Comparative times for 'make buildworld'
for unmodified and KSE (milestone-2) kernels
unmodified -current
2138.464u 3358.378s 1:37:39.77 93.8% 842+1080k 45105+176988io 3208pf+0w
modified KSE kernel
2143.716u 3363.311s 1:37:50.33 93.8% 841+1081k 45435+176988io 3214pf+0w
I'm very glad to see that the overhead added was not too great.
(well within the margin of error I'm sure)
Same system, same source tree, just different kernel.
/usr/obj was deleted before the previous reboot in both cases.
Stdout not redirected, running via ssh from another machine.
No soft-updates.
ref4# size /k* (GENERIC config)
text data bss dec hex filename
3180804 275436 350612 3806852 3a1684 /kernel.normal
3188036 275436 350836 3814308 3a33a4 /kernel.kse
My guess is that the size increase in the text area
is due to the extra code here and there to take the extra dereference
from (p) to (td->td_proc) and the places where
there is both a td variabel and a p variable. (with extra code
to initialise them)
Possibly an extra 1K for code to initialise the more complicated structures too.
More actual code will be needed to get away from 1:1, so this is just a
baseline.
the next steps are for us a s a groupt to decide if this is really the way we
want to go,
and if so, whether we want to commit these changes to make them available for
the world
to work on as a base for real threading support. The alternative is to
do linux-type threading with processes (peter wemm has been investigating a
variant
on this scheme). This is probably a no-turning-back commit.
It's presently checked in on the FreeBSD p4 tree based on freefall,
so it's safe, but we need to make a decision on where it goes next.
--
+------------------------------------+ ______ _ __
| __--_|\ Julian Elischer | \ U \/ / hard at work in
| / \ [EMAIL PROTECTED] +------>x USA \ a very strange
| ( OZ ) \___ ___ | country !
+- X_.---._/ presently in San Francisco \_/ \\
v
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-current" in the body of the message
