Hello!
Probably (or probably not) you have heard about my Software Suspend
project (http://falcon.sch.bme.hu/~seasons/linux/swsusp.html)
This patch provides you the possibility to suspend the machine and save
its state onto swap and resume later (without using APM).
In the next version I'd like to support SMP but don't know if it's needed
at all.
Right by suspendig I stop all processes (with a special SIGSTOP signal),
shrink memory, save the remaining pages in memory onto swap and reboot.
What I'm afraid about SMP machines is that by suspendig another kernel
thread e.g. kswapd could run (since kernel threads are not stopped and I
think I can't stop them with a signal anyway (no ret from syscall)).. and
mess up everything. Well I don't think it would be likely.. but can occur.
What I thought for workaround is:
Launch as many kernel threads as many processors I have. With every thread
catch a processor and wait for a common flag (what means we have resumed).
With processor #0 I do the suspend thing..
One more question: should resuming run on the same processor as
suspending? (which are one code flow (process)) from the kernel
(scheduling) view..
Ps: please cc me directly as I'm not subscribed
Seasons
\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/
"One who has time to complain has time to submit patches." <chinese proverb>
\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/
-
Linux SMP list: FIRST see FAQ at http://www.irisa.fr/prive/mentre/smp-faq/
To Unsubscribe: send "unsubscribe linux-smp" to [EMAIL PROTECTED]
