1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
|
From 712639929912c5eefb09facccb48d55b3f72c9f8 Mon Sep 17 00:00:00 2001
From: George Amanakis <gamanakis@gmail.com>
Date: Fri, 1 Mar 2019 16:04:05 +0100
Subject: [PATCH] sch_cake: Make the dual modes fairer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
CAKE host fairness does not work well with TCP flows in dual-srchost and
dual-dsthost setup. The reason is that ACKs generated by TCP flows are
classified as sparse flows, and affect flow isolation from other hosts. Fix
this by calculating host_load based only on the bulk flows a host
generates. In a hash collision the host_bulk_flow_count values must be
decremented on the old hosts and incremented on the new ones *if* the queue
is in the bulk set.
Reported-by: Pete Heist <peteheist@gmail.com>
Signed-off-by: George Amanakis <gamanakis@gmail.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk>
---
net/sched/sch_cake.c | 92 ++++++++++++++++++++++++++++++--------------
1 file changed, 63 insertions(+), 29 deletions(-)
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -138,8 +138,8 @@ struct cake_flow {
struct cake_host {
u32 srchost_tag;
u32 dsthost_tag;
- u16 srchost_refcnt;
- u16 dsthost_refcnt;
+ u16 srchost_bulk_flow_count;
+ u16 dsthost_bulk_flow_count;
};
struct cake_heap_entry {
@@ -746,8 +746,10 @@ skip_hash:
* queue, accept the collision, update the host tags.
*/
q->way_collisions++;
- q->hosts[q->flows[reduced_hash].srchost].srchost_refcnt--;
- q->hosts[q->flows[reduced_hash].dsthost].dsthost_refcnt--;
+ if (q->flows[outer_hash + k].set == CAKE_SET_BULK) {
+ q->hosts[q->flows[reduced_hash].srchost].srchost_bulk_flow_count--;
+ q->hosts[q->flows[reduced_hash].dsthost].dsthost_bulk_flow_count--;
+ }
allocate_src = cake_dsrc(flow_mode);
allocate_dst = cake_ddst(flow_mode);
found:
@@ -767,13 +769,14 @@ found:
}
for (i = 0; i < CAKE_SET_WAYS;
i++, k = (k + 1) % CAKE_SET_WAYS) {
- if (!q->hosts[outer_hash + k].srchost_refcnt)
+ if (!q->hosts[outer_hash + k].srchost_bulk_flow_count)
break;
}
q->hosts[outer_hash + k].srchost_tag = srchost_hash;
found_src:
srchost_idx = outer_hash + k;
- q->hosts[srchost_idx].srchost_refcnt++;
+ if (q->flows[reduced_hash].set == CAKE_SET_BULK)
+ q->hosts[srchost_idx].srchost_bulk_flow_count++;
q->flows[reduced_hash].srchost = srchost_idx;
}
@@ -789,13 +792,14 @@ found_src:
}
for (i = 0; i < CAKE_SET_WAYS;
i++, k = (k + 1) % CAKE_SET_WAYS) {
- if (!q->hosts[outer_hash + k].dsthost_refcnt)
+ if (!q->hosts[outer_hash + k].dsthost_bulk_flow_count)
break;
}
q->hosts[outer_hash + k].dsthost_tag = dsthost_hash;
found_dst:
dsthost_idx = outer_hash + k;
- q->hosts[dsthost_idx].dsthost_refcnt++;
+ if (q->flows[reduced_hash].set == CAKE_SET_BULK)
+ q->hosts[dsthost_idx].dsthost_bulk_flow_count++;
q->flows[reduced_hash].dsthost = dsthost_idx;
}
}
@@ -1793,20 +1797,30 @@ static s32 cake_enqueue(struct sk_buff *
b->sparse_flow_count++;
if (cake_dsrc(q->flow_mode))
- host_load = max(host_load, srchost->srchost_refcnt);
+ host_load = max(host_load, srchost->srchost_bulk_flow_count);
if (cake_ddst(q->flow_mode))
- host_load = max(host_load, dsthost->dsthost_refcnt);
+ host_load = max(host_load, dsthost->dsthost_bulk_flow_count);
flow->deficit = (b->flow_quantum *
quantum_div[host_load]) >> 16;
} else if (flow->set == CAKE_SET_SPARSE_WAIT) {
+ struct cake_host *srchost = &b->hosts[flow->srchost];
+ struct cake_host *dsthost = &b->hosts[flow->dsthost];
+
/* this flow was empty, accounted as a sparse flow, but actually
* in the bulk rotation.
*/
flow->set = CAKE_SET_BULK;
b->sparse_flow_count--;
b->bulk_flow_count++;
+
+ if (cake_dsrc(q->flow_mode))
+ srchost->srchost_bulk_flow_count++;
+
+ if (cake_ddst(q->flow_mode))
+ dsthost->dsthost_bulk_flow_count++;
+
}
if (q->buffer_used > q->buffer_max_used)
@@ -1974,23 +1988,8 @@ retry:
dsthost = &b->hosts[flow->dsthost];
host_load = 1;
- if (cake_dsrc(q->flow_mode))
- host_load = max(host_load, srchost->srchost_refcnt);
-
- if (cake_ddst(q->flow_mode))
- host_load = max(host_load, dsthost->dsthost_refcnt);
-
- WARN_ON(host_load > CAKE_QUEUES);
-
/* flow isolation (DRR++) */
if (flow->deficit <= 0) {
- /* The shifted prandom_u32() is a way to apply dithering to
- * avoid accumulating roundoff errors
- */
- flow->deficit += (b->flow_quantum * quantum_div[host_load] +
- (prandom_u32() >> 16)) >> 16;
- list_move_tail(&flow->flowchain, &b->old_flows);
-
/* Keep all flows with deficits out of the sparse and decaying
* rotations. No non-empty flow can go into the decaying
* rotation, so they can't get deficits
@@ -1999,6 +1998,13 @@ retry:
if (flow->head) {
b->sparse_flow_count--;
b->bulk_flow_count++;
+
+ if (cake_dsrc(q->flow_mode))
+ srchost->srchost_bulk_flow_count++;
+
+ if (cake_ddst(q->flow_mode))
+ dsthost->dsthost_bulk_flow_count++;
+
flow->set = CAKE_SET_BULK;
} else {
/* we've moved it to the bulk rotation for
@@ -2008,6 +2014,22 @@ retry:
flow->set = CAKE_SET_SPARSE_WAIT;
}
}
+
+ if (cake_dsrc(q->flow_mode))
+ host_load = max(host_load, srchost->srchost_bulk_flow_count);
+
+ if (cake_ddst(q->flow_mode))
+ host_load = max(host_load, dsthost->dsthost_bulk_flow_count);
+
+ WARN_ON(host_load > CAKE_QUEUES);
+
+ /* The shifted prandom_u32() is a way to apply dithering to
+ * avoid accumulating roundoff errors
+ */
+ flow->deficit += (b->flow_quantum * quantum_div[host_load] +
+ (prandom_u32() >> 16)) >> 16;
+ list_move_tail(&flow->flowchain, &b->old_flows);
+
goto retry;
}
@@ -2028,6 +2050,13 @@ retry:
&b->decaying_flows);
if (flow->set == CAKE_SET_BULK) {
b->bulk_flow_count--;
+
+ if (cake_dsrc(q->flow_mode))
+ srchost->srchost_bulk_flow_count--;
+
+ if (cake_ddst(q->flow_mode))
+ dsthost->dsthost_bulk_flow_count--;
+
b->decaying_flow_count++;
} else if (flow->set == CAKE_SET_SPARSE ||
flow->set == CAKE_SET_SPARSE_WAIT) {
@@ -2041,14 +2070,19 @@ retry:
if (flow->set == CAKE_SET_SPARSE ||
flow->set == CAKE_SET_SPARSE_WAIT)
b->sparse_flow_count--;
- else if (flow->set == CAKE_SET_BULK)
+ else if (flow->set == CAKE_SET_BULK) {
b->bulk_flow_count--;
- else
+
+ if (cake_dsrc(q->flow_mode))
+ srchost->srchost_bulk_flow_count--;
+
+ if (cake_ddst(q->flow_mode))
+ dsthost->dsthost_bulk_flow_count--;
+
+ } else
b->decaying_flow_count--;
flow->set = CAKE_SET_NONE;
- srchost->srchost_refcnt--;
- dsthost->dsthost_refcnt--;
}
goto begin;
}
|
