Messages in this thread | | | Subject | Re: [PATCH] increment nr_tasks in io_context when CLONE_IO is set | From | Nikanth Karthikesan <> | Date | Wed, 16 Apr 2008 09:05:11 +0530 |
| |
On Tue, 2008-04-15 at 09:24 +0200, Jens Axboe wrote: > On Tue, Apr 15 2008, Nikanth Karthikesan wrote: > > Increment the nr_tasks associated with the io_context when CLONE_IO flag > > is set. > > > > Signed-off-by: Nikanth Karthikesan <knikanth@suse.de> > > > > -- > > diff --git a/kernel/fork.c b/kernel/fork.c > > index dd249c3..01e843b 100644 > > --- a/kernel/fork.c > > +++ b/kernel/fork.c > > @@ -812,6 +812,7 @@ static int copy_io(unsigned long clone_f > > tsk->io_context = ioc_task_link(ioc); > > if (unlikely(!tsk->io_context)) > > return -ENOMEM; > > + atomic_inc(&tsk->io_context->nr_tasks); > > } else if (ioprio_valid(ioc->ioprio)) { > > tsk->io_context = alloc_io_context(GFP_KERNEL, -1); > > if (unlikely(!tsk->io_context)) > > Fix is correct, however it would be more appropriate in ioc_task_link() > instead.
Yes. Thanks.
> > diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h > index cac4b36..2b7a118 100644 > --- a/include/linux/iocontext.h > +++ b/include/linux/iocontext.h > @@ -91,8 +91,10 @@ static inline struct io_context *ioc_task_link(struct io_context *ioc) > * if ref count is zero, don't allow sharing (ioc is going away, it's > * a race). > */ > - if (ioc && atomic_inc_not_zero(&ioc->refcount)) > + if (ioc && atomic_inc_not_zero(&ioc->refcount)) { > + atomic_inc(&ioc->nr_tasks); > return ioc; > + } > > return NULL; > } >
| |