| Commit message (Collapse) | Author | Age | Files | Lines |
|
|
|
|
|
|
|
| |
to half compensate for broken scaling of p_pctcpu in the kernel, but the
previous commit removed this compensation. %cpu values will be wrong by
a factor of stathz/hz until the kernel is fixed. (The kernel gets it
wrong by a factor of stathz/hz, and top got the compensation wrong by
a factor of 100/stathz.)
|
|
|
|
| |
Submitted by: Hidetoshi Shimokawa <simokawa@sat.t.u-tokyo.ac.jp>
|
|
|
|
| |
Obtained from: pstat.c
|
| |
|
|
|
|
|
|
|
|
| |
Attempts to contact the author of top(1) (William LeFebvre) have so
far been unsuccessful.
PR: 7253
Submitted by: Yours Truly
|
| |
|
|
|
|
| |
Obtained from: ps(1)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Clean up (or if antipodic: down) some of the msgbuf stuff.
Use an inline function rather than a macro for timecounter delta.
Maintain process "on-cpu" time as 64 bits of microseconds to avoid
needless second rollover overhead.
Avoid calling microuptime the second time in mi_switch() if we do
not pass through _idle in cpu_switch()
This should reduce our context-switch overhead a bit, in particular
on pre-P5 and SMP systems.
WARNING: Programs which muck about with struct proc in userland
will have to be fixed.
Reviewed, but found imperfect by: bde
|
|
|
|
|
|
|
| |
but that isn't suitable (it gets zeroed each second apparently).
PR: bin/4957
Submitted-by: Dan Nelson <dnelson@emsphone.com>
|
|
|
|
| |
Everything following bumps right 1 character.
|
| |
|
| |
|
| |
|
|
|
|
|
|
| |
username present on the system at startup and use that for the field width.
It's not ideal but (I think) better than it was before. The width is
limited to within 8..16.
|
|
|
|
| |
appearing on uniprocessor systems since the smp->current merge.
|
| |
|
| |
|
|
|
|
| |
is remotely useful
|
| |
|
|
that pulls all the files from contrib.
Obtained from: The ports collection (mostly).
|