[PATCH v3 1/3] btrfs: add readmirror type framework

[Anand Jain <anand.jain@oracle.com>]

As of now we use %pid method to read stripped mirrored data, so
application's process id determines the stripe id to be read. This type
of read IO routing typically helps in a system with many small
independent applications tying to read random data. On the other hand
the %pid based read IO distribution policy is inefficient if there is a
single application trying to read large data as the overall disk
bandwidth remains under utilized.

So this patch introduces a framework where we could add more readmirror
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>
---
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 | 16 +++++++++++++++-
 fs/btrfs/volumes.h |  8 ++++++++
 2 files changed, 23 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index c95e47aa84f8..e26af766f2b9 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1162,6 +1162,8 @@ 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;
+	/* Set the default readmirror policy */
+	fs_devices->readmirror = BTRFS_READMIRROR_DEFAULT;
 out:
 	return ret;
 }
@@ -5300,7 +5302,19 @@ 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->readmirror) {
+	case BTRFS_READMIRROR_BY_PID:
+		preferred_mirror = first + current->pid % num_stripes;
+		break;
+	default:
+		/*
+		 * Shouln't happen, just warn and use by_pid instead of failing.
+		 */
+		btrfs_warn_rl(fs_info,
+			      "unknown readmirror type %u, fallback to by_pid",
+			      fs_info->fs_devices->readmirror);
+		preferred_mirror = first + current->pid % num_stripes;
+	}
 
 	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 68021d1ee216..513610a3e6b8 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -209,6 +209,12 @@ BTRFS_DEVICE_GETSET_FUNCS(total_bytes);
 BTRFS_DEVICE_GETSET_FUNCS(disk_total_bytes);
 BTRFS_DEVICE_GETSET_FUNCS(bytes_used);
 
+/* readmirror_policy types */
+#define BTRFS_READMIRROR_DEFAULT	BTRFS_READMIRROR_BY_PID
+enum btrfs_readmirror_policy_type {
+	BTRFS_READMIRROR_BY_PID,
+};
+
 struct btrfs_fs_devices {
 	u8 fsid[BTRFS_FSID_SIZE]; /* FS specific uuid */
 	u8 metadata_uuid[BTRFS_FSID_SIZE];
@@ -260,6 +266,8 @@ struct btrfs_fs_devices {
 	struct kobject *devices_kobj;
 	struct kobject *devinfo_kobj;
 	struct completion kobj_unregister;
+
+	enum btrfs_readmirror_policy_type readmirror;
 };
 
 #define BTRFS_BIO_INLINE_CSUM_SIZE	64
-- 
2.23.0