Re: [RFC] net_sched: mark packet staying on queue too long

[Eric Dumazet <eric.dumazet@gmail.com>]

Le mardi 04 janvier 2011 à 19:20 +0100, Eric Dumazet a écrit :

> diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
> index d54ac94..4f958e3 100644
> --- a/net/sched/sch_sfq.c
> +++ b/net/sched/sch_sfq.c
> @@ -24,6 +24,8 @@
>  #include <net/ip.h>
>  #include <net/netlink.h>
>  #include <net/pkt_sched.h>
> +#include <net/inet_ecn.h>
> +#include <linux/moduleparam.h>
>  
> 
>  /*	Stochastic Fairness Queuing algorithm.
> @@ -86,6 +88,10 @@
>  /* This type should contain at least SFQ_DEPTH + SFQ_SLOTS values */
>  typedef unsigned char sfq_index;
>  
> +static int red_delay; /* default : no RED handling */
> +module_param(red_delay, int, 0);
> +MODULE_PARM_DESC(red_delay, "mark/drop packets if they stay in queue longer than red_delay ticks");
> +
>  /*
>   * We dont use pointers to save space.
>   * Small indexes [0 ... SFQ_SLOTS - 1] are 'pointers' to slots[] array
> @@ -391,6 +397,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
>  
>  	sch->qstats.backlog += qdisc_pkt_len(skb);
>  	slot_queue_add(slot, skb);
> +	qdisc_skb_cb(skb)->timestamp = jiffies;
>  	sfq_inc(q, x);
>  	if (slot->qlen == 1) {		/* The flow is new */
>  		if (q->tail == NULL) {	/* It is the first flow */
> @@ -402,11 +409,8 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
>  		q->tail = slot;
>  		slot->allot = q->scaled_quantum;
>  	}
> -	if (++sch->q.qlen <= q->limit) {
> -		sch->bstats.bytes += qdisc_pkt_len(skb);
> -		sch->bstats.packets++;
> +	if (++sch->q.qlen <= q->limit)
>  		return NET_XMIT_SUCCESS;
> -	}
>  
>  	sfq_drop(sch);
>  	return NET_XMIT_CN;
> @@ -432,6 +436,7 @@ sfq_dequeue(struct Qdisc *sch)
>  	sfq_index a, next_a;
>  	struct sfq_slot *slot;
>  
> +restart:
>  	/* No active slots */
>  	if (q->tail == NULL)
>  		return NULL;
> @@ -455,12 +460,36 @@ next_slot:
>  		next_a = slot->next;
>  		if (a == next_a) {
>  			q->tail = NULL; /* no more active slots */
> +			/* last packet queued, dont even try to apply RED */

And of course I should do "goto end;" to properly do accounting,
or maybe do the RED thing after all ;)

>  			return skb;
>  		}
>  		q->tail->next = next_a;
>  	} else {
>  		slot->allot -= SFQ_ALLOT_SIZE(qdisc_pkt_len(skb));
>  	}
> +	if (red_delay) {
> +		long delay = jiffies - qdisc_skb_cb(skb)->timestamp;
> +
> +		if (delay >= red_delay) {
> +			long Px = delay * (0xFFFFFF / 100); /* 1 percent per jiffy */
> +			if ((net_random() & 0xFFFFFF) < Px) {
> +				if (INET_ECN_set_ce(skb)) {
> +					/* no ecnmark counter yet :) */
> +					sch->qstats.overlimits++;
> +				} else {
> +					/* penalize this flow : we drop the 
> +					 * packet while we changed slot->allot
> +					 */
> +					kfree_skb(skb);
> +					/* no early_drop counter yet :) */
> +					sch->qstats.drops++;
> +					goto restart;
> +				}
> +			}
> +		}
> +	}

end:

> +	sch->bstats.bytes += qdisc_pkt_len(skb);
> +	sch->bstats.packets++;
>  	return skb;
>  }
>  
>