Re: Remote fork() and Parallel Programming
Andrej Presern (andrejp@luz.fe.uni-lj.si)
Fri, 12 Jun 1998 11:30:09 +0200
Rogier Wolff wrote:
>
> mshar@vax.ipm.ac.ir wrote:
> > Why would you want checkpoint/restart if you had transparent process
> > migration? Checkpoint/restart requires work on the part of the application
> > programmer, while transparent process migration does notbecause it is done
> > by the kernel).
>
> You can do checkpoint/restart in userspace, now if you want to. That
> requires the application to know about it.
>
> I thought we were talking about a checkpoint/restart with minimal
> kernel support that would allow a non-aware program to be
> checkpointed/restarted.
>
> Something like
>
> killall -99 xemacs
>
> would generate a large CORE file, which would have the neccesary info
> to restart the program without any support from the "child" process.
Taking a shapshot of a single process is not a very good idea since
processes often depend on some other processes' data (not to mention the
kernel). If you want to snapshot all info that is neccessary to restart
a process, you have to snapshot all related processes and the state of
the kernel. It's a much better idea to have general persistency and take
periodic system-wide snapshots.
Andrej
--
Andrej Presern, andrejp@luz.fe.uni-lj.si
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu