netem: support delivering packets in delayed time slots

Slotting is a crude approximation of the behaviors of shared media such
as cable, wifi, and LTE, which gather up a bunch of packets within a
varying delay window and deliver them, relative to that, nearly all at
once.

It works within the existing loss, duplication, jitter and delay
parameters of netem. Some amount of inherent latency must be specified,
regardless.

The new "slot" parameter specifies a minimum and maximum delay between
transmission attempts.

The "bytes" and "packets" parameters can be used to limit the amount of
information transferred per slot.

Examples of use:

tc qdisc add dev eth0 root netem delay 200us \
         slot 800us 10ms bytes 64k packets 42

A more correct example, using stacked netem instances and a packet limit
to emulate a tail drop wifi queue with slots and variable packet
delivery, with a 200Mbit isochronous underlying rate, and 20ms path
delay:

tc qdisc add dev eth0 root handle 1: netem delay 20ms rate 200mbit \
         limit 10000
tc qdisc add dev eth0 parent 1:1 handle 10:1 netem delay 200us \
         slot 800us 10ms bytes 64k packets 42 limit 512

Signed-off-by: Dave Taht <dave.taht@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 8fe6d1842bee5c74b74e84e2bf36f3ccfb8bfc49..af3cc2f4e1ad00dff0e011a4e94e0905d085d0ca 100644 (file)
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -539,6 +539,7 @@ enum {
        TCA_NETEM_PAD,
        TCA_NETEM_LATENCY64,
        TCA_NETEM_JITTER64,
+       TCA_NETEM_SLOT,
        __TCA_NETEM_MAX,
 };
 
@@ -576,6 +577,13 @@ struct tc_netem_rate {
        __s32   cell_overhead;
 };
 
+struct tc_netem_slot {
+       __s64   min_delay; /* nsec */
+       __s64   max_delay;
+       __s32   max_packets;
+       __s32   max_bytes;
+};
+
 enum {
        NETEM_LOSS_UNSPEC,
        NETEM_LOSS_GI,          /* General Intuitive - 4 state model */

diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 47d6decba0ea66294ef0b946706cbd75a63ced38..b686e755fda996093e3b47daad53aab4b0f54e03 100644 (file)
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -135,6 +135,13 @@ struct netem_sched_data {
                u32 a5; /* p23 used only in 4-states */
        } clg;
 
+       struct tc_netem_slot slot_config;
+       struct slotstate {
+               u64 slot_next;
+               s32 packets_left;
+               s32 bytes_left;
+       } slot;
+
 };
 
 /* Time stamp put into socket buffer control block
@@ -591,6 +598,20 @@ finish_segs:
        return NET_XMIT_SUCCESS;
 }
 
+/* Delay the next round with a new future slot with a
+ * correct number of bytes and packets.
+ */
+
+static void get_slot_next(struct netem_sched_data *q, u64 now)
+{
+       q->slot.slot_next = now + q->slot_config.min_delay +
+               (prandom_u32() *
+                       (q->slot_config.max_delay -
+                               q->slot_config.min_delay) >> 32);
+       q->slot.packets_left = q->slot_config.max_packets;
+       q->slot.bytes_left = q->slot_config.max_bytes;
+}
+
 static struct sk_buff *netem_dequeue(struct Qdisc *sch)
 {
        struct netem_sched_data *q = qdisc_priv(sch);
@@ -608,14 +629,17 @@ deliver:
        p = rb_first(&q->t_root);
        if (p) {
                u64 time_to_send;
+               u64 now = ktime_get_ns();
 
                skb = rb_to_skb(p);
 
                /* if more time remaining? */
                time_to_send = netem_skb_cb(skb)->time_to_send;
-               if (time_to_send <= ktime_get_ns()) {
-                       rb_erase(p, &q->t_root);
+               if (q->slot.slot_next && q->slot.slot_next < time_to_send)
+                       get_slot_next(q, now);
 
+               if (time_to_send <= now &&  q->slot.slot_next <= now) {
+                       rb_erase(p, &q->t_root);
                        sch->q.qlen--;
                        qdisc_qstats_backlog_dec(sch, skb);
                        skb->next = NULL;
@@ -634,6 +658,14 @@ deliver:
                                skb->tstamp = 0;
 #endif
 
+                       if (q->slot.slot_next) {
+                               q->slot.packets_left--;
+                               q->slot.bytes_left -= qdisc_pkt_len(skb);
+                               if (q->slot.packets_left <= 0 ||
+                                   q->slot.bytes_left <= 0)
+                                       get_slot_next(q, now);
+                       }
+
                        if (q->qdisc) {
                                unsigned int pkt_len = qdisc_pkt_len(skb);
                                struct sk_buff *to_free = NULL;
@@ -657,7 +689,10 @@ deliver:
                        if (skb)
                                goto deliver;
                }
-               qdisc_watchdog_schedule_ns(&q->watchdog, time_to_send);
+
+               qdisc_watchdog_schedule_ns(&q->watchdog,
+                                          max(time_to_send,
+                                              q->slot.slot_next));
        }
 
        if (q->qdisc) {
@@ -688,6 +723,7 @@ static void dist_free(struct disttable *d)
  * Distribution data is a variable size payload containing
  * signed 16 bit values.
  */
+
 static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr)
 {
        struct netem_sched_data *q = qdisc_priv(sch);
@@ -718,6 +754,23 @@ static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr)
        return 0;
 }
 
+static void get_slot(struct netem_sched_data *q, const struct nlattr *attr)
+{
+       const struct tc_netem_slot *c = nla_data(attr);
+
+       q->slot_config = *c;
+       if (q->slot_config.max_packets == 0)
+               q->slot_config.max_packets = INT_MAX;
+       if (q->slot_config.max_bytes == 0)
+               q->slot_config.max_bytes = INT_MAX;
+       q->slot.packets_left = q->slot_config.max_packets;
+       q->slot.bytes_left = q->slot_config.max_bytes;
+       if (q->slot_config.min_delay | q->slot_config.max_delay)
+               q->slot.slot_next = ktime_get_ns();
+       else
+               q->slot.slot_next = 0;
+}
+
 static void get_correlation(struct netem_sched_data *q, const struct nlattr *attr)
 {
        const struct tc_netem_corr *c = nla_data(attr);
@@ -821,6 +874,7 @@ static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = {
        [TCA_NETEM_RATE64]      = { .type = NLA_U64 },
        [TCA_NETEM_LATENCY64]   = { .type = NLA_S64 },
        [TCA_NETEM_JITTER64]    = { .type = NLA_S64 },
+       [TCA_NETEM_SLOT]        = { .len = sizeof(struct tc_netem_slot) },
 };
 
 static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla,
@@ -927,6 +981,9 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt)
        if (tb[TCA_NETEM_ECN])
                q->ecn = nla_get_u32(tb[TCA_NETEM_ECN]);
 
+       if (tb[TCA_NETEM_SLOT])
+               get_slot(q, tb[TCA_NETEM_SLOT]);
+
        return ret;
 }
 
@@ -1016,6 +1073,7 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb)
        struct tc_netem_reorder reorder;
        struct tc_netem_corrupt corrupt;
        struct tc_netem_rate rate;
+       struct tc_netem_slot slot;
 
        qopt.latency = min_t(psched_tdiff_t, PSCHED_NS2TICKS(q->latency),
                             UINT_MAX);
@@ -1070,6 +1128,16 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb)
        if (dump_loss_model(q, skb) != 0)
                goto nla_put_failure;
 
+       if (q->slot_config.min_delay | q->slot_config.max_delay) {
+               slot = q->slot_config;
+               if (slot.max_packets == INT_MAX)
+                       slot.max_packets = 0;
+               if (slot.max_bytes == INT_MAX)
+                       slot.max_bytes = 0;
+               if (nla_put(skb, TCA_NETEM_SLOT, sizeof(slot), &slot))
+                       goto nla_put_failure;
+       }
+
        return nla_nest_end(skb, nla);
 
 nla_put_failure: