The read policy type latency routes the read IO based on the historical
average wait-time experienced by the read IOs through the individual
device. This patch obtains the historical read IO stats from the kernel
block layer and calculates its average.
Example usage:
echo "latency" > /sys/fs/btrfs/$uuid/read_policy
Signed-off-by: Anand Jain <anand.j...@oracle.com>
---
v3: The block layer commit 0d02129e76ed (block: merge struct block_device and
struct hd_struct) has changed the first argument in the function
part_stat_read_all() in 5.11-rc1. So the compilation will fail. This patch
fixes it.
Commit log updated.
v2: Use btrfs_debug_rl() instead of btrfs_info_rl()
It is better we have this debug until we test this on at least few
hardwares.
Drop the unrelated changes.
Update change log.
v1: Drop part_stat_read_all instead use part_stat_read
Drop inflight
fs/btrfs/sysfs.c | 3 ++-
fs/btrfs/volumes.c | 38 ++++++++++++++++++++++++++++++++++++++
fs/btrfs/volumes.h | 2 ++
3 files changed, 42 insertions(+), 1 deletion(-)
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 19b9fffa2c9c..96ca7bef6357 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -915,7 +915,8 @@ static bool strmatch(const char *buffer, const char *string)
return false;
}
-static const char * const btrfs_read_policy_name[] = { "pid" };
+/* Must follow the order as in enum btrfs_read_policy */
+static const char * const btrfs_read_policy_name[] = { "pid", "latency" };
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 f4037a6bd926..f7a0a83d2cd4 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -14,6 +14,7 @@
#include <linux/semaphore.h>
#include <linux/uuid.h>
#include <linux/list_sort.h>
+#include <linux/part_stat.h>
#include "misc.h"
#include "ctree.h"
#include "extent_map.h"
@@ -5490,6 +5491,39 @@ int btrfs_is_parity_mirror(struct btrfs_fs_info
*fs_info, u64 logical, u64 len)
return ret;
}
+static int btrfs_find_best_stripe(struct btrfs_fs_info *fs_info,
+ struct map_lookup *map, int first,
+ int num_stripe)
+{
+ u64 est_wait = 0;
+ int best_stripe = 0;
+ int index;
+
+ for (index = first; index < first + num_stripe; index++) {
+ u64 read_wait;
+ u64 avg_wait = 0;
+ unsigned long read_ios;
+ struct btrfs_device *device = map->stripes[index].dev;
+
+ read_wait = part_stat_read(device->bdev, nsecs[READ]);
+ read_ios = part_stat_read(device->bdev, ios[READ]);
+
+ if (read_wait && read_ios && read_wait >= read_ios)
+ avg_wait = div_u64(read_wait, read_ios);
+ else
+ btrfs_debug_rl(device->fs_devices->fs_info,
+ "devid: %llu avg_wait ZERO read_wait %llu read_ios %lu",
+ device->devid, read_wait, read_ios);
+
+ if (est_wait == 0 || est_wait > avg_wait) {
+ est_wait = avg_wait;
+ best_stripe = index;
+ }
+ }
+
+ return best_stripe;
+}
+
static int find_live_mirror(struct btrfs_fs_info *fs_info,
struct map_lookup *map, int first,
int dev_replace_is_ongoing)
@@ -5519,6 +5553,10 @@ static int find_live_mirror(struct btrfs_fs_info
*fs_info,
case BTRFS_READ_POLICY_PID:
preferred_mirror = first + (current->pid % num_stripes);
break;
+ case BTRFS_READ_POLICY_LATENCY:
+ preferred_mirror = btrfs_find_best_stripe(fs_info, map, first,
+ num_stripes);
+ break;
}
if (dev_replace_is_ongoing &&
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 1997a4649a66..71ba1f0e93f4 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -222,6 +222,8 @@ enum btrfs_chunk_allocation_policy {
enum btrfs_read_policy {
/* Use process PID to choose the stripe */
BTRFS_READ_POLICY_PID,
+ /* Find and use device with the lowest latency */
+ BTRFS_READ_POLICY_LATENCY,
BTRFS_NR_READ_POLICY,
};
--
2.30.0
