The patch titled
lguest: block device speedup
has been added to the -mm tree. Its filename is
lguest-trivial-guest-block-driver-lguest-block-device-speedup.patch
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
------------------------------------------------------
Subject: lguest: block device speedup
From: Rusty Russell <rusty@xxxxxxxxxxxxxxx>
Jens Axboe pointed out that end_request() does not end the entire request. Go
figure. On the upside, he wrote the replacement for me! Now we do far less
block traffic, and our performance sucks less.
Signed-off-by: Rusty Russell <rusty@xxxxxxxxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxx>
Cc: Jens Axboe <jens.axboe@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
drivers/block/lguest_blk.c | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
diff -puN drivers/block/lguest_blk.c~lguest-trivial-guest-block-driver-lguest-block-device-speedup drivers/block/lguest_blk.c
--- a/drivers/block/lguest_blk.c~lguest-trivial-guest-block-driver-lguest-block-device-speedup
+++ a/drivers/block/lguest_blk.c
@@ -45,6 +45,16 @@ struct blockdev
struct request *req;
};
+/* Jens gave me this nice helper to end all chunks of a request. */
+static void end_entire_request(struct request *req, int uptodate)
+{
+ if (end_that_request_first(req, uptodate, req->hard_nr_sectors))
+ BUG();
+ add_disk_randomness(req->rq_disk);
+ blkdev_dequeue_request(req);
+ end_that_request_last(req, uptodate);
+}
+
static irqreturn_t lgb_irq(int irq, void *_bd)
{
struct blockdev *bd = _bd;
@@ -61,7 +71,7 @@ static irqreturn_t lgb_irq(int irq, void
}
spin_lock_irqsave(&bd->lock, flags);
- end_request(bd->req, bd->lb_page->result == 1);
+ end_entire_request(bd->req, bd->lb_page->result == 1);
bd->req = NULL;
bd->dma.used_len = 0;
blk_start_queue(bd->disk->queue);
@@ -149,7 +159,7 @@ again:
pr_debug("Got non-command 0x%08x\n", req->cmd_type);
error:
req->errors++;
- end_request(req, 0);
+ end_entire_request(req, 0);
goto again;
} else {
if (rq_data_dir(req) == WRITE)
_
Patches currently in -mm which might be from rusty@xxxxxxxxxxxxxxx are
futex-restartable-futex_wait.patch
i386-vdso_prelink-warning-fix.patch
cleanup-initialize-esp0-properly-all-the-time.patch
lguest-preparation-export_symbol_gpl-5-functions.patch
lguest-preparation-expose-futex-infrastructure.patch
lguest-kconfig-and-headers.patch
lguest-the-host-code-lgko.patch
lguest-guest-code.patch
lguest-makefile.patch
lguest-trivial-guest-network-driver.patch
lguest-trivial-guest-console-driver.patch
lguest-trivial-guest-block-driver.patch
lguest-trivial-guest-block-driver-lguest-block-device-speedup.patch
lguest-documentatation-and-example-launcher.patch
lguest-bridging-support-in-example-code.patch
lguest-cleanup-allocate-separate-pages-for-switcher-code.patch
lguest-cleanup-clean-up-regs-save-restore.patch
lguest-documentation-fixes.patch
lguest-pin-stack-page-optimization.patch
lguest-use-read-only-pages-rather-than-segments-to-protect-high-mapped-switcher.patch
lguest-optimize-away-copy-in-and-out-of-per-cpu-guest-pages.patch
lguest-dont-crash-host-on-nmi.patch
module-use-krealloc.patch
extend-print_symbol-capability.patch
array_size-check-for-type.patch
____call_usermodehelper-dont-flush_signals.patch
add-ability-to-keep-track-of-callers-of-symbol_getput.patch
add-ability-to-keep-track-of-callers-of-symbol_getput-tidy.patch
update-mtd-use-of-symbol_getput.patch
update-dvb-use-of-symbol_getput.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
