summaryrefslogtreecommitdiffstats
path: root/net/sched/sch_sfq.c
diff options
context:
space:
mode:
authorEric Dumazet <eric.dumazet@gmail.com>2010-12-28 21:53:33 +0000
committerDavid S. Miller <davem@davemloft.net>2010-12-31 12:47:37 -0800
commiteeaeb068f1393b4db4861481bf594bcd1c3eda7a (patch)
treed3404b80033fa89b83e6e23fd9fbcb0d7dad614f /net/sched/sch_sfq.c
parent0f333d10e3f689640b229c8cf00b16ea51ce4951 (diff)
downloadlinux-eeaeb068f1393b4db4861481bf594bcd1c3eda7a.tar.bz2
sch_sfq: allow big packets and be fair
SFQ is currently 'limited' to small packets, because it uses a 15bit allotment number per flow. Introduce a scale by 8, so that we can handle full size TSO/GRO packets. Use appropriate handling to make sure allot is positive before a new packet is dequeued, so that fairness is respected. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Acked-by: Jarek Poplawski <jarkao2@gmail.com> Cc: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/sched/sch_sfq.c')
-rw-r--r--net/sched/sch_sfq.c26
1 files changed, 19 insertions, 7 deletions
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 6a2f88fea6d8..b76d46b71466 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -67,7 +67,7 @@
IMPLEMENTATION:
This implementation limits maximal queue length to 128;
- maximal mtu to 2^15-1; max 128 flows, number of hash buckets to 1024.
+ max mtu to 2^18-1; max 128 flows, number of hash buckets to 1024.
The only goal of this restrictions was that all data
fit into one 4K page on 32bit arches.
@@ -77,6 +77,11 @@
#define SFQ_SLOTS 128 /* max number of flows */
#define SFQ_EMPTY_SLOT 255
#define SFQ_HASH_DIVISOR 1024
+/* We use 16 bits to store allot, and want to handle packets up to 64K
+ * Scale allot by 8 (1<<3) so that no overflow occurs.
+ */
+#define SFQ_ALLOT_SHIFT 3
+#define SFQ_ALLOT_SIZE(X) DIV_ROUND_UP(X, 1 << SFQ_ALLOT_SHIFT)
/* This type should contain at least SFQ_DEPTH + SFQ_SLOTS values */
typedef unsigned char sfq_index;
@@ -115,7 +120,7 @@ struct sfq_sched_data
struct timer_list perturb_timer;
u32 perturbation;
sfq_index cur_depth; /* depth of longest slot */
-
+ unsigned short scaled_quantum; /* SFQ_ALLOT_SIZE(quantum) */
struct sfq_slot *tail; /* current slot in round */
sfq_index ht[SFQ_HASH_DIVISOR]; /* Hash table */
struct sfq_slot slots[SFQ_SLOTS];
@@ -395,7 +400,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
q->tail->next = x;
}
q->tail = slot;
- slot->allot = q->quantum;
+ slot->allot = q->scaled_quantum;
}
if (++sch->q.qlen <= q->limit) {
sch->bstats.bytes += qdisc_pkt_len(skb);
@@ -431,8 +436,14 @@ sfq_dequeue(struct Qdisc *sch)
if (q->tail == NULL)
return NULL;
+next_slot:
a = q->tail->next;
slot = &q->slots[a];
+ if (slot->allot <= 0) {
+ q->tail = slot;
+ slot->allot += q->scaled_quantum;
+ goto next_slot;
+ }
skb = slot_dequeue_head(slot);
sfq_dec(q, a);
sch->q.qlen--;
@@ -447,9 +458,8 @@ sfq_dequeue(struct Qdisc *sch)
return skb;
}
q->tail->next = next_a;
- } else if ((slot->allot -= qdisc_pkt_len(skb)) <= 0) {
- q->tail = slot;
- slot->allot += q->quantum;
+ } else {
+ slot->allot -= SFQ_ALLOT_SIZE(qdisc_pkt_len(skb));
}
return skb;
}
@@ -485,6 +495,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
sch_tree_lock(sch);
q->quantum = ctl->quantum ? : psched_mtu(qdisc_dev(sch));
+ q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum);
q->perturb_period = ctl->perturb_period * HZ;
if (ctl->limit)
q->limit = min_t(u32, ctl->limit, SFQ_DEPTH - 1);
@@ -525,6 +536,7 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt)
q->tail = NULL;
if (opt == NULL) {
q->quantum = psched_mtu(qdisc_dev(sch));
+ q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum);
q->perturb_period = 0;
q->perturbation = net_random();
} else {
@@ -617,7 +629,7 @@ static int sfq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
if (idx != SFQ_EMPTY_SLOT) {
const struct sfq_slot *slot = &q->slots[idx];
- xstats.allot = slot->allot;
+ xstats.allot = slot->allot << SFQ_ALLOT_SHIFT;
qs.qlen = slot->qlen;
slot_queue_walk(slot, skb)
qs.backlog += qdisc_pkt_len(skb);