Btrfs: add IO error device stats

index a7ffc88..e123629 100644
@@ -2556,18 +2556,21 @@ recovery_tree_root:
 
 static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate)
 {
-	char b[BDEVNAME_SIZE];
-
 	if (uptodate) {
 		set_buffer_uptodate(bh);
 	} else {
+		struct btrfs_device *device = (struct btrfs_device *)
+			bh->b_private;
+
 		printk_ratelimited(KERN_WARNING "lost page write due to "
-					"I/O error on %s\n",
-				       bdevname(bh->b_bdev, b));
+				   "I/O error on %s\n", device->name);
 		/* note, we dont' set_buffer_write_io_error because we have
 		 * our own ways of dealing with the IO errors
 		 */
 		clear_buffer_uptodate(bh);
+		btrfs_device_stat_inc(&device->cnt_write_io_errs);
+		device->device_stats_dirty = 1;
+		btrfs_device_stat_print_on_error(device);
 	}
 	unlock_buffer(bh);
 	put_bh(bh);

@@ -2682,6 +2685,7 @@ static int write_dev_supers(struct btrfs_device *device,
 			set_buffer_uptodate(bh);
 			lock_buffer(bh);
 			bh->b_end_io = btrfs_end_buffer_write_sync;
+			bh->b_private = device;
 		}
 
 		/*

@@ -2740,6 +2744,12 @@ static int write_dev_flush(struct btrfs_device *device, int wait)
 		}
 		if (!bio_flagged(bio, BIO_UPTODATE)) {
 			ret = -EIO;
+			if (!bio_flagged(bio, BIO_EOPNOTSUPP)) {
+				btrfs_device_stat_inc(
+					&device->cnt_flush_io_errs);
+				device->device_stats_dirty = 1;
+				btrfs_device_stat_print_on_error(device);
+			}
 		}
 
 		/* drop the reference from the wait == 0 run */

index 2fb52c2..6cd9a55 100644
@@ -1923,6 +1923,9 @@ int repair_io_failure(struct btrfs_mapping_tree *map_tree, u64 start,
 	if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) {
 		/* try to remap that extent elsewhere? */
 		bio_put(bio);
+		btrfs_device_stat_inc(&dev->cnt_write_io_errs);
+		dev->device_stats_dirty = 1;
+		btrfs_device_stat_print_on_error(dev);
 		return -EIO;
 	}
 

@@ -2347,10 +2350,30 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
 		if (uptodate && tree->ops && tree->ops->readpage_end_io_hook) {
 			ret = tree->ops->readpage_end_io_hook(page, start, end,
 							      state, mirror);
-			if (ret)
+			if (ret) {
+				/* no IO indicated but software detected errors
+				 * in the block, either checksum errors or
+				 * issues with the contents */
+				int failed_mirror = (int)(uintptr_t)
+						    bio->bi_bdev;
+				struct btrfs_root *root =
+					BTRFS_I(page->mapping->host)->root;
+				struct btrfs_device *device;
+
 				uptodate = 0;
-			else
+				device = btrfs_find_device_for_logical(
+						root, start,
+						(int)failed_mirror);
+				if (device) {
+					btrfs_device_stat_inc(
+						&device->cnt_corruption_errs);
+					device->device_stats_dirty = 1;
+					btrfs_device_stat_print_on_error(
+						device);
+				}
+			} else {
 				clean_io_failure(start, page);
+			}
 		}
 
 		if (!uptodate && tree->ops && tree->ops->readpage_io_failed_hook) {

196 lines not on this page · raw message

91 lines not on this page · raw message

index bb6b03f..08afa6c 100644
@@ -106,6 +106,14 @@ struct btrfs_device {
 	struct completion flush_wait;
 	int nobarriers;
 
+	/* disk I/O failure stats. For detailed description refer to
+	 * struct btrfs_device_stats_item in ctree.h */
+	int device_stats_dirty; /* counters need to be written to disk */
+	atomic_t cnt_write_io_errs;
+	atomic_t cnt_read_io_errs;
+	atomic_t cnt_flush_io_errs;
+	atomic_t cnt_corruption_errs;
+	atomic_t cnt_generation_errs;
 };
 
 struct btrfs_fs_devices {

@@ -281,4 +289,17 @@ int btrfs_cancel_balance(struct btrfs_fs_info *fs_info);
 int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset);
 int find_free_dev_extent(struct btrfs_device *device, u64 num_bytes,
 			 u64 *start, u64 *max_avail);
+struct btrfs_device *btrfs_find_device_for_logical(struct btrfs_root *root,
+						   u64 logical, int mirror_num);
+void btrfs_device_stat_print_on_error(struct btrfs_device *device);
+
+static inline void btrfs_device_stat_inc(atomic_t *cnt)
+{
+	atomic_inc(cnt);
+}
+
+static inline int btrfs_device_stat_read(atomic_t *cnt)
+{
+	return atomic_read(cnt);
+}
 #endif

index 14f8e1f..19d2244 100644
@@ -3042,6 +3042,28 @@ static long btrfs_ioctl_scrub_progress(struct btrfs_root *root,
 	return ret;
 }
 
+static long btrfs_ioctl_get_device_stats(struct btrfs_root *root,
+					 void __user *arg, int reset_after_read)
+{
+	struct btrfs_ioctl_get_device_stats *sa;
+	int ret;
+
+	if (reset_after_read && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	sa = memdup_user(arg, sizeof(*sa));
+	if (IS_ERR(sa))
+		return PTR_ERR(sa);
+
+	ret = btrfs_get_device_stats(root, sa, reset_after_read);
+
+	if (copy_to_user(arg, sa, sizeof(*sa)))
+		ret = -EFAULT;
+
+	kfree(sa);
+	return ret;
+}
+
 static long btrfs_ioctl_ino_to_path(struct btrfs_root *root, void __user *arg)
 {
 	int ret = 0;

@@ -3424,6 +3446,10 @@ long btrfs_ioctl(struct file *file, unsigned int
 		return btrfs_ioctl_balance_ctl(root, arg);
 	case BTRFS_IOC_BALANCE_PROGRESS:
 		return btrfs_ioctl_balance_progress(root, argp);
+	case BTRFS_IOC_GET_DEVICE_STATS:
+		return btrfs_ioctl_get_device_stats(root, argp, 0);
+	case BTRFS_IOC_GET_AND_RESET_DEVICE_STATS:
+		return btrfs_ioctl_get_device_stats(root, argp, 1);
 	}
 
 	return -ENOTTY;

index 086e6bd..f1c1196 100644
@@ -266,6 +266,30 @@ struct btrfs_ioctl_logical_ino_args {
 	__u64				inodes;
 };
 
+#define BTRFS_IOCTL_GET_DEVICE_STATS_MAX_NR_ITEMS	5
+struct btrfs_ioctl_get_device_stats {
+	__u64 devid;				/* in */
+	__u64 nr_items;				/* in/out */
+
+	/* out values: */
+
+	/* disk I/O failure stats */
+	__u64 cnt_write_io_errs; /* EIO or EREMOTEIO from lower layers */
+	__u64 cnt_read_io_errs; /* EIO or EREMOTEIO from lower layers */
+	__u64 cnt_flush_io_errs; /* EIO or EREMOTEIO from lower layers */
+
+	/* stats for indirect indications for I/O failures */
+	__u64 cnt_corruption_errs; /* checksum error, bytenr error or
+				    * contents is illegal: this is an
+				    * indication that the block was damaged
+				    * during read or write, or written to
+				    * wrong location or read from wrong
+				    * location */
+	__u64 cnt_generation_errs; /* an indication that blocks have not
+				    * been written */
+	__u64 unused[121]; /* pad to 1k */
+};
+
 #define BTRFS_IOC_SNAP_CREATE _IOW(BTRFS_IOCTL_MAGIC, 1, \
 				   struct btrfs_ioctl_vol_args)
 #define BTRFS_IOC_DEFRAG _IOW(BTRFS_IOCTL_MAGIC, 2, \

@@ -330,5 +354,9 @@ struct btrfs_ioctl_logical_ino_args {
 					struct btrfs_ioctl_ino_path_args)
 #define BTRFS_IOC_LOGICAL_INO _IOWR(BTRFS_IOCTL_MAGIC, 36, \
 					struct btrfs_ioctl_ino_path_args)
+#define BTRFS_IOC_GET_DEVICE_STATS _IOWR(BTRFS_IOCTL_MAGIC, 52, \
+					 struct btrfs_ioctl_get_device_stats)
+#define BTRFS_IOC_GET_AND_RESET_DEVICE_STATS _IOWR(BTRFS_IOCTL_MAGIC, 53, \
+					 struct btrfs_ioctl_get_device_stats)
 
 #endif

72 lines not on this page · raw message

index 08afa6c..e0b31f1 100644
@@ -292,6 +292,9 @@ int find_free_dev_extent(struct btrfs_device *device, u64 num_bytes,
 struct btrfs_device *btrfs_find_device_for_logical(struct btrfs_root *root,
 						   u64 logical, int mirror_num);
 void btrfs_device_stat_print_on_error(struct btrfs_device *device);
+int btrfs_get_device_stats(struct btrfs_root *root,
+			   struct btrfs_ioctl_get_device_stats *stats,
+			   int reset_after_read);
 
 static inline void btrfs_device_stat_inc(atomic_t *cnt)
 {

@@ -302,4 +305,14 @@ static inline int btrfs_device_stat_read(atomic_t *cnt)
 {
 	return atomic_read(cnt);
 }
+
+static inline int btrfs_device_stat_read_and_reset(atomic_t *cnt)
+{
+	return atomic_xchg(cnt, 0);
+}
+
+static inline void btrfs_device_stat_reset(atomic_t *cnt)
+{
+	atomic_set(cnt, 0);
+}
 #endif

index ec42a24..1dd7651 100644
@@ -823,6 +823,26 @@ struct btrfs_csum_item {
 	u8 csum;
 } __attribute__ ((__packed__));
 
+struct btrfs_device_stats_item {
+	/*
+	 * grow this item struct at the end for future enhancements and keep
+	 * the existing values unchanged
+	 */
+	__le64 cnt_write_io_errs; /* EIO or EREMOTEIO from lower layers */
+	__le64 cnt_read_io_errs; /* EIO or EREMOTEIO from lower layers */
+	__le64 cnt_flush_io_errs; /* EIO or EREMOTEIO from lower layers */
+
+	/* stats for indirect indications for I/O failures */
+	__le64 cnt_corruption_errs; /* checksum error, bytenr error or
+				     * contents is illegal: this is an
+				     * indication that the block was damaged
+				     * during read or write, or written to
+				     * wrong location or read from wrong
+				     * location */
+	__le64 cnt_generation_errs; /* an indication that blocks have not
+				     * been written */
+} __attribute__ ((__packed__));
+
 /* different types of block groups (and chunks) */
 #define BTRFS_BLOCK_GROUP_DATA		(1ULL << 0)
 #define BTRFS_BLOCK_GROUP_SYSTEM	(1ULL << 1)

@@ -1508,6 +1528,12 @@ struct btrfs_ioctl_defrag_range_args {
 #define BTRFS_BALANCE_ITEM_KEY	248
 
 /*
+ * Persistantly stores the io stats in the device tree.
+ * One key for all stats, (0, BTRFS_DEVICE_STATS_KEY, devid).
+ */
+#define BTRFS_DEVICE_STATS_KEY	249
+
+/*
  * string items are for debugging.  They just store a short string of
  * data in the FS
  */

@@ -2415,6 +2441,31 @@ static inline u32 btrfs_file_extent_inline_item_len(struct extent_buffer *eb,
 	return btrfs_item_size(eb, e) - offset;
 }
 
+/* btrfs_device_stats_item */
+BTRFS_SETGET_FUNCS(device_stats_cnt_write_io_errs,
+		   struct btrfs_device_stats_item, cnt_write_io_errs, 64);
+BTRFS_SETGET_FUNCS(device_stats_cnt_read_io_errs,
+		   struct btrfs_device_stats_item, cnt_read_io_errs, 64);
+BTRFS_SETGET_FUNCS(device_stats_cnt_flush_io_errs,
+		   struct btrfs_device_stats_item, cnt_flush_io_errs, 64);
+BTRFS_SETGET_FUNCS(device_stats_cnt_corruption_errs,
+		   struct btrfs_device_stats_item, cnt_corruption_errs, 64);
+BTRFS_SETGET_FUNCS(device_stats_cnt_generation_errs,
+		   struct btrfs_device_stats_item, cnt_generation_errs, 64);
+
+BTRFS_SETGET_STACK_FUNCS(stack_device_stats_cnt_write_io_errs,
+			 struct btrfs_device_stats_item, cnt_write_io_errs, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_device_stats_cnt_read_io_errs,
+			 struct btrfs_device_stats_item, cnt_read_io_errs, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_device_stats_cnt_flush_io_errs,
+			 struct btrfs_device_stats_item, cnt_flush_io_errs, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_device_stats_cnt_corruption_errs,
+			 struct btrfs_device_stats_item, cnt_corruption_errs,
+			 64);
+BTRFS_SETGET_STACK_FUNCS(stack_device_stats_cnt_generation_errs,
+			 struct btrfs_device_stats_item, cnt_generation_errs,
+			 64);
+
 static inline struct btrfs_fs_info *btrfs_sb(struct super_block *sb)
 {
 	return sb->s_fs_info;

index e123629..7ba08f7 100644
@@ -2353,6 +2353,13 @@ retry_root_backup:
 	fs_info->generation = generation;
 	fs_info->last_trans_committed = generation;
 
+	ret = btrfs_init_device_stats(fs_info);
+	if (ret) {
+		printk(KERN_ERR "btrfs: failed to init device_stats: %d\n",
+		       ret);
+		goto fail_block_groups;
+	}
+
 	ret = btrfs_init_space_info(fs_info);
 	if (ret) {
 		printk(KERN_ERR "Failed to initial space info: %d\n", ret);

index f38e452..a9e45e4 100644
@@ -294,6 +294,9 @@ void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l)
 			       btrfs_dev_extent_chunk_offset(l, dev_extent),
 			       (unsigned long long)
 			       btrfs_dev_extent_length(l, dev_extent));
+		case BTRFS_DEVICE_STATS_KEY:
+			printk(KERN_INFO "\t\tdevice stats\n");
+			break;
 		};
 	}
 }

index 3642225..1722af0 100644
@@ -28,6 +28,7 @@
 #include "locking.h"
 #include "tree-log.h"
 #include "inode-map.h"
+#include "volumes.h"
 
 #define BTRFS_ROOT_TRANS_TAG 0
 

@@ -758,6 +759,9 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans,
 	if (ret)
 		return ret;
 
+	ret = btrfs_run_device_stats(trans, root->fs_info);
+	BUG_ON(ret);
+
 	while (!list_empty(&fs_info->dirty_cowonly_roots)) {
 		next = fs_info->dirty_cowonly_roots.next;
 		list_del_init(next);

237 lines not on this page · raw message

index e0b31f1..3134662 100644
@@ -108,6 +108,7 @@ struct btrfs_device {
 
 	/* disk I/O failure stats. For detailed description refer to
 	 * struct btrfs_device_stats_item in ctree.h */
+	int device_stats_valid;
 	int device_stats_dirty; /* counters need to be written to disk */
 	atomic_t cnt_write_io_errs;
 	atomic_t cnt_read_io_errs;

@@ -291,6 +292,9 @@ int find_free_dev_extent(struct btrfs_device *device, u64 num_bytes,
 			 u64 *start, u64 *max_avail);
 struct btrfs_device *btrfs_find_device_for_logical(struct btrfs_root *root,
 						   u64 logical, int mirror_num);
+int btrfs_init_device_stats(struct btrfs_fs_info *fs_info);
+int btrfs_run_device_stats(struct btrfs_trans_handle *trans,
+			   struct btrfs_fs_info *fs_info);
 void btrfs_device_stat_print_on_error(struct btrfs_device *device);
 int btrfs_get_device_stats(struct btrfs_root *root,
 			   struct btrfs_ioctl_get_device_stats *stats,

@@ -315,4 +319,9 @@ static inline void btrfs_device_stat_reset(atomic_t *cnt)
 {
 	atomic_set(cnt, 0);
 }
+
+static inline void btrfs_device_stat_set(atomic_t *cnt, unsigned long val)
+{
+	atomic_set(cnt, val);
+}
 #endif