samples/bpf: Add IO latency analysis (iosnoop/heatmap) tool

BPF C program attaches to
blk_mq_start_request()/blk_update_request() kprobe events to
calculate IO latency.

For every completed block IO event it computes the time delta
in nsec and records in a histogram map:

	map[log10(delta)*10]++

User space reads this histogram map every 2 seconds and prints
it as a 'heatmap' using gray shades of text terminal. Black
spaces have many events and white spaces have very few events.
Left most space is the smallest latency, right most space is
the largest latency in the range.

Usage:

	$ sudo ./tracex3
	and do 'sudo dd if=/dev/sda of=/dev/null' in other terminal.

Observe IO latencies and how different activity (like 'make
kernel') affects it.

Similar experiments can be done for network transmit latencies,
syscalls, etc.

'-t' flag prints the heatmap using normal ascii characters:

$ sudo ./tracex3 -t
  heatmap of IO latency
  # - many events with this latency
    - few events
	|1us      |10us     |100us    |1ms      |10ms     |100ms    |1s |10s
				 *ooo. *O.#.                                    # 221
			      .  *#     .                                       # 125
				 ..   .o#*..                                    # 55
			    .  . .  .  .#O                                      # 37
				 .#                                             # 175
				       .#*.                                     # 37
				  #                                             # 199
		      .              . *#*.                                     # 55
				       *#..*                                    # 42
				  #                                             # 266
			      ...***Oo#*OO**o#* .                               # 629
				  #                                             # 271
				      . .#o* o.*o*                              # 221
				. . o* *#O..                                    # 50

Signed-off-by: Alexei Starovoitov <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Daniel Borkmann <[email protected]>
Cc: David S. Miller <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Masami Hiramatsu <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Steven Rostedt <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

samples/bpf/Makefile

@@ -8,6 +8,7 @@ hostprogs-y += sockex1
 hostprogs-y += sockex2
 hostprogs-y += tracex1
 hostprogs-y += tracex2
+hostprogs-y += tracex3
 
 test_verifier-objs := test_verifier.o libbpf.o
 test_maps-objs := test_maps.o libbpf.o
@@ -16,13 +17,15 @@ sockex1-objs := bpf_load.o libbpf.o sockex1_user.o
 sockex2-objs := bpf_load.o libbpf.o sockex2_user.o
 tracex1-objs := bpf_load.o libbpf.o tracex1_user.o
 tracex2-objs := bpf_load.o libbpf.o tracex2_user.o
+tracex3-objs := bpf_load.o libbpf.o tracex3_user.o
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
 always += sockex1_kern.o
 always += sockex2_kern.o
 always += tracex1_kern.o
 always += tracex2_kern.o
+always += tracex3_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 
@@ -31,6 +34,7 @@ HOSTLOADLIBES_sockex1 += -lelf
 HOSTLOADLIBES_sockex2 += -lelf
 HOSTLOADLIBES_tracex1 += -lelf
 HOSTLOADLIBES_tracex2 += -lelf
+HOSTLOADLIBES_tracex3 += -lelf
 
 # point this to your LLVM backend with bpf support
 LLC=$(srctree)/tools/bpf/llvm/bld/Debug+Asserts/bin/llc

samples/bpf/tracex3_kern.c

@@ -0,0 +1,89 @@
+/* Copyright (c) 2013-2015 PLUMgrid, http://plumgrid.com
+ *
+ * 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 <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/version.h>
+#include <uapi/linux/bpf.h>
+#include "bpf_helpers.h"
+
+struct bpf_map_def SEC("maps") my_map = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(long),
+	.value_size = sizeof(u64),
+	.max_entries = 4096,
+};
+
+/* kprobe is NOT a stable ABI. If kernel internals change this bpf+kprobe
+ * example will no longer be meaningful
+ */
+SEC("kprobe/blk_mq_start_request")
+int bpf_prog1(struct pt_regs *ctx)
+{
+	long rq = ctx->di;
+	u64 val = bpf_ktime_get_ns();
+
+	bpf_map_update_elem(&my_map, &rq, &val, BPF_ANY);
+	return 0;
+}
+
+static unsigned int log2l(unsigned long long n)
+{
+#define S(k) if (n >= (1ull << k)) { i += k; n >>= k; }
+	int i = -(n == 0);
+	S(32); S(16); S(8); S(4); S(2); S(1);
+	return i;
+#undef S
+}
+
+#define SLOTS 100
+
+struct bpf_map_def SEC("maps") lat_map = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(u32),
+	.value_size = sizeof(u64),
+	.max_entries = SLOTS,
+};
+
+SEC("kprobe/blk_update_request")
+int bpf_prog2(struct pt_regs *ctx)
+{
+	long rq = ctx->di;
+	u64 *value, l, base;
+	u32 index;
+
+	value = bpf_map_lookup_elem(&my_map, &rq);
+	if (!value)
+		return 0;
+
+	u64 cur_time = bpf_ktime_get_ns();
+	u64 delta = cur_time - *value;
+
+	bpf_map_delete_elem(&my_map, &rq);
+
+	/* the lines below are computing index = log10(delta)*10
+	 * using integer arithmetic
+	 * index = 29 ~ 1 usec
+	 * index = 59 ~ 1 msec
+	 * index = 89 ~ 1 sec
+	 * index = 99 ~ 10sec or more
+	 * log10(x)*10 = log2(x)*10/log2(10) = log2(x)*3
+	 */
+	l = log2l(delta);
+	base = 1ll << l;
+	index = (l * 64 + (delta - base) * 64 / base) * 3 / 64;
+
+	if (index >= SLOTS)
+		index = SLOTS - 1;
+
+	value = bpf_map_lookup_elem(&lat_map, &index);
+	if (value)
+		__sync_fetch_and_add((long *)value, 1);
+
+	return 0;
+}
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;

samples/bpf/tracex3_user.c

@@ -0,0 +1,150 @@
+/* Copyright (c) 2013-2015 PLUMgrid, http://plumgrid.com
+ *
+ * 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 <stdio.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <unistd.h>
+#include <stdbool.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))
+
+#define SLOTS 100
+
+static void clear_stats(int fd)
+{
+	__u32 key;
+	__u64 value = 0;
+
+	for (key = 0; key < SLOTS; key++)
+		bpf_update_elem(fd, &key, &value, BPF_ANY);
+}
+
+const char *color[] = {
+	"\033[48;5;255m",
+	"\033[48;5;252m",
+	"\033[48;5;250m",
+	"\033[48;5;248m",
+	"\033[48;5;246m",
+	"\033[48;5;244m",
+	"\033[48;5;242m",
+	"\033[48;5;240m",
+	"\033[48;5;238m",
+	"\033[48;5;236m",
+	"\033[48;5;234m",
+	"\033[48;5;232m",
+};
+const int num_colors = ARRAY_SIZE(color);
+
+const char nocolor[] = "\033[00m";
+
+const char *sym[] = {
+	" ",
+	" ",
+	".",
+	".",
+	"*",
+	"*",
+	"o",
+	"o",
+	"O",
+	"O",
+	"#",
+	"#",
+};
+
+bool full_range = false;
+bool text_only = false;
+
+static void print_banner(void)
+{
+	if (full_range)
+		printf("|1ns     |10ns     |100ns    |1us      |10us     |100us"
+		       "    |1ms      |10ms     |100ms    |1s       |10s\n");
+	else
+		printf("|1us      |10us     |100us    |1ms      |10ms     "
+		       "|100ms    |1s       |10s\n");
+}
+
+static void print_hist(int fd)
+{
+	__u32 key;
+	__u64 value;
+	__u64 cnt[SLOTS];
+	__u64 max_cnt = 0;
+	__u64 total_events = 0;
+
+	for (key = 0; key < SLOTS; key++) {
+		value = 0;
+		bpf_lookup_elem(fd, &key, &value);
+		cnt[key] = value;
+		total_events += value;
+		if (value > max_cnt)
+			max_cnt = value;
+	}
+	clear_stats(fd);
+	for (key = full_range ? 0 : 29; key < SLOTS; key++) {
+		int c = num_colors * cnt[key] / (max_cnt + 1);
+
+		if (text_only)
+			printf("%s", sym[c]);
+		else
+			printf("%s %s", color[c], nocolor);
+	}
+	printf(" # %lld\n", total_events);
+}
+
+int main(int ac, char **argv)
+{
+	char filename[256];
+	int i;
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	if (load_bpf_file(filename)) {
+		printf("%s", bpf_log_buf);
+		return 1;
+	}
+
+	for (i = 1; i < ac; i++) {
+		if (strcmp(argv[i], "-a") == 0) {
+			full_range = true;
+		} else if (strcmp(argv[i], "-t") == 0) {
+			text_only = true;
+		} else if (strcmp(argv[i], "-h") == 0) {
+			printf("Usage:\n"
+			       "  -a display wider latency range\n"
+			       "  -t text only\n");
+			return 1;
+		}
+	}
+
+	printf("  heatmap of IO latency\n");
+	if (text_only)
+		printf("  %s", sym[num_colors - 1]);
+	else
+		printf("  %s %s", color[num_colors - 1], nocolor);
+	printf(" - many events with this latency\n");
+
+	if (text_only)
+		printf("  %s", sym[0]);
+	else
+		printf("  %s %s", color[0], nocolor);
+	printf(" - few events\n");
+
+	for (i = 0; ; i++) {
+		if (i % 20 == 0)
+			print_banner();
+		print_hist(map_fd[1]);
+		sleep(2);
+	}
+
+	return 0;
+}