Date: Wed, 17 Mar 1999 07:01:34 +0200 (EET) From: Juha Nurmela <junki@qn-lpr2-98.quicknet.inet.fi> To: questions@FreeBSD.ORG Message-ID: <199903170501.HAA79973@qn-lpr2-98.quicknet.inet.fi>
next in thread | raw e-mail | index | archive | help
This most probably is just silly, but I have no face left to lose...
I'm running 4.0-current on AMD K5. Still pondering the 'slow clock'
problem this cpu had, I noticed something odd (for me that is).
swtch.s does something like
cli
if (!processes to run) {
sti
hlt_vector(); /* which is just a hlt; ret; */
}
I recall that sti extends the 'masked condition' to the next
instruction, but no longer. Isn't the call op in between sti/hlt
sometimes causing a userland delay of upto 1/128 seconds ?
It might not happen often, hardly ever maybe, but still...
Confused, as usual,
Juha Nurmela
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-questions" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199903170501.HAA79973>