/cx/p
x show dpmstat type=inst|ra|lct|histdata|ext
This command allows you to request drive statistics of the specified type for the specified port. These statistics can be helpful when troubleshooting performance problems.
type= specifies which statistics should be displayed. The options are:
inst for Instantaneous,
ra for Running Average,
lct for Long Command Times,
histdata for Histogram Data, and
ext for Extended Drive Statistics.
inst (Instantaneous). This measurement provides a short duration average.
ra (Running Average). Running average is a measure of long-term averages that smooth out the data, and results in older results fading from the average over time.
ext (Extended Drive Statistics). The extended drive statistics refers to statistics of a drive's read commands, write commands, write commands with FUA (Force Unit Access), flush commands, and a drive sectors's read, write, and write commands with FUA.
lct (Long Command Times). This a collection of the commands with the longest read/write response time.
histdata (Histogram Data). The histogram categorizes the read/write execution times and group them together based on time frames.
Summaries of the statistics for all drives on a controller are also available for the
inst,
ra, and
ext statistics, by using the command
/cx show dpmstat [type=inst|ra|ext]. For more information, see
Drive Performance Monitoring of the
3ware SAS/SATA RAID Software User Guide, Version 9.5.1.
//localhost> /c0/p3 show dpmstat type=ra
Queue Xfer Resp
Port Status Unit Depth IOPs Rate(MB/s) Time(ms)
--------------------------------------------------------------
p3 OK u0 0 435 25.249 2
//localhost> /c0/p3 show dpmstat type=lct
Port Status Unit
------------------------------
p3 OK u0
Resp
Date Time Time(ms) --------- CDB / ATA Task File (hex) -----------
---------------------------------------------------------------------------
2007-02-09 13:47:57 383.216 00 80 60 40 92 9f 8a 40 1a 00 00 00 00 00 00 00
2007-02-09 13:47:57 390.809 00 80 60 40 13 eb 30 40 26 00 00 00 00 00 00 00
2007-02-09 13:47:57 405.478 00 80 60 40 61 11 20 40 26 00 00 00 00 00 00 00
2007-02-09 13:47:57 410.379 00 80 60 40 cd 8b b9 40 23 00 00 00 00 00 00 00
2007-02-09 13:47:57 419.002 00 80 60 40 5e df d1 40 29 00 00 00 00 00 00 00
2007-02-09 13:47:57 444.250 00 80 60 40 8b c0 36 40 2e 00 00 00 00 00 00 00
2007-02-09 13:47:57 527.994 00 80 60 40 6e a5 b6 40 03 00 00 00 00 00 00 00
2007-02-09 13:47:57 569.429 00 80 60 40 3b e2 02 40 2d 00 00 00 00 00 00 00
2007-02-09 13:47:57 609.526 00 80 60 40 27 1c e9 40 2b 00 00 00 00 00 00 00
2007-02-09 13:47:57 612.051 00 80 60 40 dd 0b d1 40 2c 00 00 00 00 00 00 00
Note that in addition to the time and date stamps of the commands with the long response teims, their corresponding CDB or ATA Task File is displayed.
To display a histogram of IOPs grouped together based on response time associated with the specified port, use command /cx/px show dpmstat type=histdata.
//localhost> /c0/p3 show dpmstat type=histdata
Port Status Unit
------------------------------
p3 OK u0
Bin Response Time(ms) IO Count
-----------------------------------------------
1 1 0
2 2 0
3 3 0
4 4 0
5 5 0
6 6 0
7 7 0
8 8 0
9 9 0
10 10 0
11 20 204
12 30 190
13 40 161
14 50 136
15 60 130
16 70 112
17 80 94
18 90 80
19 100 540
20 200 95
21 300 42
22 400 11
23 500 2
24 600 2
25 700 0
26 800 0
27 900 0
28 1000 0
29 2000 0
30 3000 0
31 4000 0
32 5000 0
33 6000 0
34 7000 0
35 8000 0
36 9000 0
37 10000 0
38 10000+ 0
Note that in the example above, there is a set of 38 “Bins” (shown in the first column) and each bin has associated with it a different Response Time category (shown in the second column). There are no commands with response times of 10 milliseconds or shorter, and there are 204 commands with response times between 10 and 20 milliseconds (bin 11).Each time that an I/O or command sends to a drive, the response time for that I/O increments the bin associated with that response time.