On Thu, 2 Mar 2006, Linus Torvalds wrote: > > As far as I can tell, the rest of the thread has been _whining_. > > Guys, what's so hard with just raising the limits on the common SG_IO > thing (the same way people had to raise the limits on the _old_ sg-only > thing), instead of whining about it? To clarify, the thing people seem to be whining about is that SG now _honors_ the limits that we have. For example, the code now honors things like "max_sectors", which was apparently totally ignored before, and sg could pass in requests that were simply NOT VALID for the limits the driver itself could have set.. This is why I say people are "whining". It's obviously fixing something that we did wrong before. The fact that the wrong thing happened to work is not all that relevant, especially since - any breakage will likely be pretty obvious - any breakage will be limited to people who do special things on special hardware. - the people who did special things like this are apparently already used to doing things like changing SG_SCATTER_SZ and then _recompiling_ the whole kernel (it wasn't ever a dynamic option or anything like that). so we're not exactly looking at a poor clueless users going "uhhuh, my machine won't boot any more" kind of issues. We're looking at fixing a deficiency in the code, that may expose drivers etc that have set their limits low. Linus - : send the line "unsubscribe linux-scsi" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
