Here is a fixed up version of the reorder feature of netem.
It is the same as the earlier patch plus with the bugfix from Julio merged in.
Has expected backwards compatibility behaviour.
Go ahead and merge this one, the TCP strangeness I was seeing was due
to the reordering bug, and previous version of TSO patch.
Signed-off-by: Stephen Hemminger <shemminger@osdl.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
TCA_NETEM_UNSPEC,
TCA_NETEM_CORR,
TCA_NETEM_DELAY_DIST,
TCA_NETEM_UNSPEC,
TCA_NETEM_CORR,
TCA_NETEM_DELAY_DIST,
__u32 latency; /* added delay (us) */
__u32 limit; /* fifo limit (packets) */
__u32 loss; /* random packet loss (0=none ~0=100%) */
__u32 latency; /* added delay (us) */
__u32 limit; /* fifo limit (packets) */
__u32 loss; /* random packet loss (0=none ~0=100%) */
- __u32 gap; /* re-ordering gap (0 for delay all) */
+ __u32 gap; /* re-ordering gap (0 for none) */
__u32 duplicate; /* random packet dup (0=none ~0=100%) */
__u32 jitter; /* random jitter in latency (us) */
};
__u32 duplicate; /* random packet dup (0=none ~0=100%) */
__u32 jitter; /* random jitter in latency (us) */
};
__u32 dup_corr; /* duplicate correlation */
};
__u32 dup_corr; /* duplicate correlation */
};
+struct tc_netem_reorder
+{
+ __u32 probability;
+ __u32 correlation;
+};
+
#define NETEM_DIST_SCALE 8192
#endif
#define NETEM_DIST_SCALE 8192
#endif
u32 gap;
u32 jitter;
u32 duplicate;
u32 gap;
u32 jitter;
u32 duplicate;
struct crndstate {
unsigned long last;
unsigned long rho;
struct crndstate {
unsigned long last;
unsigned long rho;
- } delay_cor, loss_cor, dup_cor;
+ } delay_cor, loss_cor, dup_cor, reorder_cor;
struct disttable {
u32 size;
struct disttable {
u32 size;
q->duplicate = dupsave;
}
q->duplicate = dupsave;
}
- /*
- * Do re-ordering by putting one out of N packets at the front
- * of the queue.
- * gap == 0 is special case for no-reordering.
- */
- if (q->gap == 0 || q->counter != q->gap) {
+ if (q->gap == 0 /* not doing reordering */
+ || q->counter < q->gap /* inside last reordering gap */
+ || q->reorder < get_crandom(&q->reorder_cor)) {
psched_time_t now;
PSCHED_GET_TIME(now);
psched_time_t now;
PSCHED_GET_TIME(now);
- PSCHED_TADD2(now,
- tabledist(q->latency, q->jitter, &q->delay_cor, q->delay_dist),
+ PSCHED_TADD2(now, tabledist(q->latency, q->jitter,
+ &q->delay_cor, q->delay_dist),
++q->counter;
ret = q->qdisc->enqueue(skb, q->qdisc);
} else {
++q->counter;
ret = q->qdisc->enqueue(skb, q->qdisc);
} else {
+ /*
+ * Do re-ordering by putting one out of N packets at the front
+ * of the queue.
+ */
PSCHED_GET_TIME(cb->time_to_send);
PSCHED_GET_TIME(cb->time_to_send);
ret = q->qdisc->ops->requeue(skb, q->qdisc);
}
ret = q->qdisc->ops->requeue(skb, q->qdisc);
}
+static int get_reorder(struct Qdisc *sch, const struct rtattr *attr)
+{
+ struct netem_sched_data *q = qdisc_priv(sch);
+ const struct tc_netem_reorder *r = RTA_DATA(attr);
+
+ if (RTA_PAYLOAD(attr) != sizeof(*r))
+ return -EINVAL;
+
+ q->reorder = r->probability;
+ init_crandom(&q->reorder_cor, r->correlation);
+ return 0;
+}
+
static int netem_change(struct Qdisc *sch, struct rtattr *opt)
{
struct netem_sched_data *q = qdisc_priv(sch);
static int netem_change(struct Qdisc *sch, struct rtattr *opt)
{
struct netem_sched_data *q = qdisc_priv(sch);
q->jitter = qopt->jitter;
q->limit = qopt->limit;
q->gap = qopt->gap;
q->jitter = qopt->jitter;
q->limit = qopt->limit;
q->gap = qopt->gap;
q->loss = qopt->loss;
q->duplicate = qopt->duplicate;
q->loss = qopt->loss;
q->duplicate = qopt->duplicate;
+ /* for compatiablity with earlier versions.
+ * if gap is set, need to assume 100% probablity
+ */
+ q->reorder = ~0;
+
/* Handle nested options after initial queue options.
* Should have put all options in nested format but too late now.
*/
/* Handle nested options after initial queue options.
* Should have put all options in nested format but too late now.
*/
+ if (tb[TCA_NETEM_REORDER-1]) {
+ ret = get_reorder(sch, tb[TCA_NETEM_REORDER-1]);
+ if (ret)
+ return ret;
+ }
init_timer(&q->timer);
q->timer.function = netem_watchdog;
q->timer.data = (unsigned long) sch;
init_timer(&q->timer);
q->timer.function = netem_watchdog;
q->timer.data = (unsigned long) sch;
q->qdisc = qdisc_create_dflt(sch->dev, &pfifo_qdisc_ops);
if (!q->qdisc) {
q->qdisc = qdisc_create_dflt(sch->dev, &pfifo_qdisc_ops);
if (!q->qdisc) {
struct rtattr *rta = (struct rtattr *) b;
struct tc_netem_qopt qopt;
struct tc_netem_corr cor;
struct rtattr *rta = (struct rtattr *) b;
struct tc_netem_qopt qopt;
struct tc_netem_corr cor;
+ struct tc_netem_reorder reorder;
qopt.latency = q->latency;
qopt.jitter = q->jitter;
qopt.latency = q->latency;
qopt.jitter = q->jitter;
cor.loss_corr = q->loss_cor.rho;
cor.dup_corr = q->dup_cor.rho;
RTA_PUT(skb, TCA_NETEM_CORR, sizeof(cor), &cor);
cor.loss_corr = q->loss_cor.rho;
cor.dup_corr = q->dup_cor.rho;
RTA_PUT(skb, TCA_NETEM_CORR, sizeof(cor), &cor);
+
+ reorder.probability = q->reorder;
+ reorder.correlation = q->reorder_cor.rho;
+ RTA_PUT(skb, TCA_NETEM_REORDER, sizeof(reorder), &reorder);
+
rta->rta_len = skb->tail - b;
return skb->len;
rta->rta_len = skb->tail - b;
return skb->len;