btrfs: state information for readahead

Add state information for readahead to btrfs_fs_info and btrfs_device

Changes v2:
 - don't wait in radix_trees
 - add own set of workers for readahead

Reviewed-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Arne Jansen <sensille@gmx.net>

4 files changed, 31 insertions, 0 deletions

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 03912c5c6f49..f71fd24cc152 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1036,6 +1036,7 @@ struct btrfs_fs_info {
         struct btrfs_workers endio_freespace_worker;
         struct btrfs_workers submit_workers;
         struct btrfs_workers caching_workers;
+        struct btrfs_workers readahead_workers;
 
         /*
          * fixup workers take dirty pages that didn't properly go through
@@ -1119,6 +1120,10 @@ struct btrfs_fs_info {
         u64 fs_state;
 
         struct btrfs_delayed_root *delayed_root;
+
+        /* readahead tree */
+        spinlock_t reada_lock;
+        struct radix_tree_root reada_tree;
 };
 
 /*
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 1220d04072c8..fd28c40e9ec3 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1711,6 +1711,10 @@ struct btrfs_root *open_ctree(struct super_block *sb,
         fs_info->defrag_inodes = RB_ROOT;
         fs_info->trans_no_join = 0;
 
+        /* readahead state */
+        INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT);
+        spin_lock_init(&fs_info->reada_lock);
+
         fs_info->thread_pool_size = min_t(unsigned long,
                                           num_online_cpus() + 2, 8);
 
@@ -1903,6 +1907,9 @@ struct btrfs_root *open_ctree(struct super_block *sb,
         btrfs_init_workers(&fs_info->delayed_workers, "delayed-meta",
                            fs_info->thread_pool_size,
                            &fs_info->generic_worker);
+        btrfs_init_workers(&fs_info->readahead_workers, "readahead",
+                           fs_info->thread_pool_size,
+                           &fs_info->generic_worker);
 
         /*
          * endios are largely parallel and should have a very
@@ -1913,6 +1920,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 
         fs_info->endio_write_workers.idle_thresh = 2;
         fs_info->endio_meta_write_workers.idle_thresh = 2;
+        fs_info->readahead_workers.idle_thresh = 2;
 
         btrfs_start_workers(&fs_info->workers, 1);
         btrfs_start_workers(&fs_info->generic_worker, 1);
@@ -1926,6 +1934,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
         btrfs_start_workers(&fs_info->endio_freespace_worker, 1);
         btrfs_start_workers(&fs_info->delayed_workers, 1);
         btrfs_start_workers(&fs_info->caching_workers, 1);
+        btrfs_start_workers(&fs_info->readahead_workers, 1);
 
         fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super);
         fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages,
@@ -2650,6 +2659,7 @@ int close_ctree(struct btrfs_root *root)
         btrfs_stop_workers(&fs_info->submit_workers);
         btrfs_stop_workers(&fs_info->delayed_workers);
         btrfs_stop_workers(&fs_info->caching_workers);
+        btrfs_stop_workers(&fs_info->readahead_workers);
 
         btrfs_close_devices(fs_info->fs_devices);
         btrfs_mapping_tree_free(&fs_info->mapping_tree);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index f2a4cc79da61..1dccce5bc93d 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -366,6 +366,14 @@ static noinline int device_list_add(const char *path,
                 }
                 INIT_LIST_HEAD(&device->dev_alloc_list);
 
+                /* init readahead state */
+                spin_lock_init(&device->reada_lock);
+                device->reada_curr_zone = NULL;
+                atomic_set(&device->reada_in_flight, 0);
+                device->reada_next = 0;
+                INIT_RADIX_TREE(&device->reada_zones, GFP_NOFS & ~__GFP_WAIT);
+                INIT_RADIX_TREE(&device->reada_extents, GFP_NOFS & ~__GFP_WAIT);
+
                 mutex_lock(&fs_devices->device_list_mutex);
                 list_add_rcu(&device->dev_list, &fs_devices->devices);
                 mutex_unlock(&fs_devices->device_list_mutex);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 6d866db4e177..2a751246188a 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -92,6 +92,14 @@ struct btrfs_device {
         struct btrfs_work work;
         struct rcu_head rcu;
         struct work_struct rcu_work;
+
+        /* readahead state */
+        spinlock_t reada_lock;
+        atomic_t reada_in_flight;
+        u64 reada_next;
+        struct reada_zone *reada_curr_zone;
+        struct radix_tree_root reada_zones;
+        struct radix_tree_root reada_extents;
 };
 
 struct btrfs_fs_devices {