[PATCH] md: Support suspending of IO to regions of an md array
This allows user-space to access data safely. This is needed for raid5
reshape as user-space needs to take a backup of the first few stripes before
allowing reshape to commence.
It will also be useful in cluster-aware raid1 configurations so that all
cluster members can leave a section of the array untouched while a
resync/recovery happens.
A 'start' and 'end' of the suspended range are written to 2 sysfs attributes.
Note that only one range can be suspended at a time.
Signed-off-by: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
diff --git a/drivers/md/md.c b/drivers/md/md.c
index a79dd33..92fd010 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -2365,6 +2365,63 @@
static struct md_sysfs_entry
md_sync_completed = __ATTR_RO(sync_completed);
+static ssize_t
+suspend_lo_show(mddev_t *mddev, char *page)
+{
+ return sprintf(page, "%llu\n", (unsigned long long)mddev->suspend_lo);
+}
+
+static ssize_t
+suspend_lo_store(mddev_t *mddev, const char *buf, size_t len)
+{
+ char *e;
+ unsigned long long new = simple_strtoull(buf, &e, 10);
+
+ if (mddev->pers->quiesce == NULL)
+ return -EINVAL;
+ if (buf == e || (*e && *e != '\n'))
+ return -EINVAL;
+ if (new >= mddev->suspend_hi ||
+ (new > mddev->suspend_lo && new < mddev->suspend_hi)) {
+ mddev->suspend_lo = new;
+ mddev->pers->quiesce(mddev, 2);
+ return len;
+ } else
+ return -EINVAL;
+}
+static struct md_sysfs_entry md_suspend_lo =
+__ATTR(suspend_lo, S_IRUGO|S_IWUSR, suspend_lo_show, suspend_lo_store);
+
+
+static ssize_t
+suspend_hi_show(mddev_t *mddev, char *page)
+{
+ return sprintf(page, "%llu\n", (unsigned long long)mddev->suspend_hi);
+}
+
+static ssize_t
+suspend_hi_store(mddev_t *mddev, const char *buf, size_t len)
+{
+ char *e;
+ unsigned long long new = simple_strtoull(buf, &e, 10);
+
+ if (mddev->pers->quiesce == NULL)
+ return -EINVAL;
+ if (buf == e || (*e && *e != '\n'))
+ return -EINVAL;
+ if ((new <= mddev->suspend_lo && mddev->suspend_lo >= mddev->suspend_hi) ||
+ (new > mddev->suspend_lo && new > mddev->suspend_hi)) {
+ mddev->suspend_hi = new;
+ mddev->pers->quiesce(mddev, 1);
+ mddev->pers->quiesce(mddev, 0);
+ return len;
+ } else
+ return -EINVAL;
+}
+static struct md_sysfs_entry md_suspend_hi =
+__ATTR(suspend_hi, S_IRUGO|S_IWUSR, suspend_hi_show, suspend_hi_store);
+
+
static struct attribute *md_default_attrs[] = {
&md_level.attr,
&md_raid_disks.attr,
@@ -2382,6 +2439,8 @@
&md_sync_max.attr,
&md_sync_speed.attr,
&md_sync_completed.attr,
+ &md_suspend_lo.attr,
+ &md_suspend_hi.attr,
NULL,
};
static struct attribute_group md_redundancy_group = {
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 355dafb..bb16ac2 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1805,6 +1805,15 @@
goto retry;
}
}
+ /* FIXME what if we get a false positive because these
+ * are being updated.
+ */
+ if (logical_sector >= mddev->suspend_lo &&
+ logical_sector < mddev->suspend_hi) {
+ release_stripe(sh);
+ schedule();
+ goto retry;
+ }
if (test_bit(STRIPE_EXPANDING, &sh->state) ||
!add_stripe_bio(sh, bi, dd_idx, (bi->bi_rw&RW_MASK))) {
@@ -2725,6 +2734,10 @@
raid5_conf_t *conf = mddev_to_conf(mddev);
switch(state) {
+ case 2: /* resume for a suspend */
+ wake_up(&conf->wait_for_overlap);
+ break;
+
case 1: /* stop all writes */
spin_lock_irq(&conf->device_lock);
conf->quiesce = 1;
@@ -2738,6 +2751,7 @@
spin_lock_irq(&conf->device_lock);
conf->quiesce = 0;
wake_up(&conf->wait_for_stripe);
+ wake_up(&conf->wait_for_overlap);
spin_unlock_irq(&conf->device_lock);
break;
}
