Previous Topic: Interpret cluster-wide Disk StatisticsNext Topic: Interpret cluster-wide Hot File Statistics

Evaluate Performance in Detail › Performance Evaluation Report › Interpret cluster-wide Tape Statistics

Interpret cluster-wide Tape Statistics

The tape statistics follow the cluster-wide disk statistics.

To display only the tape statistics section of the Performance Evaluation Report, use the following qualifier:

/INCLUDE=TAPE_STATISTICS

To disable the tape statistics display from the report, use the following qualifier:

/INCLUDE=NOTAPE_STATISTICS

The following example shows the tape statistics section of the Performance Evaluation Report:

Performance                          CLUSTER                            Page   1
Evaluation                                                          PA Vx.x
					Wednesday 14-JAN-2006 09:00 to 19:20



  +-----------------------------------------------------------------------+
  | The following table gives the summary of all tape activity as seen    |
  | by the indicated node.  An "*" for service node indicates that more   |
  | than one was detected.                                                |
  +-----------------------------------------------------------------------+


Tape    Avg I/O  Avg   Avg    IOsz  Source Service  %    % IO % IO        # of
Volume  per Sec Queue Kb/sec in pgs  Node   Node   Busy  Read Split Type Samples
------  ------- ----- ------ ------ ------ ------ ------ ---- ----- ---- -------
  1        2      3     4      5      6      7       8     9    10    11    12
8JUL02        ($2$MUA43)
           3.76 20.14  119.1   63.3 LATOUR JULIO   15.46    0    0  TA90E     9
ABC           ($2$MUA43)
          99.21 61.30  270.5    5.5 LATOUR JULIO   39.62    0    0  TA90E     9

The following statements are keyed to the columns in the previous report:

  1. Volume name of the tape to which one or more nodes in the cluster directs activity.
  2. Average number of I/O operations per second to the tape volume. For each tape, the total I/O per second is reported, followed by a breakdown of this activity from contributing nodes, when applicable.
  3. Average number of I/O requests waiting for service to the tape. The average queue size for each tape is followed by a breakdown of this value from contributing nodes, when applicable.
  4. Average number of kilobytes per second transferred to or from the tape.
  5. Average size of the I/O operations to the tape, in pages. The average size for each tape is followed by a breakdown of this value from contributing nodes, when applicable.
  6. Name of the node that uses the various tape volumes. For rows in which no source node name appears, the data refers to the cluster-wide activity on the tape volume.
  7. Name of the node that services I/O requests.
  8. Percentage of time that I/O requests are outstanding to the volume for each node utilizing the tape volume.
  9. Percentage of total I/O activity devoted to read operations. This value for each tape is followed by the percentage of read operations to the tape from contributing nodes, when applicable.
  10. Percentage of total I/O activity that was split I/O operations. This value for each tape is followed by the percentage of read operations to the tape from contributing nodes, when applicable.
  11. Tape volume type. In this example, all of the tapes are TA90Es.
  12. Count of the Performance Manager records containing data for a tape volume during the interval.

The following example shows the cluster-wide tape statistics section of the Performance Evaluation report:

Performance                          CLUSTER                            Page   2
Evaluation                                                          PA Vx.x
					Wednesday 14-JAN-2006 09:00 to 19:20

  +-----------------------------------------------------------------------+
  | The following tables gives the summary of all tape activity as seen   |
  | by the indicated node.                                                |
  +-----------------------------------------------------------------------+

                               Percent      Metrics during active records
Cluster  Tape                 of records    ----------------------------- Device
 Node    controller Unit     with activity   I/Os/sec     Errors/sec      Type
-------  ---------- ----     -------------   -----------  -----------    -------
   1            2   3             4              5              6           7
SUPPLY         MFA  0           0.813          0.325          0.000       TU78
               MUA  0           0.000          0.000          0.000       TA78
               MUA  1           0.000          0.000          0.000       TA78
DEMAND         MUA  0           0.000          0.000          0.000       TA78
               MUA  1           0.000          0.000          0.000       TA78
NODE01         MFA  0           0.000          0.000          0.000       TU78
               MUA  0           0.000          0.000          0.000       TA78
               MUA  1           0.000          0.000          0.000       TA78

The following statements are keyed to the columns in the previous example:

  1. Node name
  2. Tape controller
  3. Unit number
  4. Percentage of records having tape activity on a given node during the interval
  5. I/Os per second to the tape controller unit
  6. Errors per second
  7. Tape controller unit type