@@ -1205,6 +1205,7 @@ static int open_fs_devices(struct btrfs_fs_devices *fs_devices,
fs_devices->opened = 1;
fs_devices->latest_bdev = latest_dev->bdev;
fs_devices->total_rw_bytes = 0;
+ fs_devices->read_policy = BTRFS_READ_POLICY_PID;
out:
return ret;
}
@@ -5397,7 +5398,19 @@ static int find_live_mirror(struct btrfs_fs_info *fs_info,
else
num_stripes = map->num_stripes;
- preferred_mirror = first + current->pid % num_stripes;
+ switch (fs_info->fs_devices->read_policy) {
+ default:
+ /*
+ * Shouldn't happen, just warn and use pid instead of failing.
+ */
+ btrfs_warn_rl(fs_info,
+ "unknown read_policy type %u, fallback to pid",
+ fs_info->fs_devices->read_policy);
+ /* fall through */
+ case BTRFS_READ_POLICY_PID:
+ preferred_mirror = first + current->pid % num_stripes;
+ break;
+ }
if (dev_replace_is_ongoing &&
fs_info->dev_replace.cont_reading_from_srcdev_mode ==
@@ -207,6 +207,15 @@ BTRFS_DEVICE_GETSET_FUNCS(total_bytes);
BTRFS_DEVICE_GETSET_FUNCS(disk_total_bytes);
BTRFS_DEVICE_GETSET_FUNCS(bytes_used);
+/*
+ * Read policies for the mirrored block groups, read picks the stripe based
+ * on these policies.
+ */
+enum btrfs_read_policy {
+ BTRFS_READ_POLICY_PID,
+ BTRFS_NR_READ_POLICY,
+};
+
struct btrfs_fs_devices {
u8 fsid[BTRFS_FSID_SIZE]; /* FS specific uuid */
u8 metadata_uuid[BTRFS_FSID_SIZE];
@@ -258,6 +267,11 @@ struct btrfs_fs_devices {
struct kobject *devices_kobj;
struct kobject *devinfo_kobj;
struct completion kobj_unregister;
+
+ /*
+ * policy used to read the mirrored stripes
+ */
+ enum btrfs_read_policy read_policy;
};
#define BTRFS_BIO_INLINE_CSUM_SIZE 64
As of now we use %pid method to read stripped mirrored data, which means process id determines the stripe id to be read. This type of routing typically helps in a system with many small independent processes tying to read random data. On the other hand the %pid based read IO policy is inefficient because if there is a single process trying to read large data the overall disk bandwidth remains under-utilized. So this patch introduces read policy framework so that we could add more read policies, such as IO routing based on device's wait-queue or manual when we have a read-preferred device or a policy based on the target storage caching. Signed-off-by: Anand Jain <anand.jain@oracle.com> --- v7: Fix missing /* fall through */ in the switch Removed Reviewed-by: Josef Bacik <josef@toxicpanda.com> v6:- v5: Title renamed from:- btrfs: add read_policy framework Change log updated. Unnecessary comment dropped, added more where necessary. Optimize code in the switch remove duplicate code. Define BTRFS_READ_POLICY_DEFAULT dropped. Rename enum btrfs_read_policy_type to enum btrfs_read_policy. Rename BTRFS_READ_BY_PID to BTRFS_READ_POLICY_PID. (As its mainly renames. Reviewed-by retained). v4: - v3: Declare fs_devices::readmirror as enum btrfs_readmirror_policy_type v2: Declare fs_devices::readmirror as u8 instead of atomic_t A small change in comment and change log wordings. fs/btrfs/volumes.c | 15 ++++++++++++++- fs/btrfs/volumes.h | 14 ++++++++++++++ 2 files changed, 28 insertions(+), 1 deletion(-)