Re: [RFC v6][PATCH 0/9] Kernel based checkpoint/restart

[Cedric Le Goater <clg@fr.ibm.com>]

> Oren> For now, yes. But we definitely want this capability in the long
> Oren> run; otherwise we won't be able to checkpoint a kernel compile
> Oren> ('make' uses vfork), or anything with 'gdb' running inside, or
> Oren> 'strace', and other goodies.
> 
> The strace/gdb example is *really* hard; but for vfork, you just wait
> until it's over. The interval between vfork and exec/exit should be
> short enough not to affect the overall time for a checkpoint (and
> checkpoint can be fairly slow anyway --- on the HPC machines we used
> to do it on, writing half a terabyte of checkpoint image to disc could take
> many minutes.  In hindsight, we should have multithreaded it).

we've tried that and it doesn't change a thing if you have only one disk :)
it might even give worse results as you are increasing context switches.

> Waiting for a vforked process to exec is less than a millisecond.

yes that shouldn't be too hard to handle.

Cheers,

C.