The patch titled
md: allow checkpoint of recovery with version-1 superblock
has been added to the -mm tree. Its filename is
md-allow-checkpoint-of-recovery-with-version-1-superblock.patch
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
From: NeilBrown <neilb@xxxxxxx>
For a while we have had checkpointing of resync. The version-1 superblock
allows recovery to be checkpointed as well, and this patch implements that.
Due to early carelessness we need to add a feature flag to signal that the
recovery_offset field is in use, otherwise older kernels would assume that a
partially recovered array is in fact fully recovered.
Signed-off-by: Neil Brown <neilb@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxx>
---
drivers/md/md.c | 115 +++++++++++++++++++++++++++++-------
drivers/md/raid1.c | 3
drivers/md/raid10.c | 3
drivers/md/raid5.c | 1
include/linux/raid/md_k.h | 6 +
include/linux/raid/md_p.h | 5 +
6 files changed, 109 insertions(+), 24 deletions(-)
diff -puN drivers/md/md.c~md-allow-checkpoint-of-recovery-with-version-1-superblock drivers/md/md.c
--- devel/drivers/md/md.c~md-allow-checkpoint-of-recovery-with-version-1-superblock 2006-04-30 22:41:25.000000000 -0700
+++ devel-akpm/drivers/md/md.c 2006-04-30 22:41:25.000000000 -0700
@@ -1165,7 +1165,11 @@ static int super_1_validate(mddev_t *mdd
set_bit(Faulty, &rdev->flags);
break;
default:
- set_bit(In_sync, &rdev->flags);
+ if ((le32_to_cpu(sb->feature_map) &
+ MD_FEATURE_RECOVERY_OFFSET))
+ rdev->recovery_offset = le64_to_cpu(sb->recovery_offset);
+ else
+ set_bit(In_sync, &rdev->flags);
rdev->raid_disk = role;
break;
}
@@ -1189,6 +1193,7 @@ static void super_1_sync(mddev_t *mddev,
sb->feature_map = 0;
sb->pad0 = 0;
+ sb->recovery_offset = cpu_to_le64(0);
memset(sb->pad1, 0, sizeof(sb->pad1));
memset(sb->pad2, 0, sizeof(sb->pad2));
memset(sb->pad3, 0, sizeof(sb->pad3));
@@ -1209,6 +1214,14 @@ static void super_1_sync(mddev_t *mddev,
sb->bitmap_offset = cpu_to_le32((__u32)mddev->bitmap_offset);
sb->feature_map = cpu_to_le32(MD_FEATURE_BITMAP_OFFSET);
}
+
+ if (rdev->raid_disk >= 0 &&
+ !test_bit(In_sync, &rdev->flags) &&
+ rdev->recovery_offset > 0) {
+ sb->feature_map |= cpu_to_le32(MD_FEATURE_RECOVERY_OFFSET);
+ sb->recovery_offset = cpu_to_le64(rdev->recovery_offset);
+ }
+
if (mddev->reshape_position != MaxSector) {
sb->feature_map |= cpu_to_le32(MD_FEATURE_RESHAPE_ACTIVE);
sb->reshape_position = cpu_to_le64(mddev->reshape_position);
@@ -1233,11 +1246,12 @@ static void super_1_sync(mddev_t *mddev,
sb->dev_roles[i] = cpu_to_le16(0xfffe);
else if (test_bit(In_sync, &rdev2->flags))
sb->dev_roles[i] = cpu_to_le16(rdev2->raid_disk);
+ else if (rdev2->raid_disk >= 0 && rdev2->recovery_offset > 0)
+ sb->dev_roles[i] = cpu_to_le16(rdev2->raid_disk);
else
sb->dev_roles[i] = cpu_to_le16(0xffff);
}
- sb->recovery_offset = cpu_to_le64(0); /* not supported yet */
sb->sb_csum = calc_sb_1_csum(sb);
}
@@ -2590,8 +2604,6 @@ static struct kobject *md_probe(dev_t de
return NULL;
}
-void md_wakeup_thread(mdk_thread_t *thread);
-
static void md_safemode_timeout(unsigned long data)
{
mddev_t *mddev = (mddev_t *) data;
@@ -2773,6 +2785,36 @@ static int do_md_run(mddev_t * mddev)
mddev->queue->queuedata = mddev;
mddev->queue->make_request_fn = mddev->pers->make_request;
+ /* If there is a partially-recovered drive we need to
+ * start recovery here. If we leave it to md_check_recovery,
+ * it will remove the drives and not do the right thing
+ */
+ if (mddev->degraded) {
+ struct list_head *rtmp;
+ int spares = 0;
+ ITERATE_RDEV(mddev,rdev,rtmp)
+ if (rdev->raid_disk >= 0 &&
+ !test_bit(In_sync, &rdev->flags) &&
+ !test_bit(Faulty, &rdev->flags))
+ /* complete an interrupted recovery */
+ spares++;
+ if (spares && mddev->pers->sync_request) {
+ mddev->recovery = 0;
+ set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
+ mddev->sync_thread = md_register_thread(md_do_sync,
+ mddev,
+ "%s_resync");
+ if (!mddev->sync_thread) {
+ printk(KERN_ERR "%s: could not start resync"
+ " thread...\n",
+ mdname(mddev));
+ /* leave the spares where they are, it shouldn't hurt */
+ mddev->recovery = 0;
+ } else
+ md_wakeup_thread(mddev->sync_thread);
+ }
+ }
+
mddev->changed = 1;
md_new_event(mddev);
return 0;
@@ -2806,6 +2848,7 @@ static int restart_array(mddev_t *mddev)
*/
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
+ md_wakeup_thread(mddev->sync_thread);
err = 0;
} else {
printk(KERN_ERR "md: %s has no personality assigned.\n",
@@ -2829,6 +2872,7 @@ static int do_md_stop(mddev_t * mddev, i
}
if (mddev->sync_thread) {
+ set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
md_unregister_thread(mddev->sync_thread);
mddev->sync_thread = NULL;
@@ -2858,13 +2902,14 @@ static int do_md_stop(mddev_t * mddev, i
if (mddev->ro)
mddev->ro = 0;
}
- if (!mddev->in_sync) {
+ if (!mddev->in_sync || mddev->sb_dirty) {
/* mark array as shutdown cleanly */
mddev->in_sync = 1;
md_update_sb(mddev);
}
if (ro)
set_disk_ro(disk, 1);
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
}
/*
@@ -4652,10 +4697,14 @@ void md_do_sync(mddev_t *mddev)
struct list_head *tmp;
sector_t last_check;
int skipped = 0;
+ struct list_head *rtmp;
+ mdk_rdev_t *rdev;
/* just incase thread restarts... */
if (test_bit(MD_RECOVERY_DONE, &mddev->recovery))
return;
+ if (mddev->ro) /* never try to sync a read-only array */
+ return;
/* we overload curr_resync somewhat here.
* 0 == not engaged in resync at all
@@ -4714,17 +4763,30 @@ void md_do_sync(mddev_t *mddev)
}
} while (mddev->curr_resync < 2);
+ j = 0;
if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
/* resync follows the size requested by the personality,
* which defaults to physical size, but can be virtual size
*/
max_sectors = mddev->resync_max_sectors;
mddev->resync_mismatches = 0;
+ /* we don't use the checkpoint if there's a bitmap */
+ if (!mddev->bitmap &&
+ !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
+ j = mddev->recovery_cp;
} else if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
max_sectors = mddev->size << 1;
- else
+ else {
/* recovery follows the physical size of devices */
max_sectors = mddev->size << 1;
+ j = MaxSector;
+ ITERATE_RDEV(mddev,rdev,rtmp)
+ if (rdev->raid_disk >= 0 &&
+ !test_bit(Faulty, &rdev->flags) &&
+ !test_bit(In_sync, &rdev->flags) &&
+ rdev->recovery_offset < j)
+ j = rdev->recovery_offset;
+ }
printk(KERN_INFO "md: syncing RAID array %s\n", mdname(mddev));
printk(KERN_INFO "md: minimum _guaranteed_ reconstruction speed:"
@@ -4734,12 +4796,7 @@ void md_do_sync(mddev_t *mddev)
speed_max(mddev));
is_mddev_idle(mddev); /* this also initializes IO event counters */
- /* we don't use the checkpoint if there's a bitmap */
- if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) && !mddev->bitmap
- && ! test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
- j = mddev->recovery_cp;
- else
- j = 0;
+
io_sectors = 0;
for (m = 0; m < SYNC_MARKS; m++) {
mark[m] = jiffies;
@@ -4860,15 +4917,28 @@ void md_do_sync(mddev_t *mddev)
if (!test_bit(MD_RECOVERY_ERR, &mddev->recovery) &&
test_bit(MD_RECOVERY_SYNC, &mddev->recovery) &&
!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) &&
- mddev->curr_resync > 2 &&
- mddev->curr_resync >= mddev->recovery_cp) {
- if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
- printk(KERN_INFO
- "md: checkpointing recovery of %s.\n",
- mdname(mddev));
- mddev->recovery_cp = mddev->curr_resync;
- } else
- mddev->recovery_cp = MaxSector;
+ mddev->curr_resync > 2) {
+ if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
+ if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
+ if (mddev->curr_resync >= mddev->recovery_cp) {
+ printk(KERN_INFO
+ "md: checkpointing recovery of %s.\n",
+ mdname(mddev));
+ mddev->recovery_cp = mddev->curr_resync;
+ }
+ } else
+ mddev->recovery_cp = MaxSector;
+ } else {
+ if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery))
+ mddev->curr_resync = MaxSector;
+ ITERATE_RDEV(mddev,rdev,rtmp)
+ if (rdev->raid_disk >= 0 &&
+ !test_bit(Faulty, &rdev->flags) &&
+ !test_bit(In_sync, &rdev->flags) &&
+ rdev->recovery_offset < mddev->curr_resync)
+ rdev->recovery_offset = mddev->curr_resync;
+ mddev->sb_dirty = 1;
+ }
}
skip:
@@ -4989,6 +5059,8 @@ void md_check_recovery(mddev_t *mddev)
clear_bit(MD_RECOVERY_INTR, &mddev->recovery);
clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
+ if (test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
+ goto unlock;
/* no recovery is running.
* remove any failed drives, then
* add spares if possible.
@@ -5011,6 +5083,7 @@ void md_check_recovery(mddev_t *mddev)
ITERATE_RDEV(mddev,rdev,rtmp)
if (rdev->raid_disk < 0
&& !test_bit(Faulty, &rdev->flags)) {
+ rdev->recovery_offset = 0;
if (mddev->pers->hot_add_disk(mddev,rdev)) {
char nm[20];
sprintf(nm, "rd%d", rdev->raid_disk);
diff -puN drivers/md/raid10.c~md-allow-checkpoint-of-recovery-with-version-1-superblock drivers/md/raid10.c
--- devel/drivers/md/raid10.c~md-allow-checkpoint-of-recovery-with-version-1-superblock 2006-04-30 22:41:25.000000000 -0700
+++ devel-akpm/drivers/md/raid10.c 2006-04-30 22:41:25.000000000 -0700
@@ -2015,7 +2015,8 @@ static int run(mddev_t *mddev)
disk = conf->mirrors + i;
- if (!disk->rdev) {
+ if (!disk->rdev ||
+ !test_bit(In_sync, &rdev->flags)) {
disk->head_position = 0;
mddev->degraded++;
}
diff -puN drivers/md/raid1.c~md-allow-checkpoint-of-recovery-with-version-1-superblock drivers/md/raid1.c
--- devel/drivers/md/raid1.c~md-allow-checkpoint-of-recovery-with-version-1-superblock 2006-04-30 22:41:25.000000000 -0700
+++ devel-akpm/drivers/md/raid1.c 2006-04-30 22:41:25.000000000 -0700
@@ -1888,7 +1888,8 @@ static int run(mddev_t *mddev)
disk = conf->mirrors + i;
- if (!disk->rdev) {
+ if (!disk->rdev ||
+ !test_bit(In_sync, &rdev->flags)) {
disk->head_position = 0;
mddev->degraded++;
}
diff -puN drivers/md/raid5.c~md-allow-checkpoint-of-recovery-with-version-1-superblock drivers/md/raid5.c
--- devel/drivers/md/raid5.c~md-allow-checkpoint-of-recovery-with-version-1-superblock 2006-04-30 22:41:25.000000000 -0700
+++ devel-akpm/drivers/md/raid5.c 2006-04-30 22:41:25.000000000 -0700
@@ -3555,6 +3555,7 @@ static int raid5_start_reshape(mddev_t *
set_bit(In_sync, &rdev->flags);
conf->working_disks++;
added_devices++;
+ rdev->recovery_offset = 0;
sprintf(nm, "rd%d", rdev->raid_disk);
sysfs_create_link(&mddev->kobj, &rdev->kobj, nm);
} else
diff -puN include/linux/raid/md_k.h~md-allow-checkpoint-of-recovery-with-version-1-superblock include/linux/raid/md_k.h
--- devel/include/linux/raid/md_k.h~md-allow-checkpoint-of-recovery-with-version-1-superblock 2006-04-30 22:41:25.000000000 -0700
+++ devel-akpm/include/linux/raid/md_k.h 2006-04-30 22:41:25.000000000 -0700
@@ -88,6 +88,10 @@ struct mdk_rdev_s
* array and could again if we did a partial
* resync from the bitmap
*/
+ sector_t recovery_offset;/* If this device has been partially
+ * recovered, this is where we were
+ * up to.
+ */
atomic_t nr_pending; /* number of pending requests.
* only maintained for arrays that
@@ -183,6 +187,8 @@ struct mddev_s
#define MD_RECOVERY_REQUESTED 6
#define MD_RECOVERY_CHECK 7
#define MD_RECOVERY_RESHAPE 8
+#define MD_RECOVERY_FROZEN 9
+
unsigned long recovery;
int in_sync; /* know to not need resync */
diff -puN include/linux/raid/md_p.h~md-allow-checkpoint-of-recovery-with-version-1-superblock include/linux/raid/md_p.h
--- devel/include/linux/raid/md_p.h~md-allow-checkpoint-of-recovery-with-version-1-superblock 2006-04-30 22:41:25.000000000 -0700
+++ devel-akpm/include/linux/raid/md_p.h 2006-04-30 22:41:25.000000000 -0700
@@ -265,9 +265,12 @@ struct mdp_superblock_1 {
/* feature_map bits */
#define MD_FEATURE_BITMAP_OFFSET 1
+#define MD_FEATURE_RECOVERY_OFFSET 2 /* recovery_offset is present and
+ * must be honoured
+ */
#define MD_FEATURE_RESHAPE_ACTIVE 4
-#define MD_FEATURE_ALL 5
+#define MD_FEATURE_ALL (1|2|4)
#endif
_
Patches currently in -mm which might be from neilb@xxxxxxx are
md-avoid-oops-when-attempting-to-fix-read-errors-on-raid10.patch
md-fixed-refcounting-locking-when-attempting-read-error-correction-in-raid10.patch
md-change-enotsupp-to-eopnotsupp.patch
md-improve-detection-of-lack-of-barrier-support-in-raid1.patch
md-fix-rdev-nr_pending-count-when-retrying-barrier-requests.patch
fix-dcache-race-during-umount.patch
fix-dcache-race-during-umount-fix.patch
prune_one_dentry-tweaks.patch
remove-softlockup-from-invalidate_mapping_pages.patch
make-address_space_operations-invalidatepage-return-void-reiser4.patch
md-reformat-code-in-raid1_end_write_request-to-avoid-goto.patch
md-remove-arbitrary-limit-on-chunk-size.patch
md-remove-useless-ioctl-warning.patch
md-increase-the-delay-before-marking-metadata-clean-and-make-it-configurable.patch
md-merge-raid5-and-raid6-code.patch
md-remove-nuisance-message-at-shutdown.patch
md-allow-checkpoint-of-recovery-with-version-1-superblock.patch
md-allow-a-linear-array-to-have-drives-added-while-active.patch
md-support-stripe-offset-mode-in-raid10.patch
md-make-md_print_devices-static.patch
md-split-reshape-portion-of-raid5-sync_request-into-a-separate-function.patch
md-dm-reduce-stack-usage-with-stacked-block-devices.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
