[09/24] lustre: lmv: set default LMV for "lfs mkdir -c 1"

Commit Message

James Simmons Jan. 14, 2022, 1:37 a.m. UTC

From: Lai Siyao <[e-mail]>

With the introduction of filesystem-wide default LMV, dirs will be
created on MDT by space usage, but if dir is created by
"lfs mkdir -c 1 ...", its subdirs should be kept on the same MDT.
To achieve this, set default LMV on such dirs, NB if user doesn't
want this, he needs to create dir with
"lfs mkdir -c 1 --max-inherit=0 ...".

The policy to choose MDT in mkdir is as below:
1. is "lfs mkdir -i N"? mkdir on MDT N.
2. is "lfs mkdir -i -1"? mkdir by space usage.
3. is starting MDT specified in default LMV? mkdir on MDT N.
4. is default LMV space balanced? mkdir by space usage.

WC-bug-id: https://jira.whamcloud.com/browse/LU-14560
Lustre-commit: bc2d7f065af6b4f9a ("LU-13560 lod: set default LMV for "lfs mkdir -c 1")
Signed-off-by: Lai Siyao <[e-mail]>
Reviewed-on: https://review.whamcloud.com/45290
Reviewed-by: Andreas Dilger <[e-mail]>
Reviewed-by: Hongchao Zhang <[e-mail]>
Reviewed-by: Oleg Drokin <[e-mail]>
Signed-off-by: James Simmons <[e-mail]>
---
 fs/lustre/lmv/lmv_obd.c | 104 +++++++++++++++++++++++++++---------------------
 1 file changed, 58 insertions(+), 46 deletions(-)

Patch

diff --git a/fs/lustre/lmv/lmv_obd.c b/fs/lustre/lmv/lmv_obd.c
index c87f37f..55816a1 100644
--- a/fs/lustre/lmv/lmv_obd.c
+++ b/fs/lustre/lmv/lmv_obd.c
@@ -1770,46 +1770,39 @@  int lmv_old_layout_lookup(struct lmv_obd *lmv, struct md_op_data *op_data)
 	return rc;
 }
 
+/* mkdir by QoS upon 'lfs mkdir -i -1'.
+ *
+ * NB, mkdir by QoS only if parent is not striped, this is to avoid remote
+ * directories under striped directory.
+ */
 static inline bool lmv_op_user_qos_mkdir(const struct md_op_data *op_data)
 {
 	const struct lmv_user_md *lum = op_data->op_data;
 
+	if (op_data->op_code != LUSTRE_OPC_MKDIR)
+		return false;
+
+	if (lmv_dir_striped(op_data->op_mea1))
+		return false;
+
 	return (op_data->op_cli_flags & CLI_SET_MEA) && lum &&
 	       le32_to_cpu(lum->lum_magic) == LMV_USER_MAGIC &&
 	       le32_to_cpu(lum->lum_stripe_offset) == LMV_OFFSET_DEFAULT;
 }
 
+/* mkdir by QoS if either ROOT or parent default LMV is space balanced. */
 static inline bool lmv_op_default_qos_mkdir(const struct md_op_data *op_data)
 {
 	const struct lmv_stripe_md *lsm = op_data->op_default_mea1;
 
-	return (op_data->op_flags & MF_QOS_MKDIR) ||
-	       (lsm && lsm->lsm_md_master_mdt_index == LMV_OFFSET_DEFAULT);
-}
-
-/* mkdir by QoS in three cases:
- * 1. ROOT default LMV is space balanced.
- * 2. 'lfs mkdir -i -1'
- * 3. parent default LMV master_mdt_index is -1
- *
- * NB, mkdir by QoS only if parent is not striped, this is to avoid remote
- * directories under striped directory.
- */
-static inline bool lmv_op_qos_mkdir(const struct md_op_data *op_data)
-{
 	if (op_data->op_code != LUSTRE_OPC_MKDIR)
 		return false;
 
 	if (lmv_dir_striped(op_data->op_mea1))
 		return false;
 
-	if (lmv_op_user_qos_mkdir(op_data))
-		return true;
-
-	if (lmv_op_default_qos_mkdir(op_data))
-		return true;
-
-	return false;
+	return (op_data->op_flags & MF_QOS_MKDIR) ||
+	       (lsm && lsm->lsm_md_master_mdt_index == LMV_OFFSET_DEFAULT);
 }
 
 /* if parent default LMV is space balanced, and
@@ -1853,6 +1846,38 @@  static inline bool lmv_op_user_specific_mkdir(const struct md_op_data *op_data)
 			LMV_OFFSET_DEFAULT;
 }
 
+/* locate MDT by space usage */
+static struct lu_tgt_desc *lmv_locate_tgt_by_space(struct lmv_obd *lmv,
+						   struct md_op_data *op_data,
+						   struct lmv_tgt_desc *tgt)
+{
+	struct lmv_tgt_desc *tmp = tgt;
+
+	tgt = lmv_locate_tgt_qos(lmv, op_data->op_mds, op_data->op_dir_depth);
+	if (tgt == ERR_PTR(-EAGAIN)) {
+		if (ltd_qos_is_balanced(&lmv->lmv_mdt_descs) &&
+		    !lmv_op_default_rr_mkdir(op_data) &&
+		    !lmv_op_user_qos_mkdir(op_data))
+			/* if not necessary, don't create remote directory. */
+			tgt = tmp;
+		else
+			tgt = lmv_locate_tgt_rr(lmv);
+	}
+
+	/*
+	 * only update statfs after QoS mkdir, this means the cached statfs may
+	 * be stale, and current mkdir may not follow QoS accurately, but it's
+	 * not serious, and avoids periodic statfs when client doesn't mkdir by
+	 * QoS.
+	 */
+	if (!IS_ERR(tgt)) {
+		op_data->op_mds = tgt->ltd_index;
+		lmv_statfs_check_update(lmv2obd_dev(lmv), tgt);
+	}
+
+	return tgt;
+}
+
 int lmv_create(struct obd_export *exp, struct md_op_data *op_data,
 		const void *data, size_t datalen, umode_t mode, uid_t uid,
 		gid_t gid, kernel_cap_t cap_effective, u64 rdev,
@@ -1886,6 +1911,12 @@  int lmv_create(struct obd_export *exp, struct md_op_data *op_data,
 	if (IS_ERR(tgt))
 		return PTR_ERR(tgt);
 
+	/* the order to apply policy in mkdir:
+	 * 1. is "lfs mkdir -i N"? mkdir on MDT N.
+	 * 2. is "lfs mkdir -i -1"? mkdir by space usage.
+	 * 3. is starting MDT specified in default LMV? mkdir on MDT N.
+	 * 4. is default LMV space balanced? mkdir by space usage.
+	 */
 	if (lmv_op_user_specific_mkdir(op_data)) {
 		struct lmv_user_md *lum = op_data->op_data;
 
@@ -1893,39 +1924,20 @@  int lmv_create(struct obd_export *exp, struct md_op_data *op_data,
 		tgt = lmv_tgt(lmv, op_data->op_mds);
 		if (!tgt)
 			return -ENODEV;
+	} else if (lmv_op_user_qos_mkdir(op_data)) {
+		tgt = lmv_locate_tgt_by_space(lmv, op_data, tgt);
+		if (IS_ERR(tgt))
+			return PTR_ERR(tgt);
 	} else if (lmv_op_default_specific_mkdir(op_data)) {
 		op_data->op_mds =
 			op_data->op_default_mea1->lsm_md_master_mdt_index;
 		tgt = lmv_tgt(lmv, op_data->op_mds);
 		if (!tgt)
 			return -ENODEV;
-	} else if (lmv_op_qos_mkdir(op_data)) {
-		struct lmv_tgt_desc *tmp = tgt;
-
-		tgt = lmv_locate_tgt_qos(lmv, op_data->op_mds,
-					 op_data->op_dir_depth);
-		if (tgt == ERR_PTR(-EAGAIN)) {
-			if (ltd_qos_is_balanced(&lmv->lmv_mdt_descs) &&
-			    !lmv_op_default_rr_mkdir(op_data) &&
-			    !lmv_op_user_qos_mkdir(op_data))
-				/* if it's not necessary, don't create remote
-				 * directory.
-				 */
-				tgt = tmp;
-			else
-				tgt = lmv_locate_tgt_rr(lmv);
-		}
+	} else if (lmv_op_default_qos_mkdir(op_data)) {
+		tgt = lmv_locate_tgt_by_space(lmv, op_data, tgt);
 		if (IS_ERR(tgt))
 			return PTR_ERR(tgt);
-
-		op_data->op_mds = tgt->ltd_index;
-		/*
-		 * only update statfs after QoS mkdir, this means the cached
-		 * statfs may be stale, and current mkdir may not follow QoS
-		 * accurately, but it's not serious, and avoids periodic statfs
-		 * when client doesn't mkdir by QoS.
-		 */
-		lmv_statfs_check_update(obd, tgt);
 	}
 
 retry: