![brakmo](/assets/img/avatar_default.png)
Adds support for fq's Earliest Departure Time to HBM (Host Bandwidth Manager). Includes a new BPF program supporting EDT, and also updates corresponding programs. It will drop packets with an EDT of more than 500us in the future unless the packet belongs to a flow with less than 2 packets in flight. This is done so each flow has at least 2 packets in flight, so they will not starve, and also to help prevent delayed ACK timeouts. It will also work with ECN enabled traffic, where the packets will be CE marked if their EDT is more than 50us in the future. The table below shows some performance numbers. The flows are back to back RPCS. One server sending to another, either 2 or 4 flows. One flow is a 10KB RPC, the rest are 1MB RPCs. When there are more than one flow of a given RPC size, the numbers represent averages. The rate limit applies to all flows (they are in the same cgroup). Tests ending with "-edt" ran with the new BPF program supporting EDT. Tests ending with "-hbt" ran on top HBT qdisc with the specified rate (i.e. no HBM). The other tests ran with the HBM BPF program included in the HBM patch-set. EDT has limited value when using DCTCP, but it helps in many cases when using Cubic. It usually achieves larger link utilization and lower 99% latencies for the 1MB RPCs. HBM ends up queueing a lot of packets with its default parameter values, reducing the goodput of the 10KB RPCs and increasing their latency. Also, the RTTs seen by the flows are quite large. Aggr 10K 10K 10K 1MB 1MB 1MB Limit rate drops RTT rate P90 P99 rate P90 P99 Test rate Flows Mbps % us Mbps us us Mbps ms ms -------- ---- ----- ---- ----- --- ---- ---- ---- ---- ---- ---- cubic 1G 2 904 0.02 108 257 511 539 647 13.4 24.5 cubic-edt 1G 2 982 0.01 156 239 656 967 743 14.0 17.2 dctcp 1G 2 977 0.00 105 324 408 744 653 14.5 15.9 dctcp-edt 1G 2 981 0.01 142 321 417 811 660 15.7 17.0 cubic-htb 1G 2 919 0.00 1825 40 2822 4140 879 9.7 9.9 cubic 200M 2 155 0.30 220 81 532 655 74 283 450 cubic-edt 200M 2 188 0.02 222 87 1035 1095 101 84 85 dctcp 200M 2 188 0.03 111 77 912 939 111 76 325 dctcp-edt 200M 2 188 0.03 217 74 1416 1738 114 76 79 cubic-htb 200M 2 188 0.00 5015 8 14ms 15ms 180 48 50 cubic 1G 4 952 0.03 110 165 516 546 262 38 154 cubic-edt 1G 4 973 0.01 190 111 1034 1314 287 65 79 dctcp 1G 4 951 0.00 103 180 617 905 257 37 38 dctcp-edt 1G 4 967 0.00 163 151 732 1126 272 43 55 cubic-htb 1G 4 914 0.00 3249 13 7ms 8ms 300 29 34 cubic 5G 4 4236 0.00 134 305 490 624 1310 10 17 cubic-edt 5G 4 4865 0.00 156 306 425 759 1520 10 16 dctcp 5G 4 4936 0.00 128 485 221 409 1484 7 9 dctcp-edt 5G 4 4924 0.00 148 390 392 623 1508 11 26 v1 -> v2: Incorporated Andrii's suggestions v2 -> v3: Incorporated Yonghong's suggestions v3 -> v4: Removed credit update that is not needed Signed-off-by: Lawrence Brakmo <brakmo@fb.com> Acked-by: Yonghong Song <yhs@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
221 lines
5.9 KiB
C
221 lines
5.9 KiB
C
/* SPDX-License-Identifier: GPL-2.0
|
|
*
|
|
* Copyright (c) 2019 Facebook
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of version 2 of the GNU General Public
|
|
* License as published by the Free Software Foundation.
|
|
*
|
|
* Include file for sample Host Bandwidth Manager (HBM) BPF programs
|
|
*/
|
|
#define KBUILD_MODNAME "foo"
|
|
#include <stddef.h>
|
|
#include <stdbool.h>
|
|
#include <uapi/linux/bpf.h>
|
|
#include <uapi/linux/if_ether.h>
|
|
#include <uapi/linux/if_packet.h>
|
|
#include <uapi/linux/ip.h>
|
|
#include <uapi/linux/ipv6.h>
|
|
#include <uapi/linux/in.h>
|
|
#include <uapi/linux/tcp.h>
|
|
#include <uapi/linux/filter.h>
|
|
#include <uapi/linux/pkt_cls.h>
|
|
#include <net/ipv6.h>
|
|
#include <net/inet_ecn.h>
|
|
#include "bpf_endian.h"
|
|
#include "bpf_helpers.h"
|
|
#include "hbm.h"
|
|
|
|
#define DROP_PKT 0
|
|
#define ALLOW_PKT 1
|
|
#define TCP_ECN_OK 1
|
|
#define CWR 2
|
|
|
|
#ifndef HBM_DEBUG // Define HBM_DEBUG to enable debugging
|
|
#undef bpf_printk
|
|
#define bpf_printk(fmt, ...)
|
|
#endif
|
|
|
|
#define INITIAL_CREDIT_PACKETS 100
|
|
#define MAX_BYTES_PER_PACKET 1500
|
|
#define MARK_THRESH (40 * MAX_BYTES_PER_PACKET)
|
|
#define DROP_THRESH (80 * 5 * MAX_BYTES_PER_PACKET)
|
|
#define LARGE_PKT_DROP_THRESH (DROP_THRESH - (15 * MAX_BYTES_PER_PACKET))
|
|
#define MARK_REGION_SIZE (LARGE_PKT_DROP_THRESH - MARK_THRESH)
|
|
#define LARGE_PKT_THRESH 120
|
|
#define MAX_CREDIT (100 * MAX_BYTES_PER_PACKET)
|
|
#define INIT_CREDIT (INITIAL_CREDIT_PACKETS * MAX_BYTES_PER_PACKET)
|
|
|
|
// Time base accounting for fq's EDT
|
|
#define BURST_SIZE_NS 100000 // 100us
|
|
#define MARK_THRESH_NS 50000 // 50us
|
|
#define DROP_THRESH_NS 500000 // 500us
|
|
// Reserve 20us of queuing for small packets (less than 120 bytes)
|
|
#define LARGE_PKT_DROP_THRESH_NS (DROP_THRESH_NS - 20000)
|
|
#define MARK_REGION_SIZE_NS (LARGE_PKT_DROP_THRESH_NS - MARK_THRESH_NS)
|
|
|
|
// rate in bytes per ns << 20
|
|
#define CREDIT_PER_NS(delta, rate) ((((u64)(delta)) * (rate)) >> 20)
|
|
#define BYTES_PER_NS(delta, rate) ((((u64)(delta)) * (rate)) >> 20)
|
|
#define BYTES_TO_NS(bytes, rate) div64_u64(((u64)(bytes)) << 20, (u64)(rate))
|
|
|
|
struct bpf_map_def SEC("maps") queue_state = {
|
|
.type = BPF_MAP_TYPE_CGROUP_STORAGE,
|
|
.key_size = sizeof(struct bpf_cgroup_storage_key),
|
|
.value_size = sizeof(struct hbm_vqueue),
|
|
};
|
|
BPF_ANNOTATE_KV_PAIR(queue_state, struct bpf_cgroup_storage_key,
|
|
struct hbm_vqueue);
|
|
|
|
struct bpf_map_def SEC("maps") queue_stats = {
|
|
.type = BPF_MAP_TYPE_ARRAY,
|
|
.key_size = sizeof(u32),
|
|
.value_size = sizeof(struct hbm_queue_stats),
|
|
.max_entries = 1,
|
|
};
|
|
BPF_ANNOTATE_KV_PAIR(queue_stats, int, struct hbm_queue_stats);
|
|
|
|
struct hbm_pkt_info {
|
|
int cwnd;
|
|
int rtt;
|
|
int packets_out;
|
|
bool is_ip;
|
|
bool is_tcp;
|
|
short ecn;
|
|
};
|
|
|
|
static int get_tcp_info(struct __sk_buff *skb, struct hbm_pkt_info *pkti)
|
|
{
|
|
struct bpf_sock *sk;
|
|
struct bpf_tcp_sock *tp;
|
|
|
|
sk = skb->sk;
|
|
if (sk) {
|
|
sk = bpf_sk_fullsock(sk);
|
|
if (sk) {
|
|
if (sk->protocol == IPPROTO_TCP) {
|
|
tp = bpf_tcp_sock(sk);
|
|
if (tp) {
|
|
pkti->cwnd = tp->snd_cwnd;
|
|
pkti->rtt = tp->srtt_us >> 3;
|
|
pkti->packets_out = tp->packets_out;
|
|
return 0;
|
|
}
|
|
}
|
|
}
|
|
}
|
|
pkti->cwnd = 0;
|
|
pkti->rtt = 0;
|
|
pkti->packets_out = 0;
|
|
return 1;
|
|
}
|
|
|
|
static void hbm_get_pkt_info(struct __sk_buff *skb,
|
|
struct hbm_pkt_info *pkti)
|
|
{
|
|
struct iphdr iph;
|
|
struct ipv6hdr *ip6h;
|
|
|
|
pkti->cwnd = 0;
|
|
pkti->rtt = 0;
|
|
bpf_skb_load_bytes(skb, 0, &iph, 12);
|
|
if (iph.version == 6) {
|
|
ip6h = (struct ipv6hdr *)&iph;
|
|
pkti->is_ip = true;
|
|
pkti->is_tcp = (ip6h->nexthdr == 6);
|
|
pkti->ecn = (ip6h->flow_lbl[0] >> 4) & INET_ECN_MASK;
|
|
} else if (iph.version == 4) {
|
|
pkti->is_ip = true;
|
|
pkti->is_tcp = (iph.protocol == 6);
|
|
pkti->ecn = iph.tos & INET_ECN_MASK;
|
|
} else {
|
|
pkti->is_ip = false;
|
|
pkti->is_tcp = false;
|
|
pkti->ecn = 0;
|
|
}
|
|
if (pkti->is_tcp)
|
|
get_tcp_info(skb, pkti);
|
|
}
|
|
|
|
static __always_inline void hbm_init_vqueue(struct hbm_vqueue *qdp, int rate)
|
|
{
|
|
bpf_printk("Initializing queue_state, rate:%d\n", rate * 128);
|
|
qdp->lasttime = bpf_ktime_get_ns();
|
|
qdp->credit = INIT_CREDIT;
|
|
qdp->rate = rate * 128;
|
|
}
|
|
|
|
static __always_inline void hbm_init_edt_vqueue(struct hbm_vqueue *qdp,
|
|
int rate)
|
|
{
|
|
unsigned long long curtime;
|
|
|
|
curtime = bpf_ktime_get_ns();
|
|
bpf_printk("Initializing queue_state, rate:%d\n", rate * 128);
|
|
qdp->lasttime = curtime - BURST_SIZE_NS; // support initial burst
|
|
qdp->credit = 0; // not used
|
|
qdp->rate = rate * 128;
|
|
}
|
|
|
|
static __always_inline void hbm_update_stats(struct hbm_queue_stats *qsp,
|
|
int len,
|
|
unsigned long long curtime,
|
|
bool congestion_flag,
|
|
bool drop_flag,
|
|
bool cwr_flag,
|
|
bool ecn_ce_flag,
|
|
struct hbm_pkt_info *pkti,
|
|
int credit)
|
|
{
|
|
int rv = ALLOW_PKT;
|
|
|
|
if (qsp != NULL) {
|
|
// Following is needed for work conserving
|
|
__sync_add_and_fetch(&(qsp->bytes_total), len);
|
|
if (qsp->stats) {
|
|
// Optionally update statistics
|
|
if (qsp->firstPacketTime == 0)
|
|
qsp->firstPacketTime = curtime;
|
|
qsp->lastPacketTime = curtime;
|
|
__sync_add_and_fetch(&(qsp->pkts_total), 1);
|
|
if (congestion_flag) {
|
|
__sync_add_and_fetch(&(qsp->pkts_marked), 1);
|
|
__sync_add_and_fetch(&(qsp->bytes_marked), len);
|
|
}
|
|
if (drop_flag) {
|
|
__sync_add_and_fetch(&(qsp->pkts_dropped), 1);
|
|
__sync_add_and_fetch(&(qsp->bytes_dropped),
|
|
len);
|
|
}
|
|
if (ecn_ce_flag)
|
|
__sync_add_and_fetch(&(qsp->pkts_ecn_ce), 1);
|
|
if (pkti->cwnd) {
|
|
__sync_add_and_fetch(&(qsp->sum_cwnd),
|
|
pkti->cwnd);
|
|
__sync_add_and_fetch(&(qsp->sum_cwnd_cnt), 1);
|
|
}
|
|
if (pkti->rtt)
|
|
__sync_add_and_fetch(&(qsp->sum_rtt),
|
|
pkti->rtt);
|
|
__sync_add_and_fetch(&(qsp->sum_credit), credit);
|
|
|
|
if (drop_flag)
|
|
rv = DROP_PKT;
|
|
if (cwr_flag)
|
|
rv |= 2;
|
|
if (rv == DROP_PKT)
|
|
__sync_add_and_fetch(&(qsp->returnValCount[0]),
|
|
1);
|
|
else if (rv == ALLOW_PKT)
|
|
__sync_add_and_fetch(&(qsp->returnValCount[1]),
|
|
1);
|
|
else if (rv == 2)
|
|
__sync_add_and_fetch(&(qsp->returnValCount[2]),
|
|
1);
|
|
else if (rv == 3)
|
|
__sync_add_and_fetch(&(qsp->returnValCount[3]),
|
|
1);
|
|
}
|
|
}
|
|
}
|