summaryrefslogtreecommitdiffstats
path: root/samples
diff options
context:
space:
mode:
authorbrakmo <brakmo@fb.com>2019-03-01 12:38:49 -0800
committerAlexei Starovoitov <ast@kernel.org>2019-03-02 10:48:27 -0800
commita1270fe95b74eb3195b107c494ed1f11b932a278 (patch)
tree4e5c9ed3db58c84fc9bc094ef6a3f11d72147f89 /samples
parent187d0738ff351f725a58be3d606d3a7fc8db8aed (diff)
downloadlinux-stable-a1270fe95b74eb3195b107c494ed1f11b932a278.tar.gz
linux-stable-a1270fe95b74eb3195b107c494ed1f11b932a278.tar.bz2
linux-stable-a1270fe95b74eb3195b107c494ed1f11b932a278.zip
bpf: User program for testing HBM
The program nrm creates a cgroup and attaches a BPF program to the cgroup for testing HBM (Host Bandwidth Manager) for egress traffic. One still needs to create network traffic. This can be done through netesto, netperf or iperf3. A follow-up patch contains a script to create traffic. USAGE: hbm [-d] [-l] [-n <id>] [-r <rate>] [-s] [-t <secs>] [-w] [-h] [prog] Where: -d Print BPF trace debug buffer -l Also limit flows doing loopback -n <#> To create cgroup "/hbm#" and attach prog. Default is /nrm1 This is convenient when testing HBM in more than 1 cgroup -r <rate> Rate limit in Mbps -s Get HBM stats (marked, dropped, etc.) -t <time> Exit after specified seconds (deault is 0) -w Work conserving flag. cgroup can increase its bandwidth beyond the rate limit specified while there is available bandwidth. Current implementation assumes there is only NIC (eth0), but can be extended to support multiple NICs. Currrently only supported for egress. Note, this is just a proof of concept. -h Print this info prog BPF program file name. Name defaults to hbm_out_kern.o More information about HBM can be found in the paper "BPF Host Resource Management" presented at the 2018 Linux Plumbers Conference, Networking Track (http://vger.kernel.org/lpc_net2018_talks/LPC%20BPF%20Network%20Resource%20Paper.pdf) Signed-off-by: Lawrence Brakmo <brakmo@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Diffstat (limited to 'samples')
-rw-r--r--samples/bpf/Makefile3
-rw-r--r--samples/bpf/hbm.c441
2 files changed, 444 insertions, 0 deletions
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index e1bdc96486f6..65e667bdf979 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -52,6 +52,7 @@ hostprogs-y += xdpsock
hostprogs-y += xdp_fwd
hostprogs-y += task_fd_query
hostprogs-y += xdp_sample_pkts
+hostprogs-y += hbm
# Libbpf dependencies
LIBBPF = $(TOOLS_PATH)/lib/bpf/libbpf.a
@@ -107,6 +108,7 @@ xdpsock-objs := xdpsock_user.o
xdp_fwd-objs := xdp_fwd_user.o
task_fd_query-objs := bpf_load.o task_fd_query_user.o $(TRACE_HELPERS)
xdp_sample_pkts-objs := xdp_sample_pkts_user.o $(TRACE_HELPERS)
+hbm-objs := bpf_load.o hbm.o $(CGROUP_HELPERS)
# Tell kbuild to always build the programs
always := $(hostprogs-y)
@@ -265,6 +267,7 @@ $(src)/*.c: verify_target_bpf $(LIBBPF)
$(obj)/tracex5_kern.o: $(obj)/syscall_nrs.h
$(obj)/hbm_out_kern.o: $(src)/hbm.h $(src)/hbm_kern.h
+$(obj)/hbm.o: $(src)/hbm.h
# asm/sysreg.h - inline assembly used by it is incompatible with llvm.
# But, there is no easy way to fix it, so just exclude it since it is
diff --git a/samples/bpf/hbm.c b/samples/bpf/hbm.c
new file mode 100644
index 000000000000..8408ccb7409f
--- /dev/null
+++ b/samples/bpf/hbm.c
@@ -0,0 +1,441 @@
+// 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.
+ *
+ * Example program for Host Bandwidth Managment
+ *
+ * This program loads a cgroup skb BPF program to enforce cgroup output
+ * (egress) or input (ingress) bandwidth limits.
+ *
+ * USAGE: hbm [-d] [-l] [-n <id>] [-r <rate>] [-s] [-t <secs>] [-w] [-h] [prog]
+ * Where:
+ * -d Print BPF trace debug buffer
+ * -l Also limit flows doing loopback
+ * -n <#> To create cgroup \"/hbm#\" and attach prog
+ * Default is /hbm1
+ * -r <rate> Rate limit in Mbps
+ * -s Get HBM stats (marked, dropped, etc.)
+ * -t <time> Exit after specified seconds (deault is 0)
+ * -w Work conserving flag. cgroup can increase its bandwidth
+ * beyond the rate limit specified while there is available
+ * bandwidth. Current implementation assumes there is only
+ * NIC (eth0), but can be extended to support multiple NICs.
+ * Currrently only supported for egress.
+ * -h Print this info
+ * prog BPF program file name. Name defaults to hbm_out_kern.o
+ */
+
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <assert.h>
+#include <sys/resource.h>
+#include <sys/time.h>
+#include <unistd.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/unistd.h>
+
+#include <linux/bpf.h>
+#include <bpf/bpf.h>
+
+#include "bpf_load.h"
+#include "bpf_rlimit.h"
+#include "cgroup_helpers.h"
+#include "hbm.h"
+#include "bpf_util.h"
+#include "bpf/bpf.h"
+#include "bpf/libbpf.h"
+
+bool outFlag = true;
+int minRate = 1000; /* cgroup rate limit in Mbps */
+int rate = 1000; /* can grow if rate conserving is enabled */
+int dur = 1;
+bool stats_flag;
+bool loopback_flag;
+bool debugFlag;
+bool work_conserving_flag;
+
+static void Usage(void);
+static void read_trace_pipe2(void);
+static void do_error(char *msg, bool errno_flag);
+
+#define DEBUGFS "/sys/kernel/debug/tracing/"
+
+struct bpf_object *obj;
+int bpfprog_fd;
+int cgroup_storage_fd;
+
+static void read_trace_pipe2(void)
+{
+ int trace_fd;
+ FILE *outf;
+ char *outFname = "hbm_out.log";
+
+ trace_fd = open(DEBUGFS "trace_pipe", O_RDONLY, 0);
+ if (trace_fd < 0) {
+ printf("Error opening trace_pipe\n");
+ return;
+ }
+
+// Future support of ingress
+// if (!outFlag)
+// outFname = "hbm_in.log";
+ outf = fopen(outFname, "w");
+
+ if (outf == NULL)
+ printf("Error creating %s\n", outFname);
+
+ while (1) {
+ static char buf[4097];
+ ssize_t sz;
+
+ sz = read(trace_fd, buf, sizeof(buf) - 1);
+ if (sz > 0) {
+ buf[sz] = 0;
+ puts(buf);
+ if (outf != NULL) {
+ fprintf(outf, "%s\n", buf);
+ fflush(outf);
+ }
+ }
+ }
+}
+
+static void do_error(char *msg, bool errno_flag)
+{
+ if (errno_flag)
+ printf("ERROR: %s, errno: %d\n", msg, errno);
+ else
+ printf("ERROR: %s\n", msg);
+ exit(1);
+}
+
+static int prog_load(char *prog)
+{
+ struct bpf_prog_load_attr prog_load_attr = {
+ .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+ .file = prog,
+ .expected_attach_type = BPF_CGROUP_INET_EGRESS,
+ };
+ int map_fd;
+ struct bpf_map *map;
+
+ int ret = 0;
+
+ if (access(prog, O_RDONLY) < 0) {
+ printf("Error accessing file %s: %s\n", prog, strerror(errno));
+ return 1;
+ }
+ if (bpf_prog_load_xattr(&prog_load_attr, &obj, &bpfprog_fd))
+ ret = 1;
+ if (!ret) {
+ map = bpf_object__find_map_by_name(obj, "queue_stats");
+ map_fd = bpf_map__fd(map);
+ if (map_fd < 0) {
+ printf("Map not found: %s\n", strerror(map_fd));
+ ret = 1;
+ }
+ }
+
+ if (ret) {
+ printf("ERROR: load_bpf_file failed for: %s\n", prog);
+ printf(" Output from verifier:\n%s\n------\n", bpf_log_buf);
+ ret = -1;
+ } else {
+ ret = map_fd;
+ }
+
+ return ret;
+}
+
+static int run_bpf_prog(char *prog, int cg_id)
+{
+ int map_fd;
+ int rc = 0;
+ int key = 0;
+ int cg1 = 0;
+ int type = BPF_CGROUP_INET_EGRESS;
+ char cg_dir[100];
+ struct hbm_queue_stats qstats = {0};
+
+ sprintf(cg_dir, "/hbm%d", cg_id);
+ map_fd = prog_load(prog);
+ if (map_fd == -1)
+ return 1;
+
+ if (setup_cgroup_environment()) {
+ printf("ERROR: setting cgroup environment\n");
+ goto err;
+ }
+ cg1 = create_and_get_cgroup(cg_dir);
+ if (!cg1) {
+ printf("ERROR: create_and_get_cgroup\n");
+ goto err;
+ }
+ if (join_cgroup(cg_dir)) {
+ printf("ERROR: join_cgroup\n");
+ goto err;
+ }
+
+ qstats.rate = rate;
+ qstats.stats = stats_flag ? 1 : 0;
+ qstats.loopback = loopback_flag ? 1 : 0;
+ if (bpf_map_update_elem(map_fd, &key, &qstats, BPF_ANY)) {
+ printf("ERROR: Could not update map element\n");
+ goto err;
+ }
+
+ if (!outFlag)
+ type = BPF_CGROUP_INET_INGRESS;
+ if (bpf_prog_attach(bpfprog_fd, cg1, type, 0)) {
+ printf("ERROR: bpf_prog_attach fails!\n");
+ log_err("Attaching prog");
+ goto err;
+ }
+
+ if (work_conserving_flag) {
+ struct timeval t0, t_last, t_new;
+ FILE *fin;
+ unsigned long long last_eth_tx_bytes, new_eth_tx_bytes;
+ signed long long last_cg_tx_bytes, new_cg_tx_bytes;
+ signed long long delta_time, delta_bytes, delta_rate;
+ int delta_ms;
+#define DELTA_RATE_CHECK 10000 /* in us */
+#define RATE_THRESHOLD 9500000000 /* 9.5 Gbps */
+
+ bpf_map_lookup_elem(map_fd, &key, &qstats);
+ if (gettimeofday(&t0, NULL) < 0)
+ do_error("gettimeofday failed", true);
+ t_last = t0;
+ fin = fopen("/sys/class/net/eth0/statistics/tx_bytes", "r");
+ if (fscanf(fin, "%llu", &last_eth_tx_bytes) != 1)
+ do_error("fscanf fails", false);
+ fclose(fin);
+ last_cg_tx_bytes = qstats.bytes_total;
+ while (true) {
+ usleep(DELTA_RATE_CHECK);
+ if (gettimeofday(&t_new, NULL) < 0)
+ do_error("gettimeofday failed", true);
+ delta_ms = (t_new.tv_sec - t0.tv_sec) * 1000 +
+ (t_new.tv_usec - t0.tv_usec)/1000;
+ if (delta_ms > dur * 1000)
+ break;
+ delta_time = (t_new.tv_sec - t_last.tv_sec) * 1000000 +
+ (t_new.tv_usec - t_last.tv_usec);
+ if (delta_time == 0)
+ continue;
+ t_last = t_new;
+ fin = fopen("/sys/class/net/eth0/statistics/tx_bytes",
+ "r");
+ if (fscanf(fin, "%llu", &new_eth_tx_bytes) != 1)
+ do_error("fscanf fails", false);
+ fclose(fin);
+ printf(" new_eth_tx_bytes:%llu\n",
+ new_eth_tx_bytes);
+ bpf_map_lookup_elem(map_fd, &key, &qstats);
+ new_cg_tx_bytes = qstats.bytes_total;
+ delta_bytes = new_eth_tx_bytes - last_eth_tx_bytes;
+ last_eth_tx_bytes = new_eth_tx_bytes;
+ delta_rate = (delta_bytes * 8000000) / delta_time;
+ printf("%5d - eth_rate:%.1fGbps cg_rate:%.3fGbps",
+ delta_ms, delta_rate/1000000000.0,
+ rate/1000.0);
+ if (delta_rate < RATE_THRESHOLD) {
+ /* can increase cgroup rate limit, but first
+ * check if we are using the current limit.
+ * Currently increasing by 6.25%, unknown
+ * if that is the optimal rate.
+ */
+ int rate_diff100;
+
+ delta_bytes = new_cg_tx_bytes -
+ last_cg_tx_bytes;
+ last_cg_tx_bytes = new_cg_tx_bytes;
+ delta_rate = (delta_bytes * 8000000) /
+ delta_time;
+ printf(" rate:%.3fGbps",
+ delta_rate/1000000000.0);
+ rate_diff100 = (((long long)rate)*1000000 -
+ delta_rate) * 100 /
+ (((long long) rate) * 1000000);
+ printf(" rdiff:%d", rate_diff100);
+ if (rate_diff100 <= 3) {
+ rate += (rate >> 4);
+ if (rate > RATE_THRESHOLD / 1000000)
+ rate = RATE_THRESHOLD / 1000000;
+ qstats.rate = rate;
+ printf(" INC\n");
+ } else {
+ printf("\n");
+ }
+ } else {
+ /* Need to decrease cgroup rate limit.
+ * Currently decreasing by 12.5%, unknown
+ * if that is optimal
+ */
+ printf(" DEC\n");
+ rate -= (rate >> 3);
+ if (rate < minRate)
+ rate = minRate;
+ qstats.rate = rate;
+ }
+ if (bpf_map_update_elem(map_fd, &key, &qstats, BPF_ANY))
+ do_error("update map element fails", false);
+ }
+ } else {
+ sleep(dur);
+ }
+ // Get stats!
+ if (stats_flag && bpf_map_lookup_elem(map_fd, &key, &qstats)) {
+ char fname[100];
+ FILE *fout;
+
+ if (!outFlag)
+ sprintf(fname, "hbm.%d.in", cg_id);
+ else
+ sprintf(fname, "hbm.%d.out", cg_id);
+ fout = fopen(fname, "w");
+ fprintf(fout, "id:%d\n", cg_id);
+ fprintf(fout, "ERROR: Could not lookup queue_stats\n");
+ } else if (stats_flag && qstats.lastPacketTime >
+ qstats.firstPacketTime) {
+ long long delta_us = (qstats.lastPacketTime -
+ qstats.firstPacketTime)/1000;
+ unsigned int rate_mbps = ((qstats.bytes_total -
+ qstats.bytes_dropped) * 8 /
+ delta_us);
+ double percent_pkts, percent_bytes;
+ char fname[100];
+ FILE *fout;
+
+// Future support of ingress
+// if (!outFlag)
+// sprintf(fname, "hbm.%d.in", cg_id);
+// else
+ sprintf(fname, "hbm.%d.out", cg_id);
+ fout = fopen(fname, "w");
+ fprintf(fout, "id:%d\n", cg_id);
+ fprintf(fout, "rate_mbps:%d\n", rate_mbps);
+ fprintf(fout, "duration:%.1f secs\n",
+ (qstats.lastPacketTime - qstats.firstPacketTime) /
+ 1000000000.0);
+ fprintf(fout, "packets:%d\n", (int)qstats.pkts_total);
+ fprintf(fout, "bytes_MB:%d\n", (int)(qstats.bytes_total /
+ 1000000));
+ fprintf(fout, "pkts_dropped:%d\n", (int)qstats.pkts_dropped);
+ fprintf(fout, "bytes_dropped_MB:%d\n",
+ (int)(qstats.bytes_dropped /
+ 1000000));
+ // Marked Pkts and Bytes
+ percent_pkts = (qstats.pkts_marked * 100.0) /
+ (qstats.pkts_total + 1);
+ percent_bytes = (qstats.bytes_marked * 100.0) /
+ (qstats.bytes_total + 1);
+ fprintf(fout, "pkts_marked_percent:%6.2f\n", percent_pkts);
+ fprintf(fout, "bytes_marked_percent:%6.2f\n", percent_bytes);
+
+ // Dropped Pkts and Bytes
+ percent_pkts = (qstats.pkts_dropped * 100.0) /
+ (qstats.pkts_total + 1);
+ percent_bytes = (qstats.bytes_dropped * 100.0) /
+ (qstats.bytes_total + 1);
+ fprintf(fout, "pkts_dropped_percent:%6.2f\n", percent_pkts);
+ fprintf(fout, "bytes_dropped_percent:%6.2f\n", percent_bytes);
+ fclose(fout);
+ }
+
+ if (debugFlag)
+ read_trace_pipe2();
+ return rc;
+err:
+ rc = 1;
+
+ if (cg1)
+ close(cg1);
+ cleanup_cgroup_environment();
+
+ return rc;
+}
+
+static void Usage(void)
+{
+ printf("This program loads a cgroup skb BPF program to enforce\n"
+ "cgroup output (egress) bandwidth limits.\n\n"
+ "USAGE: hbm [-o] [-d] [-l] [-n <id>] [-r <rate>] [-s]\n"
+ " [-t <secs>] [-w] [-h] [prog]\n"
+ " Where:\n"
+ " -o indicates egress direction (default)\n"
+ " -d print BPF trace debug buffer\n"
+ " -l also limit flows using loopback\n"
+ " -n <#> to create cgroup \"/hbm#\" and attach prog\n"
+ " Default is /hbm1\n"
+ " -r <rate> Rate in Mbps\n"
+ " -s Update HBM stats\n"
+ " -t <time> Exit after specified seconds (deault is 0)\n"
+ " -w Work conserving flag. cgroup can increase\n"
+ " bandwidth beyond the rate limit specified\n"
+ " while there is available bandwidth. Current\n"
+ " implementation assumes there is only eth0\n"
+ " but can be extended to support multiple NICs\n"
+ " -h print this info\n"
+ " prog BPF program file name. Name defaults to\n"
+ " hbm_out_kern.o\n");
+}
+
+int main(int argc, char **argv)
+{
+ char *prog = "hbm_out_kern.o";
+ int k;
+ int cg_id = 1;
+ char *optstring = "iodln:r:st:wh";
+
+ while ((k = getopt(argc, argv, optstring)) != -1) {
+ switch (k) {
+ case'o':
+ break;
+ case 'd':
+ debugFlag = true;
+ break;
+ case 'l':
+ loopback_flag = true;
+ break;
+ case 'n':
+ cg_id = atoi(optarg);
+ break;
+ case 'r':
+ minRate = atoi(optarg) * 1.024;
+ rate = minRate;
+ break;
+ case 's':
+ stats_flag = true;
+ break;
+ case 't':
+ dur = atoi(optarg);
+ break;
+ case 'w':
+ work_conserving_flag = true;
+ break;
+ case '?':
+ if (optopt == 'n' || optopt == 'r' || optopt == 't')
+ fprintf(stderr,
+ "Option -%c requires an argument.\n\n",
+ optopt);
+ case 'h':
+ // fallthrough
+ default:
+ Usage();
+ return 0;
+ }
+ }
+
+ if (optind < argc)
+ prog = argv[optind];
+ printf("HBM prog: %s\n", prog != NULL ? prog : "NULL");
+
+ return run_bpf_prog(prog, cg_id);
+}