This is followup to Patrick's patch. A little optimization to enqueue
routine allows to remove artificial limitation on queue length.
Plus, testing showed that hash function used by SFQ is too bad or even worse.
It does not even sweep the whole range of hash values.
Switched to Jenkins' hash.
Signed-off-by: Alexey Kuznetsov <kaber@ms2.inr.ac.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
#include <linux/init.h>
#include <linux/ipv6.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/ipv6.h>
#include <linux/skbuff.h>
+#include <linux/jhash.h>
#include <net/ip.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/ip.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
/* Variables */
struct timer_list perturb_timer;
/* Variables */
struct timer_list perturb_timer;
sfq_index tail; /* Index of current slot in round */
sfq_index max_depth; /* Maximal depth */
sfq_index tail; /* Index of current slot in round */
sfq_index max_depth; /* Maximal depth */
static __inline__ unsigned sfq_fold_hash(struct sfq_sched_data *q, u32 h, u32 h1)
{
static __inline__ unsigned sfq_fold_hash(struct sfq_sched_data *q, u32 h, u32 h1)
{
- int pert = q->perturbation;
-
- /* Have we any rotation primitives? If not, WHY? */
- h ^= (h1<<pert) ^ (h1>>(0x1F - pert));
- h ^= h>>10;
- return h & 0x3FF;
+ return jhash_2words(h, h1, q->perturbation) & (SFQ_HASH_DIVISOR - 1);
}
static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb)
}
static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb)
q->ht[hash] = x = q->dep[SFQ_DEPTH].next;
q->hash[x] = hash;
}
q->ht[hash] = x = q->dep[SFQ_DEPTH].next;
q->hash[x] = hash;
}
+ /* If selected queue has length q->limit, this means that
+ * all another queues are empty and that we do simple tail drop,
+ * i.e. drop _this_ packet.
+ */
+ if (q->qs[x].qlen >= q->limit)
+ return qdisc_drop(skb, sch);
+
sch->qstats.backlog += skb->len;
__skb_queue_tail(&q->qs[x], skb);
sfq_inc(q, x);
sch->qstats.backlog += skb->len;
__skb_queue_tail(&q->qs[x], skb);
sfq_inc(q, x);
}
sch->qstats.backlog += skb->len;
__skb_queue_head(&q->qs[x], skb);
}
sch->qstats.backlog += skb->len;
__skb_queue_head(&q->qs[x], skb);
+ /* If selected queue has length q->limit+1, this means that
+ * all another queues are empty and we do simple tail drop.
+ * This packet is still requeued at head of queue, tail packet
+ * is dropped.
+ */
+ if (q->qs[x].qlen > q->limit) {
+ skb = q->qs[x].prev;
+ __skb_unlink(skb, &q->qs[x]);
+ sch->qstats.drops++;
+ sch->qstats.backlog -= skb->len;
+ kfree_skb(skb);
+ return NET_XMIT_CN;
+ }
sfq_inc(q, x);
if (q->qs[x].qlen == 1) { /* The flow is new */
if (q->tail == SFQ_DEPTH) { /* It is the first flow */
sfq_inc(q, x);
if (q->qs[x].qlen == 1) { /* The flow is new */
if (q->tail == SFQ_DEPTH) { /* It is the first flow */
struct Qdisc *sch = (struct Qdisc*)arg;
struct sfq_sched_data *q = qdisc_priv(sch);
struct Qdisc *sch = (struct Qdisc*)arg;
struct sfq_sched_data *q = qdisc_priv(sch);
- q->perturbation = net_random()&0x1F;
+ get_random_bytes(&q->perturbation, 4);
- if (q->perturb_period) {
- q->perturb_timer.expires = jiffies + q->perturb_period;
- add_timer(&q->perturb_timer);
- }
+ if (q->perturb_period)
+ mod_timer(&q->perturb_timer, jiffies + q->perturb_period);
}
static int sfq_change(struct Qdisc *sch, struct rtattr *opt)
}
static int sfq_change(struct Qdisc *sch, struct rtattr *opt)
q->quantum = ctl->quantum ? : psched_mtu(sch->dev);
q->perturb_period = ctl->perturb_period*HZ;
if (ctl->limit)
q->quantum = ctl->quantum ? : psched_mtu(sch->dev);
q->perturb_period = ctl->perturb_period*HZ;
if (ctl->limit)
- q->limit = min_t(u32, ctl->limit, SFQ_DEPTH - 2);
+ q->limit = min_t(u32, ctl->limit, SFQ_DEPTH - 1);
qlen = sch->q.qlen;
while (sch->q.qlen > q->limit)
qlen = sch->q.qlen;
while (sch->q.qlen > q->limit)
del_timer(&q->perturb_timer);
if (q->perturb_period) {
del_timer(&q->perturb_timer);
if (q->perturb_period) {
- q->perturb_timer.expires = jiffies + q->perturb_period;
- add_timer(&q->perturb_timer);
+ mod_timer(&q->perturb_timer, jiffies + q->perturb_period);
+ get_random_bytes(&q->perturbation, 4);
}
sch_tree_unlock(sch);
return 0;
}
sch_tree_unlock(sch);
return 0;
q->dep[i+SFQ_DEPTH].next = i+SFQ_DEPTH;
q->dep[i+SFQ_DEPTH].prev = i+SFQ_DEPTH;
}
q->dep[i+SFQ_DEPTH].next = i+SFQ_DEPTH;
q->dep[i+SFQ_DEPTH].prev = i+SFQ_DEPTH;
}
- q->limit = SFQ_DEPTH - 2;
+ q->limit = SFQ_DEPTH - 1;
q->max_depth = 0;
q->tail = SFQ_DEPTH;
if (opt == NULL) {
q->quantum = psched_mtu(sch->dev);
q->perturb_period = 0;
q->max_depth = 0;
q->tail = SFQ_DEPTH;
if (opt == NULL) {
q->quantum = psched_mtu(sch->dev);
q->perturb_period = 0;
+ get_random_bytes(&q->perturbation, 4);
} else {
int err = sfq_change(sch, opt);
if (err)
} else {
int err = sfq_change(sch, opt);
if (err)