Re: [PATCH] vfs: Add a trace point in the mark_inode_dirty function

From: Arjan van de Ven
Date: Mon Oct 26 2009 - 02:54:21 EST


On Sun, 25 Oct 2009 23:03:21 -0700
Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> wrote:

> > ...
> >
> > @@ -1071,6 +1072,8 @@ void __mark_inode_dirty(struct inode *inode,
> > int flags) if ((inode->i_state & flags) == flags)
> > return;
> >
> > + trace_dirty_inode(inode, current);
> > +
> > if (unlikely(block_dump))
> > block_dump___mark_inode_dirty(inode);
> >
>
> Doesn't powertop also want to know who is spinning up the disk via
> buffered reads, direct-io reads and direct-io writes?
>
> That's why the block_dump hook in submit_bio() is there.

there is already an existing trace event for this in the block layer...
I was planning to use block_bio_queue for this.

--
Arjan van de Ven Intel Open Source Technology Centre
For development, discussion and tips for power savings,
visit http://www.lesswatts.org
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/