btrfs: create read policy framework

As of now, we use the pid method to read striped mirrored data, which
means process id determines the stripe id to 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 a large
file, the overall disk bandwidth remains underutilized.

So this patch introduces a read policy framework so that we could add
more read policies, such as IO routing based on the device's wait-queue
or manual when we have a read-preferred device or a policy based on the
target storage caching.

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 07c6b0c853396867b88ab147e4c3b34f5d7e113d..ed4163b54f756221cdc19d6be21c8b84e1b9cda7 100644 (file)
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1217,6 +1217,7 @@ static int open_fs_devices(struct btrfs_fs_devices *fs_devices,
        fs_devices->latest_bdev = latest_dev->bdev;
        fs_devices->total_rw_bytes = 0;
        fs_devices->chunk_alloc_policy = BTRFS_CHUNK_ALLOC_REGULAR;
+       fs_devices->read_policy = BTRFS_READ_POLICY_PID;
 
        return 0;
 }
@@ -5479,7 +5480,18 @@ 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, reset to pid",
+                             fs_info->fs_devices->read_policy);
+               fs_info->fs_devices->read_policy = BTRFS_READ_POLICY_PID;
+               fallthrough;
+       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 ==

diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 232f02bd214fc44e013574357c1e3cd926c6e77f..34fd440fd30b37fd865602073ed74a3a61ed66e7 100644 (file)
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -211,6 +211,16 @@ enum btrfs_chunk_allocation_policy {
        BTRFS_CHUNK_ALLOC_REGULAR,
 };
 
+/*
+ * Read policies for mirrored block group profiles, read picks the stripe based
+ * on these policies.
+ */
+enum btrfs_read_policy {
+       /* Use process PID to choose the stripe */
+       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];
@@ -264,6 +274,9 @@ struct btrfs_fs_devices {
        struct completion kobj_unregister;
 
        enum btrfs_chunk_allocation_policy chunk_alloc_policy;
+
+       /* Policy used to read the mirrored stripes */
+       enum btrfs_read_policy read_policy;
 };
 
 #define BTRFS_BIO_INLINE_CSUM_SIZE     64