On Fri, Dec 12, 2014 at 04:23:16PM -0800, Linus Torvalds wrote:
> On Fri, Dec 12, 2014 at 3:54 PM, Sasha Levin <sasha.le...@oracle.com> wrote:
> >
> > I ran bisection on trinity, rather than the kernel, and got the following
> > result:
>
> Heh. That commit is pretty small, but I guess the effect of having a
> number of regular files open and being used on the trinity loads can
> be almost arbitrarily large.
>
> Where do those files get opened? What filesystem?
in the cwd where trinity is run from. In my case, ext4
> > I've been running trinity f2be2d5ff^ on -next for two hours now, and
> > there's
> > no sign of a lockup. Previously it took ~10 minutes trigger.
>
> DaveJ? Is there anything limiting the size of those files?
Nope. We could for eg, do a random truncate() with a huge size, and it would
try and create something enormous. write()'s are limited to page size,
there might be some other syscalls I haven't added safety guards to.
Dave
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
