Romain Lenglet wrote:
Added documentation for the new -U option, and did some cleanups.


a few *tiny* issues.

-d   eg: /dev/hda1 might be better than /dev/hda/,  and drop trailing slash.

-m, -M.    log-file not required.

-N   path can be /absolute too, not just ../relative

-p 'cmd'   no longer run between latencies, just before & after


-s -T 10 -q    the 10 is now 120.

more subtly - your intro doesnt express the defaulting behavior that this section does describe. any pass-thru provided with turn off those defaults, so if you just use -h, the test will output lines each second, and never finish, so you dont get histogram (IIRC - you may get it from ^C handler). Im not at all sure its worth touching, and I should probably change the defaults to add histogram,
and drop quiet.

-h implies -s   (its just easier that way)

-- needed by testsuite/*/run scripts, not by xeno-test. I dont recall every using it.


-N   name is timestamped, giving uniqueness.  This is a caveat, not a bug

-p   oops.   Im open to suggestions whether this is worth fixing.

(workload mgmt)

  workload tasks arent always (ever?) restarted once they finish,
so a real /dev/hda1 workload may end before your test does, causing non-uniform &
unexpected load variations.

workloads arent always killed if test is interrupted.


Xenomai-core mailing list

Reply via email to