* [PATCH 09/24] Use separate bitmaps for each nodes in the cluster
@ 2014-12-18 16:16 Goldwyn Rodrigues
0 siblings, 0 replies; only message in thread
From: Goldwyn Rodrigues @ 2014-12-18 16:16 UTC (permalink / raw)
To: neilb; +Cc: lzhong, linux-raid
On-disk format:
0 4k 8k 12k
-------------------------------------------------------------------
| idle | md super | bm super [0] + bits |
| bm bits[0, contd] | bm super[1] + bits | bm bits[1, contd] |
| bm super[2] + bits | bm bits [2, contd] | bm super[3] + bits |
| bm bits [3, contd] | | |
Bitmap super has a field nodes, which defines the maximum number
of nodes the device can use. While reading the bitmap super, if
the cluster finds out that the number of nodes is > 0:
1. Requests the md-cluster module.
2. Calls md_cluster_ops->join(), which sets up clustering such as
joining DLM lockspace.
Since the first time, the first bitmap is read. After the call
to the cluster_setup, the bitmap offset is adjusted and the
superblock is re-read. This also ensures the bitmap is read
the bitmap lock (when bitmap lock is introduced in later patches)
Questions:
1. cluster name is repeated in all bitmap supers. Is that okay?
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
---
drivers/md/bitmap.c | 68 ++++++++++++++++++++++++++++++++++++++++---------
drivers/md/bitmap.h | 1 +
drivers/md/md-cluster.c | 7 +++++
drivers/md/md-cluster.h | 1 -
4 files changed, 64 insertions(+), 13 deletions(-)
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index f4df37c..23a71a7 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -192,6 +192,10 @@ static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
struct block_device *bdev;
struct mddev *mddev = bitmap->mddev;
struct bitmap_storage *store = &bitmap->storage;
+ int node_offset = 0;
+
+ if (mddev_is_clustered(bitmap->mddev))
+ node_offset = bitmap->cluster_slot * store->file_pages;
while ((rdev = next_active_rdev(rdev, mddev)) != NULL) {
int size = PAGE_SIZE;
@@ -536,6 +540,7 @@ static int bitmap_read_sb(struct bitmap *bitmap)
unsigned long sectors_reserved = 0;
int err = -EINVAL;
struct page *sb_page;
+ int cluster_setup_done = 0;
if (!bitmap->storage.file && !bitmap->mddev->bitmap_info.offset) {
chunksize = 128 * 1024 * 1024;
@@ -551,6 +556,7 @@ static int bitmap_read_sb(struct bitmap *bitmap)
return -ENOMEM;
bitmap->storage.sb_page = sb_page;
+re_read:
if (bitmap->storage.file) {
loff_t isize = i_size_read(bitmap->storage.file->f_mapping->host);
int bytes = isize > PAGE_SIZE ? PAGE_SIZE : isize;
@@ -566,6 +572,7 @@ static int bitmap_read_sb(struct bitmap *bitmap)
if (err)
return err;
+ err = -EINVAL;
sb = kmap_atomic(sb_page);
chunksize = le32_to_cpu(sb->chunksize);
@@ -573,6 +580,7 @@ static int bitmap_read_sb(struct bitmap *bitmap)
write_behind = le32_to_cpu(sb->write_behind);
sectors_reserved = le32_to_cpu(sb->sectors_reserved);
nodes = le32_to_cpu(sb->nodes);
+ strlcpy(bitmap->mddev->bitmap_info.cluster_name, sb->cluster_name, 64);
/* verify that the bitmap-specific fields are valid */
if (sb->magic != cpu_to_le32(BITMAP_MAGIC))
@@ -609,7 +617,7 @@ static int bitmap_read_sb(struct bitmap *bitmap)
goto out;
}
events = le64_to_cpu(sb->events);
- if (events < bitmap->mddev->events) {
+ if (!nodes && (events < bitmap->mddev->events)) {
printk(KERN_INFO
"%s: bitmap file is out of date (%llu < %llu) "
"-- forcing full recovery\n",
@@ -626,8 +634,32 @@ static int bitmap_read_sb(struct bitmap *bitmap)
bitmap->events_cleared = le64_to_cpu(sb->events_cleared);
strlcpy(bitmap->mddev->bitmap_info.cluster_name, sb->cluster_name, 64);
err = 0;
+
out:
kunmap_atomic(sb);
+ if (nodes && !cluster_setup_done) {
+ sector_t bm_blocks = sector_div(bitmap->mddev->resync_max_sectors,(chunksize >> 9));
+ bm_blocks = bm_blocks << 3;
+ /* We have bitmap supers at 4k boundaries, hence this
+ * is hardcoded */
+ bm_blocks = DIV_ROUND_UP(bm_blocks, 4096);
+ err = md_setup_cluster(bitmap->mddev, nodes);
+ if (err) {
+ pr_err("%s: Could not setup cluster service (%d)\n",
+ bmname(bitmap), err);
+ goto out_no_sb;
+ }
+ bitmap->cluster_slot = md_cluster_ops->slot_number(bitmap->mddev);
+ bitmap->mddev->bitmap_info.offset +=
+ bitmap->cluster_slot * (bm_blocks << 3);
+ printk("%s:%d bm slot: %d offset: %llu\n", __func__, __LINE__,
+ bitmap->cluster_slot,
+ (unsigned long long)bitmap->mddev->bitmap_info.offset);
+ cluster_setup_done = 1;
+ goto re_read;
+ }
+
+
out_no_sb:
if (test_bit(BITMAP_STALE, &bitmap->flags))
bitmap->events_cleared = bitmap->mddev->events;
@@ -638,8 +670,11 @@ out_no_sb:
if (bitmap->mddev->bitmap_info.space == 0 ||
bitmap->mddev->bitmap_info.space > sectors_reserved)
bitmap->mddev->bitmap_info.space = sectors_reserved;
- if (err)
+ if (err) {
bitmap_print_sb(bitmap);
+ if (cluster_setup_done)
+ md_cluster_stop(bitmap->mddev);
+ }
return err;
}
@@ -683,14 +718,14 @@ static inline struct page *filemap_get_page(struct bitmap_storage *store,
{
if (file_page_index(store, chunk) >= store->file_pages)
return NULL;
- return store->filemap[file_page_index(store, chunk)
- - file_page_index(store, 0)];
+ return store->filemap[file_page_index(store, chunk)];
}
static int bitmap_storage_alloc(struct bitmap_storage *store,
- unsigned long chunks, int with_super)
+ unsigned long chunks, int with_super,
+ int slot_number)
{
- int pnum;
+ int pnum, offset = 0;
unsigned long num_pages;
unsigned long bytes;
@@ -699,6 +734,7 @@ static int bitmap_storage_alloc(struct bitmap_storage *store,
bytes += sizeof(bitmap_super_t);
num_pages = DIV_ROUND_UP(bytes, PAGE_SIZE);
+ offset = slot_number * (num_pages - 1);
store->filemap = kmalloc(sizeof(struct page *)
* num_pages, GFP_KERNEL);
@@ -709,20 +745,22 @@ static int bitmap_storage_alloc(struct bitmap_storage *store,
store->sb_page = alloc_page(GFP_KERNEL|__GFP_ZERO);
if (store->sb_page == NULL)
return -ENOMEM;
- store->sb_page->index = 0;
}
+
pnum = 0;
if (store->sb_page) {
store->filemap[0] = store->sb_page;
pnum = 1;
+ store->sb_page->index = offset;
}
+
for ( ; pnum < num_pages; pnum++) {
store->filemap[pnum] = alloc_page(GFP_KERNEL|__GFP_ZERO);
if (!store->filemap[pnum]) {
store->file_pages = pnum;
return -ENOMEM;
}
- store->filemap[pnum]->index = pnum;
+ store->filemap[pnum]->index = pnum + offset;
}
store->file_pages = pnum;
@@ -935,7 +973,7 @@ static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int n
*/
static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
{
- unsigned long i, chunks, index, oldindex, bit;
+ unsigned long i, chunks, index, oldindex, bit, node_offset = 0;
struct page *page = NULL;
unsigned long bit_cnt = 0;
struct file *file;
@@ -981,6 +1019,9 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
if (!bitmap->mddev->bitmap_info.external)
offset = sizeof(bitmap_super_t);
+ if (mddev_is_clustered(bitmap->mddev))
+ node_offset = bitmap->cluster_slot * (DIV_ROUND_UP(store->bytes, PAGE_SIZE));
+
for (i = 0; i < chunks; i++) {
int b;
index = file_page_index(&bitmap->storage, i);
@@ -1001,7 +1042,7 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
bitmap->mddev,
bitmap->mddev->bitmap_info.offset,
page,
- index, count);
+ index + node_offset, count);
if (ret)
goto err;
@@ -1207,7 +1248,6 @@ void bitmap_daemon_work(struct mddev *mddev)
j < bitmap->storage.file_pages
&& !test_bit(BITMAP_STALE, &bitmap->flags);
j++) {
-
if (test_page_attr(bitmap, j,
BITMAP_PAGE_DIRTY))
/* bitmap_unplug will handle the rest */
@@ -1591,6 +1631,9 @@ static void bitmap_free(struct bitmap *bitmap)
if (!bitmap) /* there was no bitmap */
return;
+ if (mddev_is_clustered(bitmap->mddev) && bitmap->mddev->cluster_info)
+ md_cluster_stop(bitmap->mddev);
+
/* Shouldn't be needed - but just in case.... */
wait_event(bitmap->write_wait,
atomic_read(&bitmap->pending_writes) == 0);
@@ -1847,7 +1890,8 @@ int bitmap_resize(struct bitmap *bitmap, sector_t blocks,
memset(&store, 0, sizeof(store));
if (bitmap->mddev->bitmap_info.offset || bitmap->mddev->bitmap_info.file)
ret = bitmap_storage_alloc(&store, chunks,
- !bitmap->mddev->bitmap_info.external);
+ !bitmap->mddev->bitmap_info.external,
+ bitmap->cluster_slot);
if (ret)
goto err;
diff --git a/drivers/md/bitmap.h b/drivers/md/bitmap.h
index 49163b6..2e0f540 100644
--- a/drivers/md/bitmap.h
+++ b/drivers/md/bitmap.h
@@ -227,6 +227,7 @@ struct bitmap {
wait_queue_head_t behind_wait;
struct kernfs_node *sysfs_can_clear;
+ int cluster_slot; /* Slot offset for clustered env */
};
/* the bitmap API */
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 98e45e1..43b3cda 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -199,6 +199,13 @@ static int join(struct mddev *mddev, int nodes)
if (ret)
goto err;
wait_for_completion(&cinfo->completion);
+ if (nodes <= cinfo->slot_number) {
+ pr_err("md-cluster: Slot allotted(%d) greater than"
+ "available slots(%d)", cinfo->slot_number - 1,
+ nodes);
+ ret = -ERANGE;
+ goto err;
+ }
cinfo->sb_lock = lockres_init(mddev, "cmd-super",
NULL, 0);
if (!cinfo->sb_lock) {
diff --git a/drivers/md/md-cluster.h b/drivers/md/md-cluster.h
index d9a1d88..52a21e0 100644
--- a/drivers/md/md-cluster.h
+++ b/drivers/md/md-cluster.h
@@ -11,7 +11,6 @@ struct md_cluster_operations {
int (*join)(struct mddev *mddev, int nodes);
int (*leave)(struct mddev *mddev);
int (*slot_number)(struct mddev *mddev);
-
};
#endif /* _MD_CLUSTER_H */
--
2.1.2
^ permalink raw reply related [flat|nested] only message in thread
only message in thread, other threads:[~2014-12-18 16:16 UTC | newest]
Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2014-12-18 16:16 [PATCH 09/24] Use separate bitmaps for each nodes in the cluster Goldwyn Rodrigues
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox