Device Detail (PI_DEVD)
- Organization of this page
Function
The Device Detail (PI_DEVD) record stores the performance data per unit time on the local disk device usage. Every time performance data is collected, a record is created for each local disk device. This is a multi-instance record.
- Notes:
-
-
In AIX, performance data of devices whose device names begin with vscsi or vhost is not collected.
-
In Linux, the Device Detail (PI_DEVD) record is collected as performance data for block devices matching the following major numbers from the information recorded in /proc/partitions:
• In Linux 6: 1 to 4, 7 to 9, 11 to 37, 40, 41, 43 to 59, 64 to 94, 96, 98, 99, 101 to 117, 128 to 147, 152, 153, 160, 161, 180, 199, 201, 202, 256
• In Linux 7, Linux 8, Oracle Linux 7#, or Oracle Linux 8: 1 to 4, 7 to 9, 11, 15 to 35, 37, 43 to 59, 64 to 94, 96, 98, 99, 101 to 117, 128 to 147, 152, 153, 160, 161, 179, 180, 199, 201, 202, 256 to 259
# When the Unbreakable Enterprise Kernel (UEK) is used, the performance data to be collected is the same as that defined for Linux 6 above.
-
If the DR function of Solaris is used to modify a system resource while a PFM - Agent for Platform service is running, some types of performance data cannot be correctly collected. The table below shows the types of system resources that are affected and the actions that you can take to correctly display reports after the modification.
System resource type
Report type
Actions to be taken after modification
Device
Real-time
Display the report again.
Historical
Specify the display period such that it does not include the date and time when the system resources were modified.
Fields other than those listed below are affected by a system resource modification:
• Interval (INTERVAL)
• Record Time (RECORD_TIME)
• Record Type (INPUT_RECORD_TYPE)
• Fields that are added only when data is recorded in the Store database
For details about modifying system resources, see Notes on performance information when modifying system resources in Notes on records.
-
In HP-UX, the local disk device of Legacy DSF and Persistent DSF both are collected.
-
In AIX, a PI_DEVD record's key field is a device name. Therefore, if the device name is changed (by using the rendev command), the continuity of performance data cannot be maintained even if the same device is used before and after the device name changes. In this case, that device is recognized as a different device and performance data is collected.
-
Default values and values that can be specified
Item |
Default value |
Modifiable |
---|---|---|
Collection Interval |
60 |
Yes |
Collection Offset# |
0 |
Yes |
Log |
No |
Yes |
LOGIF |
Blank |
Yes |
Over 10 Sec Collection Time |
No |
No |
Realtime Report Data Collection Mode |
Reschedule |
Yes |
- #
-
A value between 0 and 32,767 seconds can be specified (a value within the range specified for Collection Interval). Use this item to distribute the collection load, because executing data collection all at once results in concentration of the processing workload. Note that the data collection duration to be recorded is the same as the Collection Interval, regardless of the value specified for Collection Offset.
When changing the Collection Offset value, specify a value that takes into account the impact of the collection processing load.
ODBC key fields
PI_DEVD_DEVICE_NAME
Lifetime
None
Record size
-
Fixed portion: 681 bytes
-
Variable portion: 405 bytes
Fields
PFM-View name (PFM-Manager name) |
Description |
Smry |
Format |
Delta |
Not sprtd in |
Data source |
---|---|---|---|---|---|---|
Avg Service Time(AVG_SERVICE_TIME) |
Average I/O service time for devices (seconds) |
AVG |
utime |
No |
-- |
TOTAL_SERVICE_TIME ÷ TOTAL_OPS |
Avg Wait Time(AVG_WAIT_TIME) |
Average I/O wait time for devices (seconds) |
AVG |
utime |
No |
AIX |
TOTAL_WAIT_TIME ÷ TOTAL_OPS |
Busy %(BUSY_PERCENT) |
Percentage of time a disk was busy (%). This value may exceed 100 when processes are continuously executed on a device. |
% |
float |
No |
-- |
(TOTAL_BUSY_TIME ÷ INTERVAL) × 100 |
Device Name(DEVICE_NAME) |
Device name |
COPY |
string(40) |
No |
-- |
-- |
Device Type(DEVICE_TYPE) |
Device type. Disk (disk device) or Tape (tape device) |
COPY |
string(5) |
No |
-- |
-- |
I/O Mbytes(TOTAL_IO_MBYTES) |
Total size of data transferred through I/O operations (MB) |
AVG |
float |
Yes |
-- |
-- |
Interval(INTERVAL) |
Interval at which the Device Detail (PI_DEVD) record was stored (seconds) |
COPY |
ulong |
Yes |
-- |
• When delta values are not checked in real time, RECORD_TIME - last-boot-time • Other cases, RECORD_TIME - previous-record-time |
Mbytes Xferd/sec(MBYTES_TRANSFERRED_PER_SECOND) |
Average I/O speed (MB per second) |
R |
float |
Yes |
-- |
TOTAL_IO_MBYTES ÷ INTERVAL |
Queue Length(QUEUE_LENGTH) |
Number of I/O requests in the device queue |
AVG |
ulong |
No |
AIX |
-- |
Read %(READ_OPS_PERCENT) |
Read operations as a percentage of all I/O operations (%) |
% |
float |
No |
HP-UX, AIX |
READ_OPS ÷ (READ_OPS + WRITE_OPS) × 100 |
Read Mbytes(TOTAL_READ_MBYTES) |
Size of data transferred in read operations (MB) |
AVG |
float |
Yes |
HP-UX |
-- |
Read Ops(READ_OPS) |
Number of read operations that occurred |
AVG |
ulong |
Yes |
HP-UX, AIX |
-- |
Reads/sec(READ_OPS_PER_SECOND) |
Frequency at which read operations occurred (number of read operations per second) |
R |
float |
Yes |
HP-UX, AIX |
READ_OPS ÷ INTERVAL |
Record Time(RECORD_TIME) |
Time at which the record was created (Greenwich Mean Time) |
COPY |
time_t |
No |
-- |
-- |
Record Type(INPUT_RECORD_TYPE) |
Record type. Always DEVD. |
COPY |
char(8) |
No |
-- |
-- |
Seek Ops(SEEK_OPS) |
Number of seek operations |
AVG |
ulong |
Yes |
Solaris, AIX, Linux |
-- |
Total Busy Time(TOTAL_BUSY_TIME) |
Total busy time for a device (seconds). This value may exceed the value of Interval when processes are continuously executed on a device. |
AVG |
utime |
Yes |
-- |
-- |
Total I/O Ops(TOTAL_OPS) |
Number of I/O operations that occurred |
AVG |
ulong |
Yes |
-- |
-- |
Total I/O Ops/sec(TOTAL_OPS_PER_SECOND) |
Frequency at which I/O operations occurred (number of I/O operations per second) |
R |
float |
Yes |
-- |
TOTAL_OPS ÷ INTERVAL |
Total Service Time(TOTAL_SERVICE_TIME) |
Total service time for a device (seconds). This value includes wait time. In HP-UX, this value indicates the total service time of all I/Os, and therefore, it may significantly exceed the value of Interval when processes are continuously executed on a device. Even with other OSs, the value may exceed the value of Interval when processes are continuously executed on a device. |
AVG |
utime |
Yes |
-- |
-- |
Total Wait Time(TOTAL_WAIT_TIME) |
Total wait time for a device (seconds). In HP-UX, this value indicates the total wait time of all I/Os, and therefore, it may significantly exceed the value of Interval when processes are continuously executed on a device. |
AVG |
utime |
Yes |
AIX |
-- |
Wait Length Time(WAIT_LEN_TIME) |
Length of time I/Os waited for a device (seconds). The processing capacity of the I/Os that were waiting is divided by the I/Os' processing capacity per second, and is then integrated over the wait time. |
AVG |
utime |
Yes |
AIX |
-- |
Write %(WRITE_OPS_PERCENT) |
Write operations as a percentage of all I/O operations (%) |
% |
float |
No |
HP-UX, AIX |
WRITE_OPS ÷ (READ_OPS + WRITE_OPS) × 100 |
Write Mbytes(TOTAL_WRITE_MBYTES) |
Size of data transferred in write operations (MB) |
AVG |
float |
Yes |
HP-UX |
-- |
Write Ops(WRITE_OPS) |
Number of write operations that occurred |
AVG |
ulong |
Yes |
HP-UX, AIX |
-- |
Writes/sec(WRITE_OPS_PER_SECOND) |
Frequency at which write operations occurred (number of write operations per second) |
R |
float |
Yes |
HP-UX, AIX |
WRITE_OPS ÷ INTERVAL |