@@ -3322,6 +3322,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
fs_info->sectorsize = sectorsize;
#ifdef CONFIG_BTRFS_EXPERIMENTAL
fs_info->fs_devices->min_contiguous_read = sectorsize;
+ fs_info->fs_devices->read_devid = fs_info->fs_devices->latest_dev->devid;
#endif
fs_info->sectorsize_bits = ilog2(sectorsize);
fs_info->sectors_per_page = (PAGE_SIZE >> fs_info->sectorsize_bits);
@@ -1306,7 +1306,7 @@ static ssize_t btrfs_temp_fsid_show(struct kobject *kobj,
BTRFS_ATTR(, temp_fsid, btrfs_temp_fsid_show);
#ifdef CONFIG_BTRFS_EXPERIMENTAL
-static const char * const btrfs_read_policy_name[] = { "pid", "rotation", "latency" };
+static const char * const btrfs_read_policy_name[] = { "pid", "rotation", "latency", "devid" };
#else
static const char * const btrfs_read_policy_name[] = { "pid" };
#endif
@@ -1332,8 +1332,11 @@ static ssize_t btrfs_read_policy_show(struct kobject *kobj,
if (i == BTRFS_READ_POLICY_ROTATION)
ret += sysfs_emit_at(buf, ret, ":%d",
fs_devices->min_contiguous_read);
-#endif
+ if (i == BTRFS_READ_POLICY_DEVID)
+ ret += sysfs_emit_at(buf, ret, ":%llu",
+ fs_devices->read_devid);
+#endif
if (i == policy)
ret += sysfs_emit_at(buf, ret, "]");
}
@@ -1401,7 +1404,32 @@ static ssize_t btrfs_read_policy_store(struct kobject *kobj,
return len;
}
+
+ if (index == BTRFS_READ_POLICY_DEVID) {
+ u64 value_devid;
+ BTRFS_DEV_LOOKUP_ARGS(args);
+
+ if (value == NULL || kstrtou64(value, 10, &value_devid))
+ return -EINVAL;
+
+ args.devid = value_devid;
+ if (btrfs_find_device(fs_devices, &args) == NULL)
+ return -EINVAL;
+
+ if (index != READ_ONCE(fs_devices->read_policy) ||
+ (value_devid != READ_ONCE(fs_devices->read_devid))) {
+ WRITE_ONCE(fs_devices->read_policy, index);
+ WRITE_ONCE(fs_devices->read_devid, value_devid);
+
+ btrfs_info(fs_devices->fs_info, "read policy set to '%s:%llu'",
+ btrfs_read_policy_name[index], value_devid);
+
+ }
+
+ return len;
+ }
#endif
+
if (index != READ_ONCE(fs_devices->read_policy)) {
WRITE_ONCE(fs_devices->read_policy, index);
btrfs_info(fs_devices->fs_info, "read policy set to '%s'",
@@ -5966,6 +5966,23 @@ unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info,
}
#ifdef CONFIG_BTRFS_EXPERIMENTAL
+static int btrfs_read_preferred(struct btrfs_chunk_map *map, int first,
+ int num_stripe)
+{
+ int last = first + num_stripe;
+ int stripe_index;
+
+ for (stripe_index = first; stripe_index < last; stripe_index++) {
+ struct btrfs_device *device = map->stripes[stripe_index].dev;
+
+ if (device->devid == READ_ONCE(device->fs_devices->read_devid))
+ return stripe_index;
+ }
+
+ /* If no read-preferred device, use first stripe */
+ return first;
+}
+
static int btrfs_best_stripe(struct btrfs_fs_info *fs_info,
struct btrfs_chunk_map *map, int first,
int num_stripe)
@@ -6079,6 +6096,9 @@ static int find_live_mirror(struct btrfs_fs_info *fs_info,
preferred_mirror = btrfs_best_stripe(fs_info, map, first,
num_stripes);
break;
+ case BTRFS_READ_POLICY_DEVID:
+ preferred_mirror = btrfs_read_preferred(map, first, num_stripes);
+ break;
#endif
}
@@ -308,6 +308,8 @@ enum btrfs_read_policy {
BTRFS_READ_POLICY_ROTATION,
/* Use the lowest-latency device dynamically */
BTRFS_READ_POLICY_LATENCY,
+ /* Read from the specific device */
+ BTRFS_READ_POLICY_DEVID,
#endif
BTRFS_NR_READ_POLICY,
};
@@ -442,6 +444,9 @@ struct btrfs_fs_devices {
/* Min contiguous reads before switching to next device. */
int min_contiguous_read;
+ /* Device to be used for reading in case of RAID1. */
+ u64 read_devid;
+
/* Checksum mode - offload it or do it synchronously. */
enum btrfs_offload_csum_mode offload_csum_mode;
#endif
When there's stale data on a mirrored device, this feature lets you choose which device to read from. Mainly used for testing. echo "devid:2" > /sys/fs/btrfs/<UUID>/read_policy Signed-off-by: Anand Jain <anand.jain@oracle.com> --- fs/btrfs/disk-io.c | 1 + fs/btrfs/sysfs.c | 32 ++++++++++++++++++++++++++++++-- fs/btrfs/volumes.c | 20 ++++++++++++++++++++ fs/btrfs/volumes.h | 5 +++++ 4 files changed, 56 insertions(+), 2 deletions(-)