conflict. The column contains an L if lock, blank if seize.

LAPD Pct Frames Recd in Error

(Resource Interval) The percentage of frames received in error (applies to D-channel only). Errors can occur when the host system has an error or cannot process received data fast enough.

LAPD Pct Frames Trnsmitd Again

(Resource Interval) The percentage of frames retransmitted due to error (applies to D-channel only).

LAPD Total Frames Recd

(Resource Interval) The total number of frames received including frames with errors and frames that are not valid (applies to D-channel only).

LAPD Total Frames Trnsmitd

(Resource Interval) The total number of frames transmitted (applies to D-channel only).

Last 4 Programs in Invocation Stack

(Transaction) The last four programs in the program stack. For example, at the start of a transaction (such as when the work station operator presses the Enter key), you see the program names QT3REQIO, QWSGET, and the program that issued a read operation. At the end of the transaction (such as when the program writes to the display), you see QT3REQIO, QWSPUT, and the program that wrote the display. Usually, the third or fourth program in the stack is the program shown in the transaction summary PGMNAME data. However, if the Wait Code column has a value, the program in the column labeled Last is the one that caused the trace record. If there is no program name in a column, the program name was the same as the previous one in the column, and the name is omitted.

Length of Wait

(Lock) The number of milliseconds the requester waited for the locked object.

Lgl I/O /Sec

(Job Interval) The average number of logical disk I/O operations performed per second by the job during the interval. This is calculated from the logical disk I/O count divided by the elapsed time.

Library

(System, Transaction) The library that contains the object.

LIBRARY

(Job Trace) The library name that contains the program associated with the trace entry.

Line Count

(Job Interval) The number of lines printed by the selected noninteractive jobs during the interval.

Line Descriptn

(Resource Interval) Line description name.

Line Errors

(Resource Interval) The total of all detected errors. Check the condition of the line if this value increases greatly over time.

Line Speed

(System, Resource Interval) The line speed in kilobits (1 kilobit = 1000 bits) per second.

Line Type/Line Name

(Component, System) The type and name of the line description that is used by the interface. For interfaces that do not use a line descriptions, the Line Name field will be shown as *LOOPBACK, *OPC, or *VIRTUALIP with no Line Type specified.

Line Util

(Resource Interval) The percent of available line capacity used by transmit and receive operations.

LKRL

(Transaction) Lock Released. The job released a lock it had on the object named on the next detail line of the report (OBJECT --). The job that was waiting for the object is named on this line (WAITER --) along with the amount of time the job spent waiting for the lock to be released.

LKW

(Transaction) Listed in the Wait Code column, Lock Wait. If there are a number of these, or you see entries with a significant length of time in the ACTIVE/RSP* column, additional analysis is necessary. The LKWT report lines that precede this LKW report line show you what object is being waited on, and who has the object.

LKWT

(Transaction) Listed in the Wait Code column, Lock Conflict Wait. The job is waiting on a lock conflict. The time (*/ time /*) is the duration of the lock conflict and, though not equal to the LKW time, should be very close to it. The holder of the lock is named at the right of the report line (HOLDER --). The object being locked is named on the next report line (OBJECT --).

Local End Code Violation

(Resource Interval) The number of times an unintended code violation was detected by the terminal equipment (TE) for frames received at the interface for the ISDN S/T reference point.

Local Not Ready

(Resource Interval) The percent of all receive-not-ready frames that were transmitted by the host system. A large percentage often means the host cannot process data fast enough (congestion).

Local work station IOP utilization

The fraction of the time interval the work station I/O processors are busy.

Local work station IOPs

(System) The resource name and model number for each local workstation IOP.

Lock Conflict

(Component) Number of lock exceptions per second. Database record contention is reflected in this count. For more information, issue the Start Performance Trace (STRPFRTRC) command and use the Print Transaction Report (PRTTNSRPT) and Print Lock Report (PRTLCKRPT) commands. This count could be very high, even under normal system operation. Use the count as a monitor. If there are large variations or changes, explore these variations in more detail.

Lock Wait /Tns

(Transaction) The average time, in seconds, of the lock-wait time per transaction. If the value is high, investigate with the transaction detail calculation and the Print Lock Report (PRTLCKRPT) command.

Logical

(Job Interval) The number of logical disk I/O operations performed by the selected interactive jobs during the interval.

Logical Database I/O Other

(System) Other logical database operations per transaction. This includes operations such as update and delete.

Logical Database I/O Read

(System) Logical database read operations per transaction.

Logical Database I/O Write

(System) Logical database write operations per transaction.

Logical DB I/O

(System) Average number of logical I/O operations per transaction.

Logical DB I/O Count

(System) Number of times an internal database I/O read, write, or miscellaneous function was called. This does not include I/O operations to readers, writers, or I/O operations caused by the Copy Spooled File (CPYSPLF) command or the Display Spooled File (DSPSPLF) command. If you specify SEQONLY(*YES), you see numbers that show each block of records read or written, not the number of individual records read or written. Miscellaneous functions include the following: updates, deletes, force-end-of-data, and releases.

Logical Disk I/O

(Component) Number of logical disk operations (Get, Put, Update, Other).

Logical I/O /Second

(System) Average number of logical disk I/O operations per second.

Logical I/O Per Second

(Job Interval) The average number of logical disk I/O operations performed per second by the selected noninteractive jobs during the interval.

Long Wait

(Transaction) The time the job spent waiting for a system resource. An example of a long wait would be a record-lock conflict. Also listed in the Elapsed Time--Seconds column, it is the elapsed time in the state (such as waiting for the next transaction or lock-wait time).

Long Wait Lck/Oth

(Transaction) The amount of time the job spent waiting for a system resource. An example of a long wait would be a record-lock conflict.

Loss of Frame Alignment

(Resource Interval) The number of times a time period equivalent to two 48-bit frames elapsed without detecting valid pairs of line code violations.

MAC Errors

(Resource Interval) The number of medium access control (MAC) errors.

Main storage (MB)

(System) The total main storage size, as measured in megabytes. These codes are in the wait code column, but they are not wait codes. They indicate transaction boundary trace records.

Max Util

(System) Consistent use at or above the threshold value given will affect system performance and cause longer response times or less throughput.

Maximum

(Transaction) The maximum value of the item that occurred in the column.

Member

(System, Transaction) For the System Report, this is the name of the performance data member that was specified on the TOMBR parameter of the Create Performance Data (CRTPFRDTA) command. For the Transaction Report, the member that was involved in the conflict.

Minimum

(Transaction) The minimum value of the item that occurred in the column.

MRT Max Time

(System) The time spent waiting, after MRTMAX is reached, by jobs routed to a multiple requester terminal.

No value appears in this column if job type is not MRT.

MSGS

(Job Trace) The number of messages sent to the job during each transaction.

MTU size (bytes)

(System) The size of the largest datagram that can be sent or received on the interface. The size is specified in octets (bytes). For interfaces that are used for transmitting network datagrams, this is the size of the largest network datagram that can be sent on the interface.

Nbr A-I

(Transaction) The number of active-to-ineligible state transitions by the job. This column shows the number of times that the job exceeded the time-slice value assigned to the job, and had to wait for an activity-level slot before the system could begin processing the transaction. If a value appears in this column, check the work that the job was doing, and determine if changes to the time-slice value are necessary.

Nbr Evt

(Transaction) The number of event waits that occurred during the job processing.

Nbr Jobs

(Transaction) The number of jobs.

Nbr Sign offs

(Transaction) The number of jobs that signed off during the interval.

Nbr Sign ons

(Transaction) The number of jobs that signed on during the interval.

Nbr Tns

(Transaction) The number of transactions in a given category.

The values for transaction counts and other transaction-related information shown on the reports you produce using the Print Transaction Report (PRTTNSRPT) command may vary from the values shown on the reports you produce using the Print System Report (PRTSYSRPT) and Print Component Report (PRTCPTRPT) commands. These differences are caused because the PRTTNSRPT command uses trace data as input, while the PRTSYSRPT and PRTCPTRPT commands use sample data as input.

If there are significant differences in the values for transaction-related information shown on these reports, do not use the data until you investigate why these differences exist.

Nbr W-I

(Transaction) The number of wait-to-ineligible state transitions by the job. This column shows how many times the job had to wait for a transaction.

NDB Read

(Transaction) Listed in Physical I/O Counts column, it is the number of nondatabase read requests while the job was in that state. Listed in the Sync Disk I/O Rqs/Tns column, it is the average number of synchronous nondatabase read requests per transaction.

NDB Write

(Transaction) Listed in the Sync Disk I/O Rqs/Tns column, it is the average number of synchronous nondatabase write requests per transaction.

NDB Wrt

(Transaction) Listed in Physical I/O Counts column, the number of nondatabase write requests while the job was in that state. Listed under Synchronous Disk I/O Counts column, it is the number of synchronous nondatabase write requests per transaction.

NON-DB

(Job Trace) The number of physical nondatabase reads that occurred for the entry.

Non-DB Fault

(System, Component) Average number of nondatabase faults per second.

Non-DB Pages

(System, Component) Average number of nondatabase pages read per second.

NON-DB RDS

(Job Trace) The number of physical nondatabase reads that occurred.

Non SMAPP

(Component) Journal deposits not directly related to SMAPP (System Managed Access Path Protection).

Non-SSL Inbound Connect

(System) The number of non-SSL inbound connections accepted by the server.

Non-Unicast Packets Received

(System) The total number of non-unicast packets delivered to a higher-layer protocol for packets received on the specified interface.

Non-Unicast Packets Sent

(System) The total number of packets that higher-level protocols requested to be transmitted to a non-unicast address; therefore, this number includes those packets that were discarded or were not sent as well as those packets that were sent.

Number

(Transaction) The number of the job with which the transaction is associated.

Number I/Os per Second

(System) The number of I/Os per second for this particular IOP.

Number Jobs

(Transaction) The number of batch jobs in the job set.

Number Lck Cft

(Transaction) The number of lock-wait (including database record lock) state conflicts that occurred during the job processing. If this number is high, look at the Transaction and Transition Reports for the job to see how long the lock-wait state conflicts were lasting. In addition, you can do further investigation using the reports produced when you use the Print Lock Report (PRTLCKRPT) command.

Number Lck Conflict

(Transaction) The number of times the job had a lock conflict.

Number Locks

(Transaction) The number of locks attributed to interactive or noninteractive waiters.

Number of batch jobs

(System) The average number of active batch jobs. A batch job is considered active if it averages at least one I/O per 5 minutes.

Number of Jobs

(System) Number of jobs.

Number of Packets Received with Errors

(System) The total number of packets that were received with errors or discarded for other reasons. For example, a packet could be discarded to free up buffer space.

Number Seizes

(Transaction) The number of seizes attributed to interactive or noninteractive waiters.

Number Sze Cft

(Transaction) The number of seize/lock conflicts that occurred during the job processing. If this number is high, look at the Transaction and Transition Reports for the job to see how long the conflicts lasted, the qualified name of the job that held the object, the name and type of object being held, and what the job was waiting for.

Number Sze Conflict

(Transaction) The number of times the job had a seize conflict.

Number Tns

(System, Transaction) Total number of transactions processed. For example, in the System Report it is the total number of transactions processed by jobs in this pool. In the Transaction Report it is the number of transactions associated with the program.

Number Traces

(Batch Job Trace) Number of traces.

Number Transactions

(System) Total number of transactions processed.

Object File

(Transaction) The file that contains the object.

Object Library

(Transaction) The library that contains the object.

Object Member

(Transaction) The member that was involved in the conflict.

Object Name

(Lock) The name of the locked object.

Object RRN

(Transaction) The relative record number of the record involved in the conflict.

Object Type

(Transaction, Lock) The type of the locked object. The following are possible object types:

AG: Access group
CB: Commit block
CBLK: Commit block
CD: Controller description
CLS: Class
CMD: Command
CTLD: Controller description
CTX: Context
CUD: Control unit description
CUR: Cursor
DEVD: Device description
DS: Data space
DSI: Data space index
DTAARA: Data area
EDTD: Edit description
FILE: File
JOBD: Job description
JOBQ: Job queue
JP: Journal port
JRN: Journal
JRNRCV: Journal receiver
JS: Journal space
LIB: Library
LIND: Line description
LUD: Logical unit description
MBR: Member
MEM: Database file member
MSGF: Message file
MSGQ: Message queue
ND: Network description
OCUR: Database operational cursor
OUTQ: Output queue
PGM: Program
PROG: Program
PRTIMG: Print image
QDAG: Composite piece - access group
QDDS: Composite piece - data space
QDDSI: Composite piece - data space index
QTAG: Temporary - access group
QTDS: Temporary - data space
QTDSI: Temporary - data space index
SBSD: Subsystem description
TBL: Table

Omit Parameters

(System, Component, Transaction, Job Interval, Pool Interval) The criteria used to choose the data records to be excluded from the report. The criteria are generally specified using an OMTxxx parameter of the command. Only nondefault values (something other than *NONE) are printed. If a parameter was not specified, it does not appear on the report.

Op per Second

(System) Average number of disk operations per second.

Other Wait /Tns

(Transaction) The average time, in seconds, spent waiting that was not in any of the previous categories per transaction. For example, the time spent waiting during a save/restore operation when the system requested new media (tape or diskette).

Outgoing Calls Pct Retry

(Resource Interval) The percentage of outgoing calls that were rejected by the network.

Outgoing Calls Total

(Resource Interval) The total number of outgoing call attempts.

Over commitment ratio

(System) The main storage over commitment ratio (OCR).

PAG

(Transaction) The number of process access group faults.

PAG Fault

(Component, Job Interval) In the Exception Occurrence Summary of the Component Report, it is the total number of times the program access group (PAG) was referred to, but was not in main storage. The Licensed Internal Code no longer uses process access groups for caching data. Because of this implementation, the value will always be 0 for more current releases. In the Exception Occurrence Summary of the Component Report, it is the number of faults involving the process access group per second.

Page Count

(Job Interval) The number of pages printed by the selected noninteractive jobs during the interval.

Pct CPU By Categories

(Transaction) The percentage of available processing unit time used by the transactions that fell into the various categories. See the ANALYSIS by Interactive Transaction Categories part of the System Summary Data Section for an explanation of the categories.

Pct Data Characters Received in Error

(Resource Interval) The percent of data characters received with error.

Pct Data Characters Transmitted in Error

(Resource Interval) The percent of data characters transmitted with error.

Pct Datagrams Error

(Component) The percentage of datagrams that were discarded due to these errors:

The IP address in the destination field of the IP header was not a valid address to be received at this entity.
The protocol was unknown or unsupported.
Not enough buffer space.

Pct Error Responses

(Component) Percentage of responses in error.

Pct Ex-Wt /Rsp

(Transaction) The percentage of the response time that is due to exceptional wait.

Pct ICMP Messages Error

Pct Of Tns Categories

(Transaction) The percentage of all transactions that fell into the various categories. See the Analysis by Interactive Transaction Categories part of the System Summary Data Section for an explanation of the categories.

Pct Packets Received Error

(System) The percentage of packets that were received with errors or discarded for other reasons. For example, a packet could be discarded to free up buffer space.

Pct Packets Sent Error

(System) The percentage of packets that were not sent because of errors or discarded for other reasons. For example, a packet could be discarded to free up buffer space.

Pct PDUs Received in Error

(Resource Interval) The percent of protocol data units (PDUs) received in error during the time interval. These errors can occur if the host system has errors or cannot receive data fast enough (congestion).

A protocol data unit (PDU) for asynchronous communications is a variable-length unit of data that is ended by a protocol control character or by the size of the buffer.

Pct Poll Retry Time

(Resource Interval) The percent of the time interval the line was unavailable while the IOP waited for a response from a work station controller (or remote system) that was in disconnect mode.

To minimize this lost time:

Vary on only the controllers that are turned on.
Turn on all controllers.
Use the Change Line Description (SDLC) (CHGLINSDLC) command to set the connect poll timer to a small value (reduces wait time).
Use the Change Controller Description (CHGCTLxxxx) command (where xxxx is APPC, FNC, RWS, or RTL, as appropriate) to set the NDMPOLLTMR value to a large value (increases time between polls).

Pct Tns

(Transaction) The percentage of the total transactions. For the System Summary section of the Job Summary Report, the transactions are within the given trace period with the given purge attribute. For the Interactive Program Transaction Statistics section of the Job Summary Report, the percentage of transactions that were associated with a program. For the Job Statistics section, it is the percentage of total transactions that were due to this job. For the Interactive Program Statistics section, it is all transactions that were associated to a program.

Pct UDP Datagrams Error

(Component) The percentage of User Datagram Protocol (UDP) datagrams for which there was no application at the destination port or that could not be delivered for other reasons.

Percent Errored Seconds

(Resource Interval) The percentage of seconds in which at least one Detected Access Transmission (DTSE) in or out error occurred.

Percent Frames Received in Error

(Resource Interval) The percent of all received frames that were received in error. Errors can occur when the host system has an error or cannot process received data fast enough (congestion).

Percent Full

(System) Percentage of disk space capacity in use.

Percent I Frames Trnsmitd in Error

(Resource Interval) The percent of transmitted information frames that required retransmission. Retransmissions can occur when a remote device has an error or cannot process received data fast enough (congestion).

Percent Severely Errored Seconds

(Resource Interval) The percent of seconds in which at least three Detected Access Transmission (DTSE) in or out errors occurred.

Percent transactions (dynamic no)

(System) A measure of system main storage utilization. The percent of all interactive transactions that were done with the purge attribute of dynamic NO.

Percent transactions (purge no)

(System) A measure of system main storage utilization. The percent of all interactive transactions that were done with the purge attribute of NO.

Percent transactions (purge yes)

(System) A measure of system main storage utilization. The percent of all interactive transactions that were done with the purge attribute of YES.

Percent Util

(System) Average disk arm utilization (busy). Consistent use at or above the threshold value provided for disk arm utilization affects system performance, which causes longer response times or less throughput.

The percent busy value is calculated from data measured in the I/O processor. When comparing this value with percent busy reported by the Work with Disk Status (WRKDSKSTS) command, some differences may exist. The WRKDSKSTS command estimates percent busy based on the number of I/O requests, amount of data transferred, and type of disk unit.

The system-wide average utilization does not include data for mirrored arms in measurement intervals for which such intervals are either in resuming or suspended status.

Perm Size

(Component) Kilobytes placed within the permanent area; these are traditional journal entries which can be retrieved and displayed.

Perm Write

(Component, Job Interval) The number of permanent write operations performed for the selected jobs during the interval.

Permanent writes per transaction

(System) The average number of permanent write operations per interactive transaction.

Physical I/O Count

(Transaction, Batch Job Trace) For the Job Summary section of the Batch Job Trace Report, the number of synchronous and asynchronous disk operations (reads and writes). For the Transition Report, the next five columns provide information about the number of synchronous and asynchronous disk I/O requests while the job was in the given state. The first line is the synchronous disk I/O requests, and the second line is the asynchronous disk I/O requests.

DB Read: The number of database read requests while the job was in that state.
DB Wrt: The number of database write requests while the job was in that state.
NDB Read: The number of nondatabase read requests while the job was in that state.
NDB Wrt: The number of nondatabase write requests while the job was in that state.
Tot: The total number of DB Read, DB Wrt, NDB Read, and NDB Wrt requests.

Physical Writes

(Component) Physical journal write operations to disk.

(Component, Transaction, Job Interval, Pool Interval) The number of the pool in which the subsystem or job ran.

Pool

(Transaction, Job Interval, Batch Job Trace) The number of the pool containing the transaction (for example, in which the job ran.)

Pool ID

(System) Pool identifier.

Pool ID Faults

(Component) User pool that had the highest page fault rate.

Pool Mch Faults/Sec

(Component) Average number of machine pool page faults per second.

Pool size (MB)

(Component) For the Storage Pool Activity section of the Component Report it is the initial pool size in megabytes.

Pool User Faults/Sec

(Component) Average number of user pool page faults per second, for the user pool with highest fault rate during this interval.

Pools

(System, Component, Transaction, Job Interval, Pool Interval) In the Report-Selection Criteria section, the list of pools selected to be included (SLTPOOLS parameter) or excluded (OMTPOOLS parameter). Otherwise, the pools you specify. The values can be from 1 through 64.

Prg

(Transaction) The purge attribute of the jobs.

Printer Lines

(System, Job Interval) The number of lines printed by the job during the interval.

Printer Pages

(System, Job Interval) The number of pages printed by the job during the interval.

Priority

(System, Transaction) The priority of the job.

Program

(Transaction) The name of the program with which the transaction is associated.

PROGRAM

(Job Trace) The name of the program for the entry.

PROGRAM CALL

(Job Trace) The number of non-QSYS library programs called during the step. This is not the number of times that the program named in the PROGRAM NAME field was called.

PROGRAM DATABASE I/O

(Job Trace) The number of times the IBM-supplied database modules were used during the transaction. The database module names have had the QDB prefix removed (PUT instead of QDBPUT). The type of logical I/O operation performed by each is as follows:

GETDR: Get direct
GETSQ: Get sequential
GETKY: Get by key
GETM: Get multiple
PUT, PUTM: Add a record
UDR: Update, delete, or release a record

PROGRAM INIT

(Job Trace) The number of times that the IBM-supplied initialization program was called during the transaction. For RPG programs this is QRGXINIT, for COBOL it is QCRMAIN. Each time the user program ends with LR (RPG) or END (COBOL), the IBM-supplied program is also called. This is not the number of times the program named in the PROGRAM NAME field was initialized. QCRMAIN is used for functions other than program initialization (for example, blocked record I/O, some data conversions).

Program Name

(Transaction) For the Job Summary section of the Transaction Report, the name of the program in control at the start of the transaction. Other programs may be used during the transaction. For the Transaction Report section, the name of the program active at the start of the transaction. If ADR=UNKNWN (address unknown) is shown under the column, the program was deleted before the trace data was dumped to the database file. If ADR=000000 is shown under the column, there was not enough trace data to determine the program name, or there was no program active at that level in the job when the trace record was created.

PROGRAM NAME

(Job Trace) The name of the last program called that was not in the library QSYS before the end of a transaction.

Protocol

(System) Line protocol.

SDLC
ASYNC
BSC
X25
TRLAN
ELAN (Ethernet)
IDLC
DDI
FRLY
PPP

Pty

(Component, Transaction, Job Interval) Priority of the job. For the Concurrent Batch Job Statistics section of the Transaction Report, it is the priority of the jobs in the job set.

Purge

(Transaction) The purge attribute of the jobs.

PWrt

(Transaction) The number of permanent write I/O operations.

Queue Length

(Resource Interval) The average number of I/O requests that had to wait in the queue for this unit.

Rank

(Transaction) The order. For the Job Summary section, it is the order of the program according to the number of transactions. For the Job Statistics section, it is the order of the job. For the Interactive Program Statistics section, it is the order of the program. For the Individual Transaction Statistics section, it is the order of the transaction according to the data being put in order by importance. For the Largest Seize/Lock Conflicts section, it is the order of the seize or lock conflict.

Ratio of write disk I/O to total disk I/O

(System) The fraction of the total disk activity that is due to writing data to the disks.

Reads per Second

(Resource Interval) The average number of disk read operations performed per second by the disk arm.

Receive CRC Errors

(Resource Interval) The number of received frames that contained a cycle redundancy check (CRC) error. This indicates that the data was not received error free.

Record Number

(Lock) For database file members, the relative record number of the record within the database file member.

Remote LAN Pct Frames Recd

(Resource Interval) The number of frames received from a local area network (LAN) connected to the locally attached LAN.

Remote LAN Pct Frames Trnsmitd

(Resource Interval) The number of frames transmitted to a local area network (LAN) connected to the locally attached LAN.

Remote Not Ready

(Resource Interval) The percentage of all receive-not-ready frames that were received by the host system. A large percentage often means the remote device cannot process data fast enough (congestion).

Remote Seq Error

(Resource Interval) The percent of frames received out of order by a remote device or system. This can occur when the remote device or system cannot process data fast enough.

Req type

(Component) The type of request being reported.

Requests received

(System, Component) The number of requests of all types received by the server.

Requestor's Job Name

(Lock) The name of the job requesting the locked object (the same as in the detail listing).

Reset Packets Recd

(Resource Interval) The number of reset packets received by the network. Reset packets are packets retransmitted because an error occurred.

Reset Packets Trnsmitd

(Resource Interval) The number of reset packets transmitted by the network.

Response

(System) Average system response (service) time.

Response Sec Avg and Max

(Transaction) The average (AVG) and maximum (MAX) transaction response time, in seconds, for the job. The average response time is calculated as the sum of the time between each pair of wait-to-active and active-to-wait transitions divided by the number of pairs that were encountered for the job. The MAX response time is the largest response time in the job.

Response Seconds

(System) Average response time in seconds per transaction.

Responses sent

(System, Component) The number of responses of all types sent by the server.

Rsp

(Component) Average interactive transaction response time in seconds.

Rsp Time

(Component, Resource Interval) The average external response time (in seconds). For the Local Work Station IOP Utilizations section of the Resource Interval Report, it is the response time for work stations on this controller. For the Remote Work Stations section of the Component Report, it is the response time for this work station.

Rsp Timer Ended

(Resource Interval) The number of times the response timer ended waiting for a response from a remote device.

Rsp/Tns

(Component, Transaction, Job Interval) The average response time (seconds) per transaction. For the Job Summary section of the Job Interval Report, it is the response time per transaction for the selected interactive jobs during the interval (the amount of time spent waiting for or using the system resources divided by the number of transactions processed). This number will not be accurate unless at least several seconds were spent processing transactions.

S/L

(Transaction) Whether the conflict was a seize (S) or lock (L) conflict.

SECONDS

(Job Trace) The approximate time the job was waiting or active.

Segments Pct Rtrns

(Component) The percentage of segments retransmitted. This number is the TCP segments that were transmitted and that contain one or more previously transmitted octets (bytes).

Segments Rcvd per Second

(Component) The number of segments received per second. This number includes those received in error and those received on currently established connections.

Segments Sent per Second

(Component) The number of segments sent per second. This number includes those sent on currently established connections and excludes those that contain only retransmitted octets (bytes).

Seize and Lock Conflicts

(Batch Job Trace) Number of seize conflicts and lock waits.

Seize Conflict

(Component) Number of seize exceptions per second. For more detailed information, issue the Start Performance Trace (STRPFRTRC) command, and use the PRTTNSRPT or PRTLCKRPT commands. This count could be very high, even under normal system operation. Use the count as a monitor. If there are large variations or changes, explore these variations in more detail.

Seize Hold Time

(Transaction) The amount of time that the transaction held up other jobs in the system by a seize or lock on an object.

Seize Wait /Tns

(Transaction) The average time, in seconds, for all seize-lock conflicts that occur during an average transaction. More than one seize-lock conflict can occur during a single transaction for the same job. If this number is high, investigate those jobs with seize conflicts. The Transaction Report lists each conflict that occurs, the name of the holder, and the name of the object held. For the Transaction by 5-Minute Intervals section of the Job Summary Report, it is the average seize wait time per transaction in seconds. This is the average amount of time that the transactions spent in a seize/lock conflict. If this number is high, look at the Transaction and Transition Reports for the jobs that are causing the excessive wait time.

Select Parameters

(System, Component, Transaction, Job Interval, Pool Interval) The criteria used to choose the data records to be included in the report. The criteria are generally specified using an SLTxxx parameter of the command. Only nondefault values (something other than *ALL) are printed. If a parameter is not specified, it does not appear on the report.

SEQNBR

(Job Trace) The number of the trace entry.

SEQNCE or SEQUENCE

(Job Trace) The job trace sequence number in the detail report that this summary line refers to.

Sequence Error

(Resource Interval) The number of frames received that contained sequence numbers indicating that frames were lost.

Server job name

(System) The server job number. Identifies the child job for the server.

Server job user

(System) The server job user. Identifies the child job for the server.

Server name

(System) The server job name. Identifies the child job for the server.

Server start date/time

(System) The most recent start or restart time in format mm/dd/yy hh:mm:ss

Short Frame Errors

(Resource Interval) The number of short frames received. A short frame is a frame that has fewer octets between its start flag and end flag than are permitted.

Short Wait /Tns

(Transaction) The average time, in seconds, of short (active) wait time per transaction. For the Interactive Program Statistics section, if the value is high, it may be due to the use of data queues or to the use of DFRWRT(*NO) or RSTDSP(*YES) in the program display files.

Short WaitX /Tns (Short wait extended)

(Transaction) The average time, in seconds, of wait time per transaction that resulted due to a short (active) wait that exceeded 2 seconds, and caused a long wait transition to occur. The activity level has been released but this time is still counted against your total response time. Waits on data queues or the use of DFRWRT(*NO) and/or RSTDSP(*YES) in the display files could be reasons for this value to be high.

Size

(Component) Decimal data overflow and underflow exceptions per second. An indication of improper field size on numeric calculations.

Size (MB)

(System) The size of the pool in megabytes.

Size (GB)

(Pool Interval) The size of the pool in gigabytes.

Size (M)

(System) Disk space capacity in millions of bytes.

SHARE CLS

(Job Trace) The number of shared closes for all types of files.

SHARE OPN

(Job Trace) The number of shared opens for all types of files.

SMAPP ReTune

(Component) System-managed access path protection tuning adjustments.

SMAPP System

(Component) SMAPP-induced journal entries deposited in system-provided (default) journals.

SMAPP User

(Component) SMAPP-induced journal entries deposited in user-provided journals.

SOTn

(Transaction) Listed in the Wait Code column, Start of transaction n. These codes are in the wait code column, but they are not wait codes. They indicate transaction boundary trace records.

Spool CPU seconds per I/O

(System) The average number of system processing unit seconds used by all spool jobs for each I/O performed by a spool job.

Spool database reads per second

(System) The average number of read operations to database files per second of spool processing.

Spool I/O per second

(System) The average number of physical disk I/O operations per second of spool processing.

Srv Time

(Component) Average disk service time per request in seconds not including the disk wait time.

SSL Inbound Connections

(System) AThe number of SSL inbound connections accepted by the server.

Start

(Transaction) The time the job started.

Started

(Transaction) The time of the first record in the trace data, in the form HH.MM.SS (hours, minutes, seconds).

State

(Transaction) The three possible job states are:

W--(Wait state) not holding an activity level.
A--(Active or wait state) holding an activity level.
I--(Ineligible state) waiting for an activity level.

The table below shows the possible job state transitions. For example, from W to A is yes, which means it is possible for a job to change from the wait state to the active state.

Table 2.
		To state
		A	W	I
From state	A	yes	yes	yes
	W	yes		yes
	I	yes

State Transitions A-A

(Batch Job Trace) Number of active-to-active transitions.

State Transitions A-I

(Batch Job Trace) Number of active-to-ineligible transitions.

Stop

(Transaction) The time the job ended.

Stopped

(Transaction) The time of the last record in the trace data, in the form HH.MM.SS (hours, minutes, seconds).

SUBFILE READS

(Job Trace) The number of subfile reads.

SUBFILE WRITES

(Job Trace) The number of subfile writes.

Subsystem Name

(Pool Interval) The name of the subsystem.

Subsystems

(System, Component, Pool Interval) For the System Report, the subsystem names you specify. Each name is a 10-character name. For the Component Report, the list of subsystems selected to be included (SLTSBS parameter) or excluded (OMTSBS parameter).

Sum

(Transaction) Listed in the Sync Disk I/O Rqs/Tns column, the sum of the averages of the synchronous DB READ, DB WRITE, NDB READ, and NDB WRITE requests (the average number of synchronous I/O requests per transaction for the job).

SWX

(Transaction) Listed in the Wait Code column, Short Wait Extended. The short wait has exceeded a 2-second limit and the system has put the transaction into a long wait. This long wait must be charged to the transaction response time. In most cases, this active-to-wait transaction does not reflect a transaction boundary.

Sync

(Job Interval) The number of synchronous disk I/O operations performed by the selected interactive jobs during the interval.

Sync DIO /Tns

(Transaction) The average number of synchronous I/O requests per transaction during the interval.

Sync Disk I/O

(System, Component, Transaction) Synchronous disk I/O operations.

Sync Disk I/O per Second

(Component) Average synchronous disk I/O operations per second.

Sync Disk I/O Requests

(Transaction) The total number of synchronous disk I/O requests for the given combination of priority, job type, and pool.

Sync Disk I/O Rqs/Tns

(Transaction) The next five columns provide information about the number of synchronous disk I/O requests per transaction:

DB Read: The average number of synchronous database read requests per transaction.
DB Write: The average number of synchronous database write requests per transaction.
NDB Read: The average number of synchronous nondatabase read requests per transaction.
NDB Write: The average number of synchronous nondatabase write requests per transaction.
Sum: The sum of the averages of the synchronous DB READ, DB WRITE, NDB READ, and NDB WRITE requests (the average number of synchronous I/O requests per transaction for the job).

Sync I/O /Elp Sec

(Transaction) The average number of synchronous disk I/O requests for all jobs, per second of elapsed time used by the jobs.

Sync I/O /Sec

(Job Interval) The average number of synchronous disk I/O operations performed per second by the job during the interval. This is calculated from the synchronous disk I/O count divided by the elapsed time.

Sync I/O Per Second

(Job Interval) The average number of synchronous disk I/O operations performed per second by the selected noninteractive jobs during the interval.

Synchronous DBR

(System, Transaction, Job Interval, Pool Interval) The average number of synchronous database read operations. It is the total synchronous database reads divided by the total transactions. For the Pool Interval and Job Interval Reports, it is calculated per transaction for the job during the intervals. For the System Report, it is calculated per second. For the Transaction (Job Summary) it is calculated per transaction. Listed under Average DIO/Transaction, the average number of synchronous database read requests per transaction. This field is not printed if the jobs in the system did not process any transactions.

Synchronous DBW

(System, Transaction, Job Interval, Pool Interval) The average number of synchronous database write operations. It is the total synchronous database writes divided by the total transactions. For the Pool Interval and Job Interval Reports, it is calculated per transaction for the job during the intervals. For the System Report, it is calculated per second. For the Transaction (Job Summary) it is calculated per transaction. Listed under Average DIO/Transaction, the average number of synchronous database read requests per transaction. This field is not printed if the jobs in the system did not process any transactions.

Synchronous DIO / Act Sec

(System, Transaction) The number of synchronous disk I/O operations per active second. The active time is the elapsed time minus the wait times.

Synchronous DIO / Ded Sec

(Transaction) The estimated number of synchronous disk I/O operations per second as if the job were running in dedicated mode. Dedicated mode means that no other job would be active or in contention for resources in the system.

Synchronous DIO / Elp Sec

(Transaction) The number of synchronous disk I/O operations per elapsed second.

Synchronous Disk I/O Counts

(Transaction) The next five columns provide information about the number of synchronous disk I/O requests per transaction:

DB Read: The number of synchronous database read requests per transaction.
DB Wrt: The number of synchronous database write requests per transaction.
NDB Read: The number of synchronous nondatabase read requests per transaction.
NDB Wrt: The number of synchronous nondatabase write requests per transaction.
Sum: The sum of the synchronous DB Read, DB Wrt, NDB Read, and NDB Wrt requests (the number of synchronous I/O requests per transaction).

Synchronous disk I/O per transaction

(System, Transaction) The average number of synchronous physical disk I/O operations per interactive transaction.

Synchronous Max

(Transaction) The maximum number of synchronous DBR, NDBR, and WRT I/O requests encountered for any single transaction by that job. If the job is not an interactive or autostart job type, the total disk I/O for the job is listed here.

Synchronous NDBR

(System, Transaction, Job Interval, Pool Interval) The average number of synchronous nondatabase read operations per transaction for the jobs in the system during the interval. For the Transaction Report, the operations on the disk per transaction for the selected jobs in the pool. This is calculated from the synchronous nondatabase read count divided by the transactions processed. This field is not printed if the jobs in the system did not process any transactions.

Synchronous NDBW

(System, Job Interval, Pool Interval) The average number of synchronous nondatabase write operations on the disk per transaction for the selected jobs in the pool. For the System Report, it is the operations per transaction for the jobs in the system during the interval. This is calculated from the synchronous nondatabase write count divided by the transactions processed. This field is not printed if the jobs in the system did not process any transactions.

Synchronous Sum

(Transaction) The sum of the averages of the synchronous DBR, NDBR, and WRT requests (the average number of synchronous I/O requests per transaction for the job).

Synchronous wrt

(Transaction) The average number of synchronous database and nondatabase write requests per transaction.

System CPU per transaction (seconds)

(System) The average number of system processing unit seconds per interactive transaction.

System disk I/O per transaction

(System) The total number of physical disk I/O operations attributed to the system per interactive transaction.

System Starts

(Component) The number of start journal operations initiated by the system.

System Stops

(Component) The number of stop journal operations initiated by the system.

System Total

(Component) The total number of journal deposits resulting from system-journaled objects. These are the deposits performed by system-managed access path protection (SMAPP).

System ToUser

(Component) The number of journal deposits resulting from system-journaled objects to user-created journals.

SZWG

(Transaction) Listed in the Wait Code column, Seize Wait Granted. The job was waiting on a seize conflict. The original holder released the lock that it had on the object, and the lock was then granted to the waiting job. The job that was waiting for the object is named on this line (WAITER --) along with the amount of time the job spent waiting for the seize conflict to be released. The object that is held is named on the next line of the report (OBJECT --).

SZWT

(Transaction) Listed in the Wait Code column, Seize/Lock Conflict Wait. The job is waiting on a seize/lock conflict. The time (*/ time /*) is the duration of the seize/lock conflict, and is included in the active time that follows it on the report. The holder of the lock is named at the right of the report line (HOLDER --). The object being held is named on the next report line (OBJECT --).

Teraspace EAO

(Component) Listed in the Exception Occurrence summary and Interval Counts. A teraspace effective address overflow (EAO) occurs when computing a teraspace address that crosses a 16-boundary. A quick estimate indicates that a 1% performance degradation would occur if there were 2,300 EAOs per second.

Thread

(Job Summary, Transaction, Transition) A thread is a unique flow of control within a process. Every job has an initial thread associated with it. Each job can start one or more secondary threads. The system assigns the thread number to a job as follows:

The system assigns thread IDs sequentially. When a job is started that uses a job structure that was previously active, the thread ID that is assigned to the initial thread is the next number in the sequence.
The first thread of a job is assigned a number.
Any additional threads from the same job are assigned a number that is incremented by 1. For example:
```
Job Name   User Name/  Job Number             Thread QJVACMDSRV   SMITH       023416 QJVACMDSRV    00000006   023416 QJVACMDSRV    00000007   023416 QJVACMDSRV    00000008   023416
```
A thread value greater than 1 does not necessarily mean the job has had that many threads active at the same time. To determine how many threads are currently active for the same job, use the WRKACTJOB, WRKSBSJOB, or WRKUSRJOB commands to find the multiple three-part identifiers with the same job name.

Threads active

(System) The number of threads doing work when the data was sampled.

Threads idle

(System) The number of idle threads when the data was sampled.

Time

(Transaction) The time when the transaction completed, or when a seize or lock conflict occurred. Also, a column heading that shows the time the transition from one state to another occurred, in the HH.MM.SS.mmm arrangement.

TIME

(Job Trace) The time of day for the trace entry. The time is sequentially given in hours, minutes, seconds, and microseconds.

Tns

(Component, Pool Interval) The total number of transactions processed by the selected jobs in the pool or subsystem.

Tns Count

(Component, Job Interval) The number of transactions performed by the selected interactive jobs during the interval.

Tns/Hour

(Component, Transaction, Job Interval) The average number of transactions per hour processed by the selected interactive jobs during the interval.

Tns/Hour Rate

(System) Average number of transactions per hour.

TOD of Wait

(Lock) The time of day of the start of the conflict.

Tot

(Transaction) Listed in Physical I/O Counts column, the total number of DB Read, DB Wrt, NDB Read, and NDB Wrt requests.

Tot Nbr Tns

(Transaction) The total number of transactions the PRTTNSRPT program determined from the input data that were accomplished for the job.

Total

(Component) Total exception counts for the reporting period.

TOTAL

(Job Trace) Totals for the fields.

Total /Job

(Transaction) The total (sum) of the items in the column for the job.

Total characters per transaction

(System) The average number of characters either read from or written to display station screens per interactive transaction.

Total CPU Sec /Sync DIO

(Transaction) The ratio of total CPU seconds divided by the total synchronous disk I/O requests.

Total CPU Utilization

(System, Component) Percentage of available processing unit time used by the partition. For a multiple-processor system, this is the average use across all processors. For dedicated partitions, Total CPU Utilization is replaced by a utilization value for each processor in the partition. Here is an example of this part of the display for a dedicated partition with two processors:

 Average CPU utilization  . . . . . :    41.9  CPU 1 utilization  . . . . . . . . :    41.7  CPU 2 utilization  . . . . . . . . :    42.2

In shared processor partitions, individual CPU utilization rows are not printed.

This value is taken from a system counter. Other processing unit uses are taken from the individual job work control blocks (WCBs). These totals may differ slightly. For uncapped partitions, Total CPU utilization might exceed 100 percent.

Total CPU Utilization (Database Capability)

(System) Shows you the DB2 Universal Database™ for iSeries activity on your systems. This field applies to all systems running V4R5 or later and includes all database activity, including all SQL and data I/O operations.

Total CPU Utilization (Interactive Feature)

(System) The CPU Utilization (Interactive Feature) shows the CPU utilization for all jobs doing 5250 workstation I/O operations relative to the capacity of the system for interactive work. Depending on the system and associated features purchased, the interactive capacity is equal to or less than the total capacity of the system.

Total Data Characters Received

(Resource Interval) The number of data characters received successfully.

Total Data Characters Transmitted

(Resource Interval) The number of data characters transmitted successfully.

Total Datagrams Requested for Transmission

(Component) The percentage of IP datagrams that are discarded because of the following reasons:

No route was found to transmit the datagrams to their destination.
Lack of buffer space.

Total fields per transaction

(System) The average number of display station fields either read from or written to per interactive transaction.

Total Frames Recd

(Resource Interval) The number of frames received, including frames with errors and frames that are not valid.

Total I Frames Trnsmitd

(Resource Interval) The total number of information frames transmitted.

Total I/O

(System) Sum of the read and write operations.

Total PDUs Received

(Resource Interval) The number of protocol data units (PDUs) received during the time interval.

A protocol data unit (PDU) for asynchronous communications is a variable-length unit of data that is ended by a protocol control character or by the size of the buffer.

Total Physical I/O per Second

(Resource Interval) The average number of physical disk I/O operations performed per second by the disk arm.

Total Responses

(Component, Resource Interval) The total number of transactions counted along with the average response time for all active work stations or devices on this controller for the report period.

Total Seize/Wait Time

(Component) The response time in milliseconds for each job.

Total Tns

(Component) Number of transactions processed in this pool.

Transaction Response Time (Sec/Tns)

(Transaction) The response time in seconds for each transaction. This value includes no communications line time. Response times measured at the work station exceed this time by the data transmission time (the time required to transmit data from the work station to the processing unit and to transmit the response data back to the work station from the processing unit).

Transactions per hour (local)

(System) The interactive transactions per hour attributed to local display stations.

Transactions per hour (remote)

(System) The interactive transactions per hour attributed to remote display stations.

Transient Size

(Component) Kilobytes placed within the journal transient area; these are hidden journal entries produced by the system.

Transmit/Receive/Average Line Util

(Resource Interval) In duplex mode, the percentage of transmit line capacity used, the percentage of receive line capacity used, and the average of the transmit and receive capacities.

TSE

(Transaction) Listed in the Wait Code column, Time Slice End. The program shown in the stack entry labeled LAST is the program that went to time slice end.

Typ

(Component, Transaction) The system job type and subtype. The Component Report allows only one character in this column. The Transaction Report allows two characters. The Transaction Report reports the job type and job subtype directly from the QAPMJOBS fields. The Component Report takes the job type and job subtype values and converts it to a character that may or may not be the value from the QAPMJOBS field. The possible job types are:

A

Autostart

B

Batch

BD

Batch immediate (Transaction only)

The batch immediate values are shown as BCI on the Work with Active Job display and as BATCHI on the Work with Subsystem Job display.

BE

Batch evoke (Transaction only)

BJ

Batch pre-start job (Transaction only)

C

Programmable work station application server, which includes 5250 emulation over APPC and iSeries Access host servers running either APPC or TCP/IP. See the Host server administration topic for more information. A job is reported as a iSeries Access server if any of the following items are true:

Incoming APPC evoke requests one of the server program names. This also applies to the pre-started jobs for the QSERVER, QCMN, and QSYSWRK subsystems that are already waiting for the named program.
Incoming IP port number corresponds to one of the service name-description-port-numbers. This also applies to the pre-started jobs for the QSERVER, QCMN, and QSYSWRK subsystems that are already waiting for the assigned IP port number.
Incoming IPX socket number corresponds to one of the service name-description-port-numbers. This also applies to the pre-started jobs for the QSERVER, QCMN, and QSYSWRK subsystems that are already waiting for the assigned IPX port number.
Incoming 5250 display emulation jobs that come from APPC data streams sent by 5250 emulation under OS/2 Communications Manager or WARP equivalent.

D

Target distributed data management (DDM) server

I

Interactive. For the Component Report, this includes twinaxial data link control (TDLC), 5250 remote workstation, and 3270 remote workstation. For the Transaction Report, this includes twinaxial data link control (TDLC), 5250 remote workstation, 3270 remote workstation, SNA pass-through, and 5250 Telnet.

L

Licensed Internal Code Task

M

Subsystem monitor

P

SNA pass-through and 5250 Telnet pass-through. On the Transaction Report, these jobs appear as I (interactive).

R

Spool reader

S

System

W

Spool writer, which includes the spool write job, and if Advanced Function Printing (AFP) is specified, the print driver job.

WP

Spool print driver (Transaction only)

X

Start the system

The possible job subtypes are:

D: Batch immediate job
E: Evoke (communications batch)
J: Pre-start job
P: Print driver job
T: Multiple requester terminal (MRT) (System/36 environment only)
3: System/36

Notes:

Job subtypes do not appear on the Component Report.
If the job type is blank or you want to reassign it, use the Change Job Type (CHGJOBTYP) command to assign an appropriate job type.

Type

(System, Transaction, Job Interval) One of the transaction types listed in the description of the DTNTY field.

(System): The disk type.
(Transaction): The type and subtype of the job.
(Transaction): For the Seize/Lock Conflicts by Object section, the type of seize/lock conflict.

UDP Datagrams Received

(Component) The total number of User Datagram Protocol (UDP) datagrams delivered to UDP users.

UDP Datagrams Sent

(Component) The total number of User Datagram Protocol (UDP) datagrams sent from this entity.

Uncap CPU Avail

(Component)Percentage of CPU time available to a partition in the shared processors pool during the interval in addition to its configured CPU. This value is relative to the configured CPU available for the particular partition.

Unicast Packets Received

(System) The total number of subnetwork-unicast packets delivered to a higher-layer protocol. The number includes only packets received on the specified interface.

Unicast Packets Sent

(System) The total number of packets that higher-level protocols requested to be transmitted to a subnetwork-unicast address. This number includes those packets that were discarded or were not sent.

Unit

(System, Component, Resource Interval) The number assigned by the system to identify a specific disk unit or arm. An 'A' or 'B' following the unit number indicates that the disk unit is mirrored. (For example, 0001A and 0001B are a mirrored pair.)

Unit Name

The resource name of the disk arm.

User ID

(System, Component, Transaction, Job Interval, Pool) The list of users selected to be included (SLTUSRID parameter) or excluded (OMTUSRID parameter).

User Name

(Component, Transaction, Job Interval, Batch Job Trace) Name of the user involved (submitted the job, had a conflict, and so on.)

User Name/Thread

(Component, Transaction) If the job information contains a secondary thread, then this column shows the thread identifier. If the job information does not contain a secondary thread, then the column shows the user name. The system assigns the thread number to a job as follows:

The system assigns thread IDs sequentially. When a job is started that uses a job structure that was previously active, the thread ID that is assigned to the initial thread is the next number in the sequence.
The first thread of a job is assigned a number.
Any additional threads from the same job are assigned a number that is incremented by 1. For example:
```
Job Name   User Name/  Job Number             Thread QJVACMDSRV   SMITH       023416 QJVACMDSRV    00000006   023416 QJVACMDSRV    00000007   023416 QJVACMDSRV    00000008   023416
```
A thread value greater than 1 does not necessarily mean the job has had that many threads active at the same time. To determine how many threads are currently active for the same job, use the WRKACTJOB, WRKSBSJOB, or WRKUSRJOB commands to find the multiple three-part identifiers with the same job name.

User Starts

(Component) The number of start journal operations initiated by the user.

User Stops

(Component) The number of stop journal operations initiated by the user.

User Total

(Component) The total number of journal deposits resulting from system-journaled objects.

Util

(Component, Resource Interval) The percent of utilization for each local work station, disk, or communications IOP, controller, or drive.

The system-wide average utilization does not include data for mirrored arms in measurement intervals for which such intervals are either in resuming or suspended status.

Util 2

(Component, Resource) Utilization of co-processor.

Value

(Transaction) For the Individual Transaction Statistics section of the Job Summary report, it is the value of the data being compared for the transaction. For the Longest Seize/Lock Conflicts section, it is the number of seconds in which the seize or lock conflict occurred.

Verify

(Component) Number of verify exceptions per second. Verify exceptions occur when a pointer needs to be resolved, when blocked MI instructions are used at security levels 10, 20, or 30, and when an unresolved symbolic name is called. This count could be very high, even under normal system operation. Use the count as a monitor. If there are large variations or changes, explore these variations in more detail.

W-I Wait/Tns

(Transaction) The average time, in seconds, of wait-to-ineligible time per transaction. This value is an indication of what effect the activity level has on response time. If this value is low, the number of wait-to-ineligible transitions probably has little effect on response time. If the value is high, adding additional interactive pool storage and increasing the interactive pool activity level should improve response time. If you are unable to increase the interactive pool storage (due to limited available storage), increasing the activity level may also improve response time. However, increasing the activity level might result in excessive faulting within the storage pool.

Wait Code

(Transaction) The job state transition that causes the trace record to be produced. The values can be as follows:

EVT: Event Wait. A long wait that occurs when waiting on a message queue.
EOTn: End of transaction for transaction for type n. These codes are in the wait code column, but they are not wait codes. They indicate transaction boundary trace records.
EORn: End of response time for transaction n. These codes are in the wait code column, but they are not wait codes. They indicate transaction boundary trace records.
Error Responses: (Component> The number of responses in error.
HDW: Hold Wait (job suspended or system request).
LKRL: Lock Released. The job released a lock it had on the object named on the next detail line of the report (OBJECT --). The job that was waiting for the object is named on this line (WAITER --) along with the amount of time the job spent waiting for the lock to be released.
LKW: Lock Wait. If there are a number of these, or you see entries with a significant length of time in the ACTIVE/RSP* column, additional analysis is necessary. The LKWT report lines that precede this LKW report line show you what object is being waited on, and who has the object.
LKWT: Lock Conflict Wait. The job is waiting on a lock conflict. The time (*/ time /*) is the duration of the lock conflict and, though not equal to the LKW time, should be very close to it. The holder of the lock is named at the right of the report line (HOLDER --). The object being locked is named on the next report line (OBJECT --).
SOTn: Start of transaction n. These codes are in the wait code column, but they are not wait codes. They indicate transaction boundary trace records.
SWX: Short Wait Extended. The short wait has exceeded a 2-second limit and the system has put the transaction into a long wait. This long wait must be charged to the transaction response time. In other words, this active-to-wait transaction does not reflect a transaction boundary.
SZWG: (Transaction) Listed in the Wait Code column, Seize Wait Granted. The job was waiting on a seize conflict. The original holder released the lock that it had on the object, and the lock was then granted to the waiting job. The job that was waiting for the object is named on this line (WAITER --) along with the amount of time the job spent waiting for the seize conflict to be released. The object that is held is named on the next line of the report (OBJECT --).
SZWT: Seize/Lock Conflict Wait. The job is waiting on a seize/lock conflict. The time (*/ time /*) is the duration of the seize/lock conflict, and is included in the active time that follows it on the report. The holder of the lock is named at the right of the report line (HOLDER --). The object being held is named on the next report line (OBJECT --).
TSE: Time Slice End. The program shown in the stack entry labeled LAST is the program that went to time slice end. Every time a job uses 0.5 seconds of CPU time (0.2 seconds on the faster processors) between long waits, the system checks if there are jobs of equal priority on the CPU queue. If there are, then the next job with equal priority is granted the CPU and the interrupted job is moved to the queue as the last of equal priority. The job, however, retains its activity level. This is an internal time slice end. When a job reaches the external time slice value, there can be a job state transition from active to ineligible if another job is waiting for an activity level. When a job is forced out of its activity level, its pages are liable to be stolen by other jobs, and cause additional I/O when the job regains an activity level. The IBM-supplied default values of 2 seconds for interactive jobs and 5 seconds for batch jobs may often be too high, especially for the high-end processors. As an initial value, set the time slice at 3 times the average CPU seconds per transaction.
WTO: Wait Timed Out. The job has exceeded the wait time-out limit defined for a wait (such as a wait on a lock, a message queue, or a record).

WAITS

(Job Trace) The number of waits that occurred.

WAIT-ACT

(Job Trace) In the Job Trace Analysis Summary, this is the time between the ENDTNS and STRTNS programs is labeled WAIT-ACT. If you were tracing an interactive job and used the default STRTNS and ENDTNS parameters, this value is the time taken to process the transaction.

In the Job Trace Analysis I/O Summary, this is the time that the job was inactive, probably due to typing or think time by the user.

Wait-Inel

(System, Component) Average number of wait-to-ineligible job state transitions per minute.

Work Station Controller

(Resource Interval) The name of the remote work station controller.

WRITES

(Job Trace) The number of physical writes that occurred.

Writes per Second

(Resource Interval) The average number of disk write operations performed per second by the disk arm.

WRITTEN

(Job Trace) The number of physical writes that occurred for the entry.

WTO

(Transaction) Listed in the Wait Code column, Wait Timed Out. The job has exceeded the wait time-out limit defined for a wait (such as a wait on a lock, a message queue, or a record).

0.0-1.0

(Component, Resource Interval) The number of times the response time was between 0 and 1 second.

1.0-2.0

(Component, Resource Interval) The number of times the response time was between 1 and 2 seconds.

2.0-4.0

(Component, Resource Interval) The number of times the response time was between 2 and 4 seconds.

4.0-8.0

(Component, Resource Interval) The number of times the response time was between 4 and 8 seconds.

Parent topic:

Performance Tools reports