From: Shaohua Li <shli@kernel.org>
To: linux-raid@vger.kernel.org
Cc: neilb@suse.de, axboe@kernel.dk, dan.j.williams@intel.com,
shli@fusionio.com
Subject: [patch 04/10 v3] raid5: lockless access raid5 overrided bi_phys_segments
Date: Mon, 25 Jun 2012 15:24:51 +0800 [thread overview]
Message-ID: <20120625072625.099376476@kernel.org> (raw)
In-Reply-To: 20120625072447.268095276@kernel.org
[-- Attachment #1: raid5-atomic-segment-accounting.patch --]
[-- Type: text/plain, Size: 6243 bytes --]
Raid5 overrides bio->bi_phys_segments, accessing it is with device_lock hold,
which is unnecessary, We can make it lockless actually.
Signed-off-by: Shaohua Li <shli@fusionio.com>
---
drivers/md/raid5.c | 58 +++++++++++++++++++++++++++++------------------------
1 file changed, 32 insertions(+), 26 deletions(-)
Index: linux/drivers/md/raid5.c
===================================================================
--- linux.orig/drivers/md/raid5.c 2012-06-25 14:37:13.651888057 +0800
+++ linux/drivers/md/raid5.c 2012-06-25 14:37:18.743841116 +0800
@@ -99,34 +99,40 @@ static inline struct bio *r5_next_bio(st
* We maintain a biased count of active stripes in the bottom 16 bits of
* bi_phys_segments, and a count of processed stripes in the upper 16 bits
*/
-static inline int raid5_bi_phys_segments(struct bio *bio)
+static inline int raid5_bi_processed_stripes(struct bio *bio)
{
- return bio->bi_phys_segments & 0xffff;
+ atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
+ return (atomic_read(segments) >> 16) & 0xffff;
}
-static inline int raid5_bi_hw_segments(struct bio *bio)
+static inline int raid5_dec_bi_active_stripes(struct bio *bio)
{
- return (bio->bi_phys_segments >> 16) & 0xffff;
+ atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
+ return atomic_sub_return(1, segments) & 0xffff;
}
-static inline int raid5_dec_bi_phys_segments(struct bio *bio)
+static inline void raid5_inc_bi_active_stripes(struct bio *bio)
{
- --bio->bi_phys_segments;
- return raid5_bi_phys_segments(bio);
+ atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
+ atomic_inc(segments);
}
-static inline int raid5_dec_bi_hw_segments(struct bio *bio)
+static inline void raid5_set_bi_processed_stripes(struct bio *bio,
+ unsigned int cnt)
{
- unsigned short val = raid5_bi_hw_segments(bio);
+ atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
+ int old, new;
- --val;
- bio->bi_phys_segments = (val << 16) | raid5_bi_phys_segments(bio);
- return val;
+ do {
+ old = atomic_read(segments);
+ new = (old & 0xffff) | (cnt << 16);
+ } while (atomic_cmpxchg(segments, old, new) != old);
}
-static inline void raid5_set_bi_hw_segments(struct bio *bio, unsigned int cnt)
+static inline void raid5_set_bi_stripes(struct bio *bio, unsigned int cnt)
{
- bio->bi_phys_segments = raid5_bi_phys_segments(bio) | (cnt << 16);
+ atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
+ atomic_set(segments, cnt);
}
/* Find first data disk in a raid6 stripe */
@@ -769,7 +775,7 @@ static void ops_complete_biofill(void *s
while (rbi && rbi->bi_sector <
dev->sector + STRIPE_SECTORS) {
rbi2 = r5_next_bio(rbi, dev->sector);
- if (!raid5_dec_bi_phys_segments(rbi)) {
+ if (!raid5_dec_bi_active_stripes(rbi)) {
rbi->bi_next = return_bi;
return_bi = rbi;
}
@@ -2356,7 +2362,7 @@ static int add_stripe_bio(struct stripe_
if (*bip)
bi->bi_next = *bip;
*bip = bi;
- bi->bi_phys_segments++;
+ raid5_inc_bi_active_stripes(bi);
if (forwrite) {
/* check if page is covered */
@@ -2456,7 +2462,7 @@ handle_failed_stripe(struct r5conf *conf
sh->dev[i].sector + STRIPE_SECTORS) {
struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector);
clear_bit(BIO_UPTODATE, &bi->bi_flags);
- if (!raid5_dec_bi_phys_segments(bi)) {
+ if (!raid5_dec_bi_active_stripes(bi)) {
md_write_end(conf->mddev);
bi->bi_next = *return_bi;
*return_bi = bi;
@@ -2471,7 +2477,7 @@ handle_failed_stripe(struct r5conf *conf
sh->dev[i].sector + STRIPE_SECTORS) {
struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);
clear_bit(BIO_UPTODATE, &bi->bi_flags);
- if (!raid5_dec_bi_phys_segments(bi)) {
+ if (!raid5_dec_bi_active_stripes(bi)) {
md_write_end(conf->mddev);
bi->bi_next = *return_bi;
*return_bi = bi;
@@ -2495,7 +2501,7 @@ handle_failed_stripe(struct r5conf *conf
struct bio *nextbi =
r5_next_bio(bi, sh->dev[i].sector);
clear_bit(BIO_UPTODATE, &bi->bi_flags);
- if (!raid5_dec_bi_phys_segments(bi)) {
+ if (!raid5_dec_bi_active_stripes(bi)) {
bi->bi_next = *return_bi;
*return_bi = bi;
}
@@ -2716,7 +2722,7 @@ static void handle_stripe_clean_event(st
while (wbi && wbi->bi_sector <
dev->sector + STRIPE_SECTORS) {
wbi2 = r5_next_bio(wbi, dev->sector);
- if (!raid5_dec_bi_phys_segments(wbi)) {
+ if (!raid5_dec_bi_active_stripes(wbi)) {
md_write_end(conf->mddev);
wbi->bi_next = *return_bi;
*return_bi = wbi;
@@ -3785,7 +3791,7 @@ static struct bio *remove_bio_from_retry
* this sets the active strip count to 1 and the processed
* strip count to zero (upper 8 bits)
*/
- bi->bi_phys_segments = 1; /* biased count of active stripes */
+ raid5_set_bi_stripes(bi, 1); /* biased count of active stripes */
}
return bi;
@@ -4124,7 +4130,7 @@ static void make_request(struct mddev *m
md_wakeup_thread(mddev->thread);
spin_lock_irq(&conf->device_lock);
- remaining = raid5_dec_bi_phys_segments(bi);
+ remaining = raid5_dec_bi_active_stripes(bi);
spin_unlock_irq(&conf->device_lock);
if (remaining == 0) {
@@ -4481,7 +4487,7 @@ static int retry_aligned_read(struct r5
sector += STRIPE_SECTORS,
scnt++) {
- if (scnt < raid5_bi_hw_segments(raid_bio))
+ if (scnt < raid5_bi_processed_stripes(raid_bio))
/* already done this stripe */
continue;
@@ -4489,14 +4495,14 @@ static int retry_aligned_read(struct r5
if (!sh) {
/* failed to get a stripe - must wait */
- raid5_set_bi_hw_segments(raid_bio, scnt);
+ raid5_set_bi_processed_stripes(raid_bio, scnt);
conf->retry_read_aligned = raid_bio;
return handled;
}
if (!add_stripe_bio(sh, raid_bio, dd_idx, 0)) {
release_stripe(sh);
- raid5_set_bi_hw_segments(raid_bio, scnt);
+ raid5_set_bi_processed_stripes(raid_bio, scnt);
conf->retry_read_aligned = raid_bio;
return handled;
}
@@ -4506,7 +4512,7 @@ static int retry_aligned_read(struct r5
handled++;
}
spin_lock_irq(&conf->device_lock);
- remaining = raid5_dec_bi_phys_segments(raid_bio);
+ remaining = raid5_dec_bi_active_stripes(raid_bio);
spin_unlock_irq(&conf->device_lock);
if (remaining == 0)
bio_endio(raid_bio, 0);
next prev parent reply other threads:[~2012-06-25 7:24 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-06-25 7:24 [patch 00/10 v3] raid5: improve write performance for fast storage Shaohua Li
2012-06-25 7:24 ` [patch 01/10 v3] raid5: use wake_up_all for overlap waking Shaohua Li
2012-06-28 7:26 ` NeilBrown
2012-06-28 8:53 ` Shaohua Li
2012-06-25 7:24 ` [patch 02/10 v3] raid5: delayed stripe fix Shaohua Li
2012-07-02 0:46 ` NeilBrown
2012-07-02 0:49 ` Shaohua Li
2012-07-02 0:55 ` NeilBrown
2012-06-25 7:24 ` [patch 03/10 v3] raid5: add a per-stripe lock Shaohua Li
2012-07-02 0:50 ` NeilBrown
2012-07-02 3:16 ` Shaohua Li
2012-07-02 7:39 ` NeilBrown
2012-07-03 1:27 ` Shaohua Li
2012-07-03 12:16 ` majianpeng
2012-07-03 23:56 ` NeilBrown
2012-07-04 1:09 ` majianpeng
2012-06-25 7:24 ` Shaohua Li [this message]
2012-06-25 7:24 ` [patch 05/10 v3] raid5: remove some device_lock locking places Shaohua Li
2012-06-25 7:24 ` [patch 06/10 v3] raid5: reduce chance release_stripe() taking device_lock Shaohua Li
2012-07-02 0:57 ` NeilBrown
2012-06-25 7:24 ` [patch 07/10 v3] md: personality can provide unplug private data Shaohua Li
2012-07-02 1:06 ` NeilBrown
2012-06-25 7:24 ` [patch 08/10 v3] raid5: make_request use batch stripe release Shaohua Li
2012-07-02 2:31 ` NeilBrown
2012-07-02 2:59 ` Shaohua Li
2012-07-02 5:07 ` NeilBrown
2012-06-25 7:24 ` [patch 09/10 v3] raid5: raid5d handle stripe in batch way Shaohua Li
2012-07-02 2:32 ` NeilBrown
2012-06-25 7:24 ` [patch 10/10 v3] raid5: create multiple threads to handle stripes Shaohua Li
2012-07-02 2:39 ` NeilBrown
2012-07-02 20:03 ` Dan Williams
2012-07-03 8:04 ` Shaohua Li
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20120625072625.099376476@kernel.org \
--to=shli@kernel.org \
--cc=axboe@kernel.dk \
--cc=dan.j.williams@intel.com \
--cc=linux-raid@vger.kernel.org \
--cc=neilb@suse.de \
--cc=shli@fusionio.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).