Merge branch 'netem-slot-param' into iproute2-next

Yousuk Seung  says:

====================

This series adds support for the new "slot" netem parameter for
slotting. Slotting is an approximation of shared media that gather up
packets within a varying delay window before delivering them nearly at
once.

====================

Signed-off-by: David Ahern <dsahern@gmail.com>

include/utils.h

@@ -46,6 +46,11 @@ void incomplete_command(void) __attribute__((noreturn));
 #define NEXT_ARG_FWD() do { argv++; argc--; } while(0)
 #define PREV_ARG() do { argv--; argc++; } while(0)
 
+#define TIME_UNITS_PER_SEC	1000000
+#define NSEC_PER_USEC 1000
+#define NSEC_PER_MSEC 1000000
+#define NSEC_PER_SEC 1000000000LL
+
 typedef struct
 {
 	__u16 flags;
@@ -310,4 +315,11 @@ size_t strlcat(char *dst, const char *src, size_t size);
 
 void drop_cap(void);
 
+int get_time(unsigned int *time, const char *str);
+int get_time64(__s64 *time, const char *str);
+void print_time(char *buf, int len, __u32 time);
+void print_time64(char *buf, int len, __s64 time);
+char *sprint_time(__u32 time, char *buf);
+char *sprint_time64(__s64 time, char *buf);
+
 #endif /* __UTILS_H__ */

lib/utils.c

@@ -1633,3 +1633,104 @@ void drop_cap(void)
 	}
 #endif
 }
+
+int get_time(unsigned int *time, const char *str)
+{
+	double t;
+	char *p;
+
+	t = strtod(str, &p);
+	if (p == str)
+		return -1;
+
+	if (*p) {
+		if (strcasecmp(p, "s") == 0 || strcasecmp(p, "sec") == 0 ||
+		    strcasecmp(p, "secs") == 0)
+			t *= TIME_UNITS_PER_SEC;
+		else if (strcasecmp(p, "ms") == 0 || strcasecmp(p, "msec") == 0 ||
+			 strcasecmp(p, "msecs") == 0)
+			t *= TIME_UNITS_PER_SEC/1000;
+		else if (strcasecmp(p, "us") == 0 || strcasecmp(p, "usec") == 0 ||
+			 strcasecmp(p, "usecs") == 0)
+			t *= TIME_UNITS_PER_SEC/1000000;
+		else
+			return -1;
+	}
+
+	*time = t;
+	return 0;
+}
+
+
+void print_time(char *buf, int len, __u32 time)
+{
+	double tmp = time;
+
+	if (tmp >= TIME_UNITS_PER_SEC)
+		snprintf(buf, len, "%.1fs", tmp/TIME_UNITS_PER_SEC);
+	else if (tmp >= TIME_UNITS_PER_SEC/1000)
+		snprintf(buf, len, "%.1fms", tmp/(TIME_UNITS_PER_SEC/1000));
+	else
+		snprintf(buf, len, "%uus", time);
+}
+
+char *sprint_time(__u32 time, char *buf)
+{
+	print_time(buf, SPRINT_BSIZE-1, time);
+	return buf;
+}
+
+/* 64 bit times are represented internally in nanoseconds */
+int get_time64(__s64 *time, const char *str)
+{
+	double nsec;
+	char *p;
+
+	nsec = strtod(str, &p);
+	if (p == str)
+		return -1;
+
+	if (*p) {
+		if (strcasecmp(p, "s") == 0 ||
+		    strcasecmp(p, "sec") == 0 ||
+		    strcasecmp(p, "secs") == 0)
+			nsec *= NSEC_PER_SEC;
+		else if (strcasecmp(p, "ms") == 0 ||
+			 strcasecmp(p, "msec") == 0 ||
+			 strcasecmp(p, "msecs") == 0)
+			nsec *= NSEC_PER_MSEC;
+		else if (strcasecmp(p, "us") == 0 ||
+			 strcasecmp(p, "usec") == 0 ||
+			 strcasecmp(p, "usecs") == 0)
+			nsec *= NSEC_PER_USEC;
+		else if (strcasecmp(p, "ns") == 0 ||
+			 strcasecmp(p, "nsec") == 0 ||
+			 strcasecmp(p, "nsecs") == 0)
+			nsec *= 1;
+		else
+			return -1;
+	}
+
+	*time = nsec;
+	return 0;
+}
+
+void print_time64(char *buf, int len, __s64 time)
+{
+	double nsec = time;
+
+	if (time >= NSEC_PER_SEC)
+		snprintf(buf, len, "%.3fs", nsec/NSEC_PER_SEC);
+	else if (time >= NSEC_PER_MSEC)
+		snprintf(buf, len, "%.3fms", nsec/NSEC_PER_MSEC);
+	else if (time >= NSEC_PER_USEC)
+		snprintf(buf, len, "%.3fus", nsec/NSEC_PER_USEC);
+	else
+		snprintf(buf, len, "%lldns", time);
+}
+
+char *sprint_time64(__s64 time, char *buf)
+{
+	print_time64(buf, SPRINT_BSIZE-1, time);
+	return buf;
+}

man/man8/tc-netem.8

@@ -8,7 +8,8 @@ NetEm \- Network Emulator
 .I OPTIONS
 
 .IR OPTIONS " := [ " LIMIT " ] [ " DELAY " ] [ " LOSS \
-" ] [ " CORRUPT " ] [ " DUPLICATION " ] [ " REORDERING " ][ " RATE " ]"
+" ] [ " CORRUPT " ] [ " DUPLICATION " ] [ " REORDERING " ] [ " RATE \
+" ] [ " SLOT " ]"
 
 .IR LIMIT " := "
 .B limit
@@ -51,6 +52,18 @@ NetEm \- Network Emulator
 .B rate
 .IR RATE " [ " PACKETOVERHEAD " [ " CELLSIZE " [ " CELLOVERHEAD " ]]]]"
 
+.IR SLOT " := "
+.BR slot " { "
+.IR MIN_DELAY " [ " MAX_DELAY " ] |"
+.br
+.RB "               " distribution " { "uniform " | " normal " | " pareto " | " paretonormal " | "
+.IR FILE " } " DELAY " " JITTER " } "
+.br
+.RB "             [ " packets
+.IR PACKETS " ] [ "
+.BR bytes
+.IR BYTES " ]"
+
 
 .SH DESCRIPTION
 NetEm is an enhancement of the Linux traffic control facilities
@@ -162,6 +175,31 @@ granularity avoid a perfect shaping at a specific level. This will show up in
 an artificial packet compression (bursts). Another influence factor are network
 adapter buffers which can also add artificial delay.
 
+.SS slot
+defer delivering accumulated packets to within a slot. Each available slot can be
+configured with a minimum delay to acquire, and an optional maximum delay.
+Alternatively it can be configured with the distribution similar to
+.BR distribution
+for
+.BR delay
+option. Slot delays can be specified in nanoseconds, microseconds, milliseconds or seconds
+(e.g. 800us). Values for the optional parameters
+.I BYTES
+will limit the number of bytes delivered per slot, and/or
+.I PACKETS
+will limit the number of packets delivered per slot.
+
+These slot options can provide a crude approximation of bursty MACs such as
+DOCSIS, WiFi, and LTE.
+
+Note that slotting is limited by several factors: the kernel clock granularity,
+as with a rate, and attempts to deliver many packets within a slot will be
+smeared by the timer resolution, and by the underlying native bandwidth also.
+
+It is possible to combine slotting with a rate, in which case complex behaviors
+where either the rate, or the slot limits on bytes or packets per slot, govern
+the actual delivered rate.
+
 .SH LIMITATIONS
 The main known limitation of Netem are related to timer granularity, since
 Linux is not a real-time operating system.

tc/q_netem.c

@@ -40,7 +40,12 @@ static void explain(void)
 "                 [ loss gemodel PERCENT [R [1-H [1-K]]]\n" \
 "                 [ ecn ]\n" \
 "                 [ reorder PRECENT [CORRELATION] [ gap DISTANCE ]]\n" \
-"                 [ rate RATE [PACKETOVERHEAD] [CELLSIZE] [CELLOVERHEAD]]\n");
+"                 [ rate RATE [PACKETOVERHEAD] [CELLSIZE] [CELLOVERHEAD]]\n" \
+"                 [ slot MIN_DELAY [MAX_DELAY] [packets MAX_PACKETS]" \
+" [bytes MAX_BYTES]]\n" \
+"                 [ slot distribution" \
+" {uniform|normal|pareto|paretonormal|custom} DELAY JITTER" \
+" [packets MAX_PACKETS] [bytes MAX_BYTES]]\n");
 }
 
 static void explain1(const char *arg)
@@ -156,6 +161,7 @@ static int netem_parse_opt(struct qdisc_util *qu, int argc, char **argv,
 			   struct nlmsghdr *n, const char *dev)
 {
 	int dist_size = 0;
+	int slot_dist_size = 0;
 	struct rtattr *tail;
 	struct tc_netem_qopt opt = { .limit = 1000 };
 	struct tc_netem_corr cor = {};
@@ -164,7 +170,9 @@ static int netem_parse_opt(struct qdisc_util *qu, int argc, char **argv,
 	struct tc_netem_gimodel gimodel;
 	struct tc_netem_gemodel gemodel;
 	struct tc_netem_rate rate = {};
+	struct tc_netem_slot slot = {};
 	__s16 *dist_data = NULL;
+	__s16 *slot_dist_data = NULL;
 	__u16 loss_type = NETEM_LOSS_UNSPEC;
 	int present[__TCA_NETEM_MAX] = {};
 	__u64 rate64 = 0;
@@ -412,6 +420,79 @@ static int netem_parse_opt(struct qdisc_util *qu, int argc, char **argv,
 					return -1;
 				}
 			}
+		} else if (matches(*argv, "slot") == 0) {
+			if (NEXT_IS_NUMBER()) {
+				NEXT_ARG();
+				present[TCA_NETEM_SLOT] = 1;
+				if (get_time64(&slot.min_delay, *argv)) {
+					explain1("slot min_delay");
+					return -1;
+				}
+				if (NEXT_IS_NUMBER()) {
+					NEXT_ARG();
+					if (get_time64(&slot.max_delay, *argv) ||
+					    slot.max_delay < slot.min_delay) {
+						explain1("slot max_delay");
+						return -1;
+					}
+				} else {
+					slot.max_delay = slot.min_delay;
+				}
+			} else {
+				NEXT_ARG();
+				if (strcmp(*argv, "distribution") == 0) {
+					present[TCA_NETEM_SLOT] = 1;
+					NEXT_ARG();
+					slot_dist_data = calloc(sizeof(slot_dist_data[0]), MAX_DIST);
+					if (!slot_dist_data)
+						return -1;
+					slot_dist_size = get_distribution(*argv, slot_dist_data, MAX_DIST);
+					if (slot_dist_size <= 0) {
+						free(slot_dist_data);
+						return -1;
+					}
+					NEXT_ARG();
+					if (get_time64(&slot.dist_delay, *argv)) {
+						explain1("slot delay");
+						return -1;
+					}
+					NEXT_ARG();
+					if (get_time64(&slot.dist_jitter, *argv)) {
+						explain1("slot jitter");
+						return -1;
+					}
+					if (slot.dist_jitter <= 0) {
+						fprintf(stderr, "Non-positive jitter\n");
+						return -1;
+					}
+				} else {
+					fprintf(stderr, "Unknown slot parameter: %s\n",
+						*argv);
+					return -1;
+				}
+			}
+			if (NEXT_ARG_OK() &&
+			    matches(*(argv+1), "packets") == 0) {
+				NEXT_ARG();
+				if (!NEXT_ARG_OK() ||
+				    get_s32(&slot.max_packets, *(argv+1), 0)) {
+					explain1("slot packets");
+					return -1;
+				}
+				NEXT_ARG();
+			}
+			if (NEXT_ARG_OK() &&
+			    matches(*(argv+1), "bytes") == 0) {
+				unsigned int max_bytes;
+				NEXT_ARG();
+				if (!NEXT_ARG_OK() ||
+				    get_size(&max_bytes, *(argv+1))) {
+					explain1("slot bytes");
+					return -1;
+				}
+				slot.max_bytes = (int) max_bytes;
+				NEXT_ARG();
+			}
 		} else if (strcmp(*argv, "help") == 0) {
 			explain();
 			return -1;
@@ -472,6 +553,10 @@ static int netem_parse_opt(struct qdisc_util *qu, int argc, char **argv,
 	    addattr_l(n, 1024, TCA_NETEM_CORRUPT, &corrupt, sizeof(corrupt)) < 0)
 		return -1;
 
+	if (present[TCA_NETEM_SLOT] &&
+	    addattr_l(n, 1024, TCA_NETEM_SLOT, &slot, sizeof(slot)) < 0)
+		return -1;
+
 	if (loss_type != NETEM_LOSS_UNSPEC) {
 		struct rtattr *start;
 
@@ -512,6 +597,14 @@ static int netem_parse_opt(struct qdisc_util *qu, int argc, char **argv,
 			return -1;
 		free(dist_data);
 	}
+
+	if (slot_dist_data) {
+		if (addattr_l(n, MAX_DIST * sizeof(slot_dist_data[0]),
+			      TCA_NETEM_SLOT_DIST,
+			      slot_dist_data, slot_dist_size * sizeof(slot_dist_data[0])) < 0)
+			return -1;
+		free(slot_dist_data);
+	}
 	tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
 	return 0;
 }
@@ -526,6 +619,7 @@ static int netem_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
 	int *ecn = NULL;
 	struct tc_netem_qopt qopt;
 	const struct tc_netem_rate *rate = NULL;
+	const struct tc_netem_slot *slot = NULL;
 	int len;
 	__u64 rate64 = 0;
 
@@ -586,6 +680,11 @@ static int netem_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
 				return -1;
 			rate64 = rta_getattr_u64(tb[TCA_NETEM_RATE64]);
 		}
+		if (tb[TCA_NETEM_SLOT]) {
+			if (RTA_PAYLOAD(tb[TCA_NETEM_SLOT]) < sizeof(*slot))
+				return -1;
+			slot = RTA_DATA(tb[TCA_NETEM_SLOT]);
+		}
 	}
 
 	fprintf(f, "limit %d", qopt.limit);
@@ -659,6 +758,20 @@ static int netem_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
 			fprintf(f, " celloverhead %d", rate->cell_overhead);
 	}
 
+	if (slot) {
+		if (slot->dist_jitter > 0) {
+		    fprintf(f, " slot distribution %s", sprint_time64(slot->dist_delay, b1));
+		    fprintf(f, " %s", sprint_time64(slot->dist_jitter, b1));
+		} else {
+		    fprintf(f, " slot %s", sprint_time64(slot->min_delay, b1));
+		    fprintf(f, " %s", sprint_time64(slot->max_delay, b1));
+		}
+		if (slot->max_packets)
+			fprintf(f, " packets %d", slot->max_packets);
+		if (slot->max_bytes)
+			fprintf(f, " bytes %d", slot->max_bytes);
+	}
+
 	if (ecn)
 		fprintf(f, " ecn ");
 

tc/tc_cbq.c

@@ -20,6 +20,7 @@
 #include <arpa/inet.h>
 #include <string.h>
 
+#include "utils.h"
 #include "tc_core.h"
 #include "tc_cbq.h"
 

tc/tc_core.c

@@ -21,6 +21,7 @@
 #include <arpa/inet.h>
 #include <string.h>
 
+#include "utils.h"
 #include "tc_core.h"
 #include <linux/atm.h>
 

tc/tc_core.h

@@ -5,8 +5,6 @@
 #include <asm/types.h>
 #include <linux/pkt_sched.h>
 
-#define TIME_UNITS_PER_SEC	1000000
-
 enum link_layer {
 	LINKLAYER_UNSPEC,
 	LINKLAYER_ETHERNET,

tc/tc_estimator.c

@@ -20,6 +20,7 @@
 #include <arpa/inet.h>
 #include <string.h>
 
+#include "utils.h"
 #include "tc_core.h"
 
 int tc_setup_estimator(unsigned int A, unsigned int time_const, struct tc_estimator *est)

tc/tc_util.c

@@ -334,52 +334,6 @@ char *sprint_rate(__u64 rate, char *buf)
 	return buf;
 }
 
-int get_time(unsigned int *time, const char *str)
-{
-	double t;
-	char *p;
-
-	t = strtod(str, &p);
-	if (p == str)
-		return -1;
-
-	if (*p) {
-		if (strcasecmp(p, "s") == 0 || strcasecmp(p, "sec") == 0 ||
-		    strcasecmp(p, "secs") == 0)
-			t *= TIME_UNITS_PER_SEC;
-		else if (strcasecmp(p, "ms") == 0 || strcasecmp(p, "msec") == 0 ||
-			 strcasecmp(p, "msecs") == 0)
-			t *= TIME_UNITS_PER_SEC/1000;
-		else if (strcasecmp(p, "us") == 0 || strcasecmp(p, "usec") == 0 ||
-			 strcasecmp(p, "usecs") == 0)
-			t *= TIME_UNITS_PER_SEC/1000000;
-		else
-			return -1;
-	}
-
-	*time = t;
-	return 0;
-}
-
-
-void print_time(char *buf, int len, __u32 time)
-{
-	double tmp = time;
-
-	if (tmp >= TIME_UNITS_PER_SEC)
-		snprintf(buf, len, "%.1fs", tmp/TIME_UNITS_PER_SEC);
-	else if (tmp >= TIME_UNITS_PER_SEC/1000)
-		snprintf(buf, len, "%.1fms", tmp/(TIME_UNITS_PER_SEC/1000));
-	else
-		snprintf(buf, len, "%uus", time);
-}
-
-char *sprint_time(__u32 time, char *buf)
-{
-	print_time(buf, SPRINT_BSIZE-1, time);
-	return buf;
-}
-
 char *sprint_ticks(__u32 ticks, char *buf)
 {
 	return sprint_time(tc_core_tick2time(ticks), buf);

tc/tc_util.h

@@ -81,13 +81,11 @@ int get_rate64(__u64 *rate, const char *str);
 int get_percent_rate64(__u64 *rate, const char *str, const char *dev);
 int get_size(unsigned int *size, const char *str);
 int get_size_and_cell(unsigned int *size, int *cell_log, char *str);
-int get_time(unsigned int *time, const char *str);
 int get_linklayer(unsigned int *val, const char *arg);
 
 void print_rate(char *buf, int len, __u64 rate);
 void print_size(char *buf, int len, __u32 size);
 void print_qdisc_handle(char *buf, int len, __u32 h);
-void print_time(char *buf, int len, __u32 time);
 void print_linklayer(char *buf, int len, unsigned int linklayer);
 void print_devname(enum output_type type, int ifindex);
 
@@ -95,7 +93,6 @@ char *sprint_rate(__u64 rate, char *buf);
 char *sprint_size(__u32 size, char *buf);
 char *sprint_qdisc_handle(__u32 h, char *buf);
 char *sprint_tc_classid(__u32 h, char *buf);
-char *sprint_time(__u32 time, char *buf);
 char *sprint_ticks(__u32 ticks, char *buf);
 char *sprint_linklayer(unsigned int linklayer, char *buf);