[LU-5394] routerstat units

• Type: Bug
• Resolution: Fixed
• Priority: Minor
• Fix Version/s: Lustre 2.7.0
• Affects Version/s: Lustre 2.5.1
• Severity: 3
• Assignee: James Nunez (Inactive)
• Reporter: Susan Coulter

Description

Where can I find information on the units attached to the results from routerstat? ( or any other details since the man page is pretty simple )

Issue Links

• is related to: LUDOC-253 Routerstat output needs correction

Comments

[James Nunez (Inactive)]

Man page update landed to master and Documentation included in latest manual.

[James Nunez (Inactive)]

Patch to update the routerstat man page at: http://review.whamcloud.com/#/c/11345/

Lustre Documentation ticket opened to update routerstat information in the manual is LUDOC-253

[Susan Coulter]

This answers my question perfectly - and updating the man page would be GREAT !

Thanx.

[James Nunez (Inactive)]

The output from routerstat looks something like:

# routerstat 
M 0(81) E 0 S 9469672032/1504246 R 522093480/1572375 F 0/0 D 0/0

The numbers after each letter are as follows:
M - Number of messages currently being processed by LNet (the maximum number of messages which were ever processed by LNet concurrently)
E - Number of LNet errors
S - Total size (length) of messages sent in bytes/ Number of messages sent
R - Total size (length) of messages received in bytes/Number of messages received
F - Total size (length) of messages routed in bytes/Number of messages routed
D - Total size (length) of messages dropped in bytes/Number of messages dropped

When you provide routerstat with an interval, in seconds, you will see something like:

# routerstat 1
M 0(13) E 0 S 117379184/4250 R 878480/4356 F 0/0 D 0/0
M   0( 13) E 0 S    0.00/     0 R    0.00/     0 F    0.00/     0 D 0.00/0
M   0( 13) E 0 S    0.00/     0 R    0.00/     0 F    0.00/     0 D 0.00/0
M   0( 13) E 0 S    7.00/     7 R    0.00/    14 F    0.00/     0 D 0.00/0
M   0( 13) E 0 S    8.00/     8 R    0.00/    16 F    0.00/     0 D 0.00/0
M   0( 13) E 0 S    7.00/     7 R    0.00/    14 F    0.00/     0 D 0.00/0
M   0( 13) E 0 S    7.00/     7 R    0.00/    14 F    0.00/     0 D 0.00/0
M   0( 13) E 0 S    7.00/     7 R    0.00/    14 F    0.00/     0 D 0.00/0
M   0( 13) E 0 S    7.00/     7 R    0.00/    14 F    0.00/     0 D 0.00/0
M   0( 13) E 0 S    8.00/     8 R    0.00/    16 F    0.00/     0 D 0.00/0

The first line of output is the same as if you didn't give routerstat an interval as in the previous example. Each of the other lines are:
M - Number of messages currently being processed by LNet (the maximum number of messages which were ever processed by LNet concurrently)
E - Number of LNet errors per second
S - Total size (length) of messages sent in Mbytes per second / Number of messages sent per second
R - Total size (length) of messages received in Mbytes per second /Number of messages received per second
F - Total size (length) of messages routed in Mbytes per second /Number of messages routed per second
D - Total size (length) of messages dropped in Mbytes per second /Number of messages dropped per second

I"ll upload a patch to update the man page and manual entry for routerstat with this information.

Please let me know if this answers your questions.