On Wed, 12 Mar 2014, David Mosberger wrote:
> On Wed, Mar 12, 2014 at 2:53 PM, Alan Stern <stern@xxxxxxxxxxxxxxxxxxx> wrote:
> > On Wed, 12 Mar 2014, David Mosberger wrote:
>
> >> I see the same WRITE_10 commands of 122,880 bytes (240 sectors), but
> >> the glaring difference is that each such WRITE_10 command seems to be
> >> followed by ~ 27 READ_10 commands reading 1KB (2 sectors), whereas
> >> with the MAX3421 driver, I see consecutive WRITE_10 commands. Anybody
> >> know where those READ_10 commands are coming from?
> >
> > I'd guess it's some sort of readahead. Not that it makes much sense to
> > read sectors that are about to be overwritten.
> >
> > Did those READ commands occur before you started running dd?
>
> Definitely not.
>
> I attached a log of a good (working) dd, showing only the "USBC"
> transactions. The '\n (" commands are READ_10, the "\n *" commands
> are WRITE_10.
I can't tell much by looking at that log. (Incidentally, usbmon ought
to show much the same information in a more readable form.)
I think you can disable readahead by doing
echo 0 >/sys/block/sdX/queue/read_ahead_kb
where X is replaced by the appropriate letter for the USB drive.
Alan Stern
--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
