From: scjody@sun.com
To: linux-ext4@vger.kernel.org, linux-raid@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, Andreas Dilger <adilger@sun.com>
Subject: [patch 1/5] [md] Add fs_raidsync buffer & bio flags
Date: Thu, 19 Nov 2009 16:22:42 -0500 [thread overview]
Message-ID: <20091119212355.980768235@sun.com> (raw)
In-Reply-To: 20091119212241.283629302@sun.com
[-- Attachment #1: md-add-fs-raidsync.patch --]
[-- Type: TEXT/PLAIN, Size: 5549 bytes --]
Adds the BIO_FS_RAIDSYNC bio flag and the fs_raidsync buffer flag. These
are used to inform md that the filesystem takes responsibility for
resynchronizing parity information after a system crash.
When this flag is set on a raid4/5/6 device, the write will not be recorded
in the bitmap.
Signed-off-by: Jody McIntyre <scjody@sun.com>
Index: linux-2.6.18-128.7.1/drivers/md/raid5.c
===================================================================
--- linux-2.6.18-128.7.1.orig/drivers/md/raid5.c
+++ linux-2.6.18-128.7.1/drivers/md/raid5.c
@@ -1465,7 +1465,8 @@ static int add_stripe_bio(struct stripe_
(unsigned long long)bi->bi_sector,
(unsigned long long)sh->sector, dd_idx);
- if (conf->mddev->bitmap && firstwrite) {
+ if (conf->mddev->bitmap && firstwrite &&
+ !bio_flagged(bi, BIO_FS_RAIDSYNC)) {
bitmap_startwrite(conf->mddev->bitmap, sh->sector,
STRIPE_SECTORS, 0);
sh->bm_seq = conf->seq_flush+1;
@@ -1643,7 +1644,11 @@ static void handle_stripe5(struct stripe
/* fail all writes first */
bi = sh->dev[i].towrite;
sh->dev[i].towrite = NULL;
- if (bi) { to_write--; bitmap_end = 1; }
+ if (bi) {
+ to_write--;
+ if (!bio_flagged(bi, BIO_FS_RAIDSYNC))
+ bitmap_end = 1;
+ }
if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
wake_up(&conf->wait_for_overlap);
@@ -1661,7 +1666,8 @@ static void handle_stripe5(struct stripe
/* and fail all 'written' */
bi = sh->dev[i].written;
sh->dev[i].written = NULL;
- if (bi) bitmap_end = 1;
+ if (bi && !bio_flagged(bi, BIO_FS_RAIDSYNC))
+ bitmap_end = 1;
while (bi && bi->bi_sector < sh->dev[i].sector + STRIPE_SECTORS) {
struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);
clear_bit(BIO_UPTODATE, &bi->bi_flags);
@@ -1736,11 +1742,14 @@ static void handle_stripe5(struct stripe
md_write_end(conf->mddev);
wbi->bi_next = return_bi;
return_bi = wbi;
+ if (!bio_flagged(wbi,
+ BIO_FS_RAIDSYNC))
+ bitmap_end = 1;
}
wbi = wbi2;
}
- if (dev->towrite == NULL)
- bitmap_end = 1;
+ if (dev->towrite != NULL)
+ bitmap_end = 0;
spin_unlock_irq(&conf->device_lock);
if (bitmap_end)
bitmap_endwrite(conf->mddev->bitmap, sh->sector,
@@ -2220,7 +2229,11 @@ static void handle_stripe6(struct stripe
/* fail all writes first */
bi = sh->dev[i].towrite;
sh->dev[i].towrite = NULL;
- if (bi) { to_write--; bitmap_end = 1; }
+ if (bi) {
+ to_write--;
+ if (!bio_flagged(bi, BIO_FS_RAIDSYNC))
+ bitmap_end = 1;
+ }
if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
wake_up(&conf->wait_for_overlap);
@@ -2238,7 +2251,8 @@ static void handle_stripe6(struct stripe
/* and fail all 'written' */
bi = sh->dev[i].written;
sh->dev[i].written = NULL;
- if (bi) bitmap_end = 1;
+ if (bi && !bio_flagged(bi, BIO_FS_RAIDSYNC))
+ bitmap_end = 1;
while (bi && bi->bi_sector < sh->dev[i].sector + STRIPE_SECTORS) {
struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);
clear_bit(BIO_UPTODATE, &bi->bi_flags);
@@ -2324,11 +2338,14 @@ static void handle_stripe6(struct stripe
md_write_end(conf->mddev);
wbi->bi_next = return_bi;
return_bi = wbi;
+ if (!bio_flagged(wbi,
+ BIO_FS_RAIDSYNC))
+ bitmap_end = 1;
}
wbi = wbi2;
}
- if (dev->towrite == NULL)
- bitmap_end = 1;
+ if (dev->towrite != NULL)
+ bitmap_end = 0;
spin_unlock_irq(&conf->device_lock);
if (bitmap_end)
bitmap_endwrite(conf->mddev->bitmap, sh->sector,
Index: linux-2.6.18-128.7.1/fs/buffer.c
===================================================================
--- linux-2.6.18-128.7.1.orig/fs/buffer.c
+++ linux-2.6.18-128.7.1/fs/buffer.c
@@ -2859,6 +2859,9 @@ int submit_bh(int rw, struct buffer_head
bio->bi_end_io = end_bio_bh_io_sync;
bio->bi_private = bh;
+ if (buffer_fs_raidsync(bh))
+ set_bit(BIO_FS_RAIDSYNC, &bio->bi_flags);
+
bio_get(bio);
submit_bio(rw, bio);
Index: linux-2.6.18-128.7.1/include/linux/bio.h
===================================================================
--- linux-2.6.18-128.7.1.orig/include/linux/bio.h
+++ linux-2.6.18-128.7.1/include/linux/bio.h
@@ -124,6 +124,7 @@ struct bio {
#define BIO_BOUNCED 5 /* bio is a bounce bio */
#define BIO_USER_MAPPED 6 /* contains user pages */
#define BIO_EOPNOTSUPP 7 /* not supported */
+#define BIO_FS_RAIDSYNC 8 /* fs is responsible for RAID parity resync */
#define bio_flagged(bio, flag) ((bio)->bi_flags & (1 << (flag)))
/*
Index: linux-2.6.18-128.7.1/include/linux/buffer_head.h
===================================================================
--- linux-2.6.18-128.7.1.orig/include/linux/buffer_head.h
+++ linux-2.6.18-128.7.1/include/linux/buffer_head.h
@@ -32,6 +32,7 @@ enum bh_state_bits {
BH_Write_EIO, /* I/O error on write */
BH_Ordered, /* ordered write */
BH_Eopnotsupp, /* operation not supported (barrier) */
+ BH_FS_Raidsync, /* FS is responsible for RAID parity resyncs */
BH_PrivateStart,/* not a state bit, but the first bit available
* for private allocation by other entities
*/
@@ -124,6 +125,7 @@ BUFFER_FNS(Write_EIO, write_io_error)
BUFFER_FNS(Ordered, ordered)
BUFFER_FNS(Eopnotsupp, eopnotsupp)
BUFFER_FNS(Unwritten, unwritten)
+BUFFER_FNS(FS_Raidsync, fs_raidsync)
#define bh_offset(bh) ((unsigned long)(bh)->b_data & ~PAGE_MASK)
#define touch_buffer(bh) mark_page_accessed(bh->b_page)
--
next prev parent reply other threads:[~2009-11-19 21:23 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-11-19 21:22 [patch 0/5] Journal guided resync and support scjody
2009-11-19 21:22 ` scjody [this message]
2009-11-19 21:22 ` [patch 2/5] [md] Add syncraid buffer & bio flags scjody
2009-11-19 21:22 ` [patch 3/5] [jbd] Add support for journal guided resync scjody
2009-11-19 21:22 ` [patch 4/5] [ext3] Add journal guided resync (data=declared mode) scjody
2009-11-19 21:22 ` [patch 5/5] [md] Add SET_RESYNC_ALL and CLEAR_RESYNC_ALL ioctls scjody
2009-11-24 11:43 ` [patch 0/5] Journal guided resync and support Pavel Machek
2009-11-24 18:51 ` Andreas Dilger
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=20091119212355.980768235@sun.com \
--to=scjody@sun.com \
--cc=adilger@sun.com \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-raid@vger.kernel.org \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.