Btrfs: add device counters for detected IO and checksum errors

The goal is to detect when drives start to get an increased error rate,
when drives should be replaced soon. Therefore statistic counters are
added that count IO errors (read, write and flush). Additionally, the
software detected errors like checksum errors and corrupted blocks are
counted.

Signed-off-by: Stefan Behrens <sbehrens@giantdisaster.de>

1 files changed, 45 insertions, 0 deletions

diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index bb6b03f97aaa..193b2835e6ae 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -22,6 +22,7 @@
 #include <linux/bio.h>
 #include <linux/sort.h>
 #include "async-thread.h"
+#include "ioctl.h"
 
 #define BTRFS_STRIPE_LEN        (64 * 1024)
 
@@ -106,6 +107,10 @@ struct btrfs_device {
         struct completion flush_wait;
         int nobarriers;
 
+        /* disk I/O failure stats. For detailed description refer to
+         * enum btrfs_dev_stat_values in ioctl.h */
+        int dev_stats_dirty; /* counters need to be written to disk */
+        atomic_t dev_stat_values[BTRFS_DEV_STAT_VALUES_MAX];
 };
 
 struct btrfs_fs_devices {
@@ -281,4 +286,44 @@ 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_dev_stat_print_on_error(struct btrfs_device *device);
+void btrfs_dev_stat_inc_and_print(struct btrfs_device *dev, int index);
+
+static inline void btrfs_dev_stat_inc(struct btrfs_device *dev,
+                                      int index)
+{
+        atomic_inc(dev->dev_stat_values + index);
+        dev->dev_stats_dirty = 1;
+}
+
+static inline int btrfs_dev_stat_read(struct btrfs_device *dev,
+                                      int index)
+{
+        return atomic_read(dev->dev_stat_values + index);
+}
+
+static inline int btrfs_dev_stat_read_and_reset(struct btrfs_device *dev,
+                                                int index)
+{
+        int ret;
+
+        ret = atomic_xchg(dev->dev_stat_values + index, 0);
+        dev->dev_stats_dirty = 1;
+        return ret;
+}
+
+static inline void btrfs_dev_stat_set(struct btrfs_device *dev,
+                                      int index, unsigned long val)
+{
+        atomic_set(dev->dev_stat_values + index, val);
+        dev->dev_stats_dirty = 1;
+}
+
+static inline void btrfs_dev_stat_reset(struct btrfs_device *dev,
+                                        int index)
+{
+        btrfs_dev_stat_set(dev, index, 0);
+}
 #endif