[PATCH RFC 4/4] btrfs: introduce new read_policy round-robin

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

Add round-robin read policy to route the read IO to the next device in the
round-robin order. The chunk allocation and thus the stripe-index follows
the order of free space available on devices. So to make the round-robin
effective it shall follow the devid order instead of the stripe-index
order.

Signed-off-by: Anand Jain <anand.jain@oracle.com>
--
RFC because: Provides terrible performance with the fio tests.
I am not yet sure if there is any io workload or a block layer
tuning that shall make this policy better. As of now just an
experimental patch.

 fs/btrfs/sysfs.c   |  2 +-
 fs/btrfs/volumes.c | 50 ++++++++++++++++++++++++++++++++++++++++++++++
 fs/btrfs/volumes.h |  3 +++
 3 files changed, 54 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 899b66c83db1..d40b0ff054ca 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -917,7 +917,7 @@ static bool strmatch(const char *buffer, const char *string)
 
 /* Must follow the order as in enum btrfs_read_policy */
 static const char * const btrfs_read_policy_name[] = { "pid", "latency",
-						       "device" };
+						       "device", "roundrobin" };
 
 static ssize_t btrfs_read_policy_show(struct kobject *kobj,
 				      struct kobj_attribute *a, char *buf)
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 50d4d54f7abd..60370b9121e0 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -5491,6 +5491,52 @@ int btrfs_is_parity_mirror(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 	return ret;
 }
 
+struct stripe_mirror {
+	u64 devid;
+	int map;
+};
+
+static int btrfs_cmp_devid(const void *a, const void *b)
+{
+	struct stripe_mirror *s1 = (struct stripe_mirror *)a;
+	struct stripe_mirror *s2 = (struct stripe_mirror *)b;
+
+	if (s1->devid < s2->devid)
+		return -1;
+	if (s1->devid > s2->devid)
+		return 1;
+	return 0;
+}
+
+static int btrfs_find_read_round_robin(struct map_lookup *map, int first,
+				       int num_stripe)
+{
+	struct stripe_mirror stripes[4] = {0}; //4: for testing, works for now.
+	struct btrfs_fs_devices *fs_devices;
+	u64 devid;
+	int index, j, cnt;
+	int next_stripe;
+
+	index = 0;
+	for (j = first; j < first + num_stripe; j++) {
+		devid = map->stripes[j].dev->devid;
+
+		stripes[index].devid = devid;
+		stripes[index].map = j;
+
+		index++;
+	}
+
+	sort(stripes, num_stripe, sizeof(struct stripe_mirror),
+	     btrfs_cmp_devid, NULL);
+
+	fs_devices = map->stripes[first].dev->fs_devices;
+	cnt = atomic_inc_return(&fs_devices->total_reads);
+	next_stripe = stripes[cnt % num_stripe].map;
+
+	return next_stripe;
+}
+
 static int btrfs_find_best_stripe(struct btrfs_fs_info *fs_info,
 				  struct map_lookup *map, int first,
 				  int num_stripe)
@@ -5579,6 +5625,10 @@ static int find_live_mirror(struct btrfs_fs_info *fs_info,
 	case BTRFS_READ_POLICY_DEVICE:
 		preferred_mirror = btrfs_find_read_preferred(map, first, num_stripes);
 		break;
+	case BTRFS_READ_POLICY_ROUND_ROBIN:
+		preferred_mirror = btrfs_find_read_round_robin(map, first,
+							       num_stripes);
+		break;
 	}
 
 	if (dev_replace_is_ongoing &&
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 8d5a2cddc0ab..ce4490437f53 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -227,6 +227,8 @@ enum btrfs_read_policy {
 	BTRFS_READ_POLICY_LATENCY,
 	/* Use the device marked with READ_PREFERRED state */
 	BTRFS_READ_POLICY_DEVICE,
+	/* Distribute read IO equally across striped devices */
+	BTRFS_READ_POLICY_ROUND_ROBIN,
 	BTRFS_NR_READ_POLICY,
 };
 
@@ -286,6 +288,7 @@ struct btrfs_fs_devices {
 
 	/* Policy used to read the mirrored stripes */
 	enum btrfs_read_policy read_policy;
+	atomic_t total_reads;
 };
 
 #define BTRFS_BIO_INLINE_CSUM_SIZE	64
-- 
2.30.0