Re: 2.6.2-mm1 aka "Geriatric Wombat" DIO read race still fails

[Daniel McNeil]

I patched 2.6.2-mm1 with the wait_on_buffer(bh) in
__block_write_full_page() and my tests ran overnight and
though today without any errors.

I'm looking to see if there is any way to move the end_page_writeback()
for this locked bh case to the end_buffer_write_sync().  Kind of
tricky...

Daniel


On Thu, 2004-02-05 at 15:58, Badari Pulavarty wrote:
> On Thursday 05 February 2004 03:31 pm, Daniel McNeil wrote:
> > Andrew,
> >
> > I tested 2.6.2-mm1 on an 8-proc running 6 copies of the read_under
> > test and all 6 read_under tests saw uninitialized data in less than 5
> > minutes. :(
> >
> > Daniel
> 
> Daniel,
> 
> Same here... Just FYI, I am running with your original patch and
> not failed so far (2 hours..) Normally, I see the problem in 15 min or so.
> 
> Thanks,
> Badari

-
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/