1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835
|
/*
* Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
*
* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; version 2 of the License (not later!)
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, see <http://www.gnu.org/licenses>
*
* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*/
#define _LARGEFILE64_SOURCE
#include <dirent.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <getopt.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <sys/wait.h>
#include <netdb.h>
#include <unistd.h>
#include <fcntl.h>
#include <signal.h>
#include <errno.h>
#include "trace-local.h"
#define MAX_OPTION_SIZE 4096
static char *default_output_dir = ".";
static char *output_dir;
static char *default_output_file = "trace";
static char *output_file;
static FILE *logfp;
static int debug;
static int use_tcp;
static int backlog = 5;
#define TEMP_FILE_STR "%s.%s:%s.cpu%d", output_file, host, port, cpu
static char *get_temp_file(const char *host, const char *port, int cpu)
{
char *file = NULL;
int size;
size = snprintf(file, 0, TEMP_FILE_STR);
file = malloc_or_die(size + 1);
sprintf(file, TEMP_FILE_STR);
return file;
}
static void put_temp_file(char *file)
{
free(file);
}
#define MAX_PATH 1024
static void signal_setup(int sig, sighandler_t handle)
{
struct sigaction action;
sigaction(sig, NULL, &action);
/* Make accept return EINTR */
action.sa_flags &= ~SA_RESTART;
action.sa_handler = handle;
sigaction(sig, &action, NULL);
}
static void delete_temp_file(const char *host, const char *port, int cpu)
{
char file[MAX_PATH];
snprintf(file, MAX_PATH, TEMP_FILE_STR);
unlink(file);
}
static int read_string(int fd, char *buf, size_t size)
{
size_t i;
int n;
for (i = 0; i < size; i++) {
n = read(fd, buf+i, 1);
if (!buf[i] || n <= 0)
break;
}
return i;
}
static int process_option(char *option)
{
/* currently the only option we have is to us TCP */
if (strcmp(option, "TCP") == 0) {
use_tcp = 1;
return 1;
}
return 0;
}
static int done;
static void finish(int sig)
{
done = 1;
}
#define LOG_BUF_SIZE 1024
static void __plog(const char *prefix, const char *fmt, va_list ap,
FILE *fp)
{
static int newline = 1;
char buf[LOG_BUF_SIZE];
int r;
r = vsnprintf(buf, LOG_BUF_SIZE, fmt, ap);
if (r > LOG_BUF_SIZE)
r = LOG_BUF_SIZE;
if (logfp) {
if (newline)
fprintf(logfp, "[%d]%s%.*s", getpid(), prefix, r, buf);
else
fprintf(logfp, "[%d]%s%.*s", getpid(), prefix, r, buf);
newline = buf[r - 1] == '\n';
fflush(logfp);
return;
}
fprintf(fp, "%.*s", r, buf);
}
static void plog(const char *fmt, ...)
{
va_list ap;
va_start(ap, fmt);
__plog("", fmt, ap, stdout);
va_end(ap);
}
static void pdie(const char *fmt, ...)
{
va_list ap;
char *str = "";
va_start(ap, fmt);
__plog("Error: ", fmt, ap, stderr);
va_end(ap);
if (errno)
str = strerror(errno);
if (logfp)
fprintf(logfp, "\n%s\n", str);
else
fprintf(stderr, "\n%s\n", str);
exit(-1);
}
static void process_udp_child(int sfd, const char *host, const char *port,
int cpu, int page_size)
{
struct sockaddr_storage peer_addr;
socklen_t peer_addr_len;
char buf[page_size];
char *tempfile;
int cfd;
int fd;
int n;
int once = 0;
signal_setup(SIGUSR1, finish);
tempfile = get_temp_file(host, port, cpu);
fd = open(tempfile, O_WRONLY | O_TRUNC | O_CREAT, 0644);
if (fd < 0)
pdie("creating %s", tempfile);
if (use_tcp) {
if (listen(sfd, backlog) < 0)
pdie("listen");
peer_addr_len = sizeof(peer_addr);
cfd = accept(sfd, (struct sockaddr *)&peer_addr, &peer_addr_len);
if (cfd < 0 && errno == EINTR)
goto done;
if (cfd < 0)
pdie("accept");
close(sfd);
sfd = cfd;
}
do {
/* TODO, make this copyless! */
n = read(sfd, buf, page_size);
if (n < 0) {
if (errno == EINTR)
continue;
pdie("reading client");
}
if (!n)
break;
/* UDP requires that we get the full size in one go */
if (!use_tcp && n < page_size && !once) {
once = 1;
warning("read %d bytes, expected %d", n, page_size);
}
write(fd, buf, n);
} while (!done);
done:
put_temp_file(tempfile);
exit(0);
}
#define START_PORT_SEARCH 1500
#define MAX_PORT_SEARCH 6000
static int udp_bind_a_port(int start_port, int *sfd)
{
struct addrinfo hints;
struct addrinfo *result, *rp;
char buf[BUFSIZ];
int s;
int num_port = start_port;
again:
snprintf(buf, BUFSIZ, "%d", num_port);
memset(&hints, 0, sizeof(hints));
hints.ai_family = AF_UNSPEC;
hints.ai_socktype = use_tcp ? SOCK_STREAM : SOCK_DGRAM;
hints.ai_flags = AI_PASSIVE;
s = getaddrinfo(NULL, buf, &hints, &result);
if (s != 0)
pdie("getaddrinfo: error opening udp socket");
for (rp = result; rp != NULL; rp = rp->ai_next) {
*sfd = socket(rp->ai_family, rp->ai_socktype,
rp->ai_protocol);
if (*sfd < 0)
continue;
if (bind(*sfd, rp->ai_addr, rp->ai_addrlen) == 0)
break;
close(*sfd);
}
if (rp == NULL) {
freeaddrinfo(result);
if (++num_port > MAX_PORT_SEARCH)
pdie("No available ports to bind");
goto again;
}
freeaddrinfo(result);
return num_port;
}
static void fork_udp_reader(int sfd, const char *node, const char *port,
int *pid, int cpu, int pagesize)
{
*pid = fork();
if (*pid < 0)
pdie("creating udp reader");
if (!*pid)
process_udp_child(sfd, node, port, cpu, pagesize);
close(sfd);
}
static int open_udp(const char *node, const char *port, int *pid,
int cpu, int pagesize, int start_port)
{
int sfd;
int num_port;
/*
* udp_bind_a_port() currently does not return an error, but if that
* changes in the future, we have a check for it now.
*/
num_port = udp_bind_a_port(start_port, &sfd);
if (num_port < 0)
return num_port;
fork_udp_reader(sfd, node, port, pid, cpu, pagesize);
return num_port;
}
static int communicate_with_client(int fd, int *cpus, int *pagesize)
{
char buf[BUFSIZ];
char *option;
int options;
int size;
int n, s, t, i;
/* Let the client know what we are */
write(fd, "tracecmd", 8);
/* read back the CPU count */
n = read_string(fd, buf, BUFSIZ);
if (n == BUFSIZ)
/** ERROR **/
return -1;
*cpus = atoi(buf);
plog("cpus=%d\n", *cpus);
if (*cpus < 0)
return -1;
/* next read the page size */
n = read_string(fd, buf, BUFSIZ);
if (n == BUFSIZ)
/** ERROR **/
return -1;
*pagesize = atoi(buf);
plog("pagesize=%d\n", *pagesize);
if (*pagesize <= 0)
return -1;
/* Now the number of options */
n = read_string(fd, buf, BUFSIZ);
if (n == BUFSIZ)
/** ERROR **/
return -1;
options = atoi(buf);
for (i = 0; i < options; i++) {
/* next is the size of the options */
n = read_string(fd, buf, BUFSIZ);
if (n == BUFSIZ)
/** ERROR **/
return -1;
size = atoi(buf);
/* prevent a client from killing us */
if (size > MAX_OPTION_SIZE)
return -1;
option = malloc_or_die(size);
do {
t = size;
s = 0;
s = read(fd, option+s, t);
if (s <= 0)
return -1;
t -= s;
s = size - t;
} while (t);
s = process_option(option);
free(option);
/* do we understand this option? */
if (!s)
return -1;
}
if (use_tcp)
plog("Using TCP for live connection\n");
return 0;
}
static int create_client_file(const char *node, const char *port)
{
char buf[BUFSIZ];
int ofd;
snprintf(buf, BUFSIZ, "%s.%s:%s.dat", output_file, node, port);
ofd = open(buf, O_RDWR | O_CREAT | O_TRUNC, 0644);
if (ofd < 0)
pdie("Can not create file %s", buf);
return ofd;
}
static void destroy_all_readers(int cpus, int *pid_array, const char *node,
const char *port)
{
int cpu;
for (cpu = 0; cpu < cpus; cpu++) {
if (pid_array[cpu] > 0) {
kill(pid_array[cpu], SIGKILL);
waitpid(pid_array[cpu], NULL, 0);
delete_temp_file(node, port, cpu);
pid_array[cpu] = 0;
}
}
}
static int *create_all_readers(int cpus, const char *node, const char *port,
int pagesize, int fd)
{
char buf[BUFSIZ];
int *port_array;
int *pid_array;
int start_port;
int udp_port;
int cpu;
int pid;
port_array = malloc_or_die(sizeof(int) * cpus);
pid_array = malloc_or_die(sizeof(int) * cpus);
memset(pid_array, 0, sizeof(int) * cpus);
start_port = START_PORT_SEARCH;
/* Now create a UDP port for each CPU */
for (cpu = 0; cpu < cpus; cpu++) {
udp_port = open_udp(node, port, &pid, cpu,
pagesize, start_port);
if (udp_port < 0)
goto out_free;
port_array[cpu] = udp_port;
pid_array[cpu] = pid;
/*
* Due to some bugging finding ports,
* force search after last port
*/
start_port = udp_port + 1;
}
/* send the client a comma deliminated set of port numbers */
for (cpu = 0; cpu < cpus; cpu++) {
snprintf(buf, BUFSIZ, "%s%d",
cpu ? "," : "", port_array[cpu]);
write(fd, buf, strlen(buf));
}
/* end with null terminator */
write(fd, "\0", 1);
return pid_array;
out_free:
destroy_all_readers(cpus, pid_array, node, port);
return NULL;
}
static void collect_metadata_from_client(int ifd, int ofd)
{
char buf[BUFSIZ];
int n, s, t;
do {
n = read(ifd, buf, BUFSIZ);
if (n < 0) {
if (errno == EINTR)
continue;
pdie("reading client");
}
t = n;
s = 0;
do {
s = write(ofd, buf+s, t);
if (s < 0) {
if (errno == EINTR)
break;
pdie("writing to file");
}
t -= s;
s = n - t;
} while (t);
} while (n > 0 && !done);
}
static void stop_all_readers(int cpus, int *pid_array)
{
int cpu;
for (cpu = 0; cpu < cpus; cpu++) {
if (pid_array[cpu] > 0)
kill(pid_array[cpu], SIGUSR1);
}
}
static void put_together_file(int cpus, int ofd, const char *node,
const char *port)
{
char **temp_files;
int cpu;
/* Now put together the file */
temp_files = malloc_or_die(sizeof(*temp_files) * cpus);
for (cpu = 0; cpu < cpus; cpu++)
temp_files[cpu] = get_temp_file(node, port, cpu);
tracecmd_attach_cpu_data_fd(ofd, cpus, temp_files);
free(temp_files);
}
static void process_client(const char *node, const char *port, int fd)
{
int *pid_array;
int pagesize;
int cpus;
int ofd;
if (communicate_with_client(fd, &cpus, &pagesize) < 0)
return;
ofd = create_client_file(node, port);
pid_array = create_all_readers(cpus, node, port, pagesize, fd);
if (!pid_array)
return;
/* Now we are ready to start reading data from the client */
collect_metadata_from_client(fd, ofd);
/* wait a little to let our readers finish reading */
sleep(1);
/* stop our readers */
stop_all_readers(cpus, pid_array);
/* wait a little to have the readers clean up */
sleep(1);
put_together_file(cpus, ofd, node, port);
destroy_all_readers(cpus, pid_array, node, port);
}
static int do_fork(int cfd)
{
pid_t pid;
/* in debug mode, we do not fork off children */
if (debug)
return 0;
pid = fork();
if (pid < 0) {
warning("failed to create child");
return -1;
}
if (pid > 0) {
close(cfd);
return pid;
}
signal_setup(SIGINT, finish);
return 0;
}
static int do_connection(int cfd, struct sockaddr_storage *peer_addr,
socklen_t peer_addr_len)
{
char host[NI_MAXHOST], service[NI_MAXSERV];
int s;
int ret;
ret = do_fork(cfd);
if (ret)
return ret;
s = getnameinfo((struct sockaddr *)peer_addr, peer_addr_len,
host, NI_MAXHOST,
service, NI_MAXSERV, NI_NUMERICSERV);
if (s == 0)
plog("Connected with %s:%s\n",
host, service);
else {
plog("Error with getnameinfo: %s\n",
gai_strerror(s));
close(cfd);
return -1;
}
process_client(host, service, cfd);
close(cfd);
if (!debug)
exit(0);
return 0;
}
static int *client_pids;
static int saved_pids;
static int size_pids;
#define PIDS_BLOCK 32
static void add_process(int pid)
{
if (!client_pids) {
size_pids = PIDS_BLOCK;
client_pids = malloc_or_die(sizeof(*client_pids) * size_pids);
} else if (!(saved_pids % PIDS_BLOCK)) {
size_pids += PIDS_BLOCK;
client_pids = realloc(client_pids,
sizeof(*client_pids) * size_pids);
if (!client_pids)
pdie("realloc of pids");
}
client_pids[saved_pids++] = pid;
}
static void remove_process(int pid)
{
int i;
for (i = 0; i < saved_pids; i++) {
if (client_pids[i] == pid)
break;
}
if (i == saved_pids)
return;
saved_pids--;
if (saved_pids == i)
return;
memmove(&client_pids[i], &client_pids[i+1],
sizeof(*client_pids) * (saved_pids - i));
}
static void kill_clients(void)
{
int status;
int i;
for (i = 0; i < saved_pids; i++) {
kill(client_pids[i], SIGINT);
waitpid(client_pids[i], &status, 0);
}
saved_pids = 0;
}
static void clean_up(int sig)
{
int status;
int ret;
/* Clean up any children that has started before */
do {
ret = waitpid(0, &status, WNOHANG);
if (ret > 0)
remove_process(ret);
} while (ret > 0);
}
static void do_accept_loop(int sfd)
{
struct sockaddr_storage peer_addr;
socklen_t peer_addr_len;
int cfd, pid;
peer_addr_len = sizeof(peer_addr);
do {
cfd = accept(sfd, (struct sockaddr *)&peer_addr,
&peer_addr_len);
printf("connected!\n");
if (cfd < 0 && errno == EINTR)
continue;
if (cfd < 0)
pdie("connecting");
pid = do_connection(cfd, &peer_addr, peer_addr_len);
if (pid > 0)
add_process(pid);
} while (!done);
}
static void do_listen(char *port)
{
struct addrinfo hints;
struct addrinfo *result, *rp;
int sfd, s;
if (!debug)
signal_setup(SIGCHLD, clean_up);
memset(&hints, 0, sizeof(hints));
hints.ai_family = AF_UNSPEC;
hints.ai_socktype = SOCK_STREAM;
hints.ai_flags = AI_PASSIVE;
s = getaddrinfo(NULL, port, &hints, &result);
if (s != 0)
pdie("getaddrinfo: error opening %s", port);
for (rp = result; rp != NULL; rp = rp->ai_next) {
sfd = socket(rp->ai_family, rp->ai_socktype,
rp->ai_protocol);
if (sfd < 0)
continue;
if (bind(sfd, rp->ai_addr, rp->ai_addrlen) == 0)
break;
close(sfd);
}
if (rp == NULL)
pdie("Could not bind");
freeaddrinfo(result);
if (listen(sfd, backlog) < 0)
pdie("listen");
do_accept_loop(sfd);
kill_clients();
}
static void start_daemon(void)
{
if (daemon(1, 0) < 0)
die("starting daemon");
}
enum {
OPT_debug = 255,
};
void trace_listen(int argc, char **argv)
{
char *logfile = NULL;
char *port = NULL;
int daemon = 0;
int c;
if (argc < 2)
usage(argv);
if (strcmp(argv[1], "listen") != 0)
usage(argv);
for (;;) {
int option_index = 0;
static struct option long_options[] = {
{"port", required_argument, NULL, 'p'},
{"help", no_argument, NULL, '?'},
{"debug", no_argument, NULL, OPT_debug},
{NULL, 0, NULL, 0}
};
c = getopt_long (argc-1, argv+1, "+hp:o:d:l:D",
long_options, &option_index);
if (c == -1)
break;
switch (c) {
case 'h':
usage(argv);
break;
case 'p':
port = optarg;
break;
case 'd':
output_dir = optarg;
break;
case 'o':
output_file = optarg;
break;
case 'l':
logfile = optarg;
break;
case 'D':
daemon = 1;
break;
case OPT_debug:
debug = 1;
break;
default:
usage(argv);
}
}
if (!port)
usage(argv);
if ((argc - optind) >= 2)
usage(argv);
if (!output_file)
output_file = default_output_file;
if (!output_dir)
output_dir = default_output_dir;
if (logfile) {
/* set the writes to a logfile instead */
logfp = fopen(logfile, "w");
if (!logfp)
die("creating log file %s", logfile);
}
if (chdir(output_dir) < 0)
die("Can't access directory %s", output_dir);
if (daemon)
start_daemon();
signal_setup(SIGINT, finish);
signal_setup(SIGTERM, finish);
do_listen(port);
return;
}
|