staging: lustre: LNet network latency simulation

Incoming lnet message can be delayed for seconds if it can match
any of LNet Delay Rules.

User can add/remove/list Delay Rule by lctl commands:
- lctl net_delay_add
  Add a new Delay Rule to LNet, options
  <-s | --source SRC_NID>
  <-d | --dest DST_NID>
  <<-r | --rate RATE_NUMBER>
  <-i | --interlval SECONDS>>
  <-l | --latency DELAY_LATENCY>

- lctl net_delay_del
  Remove matched Delay Rule from LNet, options:
  <[-a | --all] |
  <-s | --source SRC_NID>
  <-d | --dest DST_NID>>

- lctl net_delay_list
  List all Delay Rules in LNet

- lctl net_delay_reset
  Reset statistic counters for all Delay Rules

Signed-off-by: Liang Zhen <liang.zhen@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5435
Reviewed-on: http://review.whamcloud.com/11409
Reviewed-by: Amir Shehata <amir.shehata@intel.com>
Reviewed-by: Bobi Jam <bobijam@gmail.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

3 files changed, 39 insertions, 2 deletions

diff --git a/drivers/staging/lustre/include/linux/lnet/lib-lnet.h b/drivers/staging/lustre/include/linux/lnet/lib-lnet.h
index 7b3f858..dfc0208 100644
--- a/drivers/staging/lustre/include/linux/lnet/lib-lnet.h
+++ b/drivers/staging/lustre/include/linux/lnet/lib-lnet.h
@@ -559,13 +559,22 @@ void lnet_portals_destroy(void);
 /* message functions */
 int lnet_parse(lnet_ni_t *ni, lnet_hdr_t *hdr,
 	       lnet_nid_t fromnid, void *private, int rdma_req);
+int lnet_parse_local(lnet_ni_t *ni, lnet_msg_t *msg);
+int lnet_parse_forward_locked(lnet_ni_t *ni, lnet_msg_t *msg);
+
 void lnet_recv(lnet_ni_t *ni, void *private, lnet_msg_t *msg, int delayed,
 	       unsigned int offset, unsigned int mlen, unsigned int rlen);
+void lnet_ni_recv(lnet_ni_t *ni, void *private, lnet_msg_t *msg,
+		  int delayed, unsigned int offset,
+		  unsigned int mlen, unsigned int rlen);
+
 lnet_msg_t *lnet_create_reply_msg(lnet_ni_t *ni, lnet_msg_t *get_msg);
 void lnet_set_reply_msg_len(lnet_ni_t *ni, lnet_msg_t *msg, unsigned int len);
 
 void lnet_finalize(lnet_ni_t *ni, lnet_msg_t *msg, int rc);
 
+void lnet_drop_message(lnet_ni_t *ni, int cpt, void *private,
+		       unsigned int nob);
 void lnet_drop_delayed_msg_list(struct list_head *head, char *reason);
 void lnet_recv_delayed_msg_list(struct list_head *head);
 
@@ -586,6 +595,14 @@ void lnet_fault_fini(void);
 
 bool lnet_drop_rule_match(lnet_hdr_t *hdr);
 
+int lnet_delay_rule_add(struct lnet_fault_attr *attr);
+int lnet_delay_rule_del(lnet_nid_t src, lnet_nid_t dst, bool shutdown);
+int lnet_delay_rule_list(int pos, struct lnet_fault_attr *attr,
+			 struct lnet_fault_stat *stat);
+void lnet_delay_rule_reset(void);
+void lnet_delay_rule_check(void);
+bool lnet_delay_rule_match_locked(lnet_hdr_t *hdr, struct lnet_msg *msg);
+
 /** @} lnet_fault_simulation */
 
 void lnet_counters_get(lnet_counters_t *counters);
diff --git a/drivers/staging/lustre/include/linux/lnet/lib-types.h b/drivers/staging/lustre/include/linux/lnet/lib-types.h
index cb09a8a..29c72f8 100644
--- a/drivers/staging/lustre/include/linux/lnet/lib-types.h
+++ b/drivers/staging/lustre/include/linux/lnet/lib-types.h
@@ -88,6 +88,7 @@ typedef struct lnet_msg {
 	unsigned int	msg_rtrcredit:1;	/* taken a global router credit */
 	unsigned int	msg_peerrtrcredit:1;	/* taken a peer router credit */
 	unsigned int	msg_onactivelist:1;	/* on the activelist */
+	unsigned int	msg_rdma_get:1;
 
 	struct lnet_peer	*msg_txpeer;	 /* peer I'm sending to */
 	struct lnet_peer	*msg_rxpeer;	 /* peer I received from */
@@ -574,6 +575,7 @@ typedef struct {
 	/* failure simulation */
 	struct list_head		  ln_test_peers;
 	struct list_head		  ln_drop_rules;
+	struct list_head		  ln_delay_rules;
 
 	struct list_head		  ln_nis;	/* LND instances */
 	/* NIs bond on specific CPT(s) */
@@ -610,6 +612,7 @@ typedef struct {
 
 	struct mutex			  ln_api_mutex;
 	struct mutex			  ln_lnd_mutex;
+	struct mutex			  ln_delay_mutex;
 	/* Have I called LNetNIInit myself? */
 	int				  ln_niinit_self;
 	/* LNetNIInit/LNetNIFini counter */
diff --git a/drivers/staging/lustre/include/linux/lnet/lnetctl.h b/drivers/staging/lustre/include/linux/lnet/lnetctl.h
index ec33bf8..3957507 100644
--- a/drivers/staging/lustre/include/linux/lnet/lnetctl.h
+++ b/drivers/staging/lustre/include/linux/lnet/lnetctl.h
@@ -26,6 +26,10 @@ enum {
 	LNET_CTL_DROP_DEL,
 	LNET_CTL_DROP_RESET,
 	LNET_CTL_DROP_LIST,
+	LNET_CTL_DELAY_ADD,
+	LNET_CTL_DELAY_DEL,
+	LNET_CTL_DELAY_RESET,
+	LNET_CTL_DELAY_LIST,
 };
 
 #define LNET_ACK_BIT		BIT(0)
@@ -71,7 +75,17 @@ struct lnet_fault_attr {
 			 */
 			__u32			da_interval;
 		} drop;
-		/** TODO: add more */
+		/** message latency simulation */
+		struct {
+			__u32			la_rate;
+			/**
+			 * time interval of message delay, it is exclusive
+			 * with la_rate
+			 */
+			__u32			la_interval;
+			/** latency to delay */
+			__u32			la_latency;
+		} delay;
 		__u64			space[8];
 	} u;
 };
@@ -93,7 +107,10 @@ struct lnet_fault_stat {
 			/** total # dropped messages */
 			__u64			ds_dropped;
 		} drop;
-		/** TODO: add more */
+		struct {
+			/** total # delayed messages */
+			__u64			ls_delayed;
+		} delay;
 		__u64			space[8];
 	} u;
 };