I've implemented the 'new' sorting scheme for blk.h
I just made up while writing the previous message.
Beware though, that this patch is completely untested.
Worse yet, I haven't even proofread it :-)
succes...
Rik.
+-----------------------------+------------------------------+
| For Linux mm-patches, go to | "I'm busy managing memory.." |
| my homepage (via LinuxHQ). | H.H.vanRiel@fys.ruu.nl |
| ...submissions welcome... | http://www.fys.ruu.nl/~riel/ |
+-----------------------------+------------------------------+
--- linux/include/linux/blk.h.orig Wed Mar 4 13:47:35 1998
+++ linux/include/linux/blk.h Wed Mar 4 13:50:28 1998
@@ -26,10 +26,14 @@
* over writes any more --- although reads are more time-critical than
* writes, by treating them equally we increase filesystem throughput.
* This turns out to give better overall performance. -- sct
+ * We ignore the major number and the first bit of the minor number,
+ * this way we hope to achieve some parrallelism <sp?> when flushing
+ * the disk. We ignore the SCSI minor-number scheme, since SCSI doesn't
+ * use this queue anyway -- Rik.
*/
#define IN_ORDER(s1,s2) \
-((s1)->rq_dev < (s2)->rq_dev || (((s1)->rq_dev == (s2)->rq_dev && \
-(s1)->sector < (s2)->sector)))
+(((s1)->rq_dev & 0x7f) < ((s2)->rq_dev & 0x7f) || ((((s1)->rq_dev & 0x7f) \
+== ((s2)->rq_dev & 0x7f) && (s1)->sector < (s2)->sector)))
/*
* These will have to be changed to be aware of different buffer
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu