Re: [PATCH] barrier patch set

[Jens Axboe]

On Mon, Mar 22 2004, Andrew Morton wrote:
> Jens Axboe <axboe@xxxxxxx> wrote:
> >
> >  A first release of a collected barrier patchset for 2.6.5-rc1-mm2.
> 
> The tagging of BIOs with set_buffer_ordered() or WRITE_BARRIER is a little
> awkward.
> 
> Take the case of an ext2 fsync() or even an ext3 fsync() which frequently
> will not trigger a commit.  If we must perform the barrier by tagging the
> final BIO, that will be tricky to implement.  I could set some new field in
> struct writeback_control and rework the mpage code, but working out "this
> is the final BIO for this operation" is a fairly hard thing to do. 
> sys_sync() would require even more VFS surgery.

Yeah, it's not very pretty if you have to track the last sumit. Chris
complained about that in 2.4 as well :-)

> Generally, it would be much preferable to use the blkdev_issue_flush()
> API.  What is the status of that?

It'll be fully supported.

-- 
Jens Axboe

-
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/