diff options
author | Eric Dumazet <edumazet@google.com> | 2016-05-06 17:55:12 +0200 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2016-05-09 05:49:38 +0200 |
commit | 95b58430abe74f5e50970c57d27380bd5b8be324 (patch) | |
tree | 497e1bd5097b3051ff75acc42f9ffc87bc2108e8 /net/sched/sch_fq_codel.c | |
parent | net: Add Qualcomm IPC router (diff) | |
download | linux-95b58430abe74f5e50970c57d27380bd5b8be324.tar.xz linux-95b58430abe74f5e50970c57d27380bd5b8be324.zip |
fq_codel: add memory limitation per queue
On small embedded routers, one wants to control maximal amount of
memory used by fq_codel, instead of controlling number of packets or
bytes, since GRO/TSO make these not practical.
Assuming skb->truesize is accurate, we have to keep track of
skb->truesize sum for skbs in queue.
This patch adds a new TCA_FQ_CODEL_MEMORY_LIMIT attribute.
I chose a default value of 32 MBytes, which looks reasonable even
for heavy duty usages. (Prior fq_codel users should not be hurt
when they upgrade their kernels)
Two fields are added to tc_fq_codel_qd_stats to report :
- Current memory usage
- Number of drops caused by memory limits
# tc qd replace dev eth1 root est 1sec 4sec fq_codel memory_limit 4M
..
# tc -s -d qd sh dev eth1
qdisc fq_codel 8008: root refcnt 257 limit 10240p flows 1024
quantum 1514 target 5.0ms interval 100.0ms memory_limit 4Mb ecn
Sent 2083566791363 bytes 1376214889 pkt (dropped 4994406, overlimits 0
requeues 21705223)
rate 9841Mbit 812549pps backlog 3906120b 376p requeues 21705223
maxpacket 68130 drop_overlimit 4994406 new_flow_count 28855414
ecn_mark 0 memory_used 4190048 drop_overmemory 4994406
new_flows_len 1 old_flows_len 177
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Dave Täht <dave.taht@gmail.com>
Cc: Sebastian Möller <moeller0@gmx.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/sched/sch_fq_codel.c')
-rw-r--r-- | net/sched/sch_fq_codel.c | 27 |
1 files changed, 24 insertions, 3 deletions
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index e7b42b0d5145..bb8bd9314629 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -60,8 +60,11 @@ struct fq_codel_sched_data { u32 perturbation; /* hash perturbation */ u32 quantum; /* psched_mtu(qdisc_dev(sch)); */ u32 drop_batch_size; + u32 memory_limit; struct codel_params cparams; struct codel_stats cstats; + u32 memory_usage; + u32 drop_overmemory; u32 drop_overlimit; u32 new_flow_count; @@ -143,6 +146,7 @@ static unsigned int fq_codel_drop(struct Qdisc *sch, unsigned int max_packets) unsigned int maxbacklog = 0, idx = 0, i, len; struct fq_codel_flow *flow; unsigned int threshold; + unsigned int mem = 0; /* Queue is full! Find the fat flow and drop packet(s) from it. * This might sound expensive, but with 1024 flows, we scan @@ -167,11 +171,13 @@ static unsigned int fq_codel_drop(struct Qdisc *sch, unsigned int max_packets) do { skb = dequeue_head(flow); len += qdisc_pkt_len(skb); + mem += skb->truesize; kfree_skb(skb); } while (++i < max_packets && len < threshold); flow->dropped += i; q->backlogs[idx] -= len; + q->memory_usage -= mem; sch->qstats.drops += i; sch->qstats.backlog -= len; sch->q.qlen -= i; @@ -193,6 +199,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch) unsigned int idx, prev_backlog, prev_qlen; struct fq_codel_flow *flow; int uninitialized_var(ret); + bool memory_limited; idx = fq_codel_classify(skb, sch, &ret); if (idx == 0) { @@ -215,7 +222,9 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch) flow->deficit = q->quantum; flow->dropped = 0; } - if (++sch->q.qlen <= sch->limit) + q->memory_usage += skb->truesize; + memory_limited = q->memory_usage > q->memory_limit; + if (++sch->q.qlen <= sch->limit && !memory_limited) return NET_XMIT_SUCCESS; prev_backlog = sch->qstats.backlog; @@ -229,7 +238,8 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch) ret = fq_codel_drop(sch, q->drop_batch_size); q->drop_overlimit += prev_qlen - sch->q.qlen; - + if (memory_limited) + q->drop_overmemory += prev_qlen - sch->q.qlen; /* As we dropped packet(s), better let upper stack know this */ qdisc_tree_reduce_backlog(sch, prev_qlen - sch->q.qlen, prev_backlog - sch->qstats.backlog); @@ -308,6 +318,7 @@ begin: list_del_init(&flow->flowchain); goto begin; } + q->memory_usage -= skb->truesize; qdisc_bstats_update(sch, skb); flow->deficit -= qdisc_pkt_len(skb); /* We cant call qdisc_tree_reduce_backlog() if our qlen is 0, @@ -355,6 +366,7 @@ static const struct nla_policy fq_codel_policy[TCA_FQ_CODEL_MAX + 1] = { [TCA_FQ_CODEL_QUANTUM] = { .type = NLA_U32 }, [TCA_FQ_CODEL_CE_THRESHOLD] = { .type = NLA_U32 }, [TCA_FQ_CODEL_DROP_BATCH_SIZE] = { .type = NLA_U32 }, + [TCA_FQ_CODEL_MEMORY_LIMIT] = { .type = NLA_U32 }, }; static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt) @@ -409,7 +421,11 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt) if (tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]) q->drop_batch_size = min(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])); - while (sch->q.qlen > sch->limit) { + if (tb[TCA_FQ_CODEL_MEMORY_LIMIT]) + q->memory_limit = min(1U << 31, nla_get_u32(tb[TCA_FQ_CODEL_MEMORY_LIMIT])); + + while (sch->q.qlen > sch->limit || + q->memory_usage > q->memory_limit) { struct sk_buff *skb = fq_codel_dequeue(sch); q->cstats.drop_len += qdisc_pkt_len(skb); @@ -454,6 +470,7 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt) sch->limit = 10*1024; q->flows_cnt = 1024; + q->memory_limit = 32 << 20; /* 32 MBytes */ q->drop_batch_size = 64; q->quantum = psched_mtu(qdisc_dev(sch)); q->perturbation = prandom_u32(); @@ -515,6 +532,8 @@ static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb) q->quantum) || nla_put_u32(skb, TCA_FQ_CODEL_DROP_BATCH_SIZE, q->drop_batch_size) || + nla_put_u32(skb, TCA_FQ_CODEL_MEMORY_LIMIT, + q->memory_limit) || nla_put_u32(skb, TCA_FQ_CODEL_FLOWS, q->flows_cnt)) goto nla_put_failure; @@ -543,6 +562,8 @@ static int fq_codel_dump_stats(struct Qdisc *sch, struct gnet_dump *d) st.qdisc_stats.ecn_mark = q->cstats.ecn_mark; st.qdisc_stats.new_flow_count = q->new_flow_count; st.qdisc_stats.ce_mark = q->cstats.ce_mark; + st.qdisc_stats.memory_usage = q->memory_usage; + st.qdisc_stats.drop_overmemory = q->drop_overmemory; list_for_each(pos, &q->new_flows) st.qdisc_stats.new_flows_len++; |