On Thu, 2 Mar 2006, Linus Torvalds wrote: > > - 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). And, final note: yes, the new "honor the limits" means that there may not be a single place to change like before. Most of the limits are per-driver, with some limits set by (arguably bad) SCSI midlevel code (I think max_sectors is a "unsigned short", for example, which obviously implies that 63355 sectors is a limit not of the drivers, but of the SCSI host code. The generic block layer, which people seem to like to blame, should actually be pretty blame-less. I think it tends to use full integers for its limits, for example. And tends to even allow changing the limits through sysfs (ie look for things like "max_sectors_kb" and "nr_reuests" etc in /sys/block/sdx/queue). 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
