[PATCH 7 of 8] MD: add bitmap support

[PATCH 7 of 8] MD: add bitmap support

[Jonathan Brassow]

Add bitmap support to the device-mapper specific metadata area.

This patch allows the creation of the bitmap metadata area upon initial array
creation via device-mapper.

Signed-off-by: Jonathan Brassow <jbrassow@redhat.com>

Index: linux-2.6/drivers/md/bitmap.c
===================================================================
--- linux-2.6.orig/drivers/md/bitmap.c
+++ linux-2.6/drivers/md/bitmap.c
@@ -534,6 +534,84 @@ void bitmap_print_sb(struct bitmap *bitm
 	kunmap_atomic(sb, KM_USER0);
 }
 
+/*
+ * bitmap_new_disk_sb
+ * @bitmap
+ *
+ * This function is somewhat the reverse of bitmap_read_sb.  bitmap_read_sb
+ * reads and verifies the on-disk bitmap superblock and populates bitmap_info.
+ * This function verifies 'bitmap_info' and populates the on-disk bitmap
+ * structure, which is to be written to disk.
+ *
+ * Returns: 0 on success, -Exxx on error
+ */
+static int bitmap_new_disk_sb(struct bitmap *bitmap)
+{
+	bitmap_super_t *sb;
+	unsigned long chunksize, daemon_sleep, write_behind;
+	int err = -EINVAL;
+
+	/* page 0 is the superblock, read it... */
+	bitmap->sb_page = read_sb_page(bitmap->mddev,
+				       bitmap->mddev->bitmap_info.offset,
+				       NULL, 0, sizeof(bitmap_super_t));
+
+	if (IS_ERR(bitmap->sb_page)) {
+		err = PTR_ERR(bitmap->sb_page);
+		bitmap->sb_page = NULL;
+		return err;
+	}
+
+	sb = kmap_atomic(bitmap->sb_page, KM_USER0);
+
+	sb->magic = cpu_to_le32(BITMAP_MAGIC);
+	sb->version = cpu_to_le32(BITMAP_MAJOR_HI);
+
+	chunksize = bitmap->mddev->bitmap_info.chunksize;
+	BUG_ON(!chunksize);
+	if ((1 << ffz(~chunksize)) != chunksize) {
+		kunmap_atomic(sb, KM_USER0);
+		printk(KERN_ERR "bitmap chunksize not a power of 2\n");
+		return -EINVAL;
+	}
+	sb->chunksize = cpu_to_le32(chunksize);
+
+	daemon_sleep = bitmap->mddev->bitmap_info.daemon_sleep;
+	if (!daemon_sleep ||
+	    (daemon_sleep < 1) || (daemon_sleep > MAX_SCHEDULE_TIMEOUT)) {
+		printk(KERN_INFO "Choosing daemon_sleep default (5 sec)\n");
+		daemon_sleep = 5 * HZ;
+	}
+	sb->daemon_sleep = cpu_to_le32(daemon_sleep);
+	bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep;
+
+	/*
+	 * FIXME: write_behind for RAID1.  If not specified, what
+	 * is a good choice?  We choose COUNTER_MAX / 2 arbitrarily.
+	 */
+	write_behind = bitmap->mddev->bitmap_info.max_write_behind;
+	if (write_behind > COUNTER_MAX)
+		write_behind = COUNTER_MAX / 2;
+	sb->write_behind = cpu_to_le32(write_behind);
+	bitmap->mddev->bitmap_info.max_write_behind = write_behind;
+
+	/* keep the array size field of the bitmap superblock up to date */
+	sb->sync_size = cpu_to_le64(bitmap->mddev->resync_max_sectors);
+
+	memcpy(sb->uuid, bitmap->mddev->uuid, 16);
+
+	bitmap->flags |= BITMAP_STALE;
+	sb->state |= cpu_to_le32(BITMAP_STALE);
+	bitmap->events_cleared = bitmap->mddev->events;
+	sb->events_cleared = cpu_to_le64(bitmap->mddev->events);
+
+	bitmap->flags |= BITMAP_HOSTENDIAN;
+	sb->version = cpu_to_le32(BITMAP_MAJOR_HOSTENDIAN);
+
+	kunmap_atomic(sb, KM_USER0);
+	return 0;
+}
+
 /* read the superblock from the bitmap file and initialize some bitmap fields */
 static int bitmap_read_sb(struct bitmap *bitmap)
 {
@@ -1076,8 +1154,8 @@ static int bitmap_init_from_disk(struct 
 	}
 
 	printk(KERN_INFO "%s: bitmap initialized from disk: "
-		"read %lu/%lu pages, set %lu bits\n",
-		bmname(bitmap), bitmap->file_pages, num_pages, bit_cnt);
+	       "read %lu/%lu pages, set %lu of %lu bits\n",
+	       bmname(bitmap), bitmap->file_pages, num_pages, bit_cnt, chunks);
 
 	return 0;
 
@@ -1728,9 +1806,16 @@ int bitmap_create(mddev_t *mddev)
 		vfs_fsync(file, 1);
 	}
 	/* read superblock from bitmap file (this sets mddev->bitmap_info.chunksize) */
-	if (!mddev->bitmap_info.external)
-		err = bitmap_read_sb(bitmap);
-	else {
+	if (!mddev->bitmap_info.external) {
+		/*
+		 * If 'MD_ARRAY_FIRST_USE' is set, then device-mapper is
+		 * instructing us to create a new on-disk bitmap instance.
+		 */
+		if (test_and_clear_bit(MD_ARRAY_FIRST_USE, &mddev->flags))
+			err = bitmap_new_disk_sb(bitmap);
+		else
+			err = bitmap_read_sb(bitmap);
+	} else {
 		err = 0;
 		if (mddev->bitmap_info.chunksize == 0 ||
 		    mddev->bitmap_info.daemon_sleep == 0)
Index: linux-2.6/drivers/md/md.h
===================================================================
--- linux-2.6.orig/drivers/md/md.h
+++ linux-2.6/drivers/md/md.h
@@ -124,6 +124,7 @@ struct mddev_s
 #define MD_CHANGE_DEVS	0	/* Some device status has changed */
 #define MD_CHANGE_CLEAN 1	/* transition to or from 'clean' */
 #define MD_CHANGE_PENDING 2	/* switch from 'clean' to 'active' in progress */
+#define MD_ARRAY_FIRST_USE 3    /* First use of array, needs initialization */
 
 	int				suspended;
 	atomic_t			active_io;

Re: [PATCH 7 of 8] MD: add bitmap support

[NeilBrown]

On Tue, 07 Jun 2011 17:52:39 -0500 Jonathan Brassow <jbrassow@redhat.com>
wrote:

> Add bitmap support to the device-mapper specific metadata area.
> 
> This patch allows the creation of the bitmap metadata area upon initial array
> creation via device-mapper.
> 
> Signed-off-by: Jonathan Brassow <jbrassow@redhat.com>
> 
> Index: linux-2.6/drivers/md/bitmap.c
> ===================================================================
> --- linux-2.6.orig/drivers/md/bitmap.c
> +++ linux-2.6/drivers/md/bitmap.c
> @@ -534,6 +534,84 @@ void bitmap_print_sb(struct bitmap *bitm
>  	kunmap_atomic(sb, KM_USER0);
>  }
>  
> +/*
> + * bitmap_new_disk_sb
> + * @bitmap
> + *
> + * This function is somewhat the reverse of bitmap_read_sb.  bitmap_read_sb
> + * reads and verifies the on-disk bitmap superblock and populates bitmap_info.
> + * This function verifies 'bitmap_info' and populates the on-disk bitmap
> + * structure, which is to be written to disk.
> + *
> + * Returns: 0 on success, -Exxx on error
> + */
> +static int bitmap_new_disk_sb(struct bitmap *bitmap)
> +{
> +	bitmap_super_t *sb;
> +	unsigned long chunksize, daemon_sleep, write_behind;
> +	int err = -EINVAL;
> +
> +	/* page 0 is the superblock, read it... */
> +	bitmap->sb_page = read_sb_page(bitmap->mddev,
> +				       bitmap->mddev->bitmap_info.offset,
> +				       NULL, 0, sizeof(bitmap_super_t));
> +

I don't understand ... why are you reading the page from disk when you don't
expect anything to be there are are about to create an initial bitmap
superblock?
Shouldn't this just be
    bitmap->sb_page = alloc_page(GFP_KERNEL);
??


> +	if (IS_ERR(bitmap->sb_page)) {
> +		err = PTR_ERR(bitmap->sb_page);
> +		bitmap->sb_page = NULL;
> +		return err;
> +	}
> +
> +	sb = kmap_atomic(bitmap->sb_page, KM_USER0);
> +
> +	sb->magic = cpu_to_le32(BITMAP_MAGIC);
> +	sb->version = cpu_to_le32(BITMAP_MAJOR_HI);
> +
> +	chunksize = bitmap->mddev->bitmap_info.chunksize;
> +	BUG_ON(!chunksize);
> +	if ((1 << ffz(~chunksize)) != chunksize) {

Please use  is_power_of_2(chunksize) - defined in log2.h


Otherwise it looks OK.

NeilBrown


> +		kunmap_atomic(sb, KM_USER0);
> +		printk(KERN_ERR "bitmap chunksize not a power of 2\n");
> +		return -EINVAL;
> +	}
> +	sb->chunksize = cpu_to_le32(chunksize);
> +
> +	daemon_sleep = bitmap->mddev->bitmap_info.daemon_sleep;
> +	if (!daemon_sleep ||
> +	    (daemon_sleep < 1) || (daemon_sleep > MAX_SCHEDULE_TIMEOUT)) {
> +		printk(KERN_INFO "Choosing daemon_sleep default (5 sec)\n");
> +		daemon_sleep = 5 * HZ;
> +	}
> +	sb->daemon_sleep = cpu_to_le32(daemon_sleep);
> +	bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep;
> +
> +	/*
> +	 * FIXME: write_behind for RAID1.  If not specified, what
> +	 * is a good choice?  We choose COUNTER_MAX / 2 arbitrarily.
> +	 */
> +	write_behind = bitmap->mddev->bitmap_info.max_write_behind;
> +	if (write_behind > COUNTER_MAX)
> +		write_behind = COUNTER_MAX / 2;
> +	sb->write_behind = cpu_to_le32(write_behind);
> +	bitmap->mddev->bitmap_info.max_write_behind = write_behind;
> +
> +	/* keep the array size field of the bitmap superblock up to date */
> +	sb->sync_size = cpu_to_le64(bitmap->mddev->resync_max_sectors);
> +
> +	memcpy(sb->uuid, bitmap->mddev->uuid, 16);
> +
> +	bitmap->flags |= BITMAP_STALE;
> +	sb->state |= cpu_to_le32(BITMAP_STALE);
> +	bitmap->events_cleared = bitmap->mddev->events;
> +	sb->events_cleared = cpu_to_le64(bitmap->mddev->events);
> +
> +	bitmap->flags |= BITMAP_HOSTENDIAN;
> +	sb->version = cpu_to_le32(BITMAP_MAJOR_HOSTENDIAN);
> +
> +	kunmap_atomic(sb, KM_USER0);
> +	return 0;
> +}
> +
>  /* read the superblock from the bitmap file and initialize some bitmap fields */
>  static int bitmap_read_sb(struct bitmap *bitmap)
>  {
> @@ -1076,8 +1154,8 @@ static int bitmap_init_from_disk(struct 
>  	}
>  
>  	printk(KERN_INFO "%s: bitmap initialized from disk: "
> -		"read %lu/%lu pages, set %lu bits\n",
> -		bmname(bitmap), bitmap->file_pages, num_pages, bit_cnt);
> +	       "read %lu/%lu pages, set %lu of %lu bits\n",
> +	       bmname(bitmap), bitmap->file_pages, num_pages, bit_cnt, chunks);
>  
>  	return 0;
>  
> @@ -1728,9 +1806,16 @@ int bitmap_create(mddev_t *mddev)
>  		vfs_fsync(file, 1);
>  	}
>  	/* read superblock from bitmap file (this sets mddev->bitmap_info.chunksize) */
> -	if (!mddev->bitmap_info.external)
> -		err = bitmap_read_sb(bitmap);
> -	else {
> +	if (!mddev->bitmap_info.external) {
> +		/*
> +		 * If 'MD_ARRAY_FIRST_USE' is set, then device-mapper is
> +		 * instructing us to create a new on-disk bitmap instance.
> +		 */
> +		if (test_and_clear_bit(MD_ARRAY_FIRST_USE, &mddev->flags))
> +			err = bitmap_new_disk_sb(bitmap);
> +		else
> +			err = bitmap_read_sb(bitmap);
> +	} else {
>  		err = 0;
>  		if (mddev->bitmap_info.chunksize == 0 ||
>  		    mddev->bitmap_info.daemon_sleep == 0)
> Index: linux-2.6/drivers/md/md.h
> ===================================================================
> --- linux-2.6.orig/drivers/md/md.h
> +++ linux-2.6/drivers/md/md.h
> @@ -124,6 +124,7 @@ struct mddev_s
>  #define MD_CHANGE_DEVS	0	/* Some device status has changed */
>  #define MD_CHANGE_CLEAN 1	/* transition to or from 'clean' */
>  #define MD_CHANGE_PENDING 2	/* switch from 'clean' to 'active' in progress */
> +#define MD_ARRAY_FIRST_USE 3    /* First use of array, needs initialization */
>  
>  	int				suspended;
>  	atomic_t			active_io;
> 
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-raid" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html