Btrfs: Add async worker threads for pre and post IO checksumming

Btrfs has been using workqueues to spread the checksumming load across
other CPUs in the system.  But, workqueues only schedule work on the
same CPU that queued the work, giving them a limited benefit for systems with
higher CPU counts.

This code adds a generic facility to schedule work with pools of kthreads,
and changes the bio submission code to queue bios up.  The queueing is
important to make sure large numbers of procs on the system don't
turn streaming workloads into random workloads by sending IO down
concurrently.

The end result of all of this is much higher performance (and CPU usage) when
doing checksumming on large machines.  Two worker pools are created,
one for writes and one for endio processing.  The two could deadlock if
we tried to service both from a single pool.

Signed-off-by: Chris Mason <chris.mason@oracle.com>

1 files changed, 11 insertions, 3 deletions

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 49cbc62b42f9..6c91a510c965 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -30,6 +30,7 @@
 #include "bit-radix.h"
 #include "extent_io.h"
 #include "extent_map.h"
+#include "async-thread.h"
 
 struct btrfs_trans_handle;
 struct btrfs_transaction;
@@ -518,13 +519,20 @@ struct btrfs_fs_info {
         struct list_head hashers;
         struct list_head dead_roots;
         struct list_head end_io_work_list;
-        struct list_head async_submit_work_list;
         struct work_struct end_io_work;
-        struct work_struct async_submit_work;
         spinlock_t end_io_work_lock;
-        spinlock_t async_submit_work_lock;
         atomic_t nr_async_submits;
 
+        /*
+         * there is a pool of worker threads for checksumming during writes
+         * and a pool for checksumming after reads.  This is because readers
+         * can run with FS locks held, and the writers may be waiting for
+         * those locks.  We don't want ordering in the pending list to cause
+         * deadlocks, and so the two are serviced separately.
+         */
+        struct btrfs_workers workers;
+        struct btrfs_workers endio_workers;
+
 #if LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,18)
         struct work_struct trans_work;
 #else