md_cluster_info stores the cluster information in the MD device.
The join() is called when mddev detects it is a clustered device.
The main responsibilities are:
1. Setup a DLM lockspace
2. Setup all initial locks such as super block locks and bitmap lock (will come later)
The leave() clears up the lockspace and all the locks held.
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@xxxxxxxx>
---
drivers/md/bitmap.c | 4 +++
drivers/md/md-cluster.c | 67 +++++++++++++++++++++++++++++++++++++++++++++----
drivers/md/md.h | 8 ++++++
3 files changed, 74 insertions(+), 5 deletions(-)
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 4195a01..33374de 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -420,6 +420,7 @@ void bitmap_update_sb(struct bitmap *bitmap)
/* This might have been changed by a reshape */
sb->sync_size = cpu_to_le64(bitmap->mddev->resync_max_sectors);
sb->chunksize = cpu_to_le32(bitmap->mddev->bitmap_info.chunksize);
+ sb->nodes = cpu_to_le32(bitmap->mddev->bitmap_info.nodes);
sb->sectors_reserved = cpu_to_le32(bitmap->mddev->
bitmap_info.space);
kunmap_atomic(sb);
@@ -531,6 +532,7 @@ static int bitmap_read_sb(struct bitmap *bitmap)
bitmap_super_t *sb;
unsigned long chunksize, daemon_sleep, write_behind;
unsigned long long events;
+ int nodes = 0;
unsigned long sectors_reserved = 0;
int err = -EINVAL;
struct page *sb_page;
@@ -570,6 +572,7 @@ static int bitmap_read_sb(struct bitmap *bitmap)
daemon_sleep = le32_to_cpu(sb->daemon_sleep) * HZ;
write_behind = le32_to_cpu(sb->write_behind);
sectors_reserved = le32_to_cpu(sb->sectors_reserved);
+ nodes = le32_to_cpu(sb->nodes);
/* verify that the bitmap-specific fields are valid */
if (sb->magic != cpu_to_le32(BITMAP_MAGIC))
@@ -630,6 +633,7 @@ out_no_sb:
bitmap->mddev->bitmap_info.chunksize = chunksize;
bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep;
bitmap->mddev->bitmap_info.max_write_behind = write_behind;
+ bitmap->mddev->bitmap_info.nodes = nodes;
if (bitmap->mddev->bitmap_info.space == 0 ||
bitmap->mddev->bitmap_info.space > sectors_reserved)
bitmap->mddev->bitmap_info.space = sectors_reserved;
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index d2d4d33..fa28aed 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -25,8 +25,16 @@ struct dlm_lock_resource {
struct dlm_lksb lksb;
char *name; /* lock name. */
uint32_t flags; /* flags to pass to dlm_lock() */
- void (*bast)(void *arg, int mode); /* blocking AST function pointer*/
struct completion completion; /* completion for synchronized locking */
+ struct mddev *mddev; /* pointing back to mddev. */
+ void (*bast)(void *arg, int mode); /* blocking AST function pointer*/
+};
+
+struct md_cluster_info {
+ /* dlm lock space and resources for clustered raid. */
+ dlm_lockspace_t *lockspace;
+ struct dlm_lock_resource *sb_lock;
+ struct mutex sb_mutex;
};
static void sync_ast(void *arg)
@@ -54,16 +62,18 @@ static int dlm_unlock_sync(struct dlm_lock_resource *res)
return dlm_lock_sync(res, DLM_LOCK_NL);
}
-static struct dlm_lock_resource *lockres_init(dlm_lockspace_t *lockspace,
+static struct dlm_lock_resource *lockres_init(struct mddev *mddev,
char *name, void (*bastfn)(void *arg, int mode), int with_lvb)
{
struct dlm_lock_resource *res = NULL;
int ret, namelen;
+ struct md_cluster_info *cinfo = mddev->cluster_info;
res = kzalloc(sizeof(struct dlm_lock_resource), GFP_KERNEL);
if (!res)
return NULL;
- res->ls = lockspace;
+ res->ls = cinfo->lockspace;
+ res->mddev = mddev;
namelen = strlen(name);
res->name = kzalloc(namelen + 1, GFP_KERNEL);
if (!res->name) {
@@ -119,13 +129,60 @@ static void lockres_free(struct dlm_lock_resource *res)
return;
}
-static int join(struct mddev *md, int nodes)
+static char *pretty_uuid(char *dest, char *src)
{
+ int i, len = 0;
+ for (i=0; i<16; i++) {
+ if (i==4 || i==6 || i==8 || i==10)
+ len += sprintf(dest + len, "-");
+ len += sprintf(dest + len, "%02x", (__u8)src[i]);
+ }
+ return dest;
+}
+
+static int join(struct mddev *mddev, int nodes)
+{
+ struct md_cluster_info *cinfo;
+ int ret;
+ char str[64];
+
+ if (!try_module_get(THIS_MODULE))
+ return -ENOENT;
+
+ cinfo = kzalloc(sizeof(struct md_cluster_info), GFP_KERNEL);
+ if (!cinfo)
+ return -ENOMEM;
+
+ memset(str, 0, 64);
+ pretty_uuid(str, mddev->uuid);
+ ret = dlm_new_lockspace(str, NULL, DLM_LSFL_FS, LVB_SIZE,
+ NULL, NULL, NULL, &cinfo->lockspace);
+ if (ret)
+ goto err;
+ cinfo->sb_lock = lockres_init(mddev, "cmd-super",
+ NULL, 0);
+ if (!cinfo->sb_lock) {
+ ret = -ENOMEM;
+ goto err;
+ }
+ mutex_init(&cinfo->sb_mutex);
+ mddev->cluster_info = cinfo;
return 0;
+err:
+ if (cinfo->lockspace)
+ dlm_release_lockspace(cinfo->lockspace, 2);
+ kfree(cinfo);
+ module_put(THIS_MODULE);
+ return ret;
}
-static int leave(struct mddev *md)
+static int leave(struct mddev *mddev)
{
+ struct md_cluster_info *cinfo = mddev->cluster_info;
+ if (!cinfo)
+ return 0;
+ lockres_free(cinfo->sb_lock);
+ dlm_release_lockspace(cinfo->lockspace, 2);
return 0;
}
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 076e1ae..8017e18 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -203,6 +203,8 @@ extern int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
int is_new);
extern void md_ack_all_badblocks(struct badblocks *bb);
+struct md_cluster_info;
+
struct mddev {
void *private;
struct md_personality *pers;
@@ -420,6 +422,7 @@ struct mddev {
unsigned long daemon_sleep; /* how many jiffies between updates? */
unsigned long max_write_behind; /* write-behind mode */
int external;
+ int nodes;
} bitmap_info;
atomic_t max_corr_read_errors; /* max read retries */
@@ -438,6 +441,7 @@ struct mddev {
struct work_struct flush_work;
struct work_struct event_work; /* used by dm to report failure event */
void (*sync_super)(struct mddev *mddev, struct md_rdev *rdev);
+ struct md_cluster_info *cluster_info;
};
@@ -634,4 +638,8 @@ static inline int mddev_check_plugged(struct mddev *mddev)
sizeof(struct blk_plug_cb));
}
extern struct md_cluster_operations *md_cluster_ops;
+static inline int mddev_is_clustered(struct mddev *mddev)
+{
+ return mddev->cluster_info && mddev->bitmap_info.nodes > 1;
+}
#endif /* _MD_MD_H */
--
2.1.2
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
