@@ -916,7 +916,8 @@ 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" };
+static const char * const btrfs_read_policy_name[] = { "pid", "latency",
+ "device" };
static ssize_t btrfs_read_policy_show(struct kobject *kobj,
struct kobj_attribute *a, char *buf)
@@ -5524,6 +5524,25 @@ static int btrfs_find_best_stripe(struct btrfs_fs_info *fs_info,
return best_stripe;
}
+static int btrfs_find_read_preferred(struct map_lookup *map, int first, int num_stripe)
+{
+ int stripe_index;
+ int last = first + num_stripe;
+
+ /*
+ * If there are more than one read preferred devices, then just pick the
+ * first found read preferred device as of now.
+ */
+ for (stripe_index = first; stripe_index < last; stripe_index++) {
+ if (test_bit(BTRFS_DEV_STATE_READ_PREFERRED,
+ &map->stripes[stripe_index].dev->dev_state))
+ return stripe_index;
+ }
+
+ /* If there is no read preferred device then just use the first stripe */
+ return first;
+}
+
static int find_live_mirror(struct btrfs_fs_info *fs_info,
struct map_lookup *map, int first,
int dev_replace_is_ongoing)
@@ -5557,6 +5576,9 @@ static int find_live_mirror(struct btrfs_fs_info *fs_info,
preferred_mirror = btrfs_find_best_stripe(fs_info, map, first,
num_stripes);
break;
+ case BTRFS_READ_POLICY_DEVICE:
+ preferred_mirror = btrfs_find_read_preferred(map, first, num_stripes);
+ break;
}
if (dev_replace_is_ongoing &&
@@ -225,6 +225,8 @@ enum btrfs_read_policy {
BTRFS_READ_POLICY_PID,
/* Find and use device with the lowest latency */
BTRFS_READ_POLICY_LATENCY,
+ /* Use the device marked with READ_PREFERRED state */
+ BTRFS_READ_POLICY_DEVICE,
BTRFS_NR_READ_POLICY,
};
Read-policy type 'device' and device flag 'read-preferred': The read-policy type device picks the device(s) flagged as read-preferred for reading stripes of type raid1, raid10, raid1c3 and raid1c4. A system might contain SSD, nvme, iscsi, or san lun, and which are all a non-rotational device, so it is not a good idea to set the read-preferred automatically. Instead, device read-policy along with the read-preferred flag provides an ability to do it manually. This advanced tuning is useful in more than one situation, for example, - In heterogeneous-disk volume, it provides an ability to manually choose the low latency disks for reading. - Useful for more accurate testing. - Avoid known problematic device from reading the chunk until it is replaced (by marking the other good devices as read-preferred). Note: If the read-policy type is set to 'device', but there isn't any device which is flagged as read-preferred, then stripe 0 is used for reading. The device replacement won't migrate the read-preferred flag to the new replace the target device. As of now, this is an in-memory only feature. It's pointless to set the read-preferred flag on the missing device, as IOs aren't submitted to the missing device. If there is more than one read-preferred device in a chunk, the read IO shall go to the stripe 0 as of now. Usage example: Consider a typical two disks raid1. Configure devid1 for reading. $ echo 1 > devinfo/1/read_preferred $ cat devinfo/1/read_preferred 1 $ cat devinfo/2/read_preferred 0 $ pwd /sys/fs/btrfs/12345678-1234-1234-1234-123456789abc $ cat read_policy [pid] device $ echo device > ./read_policy $ cat read_policy pid [device] Now read IOs are sent to devid 1 (sdb). $ echo 3 > /proc/sys/vm/drop_caches $ md5sum /btrfs/YkZI $ iostat -zy 1 | egrep 'sdb|sdc' (from another terminal) sdb 50.00 40048.00 0.00 40048 0 Change the read-preferred device from devid 1 to devid 2 (sdc). $ echo 0 > ./devinfo/1/read_preferred [ 3343.918658] BTRFS info (device sdb): reset read preferred on devid 1 (1334) $ echo 1 > ./devinfo/2/read_preferred [ 3343.919876] BTRFS info (device sdb): set read preferred on devid 2 (1334) $ echo 3 > /proc/sys/vm/drop_caches $ md5sum /btrfs/YkZI Further read ios are sent to devid 2 (sdc). $ iostat -zy 1 | egrep 'sdb|sdc' (from another terminal) sdc 49.00 40048.00 0.00 40048 0 Signed-off-by: Anand Jain <anand.jain@oracle.com> Reviewed-by: Josef Bacik <josef@toxicpanda.com> --- v4: add Josef rb. v3: update the change log. v2: - rfc->v1: - fs/btrfs/sysfs.c | 3 ++- fs/btrfs/volumes.c | 22 ++++++++++++++++++++++ fs/btrfs/volumes.h | 2 ++ 3 files changed, 26 insertions(+), 1 deletion(-)