linux-block.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Guilherme G. Piccoli" <gpiccoli@canonical.com>
To: linux-raid@vger.kernel.org
Cc: linux-block@vger.kernel.org, dm-devel@redhat.com,
	gpiccoli@canonical.com, jay.vosburgh@canonical.com,
	neilb@suse.com, songliubraving@fb.com
Subject: [PATCH 1/2] md/raid0: Introduce new array state 'broken' for raid0
Date: Mon, 29 Jul 2019 17:31:34 -0300	[thread overview]
Message-ID: <20190729203135.12934-2-gpiccoli@canonical.com> (raw)
In-Reply-To: <20190729203135.12934-1-gpiccoli@canonical.com>

Currently if a md/raid0 array gets one or more members removed while
being mounted, kernel keeps showing state 'clean' in the 'array_state'
sysfs attribute. Despite udev signaling the member device is gone, 'mdadm'
cannot issue the STOP_ARRAY ioctl successfully, given the array is mounted.

Nothing else hints that something is wrong (except that the removed devices
don't show properly in the output of 'mdadm detail' command). There is no
other property to be checked, and if user is not performing reads/writes
to the array, even kernel log is quiet and doesn't give a clue about the
missing member.

This patch changes this behavior; when 'array_state' is read we introduce
a non-expensive check (only for raid0) that relies in the comparison of
the total number of disks when array was assembled with gendisk flags of
those devices to validate if all members are available and functional.
A new array state 'broken' was added: it mimics the state 'clean' in every
aspect, being useful only to distinguish if such array has some member
missing. Also, we show a rate-limited warning in kernel log in such case.

This patch has no proper functional change other than adding a 'clean'-like
state; it was tested with ext4 and xfs filesystems. It requires a 'mdadm'
counterpart to handle the 'broken' state.

Cc: NeilBrown <neilb@suse.com>
Cc: Song Liu <songliubraving@fb.com>
Signed-off-by: Guilherme G. Piccoli <gpiccoli@canonical.com>
---
 drivers/md/md.c    | 23 +++++++++++++++++++----
 drivers/md/md.h    |  2 ++
 drivers/md/raid0.c | 26 ++++++++++++++++++++++++++
 3 files changed, 47 insertions(+), 4 deletions(-)

diff --git a/drivers/md/md.c b/drivers/md/md.c
index fba49918d591..b80f36084ec1 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -4160,12 +4160,18 @@ __ATTR_PREALLOC(resync_start, S_IRUGO|S_IWUSR,
  * active-idle
  *     like active, but no writes have been seen for a while (100msec).
  *
+ * broken
+ *     RAID0-only: same as clean, but array is missing a member.
+ *     It's useful because RAID0 mounted-arrays aren't stopped
+ *     when a member is gone, so this state will at least alert
+ *     the user that something is wrong.
+ *
  */
 enum array_state { clear, inactive, suspended, readonly, read_auto, clean, active,
-		   write_pending, active_idle, bad_word};
+		   write_pending, active_idle, broken, bad_word};
 static char *array_states[] = {
 	"clear", "inactive", "suspended", "readonly", "read-auto", "clean", "active",
-	"write-pending", "active-idle", NULL };
+	"write-pending", "active-idle", "broken", NULL };
 
 static int match_word(const char *word, char **list)
 {
@@ -4181,7 +4187,7 @@ array_state_show(struct mddev *mddev, char *page)
 {
 	enum array_state st = inactive;
 
-	if (mddev->pers)
+	if (mddev->pers) {
 		switch(mddev->ro) {
 		case 1:
 			st = readonly;
@@ -4201,7 +4207,15 @@ array_state_show(struct mddev *mddev, char *page)
 				st = active;
 			spin_unlock(&mddev->lock);
 		}
-	else {
+
+		if ((mddev->pers->level == 0) &&
+		   ((st == clean) || (st == broken))) {
+			if (mddev->pers->is_missing_dev(mddev))
+				st = broken;
+			else
+				st = clean;
+		}
+	} else {
 		if (list_empty(&mddev->disks) &&
 		    mddev->raid_disks == 0 &&
 		    mddev->dev_sectors == 0)
@@ -4315,6 +4329,7 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
 		break;
 	case write_pending:
 	case active_idle:
+	case broken:
 		/* these cannot be set */
 		break;
 	}
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 41552e615c4c..e7b42b75701a 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -590,6 +590,8 @@ struct md_personality
 	int (*congested)(struct mddev *mddev, int bits);
 	/* Changes the consistency policy of an active array. */
 	int (*change_consistency_policy)(struct mddev *mddev, const char *buf);
+	/* Check if there is any missing/failed members - RAID0 only for now. */
+	bool (*is_missing_dev)(struct mddev *mddev);
 };
 
 struct md_sysfs_entry {
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 58a9cc5193bf..79618a6ae31a 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -455,6 +455,31 @@ static inline int is_io_in_chunk_boundary(struct mddev *mddev,
 	}
 }
 
+bool raid0_is_missing_dev(struct mddev *mddev)
+{
+	struct md_rdev *rdev;
+	static int already_missing;
+	int def_disks, work_disks = 0;
+	struct r0conf *conf = mddev->private;
+
+	def_disks = conf->strip_zone[0].nb_dev;
+	rdev_for_each(rdev, mddev)
+		if (rdev->bdev->bd_disk->flags & GENHD_FL_UP)
+			work_disks++;
+
+	if (unlikely(def_disks - work_disks)) {
+		if (!already_missing) {
+			already_missing = 1;
+			pr_warn("md: %s: raid0 array has %d missing/failed members\n",
+				mdname(mddev), (def_disks - work_disks));
+		}
+		return true;
+	}
+
+	already_missing = 0;
+	return false;
+}
+
 static void raid0_handle_discard(struct mddev *mddev, struct bio *bio)
 {
 	struct r0conf *conf = mddev->private;
@@ -789,6 +814,7 @@ static struct md_personality raid0_personality=
 	.takeover	= raid0_takeover,
 	.quiesce	= raid0_quiesce,
 	.congested	= raid0_congested,
+	.is_missing_dev	= raid0_is_missing_dev,
 };
 
 static int __init raid0_init (void)
-- 
2.22.0


  reply	other threads:[~2019-07-29 20:32 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-07-29 20:31 [PATCH 0/2] Introduce new raid0 state 'broken' Guilherme G. Piccoli
2019-07-29 20:31 ` Guilherme G. Piccoli [this message]
2019-07-30  0:11   ` [PATCH 1/2] md/raid0: Introduce new array state 'broken' for raid0 NeilBrown
2019-07-30 11:43     ` Guilherme G. Piccoli
2019-07-30  6:20   ` Bob Liu
2019-07-30 12:18     ` Guilherme G. Piccoli
2019-07-31  0:28     ` NeilBrown
2019-07-31 13:04       ` Guilherme G. Piccoli
2019-07-31 19:47         ` Song Liu
2019-07-31 19:43   ` Song Liu
2019-08-01 12:07     ` Guilherme G. Piccoli
2019-08-16 13:48       ` Guilherme G. Piccoli
2019-07-29 20:31 ` [PATCH 2/2] mdadm: " Guilherme G. Piccoli

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=20190729203135.12934-2-gpiccoli@canonical.com \
    --to=gpiccoli@canonical.com \
    --cc=dm-devel@redhat.com \
    --cc=jay.vosburgh@canonical.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-raid@vger.kernel.org \
    --cc=neilb@suse.com \
    --cc=songliubraving@fb.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).