File 0119-Assemble-array-with-write-journal.patch of Package mdadm.5365
From 69a481166be6df468367378c16c02a2c5dbe5c24 Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Thu, 8 Oct 2015 22:51:44 -0700
Subject: [PATCH 173/359] Assemble array with write journal
References: bsc#1081910
Example output:
./mdadm --assemble /dev/md0 /dev/sd[c-f] /dev/sdb1
Mdadm: /dev/md0 has been started with 4 drives and 1 journal.
mdadm checks superblock for journal devices. If the journal device
is missing or faulty, mdadm will show warning
./mdadm --assemble /dev/md0 /dev/sd[c-q] /dev/sdb1
Mdadm: Not safe to assemble with missing or stale journal device, consider --force.
User can insist to start the array (read only) with --force
./mdadm --assemble /dev/md0 /dev/sd[c-q] /dev/sdb1 --force
Mdadm: Journal is missing or stale, starting array read only.
Mdadm: /dev/md0 has been started with 15 drives.
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Coly Li <colyli@suse.de>
---
Assemble.c | 57 ++++++++++++++++++++++++++++++++++++++++++++++-----------
mdadm.h | 3 +++
super1.c | 37 ++++++++++++++++++++++++++++++++-----
3 files changed, 81 insertions(+), 16 deletions(-)
diff --git a/Assemble.c b/Assemble.c
index d9e9001..0661e8d 100644
--- a/Assemble.c
+++ b/Assemble.c
@@ -735,7 +735,7 @@ static int load_devices(struct devs *devices, char *devmap,
i = devcnt;
else
i = devices[devcnt].i.disk.raid_disk;
- if (i+1 == 0) {
+ if (i+1 == 0 || i == MD_DISK_ROLE_JOURNAL) {
if (nextspare < content->array.raid_disks*2)
nextspare = content->array.raid_disks*2;
i = nextspare++;
@@ -913,7 +913,6 @@ static int force_array(struct mdinfo *content,
avail[chosen_drive] = 1;
okcnt++;
tst->ss->free_super(tst);
-
/* If there are any other drives of the same vintage,
* add them in as well. We can't lose and we might gain
*/
@@ -944,17 +943,29 @@ static int start_array(int mdfd,
unsigned int okcnt,
unsigned int sparecnt,
unsigned int rebuilding_cnt,
+ unsigned int journalcnt,
struct context *c,
int clean, char *avail,
int start_partial_ok,
int err_ok,
- int was_forced
+ int was_forced,
+ int expect_journal,
+ int journal_clean
)
{
int rv;
int i;
unsigned int req_cnt;
+ if (expect_journal && (journal_clean == 0)) {
+ if (!c->force) {
+ pr_err("Not safe to assemble with missing or stale journal device, consider --force.\n");
+ return 1;
+ }
+ pr_err("Journal is missing or stale, starting array read only.\n");
+ c->readonly = 1;
+ }
+
rv = set_array_info(mdfd, st, content);
if (rv && !err_ok) {
pr_err("failed to set array info for %s: %s\n",
@@ -1032,7 +1043,8 @@ static int start_array(int mdfd,
if (content->array.level == LEVEL_CONTAINER) {
if (c->verbose >= 0) {
pr_err("Container %s has been assembled with %d drive%s",
- mddev, okcnt+sparecnt, okcnt+sparecnt==1?"":"s");
+ mddev, okcnt+sparecnt+journalcnt,
+ okcnt+sparecnt+journalcnt==1?"":"s");
if (okcnt < (unsigned)content->array.raid_disks)
fprintf(stderr, " (out of %d)",
content->array.raid_disks);
@@ -1118,6 +1130,8 @@ static int start_array(int mdfd,
fprintf(stderr, "%s %d rebuilding", sparecnt?",":" and", rebuilding_cnt);
if (sparecnt)
fprintf(stderr, " and %d spare%s", sparecnt, sparecnt==1?"":"s");
+ if (journal_clean)
+ fprintf(stderr, " and %d journal", journalcnt);
fprintf(stderr, ".\n");
}
if (content->reshape_active &&
@@ -1289,10 +1303,12 @@ int Assemble(struct supertype *st, char *mddev,
int *best = NULL; /* indexed by raid_disk */
int bestcnt = 0;
int devcnt;
- unsigned int okcnt, sparecnt, rebuilding_cnt, replcnt;
+ unsigned int okcnt, sparecnt, rebuilding_cnt, replcnt, journalcnt;
int i;
int was_forced = 0;
int most_recent = 0;
+ int expect_journal = 0;
+ int journal_clean = 0;
int chosen_drive;
int change = 0;
int inargv = 0;
@@ -1355,6 +1371,14 @@ try_again:
if (!st || !st->sb || !content)
return 2;
+ if (st->ss->require_journal) {
+ expect_journal = st->ss->require_journal(st);
+ if (expect_journal == 2) {
+ pr_err("BUG: Superblock not loaded in Assemble.c:Assemble\n");
+ return 1;
+ }
+ }
+
/* We have a full set of devices - we now need to find the
* array device.
* However there is a risk that we are racing with "mdadm -I"
@@ -1530,6 +1554,7 @@ try_again:
okcnt = 0;
replcnt = 0;
sparecnt=0;
+ journalcnt=0;
rebuilding_cnt=0;
for (i=0; i< bestcnt; i++) {
int j = best[i];
@@ -1540,8 +1565,13 @@ try_again:
/* note: we ignore error flags in multipath arrays
* as they don't make sense
*/
- if (content->array.level != LEVEL_MULTIPATH)
- if (!(devices[j].i.disk.state & (1<<MD_DISK_ACTIVE))) {
+ if (content->array.level != LEVEL_MULTIPATH) {
+ if (devices[j].i.disk.state & (1<<MD_DISK_JOURNAL)) {
+ if (expect_journal)
+ journalcnt++;
+ else /* unexpected journal, mark as faulty */
+ devices[j].i.disk.state |= (1<<MD_DISK_FAULTY);
+ } else if (!(devices[j].i.disk.state & (1<<MD_DISK_ACTIVE))) {
if (!(devices[j].i.disk.state
& (1<<MD_DISK_FAULTY))) {
devices[j].uptodate = 1;
@@ -1549,6 +1579,7 @@ try_again:
}
continue;
}
+ }
/* If this device thinks that 'most_recent' has failed, then
* we must reject this device.
*/
@@ -1572,6 +1603,8 @@ try_again:
devices[most_recent].i.events
) {
devices[j].uptodate = 1;
+ if (devices[j].i.disk.state & (1<<MD_DISK_JOURNAL))
+ journal_clean = 1;
if (i < content->array.raid_disks * 2) {
if (devices[j].i.recovery_start == MaxSector ||
(content->reshape_active &&
@@ -1583,7 +1616,7 @@ try_again:
replcnt++;
} else
rebuilding_cnt++;
- } else
+ } else if (devices[j].i.disk.raid_disk != MD_DISK_ROLE_JOURNAL)
sparecnt++;
}
}
@@ -1647,7 +1680,9 @@ try_again:
int j = best[i];
unsigned int desired_state;
- if (i >= content->array.raid_disks * 2)
+ if (devices[j].i.disk.raid_disk == MD_DISK_ROLE_JOURNAL)
+ desired_state = (1<<MD_DISK_JOURNAL);
+ else if (i >= content->array.raid_disks * 2)
desired_state = 0;
else if (i & 1)
desired_state = (1<<MD_DISK_ACTIVE) | (1<<MD_DISK_REPLACEMENT);
@@ -1794,11 +1829,11 @@ try_again:
rv = start_array(mdfd, mddev, content,
st, ident, best, bestcnt,
chosen_drive, devices, okcnt, sparecnt,
- rebuilding_cnt,
+ rebuilding_cnt, journalcnt,
c,
clean, avail, start_partial_ok,
pre_exist != NULL,
- was_forced);
+ was_forced, expect_journal, journal_clean);
if (rv == 1 && !pre_exist)
ioctl(mdfd, STOP_ARRAY, NULL);
free(devices);
diff --git a/mdadm.h b/mdadm.h
index 0b27b43..b1028be 100644
--- a/mdadm.h
+++ b/mdadm.h
@@ -970,6 +970,9 @@ extern struct superswitch {
/* validate container after assemble */
int (*validate_container)(struct mdinfo *info);
+ /* whether the array require a journal device */
+ int (*require_journal)(struct supertype *st);
+
int swapuuid; /* true if uuid is bigending rather than hostendian */
int external;
const char *name; /* canonical metadata name */
diff --git a/super1.c b/super1.c
index 85e3b28..47acdec 100644
--- a/super1.c
+++ b/super1.c
@@ -140,6 +140,34 @@ struct misc_dev_info {
|MD_FEATURE_BITMAP_VERSIONED \
|MD_FEATURE_JOURNAL \
)
+/* return value:
+ * 0, jouranl not required
+ * 1, journal required
+ * 2, no superblock loated (st->sb == NULL)
+ */
+static int require_journal1(struct supertype *st)
+{
+ struct mdp_superblock_1 *sb = st->sb;
+
+ if (sb->feature_map & MD_FEATURE_JOURNAL)
+ return 1;
+ else if (!sb)
+ return 2; /* no sb loaded */
+ return 0;
+}
+
+static int role_from_sb(struct mdp_superblock_1 *sb)
+{
+ unsigned int d;
+ int role;
+
+ d = __le32_to_cpu(sb->dev_number);
+ if (d < __le32_to_cpu(sb->max_dev))
+ role = __le16_to_cpu(sb->dev_roles[d]);
+ else
+ role = MD_DISK_ROLE_SPARE;
+ return role;
+}
/* return how many bytes are needed for bitmap, for cluster-md each node
* should have it's own bitmap */
@@ -482,11 +510,7 @@ static void examine_super1(struct supertype *st, char *homehost)
printf(")\n");
#endif
printf(" Device Role : ");
- d = __le32_to_cpu(sb->dev_number);
- if (d < __le32_to_cpu(sb->max_dev))
- role = __le16_to_cpu(sb->dev_roles[d]);
- else
- role = MD_DISK_ROLE_SPARE;
+ role = role_from_sb(sb);
if (role >= MD_DISK_ROLE_FAULTY)
printf("spare\n");
else if (role == MD_DISK_ROLE_JOURNAL)
@@ -1126,6 +1150,8 @@ static int update_super1(struct supertype *st, struct mdinfo *info,
int want;
if (info->disk.state & (1<<MD_DISK_ACTIVE))
want = info->disk.raid_disk;
+ else if (info->disk.state & (1<<MD_DISK_JOURNAL))
+ want = MD_DISK_ROLE_JOURNAL;
else
want = MD_DISK_ROLE_SPARE;
if (sb->dev_roles[d] != __cpu_to_le16(want)) {
@@ -2560,6 +2586,7 @@ struct superswitch super1 = {
.locate_bitmap = locate_bitmap1,
.write_bitmap = write_bitmap1,
.free_super = free_super1,
+ .require_journal = require_journal1,
#if __BYTE_ORDER == BIG_ENDIAN
.swapuuid = 0,
#else
--
2.16.1
