2.6.5-rc2-mm2 and direct_read_under

[Daniel McNeil]

I re-ran direct_read_under test (6 copies) on 2.6.4-rc2-mm2:

ext3 failed within 2 hours.

ext2 ran overnight without errors.

Daniel

On Thu, 2004-03-18 at 11:10, Daniel McNeil wrote:
> On Thu, 2004-03-18 at 10:47, Chris Mason wrote:
> > On Thu, 2004-03-18 at 12:53, Daniel McNeil wrote:
> > > I'm ran 2.6.4-mm2 plus the 2 wait_on_page_range() patches,
> > > the test_set_page_writeback() patch and clear_page_dirty_for_io patch
> > > overnight.
> > > 
> > > 6 copies of direct_read_under test on 8-cpu system on 1
> > > ext3 file system in 1 directory on a scsi disk.
> > > (http://developer.osdl.org/daniel/AIO/TESTS/direct_read_under.c)
> > > 
> > > 5 of the 6 tests saw uninitialized data within 2 hours.
> > > The sixth test ran overnight.
> > 
> > Do you still have the errors generated?  I wondering how big the range
> > of uninitialized data was.  When I was bug hunting yesterday, I saw
> > ranges from 64k to 32mb in size, which was why I decided writes weren't
> > getting to the disk at all.
> > 
> > It might be interesting to try with data=writeback, or on ext2.  Things
> > might be easier to track if we're not worried about ll_rw_block.
> > 
> > It might also be interesting to significantly lower the size of the
> > reads and writes done by direct_read_under, or anything else you can
> > think of to get the reproduce time down to something smaller than 2
> > hours...
> > 
> > It's probably a good idea to upgrade to 2.6.5-rc1-mm2, just so we're all
> > staring at the same code.
> > 
> > -chris
> > 
> 
> Chris,
> 
> Still have the data:
> 		 63 pages (258048 bytes)
> 		 90 pages (368640 bytes)
> 		139 pages (569344 bytes)
> 		 30 pages (122880 bytes)
> 		 87 pages (356352 bytes)
> 		
> 
> I'm rebooting to 2.6.5-rc1-mm2 and will re-run.  I have do have
> versions of direct_read_under that do smaller i/o and also
> 1 that does forks off and does 'sync' calls every few seconds.
> 
> I'll give ext2 and try as well.
> 
> Daniel
> 
> --
> To unsubscribe, send a message with 'unsubscribe linux-aio' in
> the body to majordomo@xxxxxxxxxx  For more info on Linux AIO,
> see: http://www.kvack.org/aio/
> Don't email: <a href=mailto:"aart@xxxxxxxxx";>aart@xxxxxxxxx</a>

-
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/