samples/bpf: program demonstrating access to xdp_rxq_info

This sample program can be used for monitoring and reporting how many
packets per sec (pps) are received per NIC RX queue index and which
CPU processed the packet. In itself it is a useful tool for quickly
identifying RSS imbalance issues, see below.

The default XDP action is XDP_PASS in-order to provide a monitor
mode. For benchmarking purposes it is possible to specify other XDP
actions on the cmdline --action.

Output below shows an imbalance RSS case where most RXQ's deliver to
CPU-0 while CPU-2 only get packets from a single RXQ.  Looking at
things from a CPU level the two CPUs are processing approx the same
amount, BUT looking at the rx_queue_index levels it is clear that
RXQ-2 receive much better service, than other RXQs which all share CPU-0.

Running XDP on dev:i40e1 (ifindex:3) action:XDP_PASS
XDP stats       CPU     pps         issue-pps
XDP-RX CPU      0       900,473     0
XDP-RX CPU      2       906,921     0
XDP-RX CPU      total   1,807,395

RXQ stats       RXQ:CPU pps         issue-pps
rx_queue_index    0:0   180,098     0
rx_queue_index    0:sum 180,098
rx_queue_index    1:0   180,098     0
rx_queue_index    1:sum 180,098
rx_queue_index    2:2   906,921     0
rx_queue_index    2:sum 906,921
rx_queue_index    3:0   180,098     0
rx_queue_index    3:sum 180,098
rx_queue_index    4:0   180,082     0
rx_queue_index    4:sum 180,082
rx_queue_index    5:0   180,093     0
rx_queue_index    5:sum 180,093

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This commit is contained in:
Jesper Dangaard Brouer 2018-01-03 11:26:19 +01:00 committed by Alexei Starovoitov
parent 02dd3291b2
commit 0fca931a6f
3 changed files with 631 additions and 0 deletions

View file

@ -41,6 +41,7 @@ hostprogs-y += xdp_redirect
hostprogs-y += xdp_redirect_map
hostprogs-y += xdp_redirect_cpu
hostprogs-y += xdp_monitor
hostprogs-y += xdp_rxq_info
hostprogs-y += syscall_tp
# Libbpf dependencies
@ -90,6 +91,7 @@ xdp_redirect-objs := bpf_load.o $(LIBBPF) xdp_redirect_user.o
xdp_redirect_map-objs := bpf_load.o $(LIBBPF) xdp_redirect_map_user.o
xdp_redirect_cpu-objs := bpf_load.o $(LIBBPF) xdp_redirect_cpu_user.o
xdp_monitor-objs := bpf_load.o $(LIBBPF) xdp_monitor_user.o
xdp_rxq_info-objs := bpf_load.o $(LIBBPF) xdp_rxq_info_user.o
syscall_tp-objs := bpf_load.o $(LIBBPF) syscall_tp_user.o
# Tell kbuild to always build the programs
@ -139,6 +141,7 @@ always += xdp_redirect_kern.o
always += xdp_redirect_map_kern.o
always += xdp_redirect_cpu_kern.o
always += xdp_monitor_kern.o
always += xdp_rxq_info_kern.o
always += syscall_tp_kern.o
HOSTCFLAGS += -I$(objtree)/usr/include
@ -182,6 +185,7 @@ HOSTLOADLIBES_xdp_redirect += -lelf
HOSTLOADLIBES_xdp_redirect_map += -lelf
HOSTLOADLIBES_xdp_redirect_cpu += -lelf
HOSTLOADLIBES_xdp_monitor += -lelf
HOSTLOADLIBES_xdp_rxq_info += -lelf
HOSTLOADLIBES_syscall_tp += -lelf
# Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:

View file

@ -0,0 +1,96 @@
/* SPDX-License-Identifier: GPL-2.0
* Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc.
*
* Example howto extract XDP RX-queue info
*/
#include <uapi/linux/bpf.h>
#include "bpf_helpers.h"
/* Config setup from with userspace
*
* User-side setup ifindex in config_map, to verify that
* ctx->ingress_ifindex is correct (against configured ifindex)
*/
struct config {
__u32 action;
int ifindex;
};
struct bpf_map_def SEC("maps") config_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(struct config),
.max_entries = 1,
};
/* Common stats data record (shared with userspace) */
struct datarec {
__u64 processed;
__u64 issue;
};
struct bpf_map_def SEC("maps") stats_global_map = {
.type = BPF_MAP_TYPE_PERCPU_ARRAY,
.key_size = sizeof(u32),
.value_size = sizeof(struct datarec),
.max_entries = 1,
};
#define MAX_RXQs 64
/* Stats per rx_queue_index (per CPU) */
struct bpf_map_def SEC("maps") rx_queue_index_map = {
.type = BPF_MAP_TYPE_PERCPU_ARRAY,
.key_size = sizeof(u32),
.value_size = sizeof(struct datarec),
.max_entries = MAX_RXQs + 1,
};
SEC("xdp_prog0")
int xdp_prognum0(struct xdp_md *ctx)
{
void *data_end = (void *)(long)ctx->data_end;
void *data = (void *)(long)ctx->data;
struct datarec *rec, *rxq_rec;
int ingress_ifindex;
struct config *config;
u32 key = 0;
/* Global stats record */
rec = bpf_map_lookup_elem(&stats_global_map, &key);
if (!rec)
return XDP_ABORTED;
rec->processed++;
/* Accessing ctx->ingress_ifindex, cause BPF to rewrite BPF
* instructions inside kernel to access xdp_rxq->dev->ifindex
*/
ingress_ifindex = ctx->ingress_ifindex;
config = bpf_map_lookup_elem(&config_map, &key);
if (!config)
return XDP_ABORTED;
/* Simple test: check ctx provided ifindex is as expected */
if (ingress_ifindex != config->ifindex) {
/* count this error case */
rec->issue++;
return XDP_ABORTED;
}
/* Update stats per rx_queue_index. Handle if rx_queue_index
* is larger than stats map can contain info for.
*/
key = ctx->rx_queue_index;
if (key >= MAX_RXQs)
key = MAX_RXQs;
rxq_rec = bpf_map_lookup_elem(&rx_queue_index_map, &key);
if (!rxq_rec)
return XDP_ABORTED;
rxq_rec->processed++;
if (key == MAX_RXQs)
rxq_rec->issue++;
return config->action;
}
char _license[] SEC("license") = "GPL";

View file

@ -0,0 +1,531 @@
/* SPDX-License-Identifier: GPL-2.0
* Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc.
*/
static const char *__doc__ = " XDP RX-queue info extract example\n\n"
"Monitor how many packets per sec (pps) are received\n"
"per NIC RX queue index and which CPU processed the packet\n"
;
#include <errno.h>
#include <signal.h>
#include <stdio.h>
#include <stdlib.h>
#include <stdbool.h>
#include <string.h>
#include <unistd.h>
#include <locale.h>
#include <sys/resource.h>
#include <getopt.h>
#include <net/if.h>
#include <time.h>
#include <arpa/inet.h>
#include <linux/if_link.h>
#include "libbpf.h"
#include "bpf_load.h"
#include "bpf_util.h"
static int ifindex = -1;
static char ifname_buf[IF_NAMESIZE];
static char *ifname;
static __u32 xdp_flags;
/* Exit return codes */
#define EXIT_OK 0
#define EXIT_FAIL 1
#define EXIT_FAIL_OPTION 2
#define EXIT_FAIL_XDP 3
#define EXIT_FAIL_BPF 4
#define EXIT_FAIL_MEM 5
static const struct option long_options[] = {
{"help", no_argument, NULL, 'h' },
{"dev", required_argument, NULL, 'd' },
{"skb-mode", no_argument, NULL, 'S' },
{"sec", required_argument, NULL, 's' },
{"no-separators", no_argument, NULL, 'z' },
{"action", required_argument, NULL, 'a' },
{0, 0, NULL, 0 }
};
static void int_exit(int sig)
{
fprintf(stderr,
"Interrupted: Removing XDP program on ifindex:%d device:%s\n",
ifindex, ifname);
if (ifindex > -1)
set_link_xdp_fd(ifindex, -1, xdp_flags);
exit(EXIT_OK);
}
struct config {
__u32 action;
int ifindex;
};
#define XDP_ACTION_MAX (XDP_TX + 1)
#define XDP_ACTION_MAX_STRLEN 11
static const char *xdp_action_names[XDP_ACTION_MAX] = {
[XDP_ABORTED] = "XDP_ABORTED",
[XDP_DROP] = "XDP_DROP",
[XDP_PASS] = "XDP_PASS",
[XDP_TX] = "XDP_TX",
};
static const char *action2str(int action)
{
if (action < XDP_ACTION_MAX)
return xdp_action_names[action];
return NULL;
}
static int parse_xdp_action(char *action_str)
{
size_t maxlen;
__u64 action = -1;
int i;
for (i = 0; i < XDP_ACTION_MAX; i++) {
maxlen = XDP_ACTION_MAX_STRLEN;
if (strncmp(xdp_action_names[i], action_str, maxlen) == 0) {
action = i;
break;
}
}
return action;
}
static void list_xdp_actions(void)
{
int i;
printf("Available XDP --action <options>\n");
for (i = 0; i < XDP_ACTION_MAX; i++)
printf("\t%s\n", xdp_action_names[i]);
printf("\n");
}
static void usage(char *argv[])
{
int i;
printf("\nDOCUMENTATION:\n%s\n", __doc__);
printf(" Usage: %s (options-see-below)\n", argv[0]);
printf(" Listing options:\n");
for (i = 0; long_options[i].name != 0; i++) {
printf(" --%-12s", long_options[i].name);
if (long_options[i].flag != NULL)
printf(" flag (internal value:%d)",
*long_options[i].flag);
else
printf(" short-option: -%c",
long_options[i].val);
printf("\n");
}
printf("\n");
list_xdp_actions();
}
#define NANOSEC_PER_SEC 1000000000 /* 10^9 */
static __u64 gettime(void)
{
struct timespec t;
int res;
res = clock_gettime(CLOCK_MONOTONIC, &t);
if (res < 0) {
fprintf(stderr, "Error with gettimeofday! (%i)\n", res);
exit(EXIT_FAIL);
}
return (__u64) t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec;
}
/* Common stats data record shared with _kern.c */
struct datarec {
__u64 processed;
__u64 issue;
};
struct record {
__u64 timestamp;
struct datarec total;
struct datarec *cpu;
};
struct stats_record {
struct record stats;
struct record *rxq;
};
static struct datarec *alloc_record_per_cpu(void)
{
unsigned int nr_cpus = bpf_num_possible_cpus();
struct datarec *array;
size_t size;
size = sizeof(struct datarec) * nr_cpus;
array = malloc(size);
memset(array, 0, size);
if (!array) {
fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus);
exit(EXIT_FAIL_MEM);
}
return array;
}
static struct record *alloc_record_per_rxq(void)
{
unsigned int nr_rxqs = map_data[2].def.max_entries;
struct record *array;
size_t size;
size = sizeof(struct record) * nr_rxqs;
array = malloc(size);
memset(array, 0, size);
if (!array) {
fprintf(stderr, "Mem alloc error (nr_rxqs:%u)\n", nr_rxqs);
exit(EXIT_FAIL_MEM);
}
return array;
}
static struct stats_record *alloc_stats_record(void)
{
unsigned int nr_rxqs = map_data[2].def.max_entries;
struct stats_record *rec;
int i;
rec = malloc(sizeof(*rec));
memset(rec, 0, sizeof(*rec));
if (!rec) {
fprintf(stderr, "Mem alloc error\n");
exit(EXIT_FAIL_MEM);
}
rec->rxq = alloc_record_per_rxq();
for (i = 0; i < nr_rxqs; i++)
rec->rxq[i].cpu = alloc_record_per_cpu();
rec->stats.cpu = alloc_record_per_cpu();
return rec;
}
static void free_stats_record(struct stats_record *r)
{
unsigned int nr_rxqs = map_data[2].def.max_entries;
int i;
for (i = 0; i < nr_rxqs; i++)
free(r->rxq[i].cpu);
free(r->rxq);
free(r->stats.cpu);
free(r);
}
static bool map_collect_percpu(int fd, __u32 key, struct record *rec)
{
/* For percpu maps, userspace gets a value per possible CPU */
unsigned int nr_cpus = bpf_num_possible_cpus();
struct datarec values[nr_cpus];
__u64 sum_processed = 0;
__u64 sum_issue = 0;
int i;
if ((bpf_map_lookup_elem(fd, &key, values)) != 0) {
fprintf(stderr,
"ERR: bpf_map_lookup_elem failed key:0x%X\n", key);
return false;
}
/* Get time as close as possible to reading map contents */
rec->timestamp = gettime();
/* Record and sum values from each CPU */
for (i = 0; i < nr_cpus; i++) {
rec->cpu[i].processed = values[i].processed;
sum_processed += values[i].processed;
rec->cpu[i].issue = values[i].issue;
sum_issue += values[i].issue;
}
rec->total.processed = sum_processed;
rec->total.issue = sum_issue;
return true;
}
static void stats_collect(struct stats_record *rec)
{
int fd, i, max_rxqs;
fd = map_data[1].fd; /* map: stats_global_map */
map_collect_percpu(fd, 0, &rec->stats);
fd = map_data[2].fd; /* map: rx_queue_index_map */
max_rxqs = map_data[2].def.max_entries;
for (i = 0; i < max_rxqs; i++)
map_collect_percpu(fd, i, &rec->rxq[i]);
}
static double calc_period(struct record *r, struct record *p)
{
double period_ = 0;
__u64 period = 0;
period = r->timestamp - p->timestamp;
if (period > 0)
period_ = ((double) period / NANOSEC_PER_SEC);
return period_;
}
static __u64 calc_pps(struct datarec *r, struct datarec *p, double period_)
{
__u64 packets = 0;
__u64 pps = 0;
if (period_ > 0) {
packets = r->processed - p->processed;
pps = packets / period_;
}
return pps;
}
static __u64 calc_errs_pps(struct datarec *r,
struct datarec *p, double period_)
{
__u64 packets = 0;
__u64 pps = 0;
if (period_ > 0) {
packets = r->issue - p->issue;
pps = packets / period_;
}
return pps;
}
static void stats_print(struct stats_record *stats_rec,
struct stats_record *stats_prev,
int action)
{
unsigned int nr_cpus = bpf_num_possible_cpus();
unsigned int nr_rxqs = map_data[2].def.max_entries;
double pps = 0, err = 0;
struct record *rec, *prev;
double t;
int rxq;
int i;
/* Header */
printf("\nRunning XDP on dev:%s (ifindex:%d) action:%s\n",
ifname, ifindex, action2str(action));
/* stats_global_map */
{
char *fmt_rx = "%-15s %-7d %'-11.0f %'-10.0f %s\n";
char *fm2_rx = "%-15s %-7s %'-11.0f\n";
char *errstr = "";
printf("%-15s %-7s %-11s %-11s\n",
"XDP stats", "CPU", "pps", "issue-pps");
rec = &stats_rec->stats;
prev = &stats_prev->stats;
t = calc_period(rec, prev);
for (i = 0; i < nr_cpus; i++) {
struct datarec *r = &rec->cpu[i];
struct datarec *p = &prev->cpu[i];
pps = calc_pps (r, p, t);
err = calc_errs_pps(r, p, t);
if (err > 0)
errstr = "invalid-ifindex";
if (pps > 0)
printf(fmt_rx, "XDP-RX CPU",
i, pps, err, errstr);
}
pps = calc_pps (&rec->total, &prev->total, t);
err = calc_errs_pps(&rec->total, &prev->total, t);
printf(fm2_rx, "XDP-RX CPU", "total", pps, err);
}
/* rx_queue_index_map */
printf("\n%-15s %-7s %-11s %-11s\n",
"RXQ stats", "RXQ:CPU", "pps", "issue-pps");
for (rxq = 0; rxq < nr_rxqs; rxq++) {
char *fmt_rx = "%-15s %3d:%-3d %'-11.0f %'-10.0f %s\n";
char *fm2_rx = "%-15s %3d:%-3s %'-11.0f\n";
char *errstr = "";
int rxq_ = rxq;
/* Last RXQ in map catch overflows */
if (rxq_ == nr_rxqs - 1)
rxq_ = -1;
rec = &stats_rec->rxq[rxq];
prev = &stats_prev->rxq[rxq];
t = calc_period(rec, prev);
for (i = 0; i < nr_cpus; i++) {
struct datarec *r = &rec->cpu[i];
struct datarec *p = &prev->cpu[i];
pps = calc_pps (r, p, t);
err = calc_errs_pps(r, p, t);
if (err > 0) {
if (rxq_ == -1)
errstr = "map-overflow-RXQ";
else
errstr = "err";
}
if (pps > 0)
printf(fmt_rx, "rx_queue_index",
rxq_, i, pps, err, errstr);
}
pps = calc_pps (&rec->total, &prev->total, t);
err = calc_errs_pps(&rec->total, &prev->total, t);
if (pps || err)
printf(fm2_rx, "rx_queue_index", rxq_, "sum", pps, err);
}
}
/* Pointer swap trick */
static inline void swap(struct stats_record **a, struct stats_record **b)
{
struct stats_record *tmp;
tmp = *a;
*a = *b;
*b = tmp;
}
static void stats_poll(int interval, int action)
{
struct stats_record *record, *prev;
record = alloc_stats_record();
prev = alloc_stats_record();
stats_collect(record);
while (1) {
swap(&prev, &record);
stats_collect(record);
stats_print(record, prev, action);
sleep(interval);
}
free_stats_record(record);
free_stats_record(prev);
}
int main(int argc, char **argv)
{
struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
bool use_separators = true;
struct config cfg = { 0 };
char filename[256];
int longindex = 0;
int interval = 2;
__u32 key = 0;
int opt, err;
char action_str_buf[XDP_ACTION_MAX_STRLEN + 1 /* for \0 */] = { 0 };
int action = XDP_PASS; /* Default action */
char *action_str = NULL;
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
if (setrlimit(RLIMIT_MEMLOCK, &r)) {
perror("setrlimit(RLIMIT_MEMLOCK)");
return 1;
}
if (load_bpf_file(filename)) {
fprintf(stderr, "ERR in load_bpf_file(): %s", bpf_log_buf);
return EXIT_FAIL;
}
if (!prog_fd[0]) {
fprintf(stderr, "ERR: load_bpf_file: %s\n", strerror(errno));
return EXIT_FAIL;
}
/* Parse commands line args */
while ((opt = getopt_long(argc, argv, "hSd:",
long_options, &longindex)) != -1) {
switch (opt) {
case 'd':
if (strlen(optarg) >= IF_NAMESIZE) {
fprintf(stderr, "ERR: --dev name too long\n");
goto error;
}
ifname = (char *)&ifname_buf;
strncpy(ifname, optarg, IF_NAMESIZE);
ifindex = if_nametoindex(ifname);
if (ifindex == 0) {
fprintf(stderr,
"ERR: --dev name unknown err(%d):%s\n",
errno, strerror(errno));
goto error;
}
break;
case 's':
interval = atoi(optarg);
break;
case 'S':
xdp_flags |= XDP_FLAGS_SKB_MODE;
break;
case 'z':
use_separators = false;
break;
case 'a':
action_str = (char *)&action_str_buf;
strncpy(action_str, optarg, XDP_ACTION_MAX_STRLEN);
break;
case 'h':
error:
default:
usage(argv);
return EXIT_FAIL_OPTION;
}
}
/* Required option */
if (ifindex == -1) {
fprintf(stderr, "ERR: required option --dev missing\n");
usage(argv);
return EXIT_FAIL_OPTION;
}
cfg.ifindex = ifindex;
/* Parse action string */
if (action_str) {
action = parse_xdp_action(action_str);
if (action < 0) {
fprintf(stderr, "ERR: Invalid XDP --action: %s\n",
action_str);
list_xdp_actions();
return EXIT_FAIL_OPTION;
}
}
cfg.action = action;
/* Trick to pretty printf with thousands separators use %' */
if (use_separators)
setlocale(LC_NUMERIC, "en_US");
/* User-side setup ifindex in config_map */
err = bpf_map_update_elem(map_fd[0], &key, &cfg, 0);
if (err) {
fprintf(stderr, "Store config failed (err:%d)\n", err);
exit(EXIT_FAIL_BPF);
}
/* Remove XDP program when program is interrupted */
signal(SIGINT, int_exit);
if (set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
fprintf(stderr, "link set xdp fd failed\n");
return EXIT_FAIL_XDP;
}
stats_poll(interval, action);
return EXIT_OK;
}