btrfs: introduce offload_csum_mode to tweak checksum offloading behavior

We disable offloading checksum to workqueues and do it synchronously when
the checksum algorithm is fast. However, as reported in the link below,
RAID0 with multiple devices may suffer from the sync checksum, because
"fast checksum" is still not fast enough to catch up with RAID0 writing.

We don't have an effective way to determine whether to offload or not,
for now add a sysfs knob so this can be debugged. This is intentionally
under CONFIG_BTRFS_DEBUG so ti's not exposed to users as it may be
removed in the future agin.

Introduce fs_devices->offload_csum_mode, so that a btrfs developer can
change the behavior by writing to /sys/fs/btrfs/<uuid>/offload_csum. The
default is "auto" which is the same as the previous behavior. Or, you
can set "on" or "off" (or "y" or "n" whatever kstrtobool() accepts) to
always/never offload checksum.

More benchmark need to be collected with this knob to implement a proper
criteria to enable/disable checksum offloading.

Link: https://lore.kernel.org/linux-btrfs/20230731152223.4EFB.409509F4@e16-tech.com/
Link: https://lore.kernel.org/linux-btrfs/p3vo3g7pqn664mhmdhlotu5dzcna6vjtcoc2hb2lsgo2fwct7k@xzaxclba5tae/
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 44 insertions, 0 deletions

diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index f2681d634302..c6387a8ddb94 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -1307,6 +1307,47 @@ static ssize_t btrfs_bg_reclaim_threshold_store(struct kobject *kobj,
 BTRFS_ATTR_RW(, bg_reclaim_threshold, btrfs_bg_reclaim_threshold_show,
 	      btrfs_bg_reclaim_threshold_store);
 
+#ifdef CONFIG_BTRFS_DEBUG
+static ssize_t btrfs_offload_csum_show(struct kobject *kobj,
+				       struct kobj_attribute *a, char *buf)
+{
+	struct btrfs_fs_devices *fs_devices = to_fs_devs(kobj);
+
+	switch (READ_ONCE(fs_devices->offload_csum_mode)) {
+	case BTRFS_OFFLOAD_CSUM_AUTO:
+		return sysfs_emit(buf, "auto\n");
+	case BTRFS_OFFLOAD_CSUM_FORCE_ON:
+		return sysfs_emit(buf, "1\n");
+	case BTRFS_OFFLOAD_CSUM_FORCE_OFF:
+		return sysfs_emit(buf, "0\n");
+	default:
+		WARN_ON(1);
+		return -EINVAL;
+	}
+}
+
+static ssize_t btrfs_offload_csum_store(struct kobject *kobj,
+					struct kobj_attribute *a, const char *buf,
+					size_t len)
+{
+	struct btrfs_fs_devices *fs_devices = to_fs_devs(kobj);
+	int ret;
+	bool val;
+
+	ret = kstrtobool(buf, &val);
+	if (ret == 0)
+		WRITE_ONCE(fs_devices->offload_csum_mode,
+			   val ? BTRFS_OFFLOAD_CSUM_FORCE_ON : BTRFS_OFFLOAD_CSUM_FORCE_OFF);
+	else if (ret == -EINVAL && sysfs_streq(buf, "auto"))
+		WRITE_ONCE(fs_devices->offload_csum_mode, BTRFS_OFFLOAD_CSUM_AUTO);
+	else
+		return -EINVAL;
+
+	return len;
+}
+BTRFS_ATTR_RW(, offload_csum, btrfs_offload_csum_show, btrfs_offload_csum_store);
+#endif
+
 /*
  * Per-filesystem information and stats.
  *
@@ -1326,6 +1367,9 @@ static const struct attribute *btrfs_attrs[] = {
 	BTRFS_ATTR_PTR(, bg_reclaim_threshold),
 	BTRFS_ATTR_PTR(, commit_stats),
 	BTRFS_ATTR_PTR(, temp_fsid),
+#ifdef CONFIG_BTRFS_DEBUG
+	BTRFS_ATTR_PTR(, offload_csum),
+#endif
 	NULL,
 };