[PKT_SCHED]: RED: Use new generic red interface
Simplifies code a lot by separating the red algorithm and the queueing logic. We now differentiate between probability marks and forced marks but sum them together again to not break backwards compatibility. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>
This commit is contained in:
Thomas Graf
Thomas Graf
parent
2566a509ca
commit
6b31b28a44
|
|
@ -41,44 +41,10 @@
|
|||
#include <net/pkt_sched.h>
|
||||
#include <net/inet_ecn.h>
|
||||
#include <net/dsfield.h>
|
||||
#include <net/red.h>
|
||||
|
||||
|
||||
/* Random Early Detection (RED) algorithm.
|
||||
=======================================
|
||||
|
||||
Source: Sally Floyd and Van Jacobson, "Random Early Detection Gateways
|
||||
for Congestion Avoidance", 1993, IEEE/ACM Transactions on Networking.
|
||||
|
||||
This file codes a "divisionless" version of RED algorithm
|
||||
as written down in Fig.17 of the paper.
|
||||
|
||||
Short description.
|
||||
------------------
|
||||
|
||||
When a new packet arrives we calculate the average queue length:
|
||||
|
||||
avg = (1-W)*avg + W*current_queue_len,
|
||||
|
||||
W is the filter time constant (chosen as 2^(-Wlog)), it controls
|
||||
the inertia of the algorithm. To allow larger bursts, W should be
|
||||
decreased.
|
||||
|
||||
if (avg > th_max) -> packet marked (dropped).
|
||||
if (avg < th_min) -> packet passes.
|
||||
if (th_min < avg < th_max) we calculate probability:
|
||||
|
||||
Pb = max_P * (avg - th_min)/(th_max-th_min)
|
||||
|
||||
and mark (drop) packet with this probability.
|
||||
Pb changes from 0 (at avg==th_min) to max_P (avg==th_max).
|
||||
max_P should be small (not 1), usually 0.01..0.02 is good value.
|
||||
|
||||
max_P is chosen as a number, so that max_P/(th_max-th_min)
|
||||
is a negative power of two in order arithmetics to contain
|
||||
only shifts.
|
||||
|
||||
|
||||
Parameters, settable by user:
|
||||
/* Parameters, settable by user:
|
||||
-----------------------------
|
||||
|
||||
limit - bytes (must be > qth_max + burst)
|
||||
|
|
@ -89,92 +55,19 @@ Short description.
|
|||
arbitrarily high (well, less than ram size)
|
||||
Really, this limit will never be reached
|
||||
if RED works correctly.
|
||||
|
||||
qth_min - bytes (should be < qth_max/2)
|
||||
qth_max - bytes (should be at least 2*qth_min and less limit)
|
||||
Wlog - bits (<32) log(1/W).
|
||||
Plog - bits (<32)
|
||||
|
||||
Plog is related to max_P by formula:
|
||||
|
||||
max_P = (qth_max-qth_min)/2^Plog;
|
||||
|
||||
F.e. if qth_max=128K and qth_min=32K, then Plog=22
|
||||
corresponds to max_P=0.02
|
||||
|
||||
Scell_log
|
||||
Stab
|
||||
|
||||
Lookup table for log((1-W)^(t/t_ave).
|
||||
|
||||
|
||||
NOTES:
|
||||
|
||||
Upper bound on W.
|
||||
-----------------
|
||||
|
||||
If you want to allow bursts of L packets of size S,
|
||||
you should choose W:
|
||||
|
||||
L + 1 - th_min/S < (1-(1-W)^L)/W
|
||||
|
||||
th_min/S = 32 th_min/S = 4
|
||||
|
||||
log(W) L
|
||||
-1 33
|
||||
-2 35
|
||||
-3 39
|
||||
-4 46
|
||||
-5 57
|
||||
-6 75
|
||||
-7 101
|
||||
-8 135
|
||||
-9 190
|
||||
etc.
|
||||
*/
|
||||
|
||||
struct red_sched_data
|
||||
{
|
||||
/* Parameters */
|
||||
u32 limit; /* HARD maximal queue length */
|
||||
u32 qth_min; /* Min average length threshold: A scaled */
|
||||
u32 qth_max; /* Max average length threshold: A scaled */
|
||||
u32 Rmask;
|
||||
u32 Scell_max;
|
||||
unsigned char flags;
|
||||
char Wlog; /* log(W) */
|
||||
char Plog; /* random number bits */
|
||||
char Scell_log;
|
||||
u8 Stab[256];
|
||||
|
||||
/* Variables */
|
||||
unsigned long qave; /* Average queue length: A scaled */
|
||||
int qcount; /* Packets since last random number generation */
|
||||
u32 qR; /* Cached random number */
|
||||
|
||||
psched_time_t qidlestart; /* Start of idle period */
|
||||
struct tc_red_xstats st;
|
||||
u32 limit; /* HARD maximal queue length */
|
||||
unsigned char flags;
|
||||
struct red_parms parms;
|
||||
struct red_stats stats;
|
||||
};
|
||||
|
||||
static int red_ecn_mark(struct sk_buff *skb)
|
||||
static inline int red_use_ecn(struct red_sched_data *q)
|
||||
{
|
||||
if (skb->nh.raw + 20 > skb->tail)
|
||||
return 0;
|
||||
|
||||
switch (skb->protocol) {
|
||||
case __constant_htons(ETH_P_IP):
|
||||
if (INET_ECN_is_not_ect(skb->nh.iph->tos))
|
||||
return 0;
|
||||
IP_ECN_set_ce(skb->nh.iph);
|
||||
return 1;
|
||||
case __constant_htons(ETH_P_IPV6):
|
||||
if (INET_ECN_is_not_ect(ipv6_get_dsfield(skb->nh.ipv6h)))
|
||||
return 0;
|
||||
IP6_ECN_set_ce(skb->nh.ipv6h);
|
||||
return 1;
|
||||
default:
|
||||
return 0;
|
||||
}
|
||||
return q->flags & TC_RED_ECN;
|
||||
}
|
||||
|
||||
static int
|
||||
|
|
@ -182,119 +75,50 @@ red_enqueue(struct sk_buff *skb, struct Qdisc* sch)
|
|||
{
|
||||
struct red_sched_data *q = qdisc_priv(sch);
|
||||
|
||||
psched_time_t now;
|
||||
q->parms.qavg = red_calc_qavg(&q->parms, sch->qstats.backlog);
|
||||
|
||||
if (!PSCHED_IS_PASTPERFECT(q->qidlestart)) {
|
||||
long us_idle;
|
||||
int shift;
|
||||
if (red_is_idling(&q->parms))
|
||||
red_end_of_idle_period(&q->parms);
|
||||
|
||||
PSCHED_GET_TIME(now);
|
||||
us_idle = PSCHED_TDIFF_SAFE(now, q->qidlestart, q->Scell_max);
|
||||
PSCHED_SET_PASTPERFECT(q->qidlestart);
|
||||
switch (red_action(&q->parms, q->parms.qavg)) {
|
||||
case RED_DONT_MARK:
|
||||
break;
|
||||
|
||||
/*
|
||||
The problem: ideally, average length queue recalcultion should
|
||||
be done over constant clock intervals. This is too expensive, so that
|
||||
the calculation is driven by outgoing packets.
|
||||
When the queue is idle we have to model this clock by hand.
|
||||
case RED_PROB_MARK:
|
||||
sch->qstats.overlimits++;
|
||||
if (!red_use_ecn(q) || !INET_ECN_set_ce(skb)) {
|
||||
q->stats.prob_drop++;
|
||||
goto congestion_drop;
|
||||
}
|
||||
|
||||
SF+VJ proposed to "generate" m = idletime/(average_pkt_size/bandwidth)
|
||||
dummy packets as a burst after idle time, i.e.
|
||||
q->stats.prob_mark++;
|
||||
break;
|
||||
|
||||
q->qave *= (1-W)^m
|
||||
case RED_HARD_MARK:
|
||||
sch->qstats.overlimits++;
|
||||
if (!red_use_ecn(q) || !INET_ECN_set_ce(skb)) {
|
||||
q->stats.forced_drop++;
|
||||
goto congestion_drop;
|
||||
}
|
||||
|
||||
This is an apparently overcomplicated solution (f.e. we have to precompute
|
||||
a table to make this calculation in reasonable time)
|
||||
I believe that a simpler model may be used here,
|
||||
but it is field for experiments.
|
||||
*/
|
||||
shift = q->Stab[us_idle>>q->Scell_log];
|
||||
|
||||
if (shift) {
|
||||
q->qave >>= shift;
|
||||
} else {
|
||||
/* Approximate initial part of exponent
|
||||
with linear function:
|
||||
(1-W)^m ~= 1-mW + ...
|
||||
|
||||
Seems, it is the best solution to
|
||||
problem of too coarce exponent tabulation.
|
||||
*/
|
||||
|
||||
us_idle = (q->qave * us_idle)>>q->Scell_log;
|
||||
if (us_idle < q->qave/2)
|
||||
q->qave -= us_idle;
|
||||
else
|
||||
q->qave >>= 1;
|
||||
}
|
||||
} else {
|
||||
q->qave += sch->qstats.backlog - (q->qave >> q->Wlog);
|
||||
/* NOTE:
|
||||
q->qave is fixed point number with point at Wlog.
|
||||
The formulae above is equvalent to floating point
|
||||
version:
|
||||
|
||||
qave = qave*(1-W) + sch->qstats.backlog*W;
|
||||
--ANK (980924)
|
||||
*/
|
||||
q->stats.forced_mark++;
|
||||
break;
|
||||
}
|
||||
|
||||
if (q->qave < q->qth_min) {
|
||||
q->qcount = -1;
|
||||
enqueue:
|
||||
if (sch->qstats.backlog + skb->len <= q->limit) {
|
||||
__skb_queue_tail(&sch->q, skb);
|
||||
sch->qstats.backlog += skb->len;
|
||||
sch->bstats.bytes += skb->len;
|
||||
sch->bstats.packets++;
|
||||
return NET_XMIT_SUCCESS;
|
||||
} else {
|
||||
q->st.pdrop++;
|
||||
}
|
||||
kfree_skb(skb);
|
||||
sch->qstats.drops++;
|
||||
return NET_XMIT_DROP;
|
||||
}
|
||||
if (q->qave >= q->qth_max) {
|
||||
q->qcount = -1;
|
||||
sch->qstats.overlimits++;
|
||||
mark:
|
||||
if (!(q->flags&TC_RED_ECN) || !red_ecn_mark(skb)) {
|
||||
q->st.early++;
|
||||
goto drop;
|
||||
}
|
||||
q->st.marked++;
|
||||
goto enqueue;
|
||||
if (sch->qstats.backlog + skb->len <= q->limit) {
|
||||
__skb_queue_tail(&sch->q, skb);
|
||||
sch->qstats.backlog += skb->len;
|
||||
sch->bstats.bytes += skb->len;
|
||||
sch->bstats.packets++;
|
||||
return NET_XMIT_SUCCESS;
|
||||
}
|
||||
|
||||
if (++q->qcount) {
|
||||
/* The formula used below causes questions.
|
||||
q->stats.pdrop++;
|
||||
kfree_skb(skb);
|
||||
sch->qstats.drops++;
|
||||
return NET_XMIT_DROP;
|
||||
|
||||
OK. qR is random number in the interval 0..Rmask
|
||||
i.e. 0..(2^Plog). If we used floating point
|
||||
arithmetics, it would be: (2^Plog)*rnd_num,
|
||||
where rnd_num is less 1.
|
||||
|
||||
Taking into account, that qave have fixed
|
||||
point at Wlog, and Plog is related to max_P by
|
||||
max_P = (qth_max-qth_min)/2^Plog; two lines
|
||||
below have the following floating point equivalent:
|
||||
|
||||
max_P*(qave - qth_min)/(qth_max-qth_min) < rnd/qcount
|
||||
|
||||
Any questions? --ANK (980924)
|
||||
*/
|
||||
if (((q->qave - q->qth_min)>>q->Wlog)*q->qcount < q->qR)
|
||||
goto enqueue;
|
||||
q->qcount = 0;
|
||||
q->qR = net_random()&q->Rmask;
|
||||
sch->qstats.overlimits++;
|
||||
goto mark;
|
||||
}
|
||||
q->qR = net_random()&q->Rmask;
|
||||
goto enqueue;
|
||||
|
||||
drop:
|
||||
congestion_drop:
|
||||
kfree_skb(skb);
|
||||
sch->qstats.drops++;
|
||||
return NET_XMIT_CN;
|
||||
|
|
@ -305,7 +129,8 @@ red_requeue(struct sk_buff *skb, struct Qdisc* sch)
|
|||
{
|
||||
struct red_sched_data *q = qdisc_priv(sch);
|
||||
|
||||
PSCHED_SET_PASTPERFECT(q->qidlestart);
|
||||
if (red_is_idling(&q->parms))
|
||||
red_end_of_idle_period(&q->parms);
|
||||
|
||||
__skb_queue_head(&sch->q, skb);
|
||||
sch->qstats.backlog += skb->len;
|
||||
|
|
@ -324,7 +149,8 @@ red_dequeue(struct Qdisc* sch)
|
|||
sch->qstats.backlog -= skb->len;
|
||||
return skb;
|
||||
}
|
||||
PSCHED_GET_TIME(q->qidlestart);
|
||||
|
||||
red_start_of_idle_period(&q->parms);
|
||||
return NULL;
|
||||
}
|
||||
|
||||
|
|
@ -338,11 +164,12 @@ static unsigned int red_drop(struct Qdisc* sch)
|
|||
unsigned int len = skb->len;
|
||||
sch->qstats.backlog -= len;
|
||||
sch->qstats.drops++;
|
||||
q->st.other++;
|
||||
q->stats.other++;
|
||||
kfree_skb(skb);
|
||||
return len;
|
||||
}
|
||||
PSCHED_GET_TIME(q->qidlestart);
|
||||
|
||||
red_start_of_idle_period(&q->parms);
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
|
@ -352,9 +179,7 @@ static void red_reset(struct Qdisc* sch)
|
|||
|
||||
__skb_queue_purge(&sch->q);
|
||||
sch->qstats.backlog = 0;
|
||||
PSCHED_SET_PASTPERFECT(q->qidlestart);
|
||||
q->qave = 0;
|
||||
q->qcount = -1;
|
||||
red_restart(&q->parms);
|
||||
}
|
||||
|
||||
static int red_change(struct Qdisc *sch, struct rtattr *opt)
|
||||
|
|
@ -374,19 +199,14 @@ static int red_change(struct Qdisc *sch, struct rtattr *opt)
|
|||
|
||||
sch_tree_lock(sch);
|
||||
q->flags = ctl->flags;
|
||||
q->Wlog = ctl->Wlog;
|
||||
q->Plog = ctl->Plog;
|
||||
q->Rmask = ctl->Plog < 32 ? ((1<<ctl->Plog) - 1) : ~0UL;
|
||||
q->Scell_log = ctl->Scell_log;
|
||||
q->Scell_max = (255<<q->Scell_log);
|
||||
q->qth_min = ctl->qth_min<<ctl->Wlog;
|
||||
q->qth_max = ctl->qth_max<<ctl->Wlog;
|
||||
q->limit = ctl->limit;
|
||||
memcpy(q->Stab, RTA_DATA(tb[TCA_RED_STAB-1]), 256);
|
||||
|
||||
q->qcount = -1;
|
||||
red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog,
|
||||
ctl->Plog, ctl->Scell_log,
|
||||
RTA_DATA(tb[TCA_RED_STAB-1]));
|
||||
|
||||
if (skb_queue_empty(&sch->q))
|
||||
PSCHED_SET_PASTPERFECT(q->qidlestart);
|
||||
red_end_of_idle_period(&q->parms);
|
||||
sch_tree_unlock(sch);
|
||||
return 0;
|
||||
}
|
||||
|
|
@ -401,17 +221,18 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb)
|
|||
struct red_sched_data *q = qdisc_priv(sch);
|
||||
unsigned char *b = skb->tail;
|
||||
struct rtattr *rta;
|
||||
struct tc_red_qopt opt;
|
||||
struct tc_red_qopt opt = {
|
||||
.limit = q->limit,
|
||||
.flags = q->flags,
|
||||
.qth_min = q->parms.qth_min >> q->parms.Wlog,
|
||||
.qth_max = q->parms.qth_max >> q->parms.Wlog,
|
||||
.Wlog = q->parms.Wlog,
|
||||
.Plog = q->parms.Plog,
|
||||
.Scell_log = q->parms.Scell_log,
|
||||
};
|
||||
|
||||
rta = (struct rtattr*)b;
|
||||
RTA_PUT(skb, TCA_OPTIONS, 0, NULL);
|
||||
opt.limit = q->limit;
|
||||
opt.qth_min = q->qth_min>>q->Wlog;
|
||||
opt.qth_max = q->qth_max>>q->Wlog;
|
||||
opt.Wlog = q->Wlog;
|
||||
opt.Plog = q->Plog;
|
||||
opt.Scell_log = q->Scell_log;
|
||||
opt.flags = q->flags;
|
||||
RTA_PUT(skb, TCA_RED_PARMS, sizeof(opt), &opt);
|
||||
rta->rta_len = skb->tail - b;
|
||||
|
||||
|
|
@ -425,8 +246,14 @@ rtattr_failure:
|
|||
static int red_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
|
||||
{
|
||||
struct red_sched_data *q = qdisc_priv(sch);
|
||||
struct tc_red_xstats st = {
|
||||
.early = q->stats.prob_drop + q->stats.forced_drop,
|
||||
.pdrop = q->stats.pdrop,
|
||||
.other = q->stats.other,
|
||||
.marked = q->stats.prob_mark + q->stats.forced_mark,
|
||||
};
|
||||
|
||||
return gnet_stats_copy_app(d, &q->st, sizeof(q->st));
|
||||
return gnet_stats_copy_app(d, &st, sizeof(st));
|
||||
}
|
||||
|
||||
static struct Qdisc_ops red_qdisc_ops = {
|
||||
|
|
|
|||
Loading…
Reference in New Issue