|
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [Xen-devel] [PATCH 28/29] xl: split out migration related code
Include COLO / Remus code because they are built on top of the existing
migration protocol.
Signed-off-by: Wei Liu <wei.liu2@xxxxxxxxxx>
---
tools/xl/Makefile | 2 +-
tools/xl/xl_cmdimpl.c | 715 -----------------------------------------------
tools/xl/xl_migrate.c | 754 ++++++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 755 insertions(+), 716 deletions(-)
create mode 100644 tools/xl/xl_migrate.c
diff --git a/tools/xl/Makefile b/tools/xl/Makefile
index 9982b936c4..8c30fdcf9e 100644
--- a/tools/xl/Makefile
+++ b/tools/xl/Makefile
@@ -20,7 +20,7 @@ XL_OBJS += xl_tmem.o xl_parse.o xl_cpupool.o xl_flask.o
XL_OBJS += xl_vtpm.o xl_block.o xl_nic.o xl_usb.o
XL_OBJS += xl_sched.o xl_pci.o xl_vcpu.o xl_cd.o xl_mem.o
XL_OBJS += xl_psr.o xl_info.o xl_console.o xl_misc.o
-XL_OBJS += xl_vmcontrol.o xl_saverestore.o
+XL_OBJS += xl_vmcontrol.o xl_saverestore.o xl_migrate.o
$(XL_OBJS): CFLAGS += $(CFLAGS_libxentoollog)
$(XL_OBJS): CFLAGS += $(CFLAGS_XL)
diff --git a/tools/xl/xl_cmdimpl.c b/tools/xl/xl_cmdimpl.c
index c41ae31814..bd7f8edb0a 100644
--- a/tools/xl/xl_cmdimpl.c
+++ b/tools/xl/xl_cmdimpl.c
@@ -98,721 +98,6 @@ void help(const char *command)
}
}
-#ifndef LIBXL_HAVE_NO_SUSPEND_RESUME
-
-static pid_t create_migration_child(const char *rune, int *send_fd,
- int *recv_fd)
-{
- int sendpipe[2], recvpipe[2];
- pid_t child;
-
- if (!rune || !send_fd || !recv_fd)
- return -1;
-
- MUST( libxl_pipe(ctx, sendpipe) );
- MUST( libxl_pipe(ctx, recvpipe) );
-
- child = xl_fork(child_migration, "migration transport process");
-
- if (!child) {
- dup2(sendpipe[0], 0);
- dup2(recvpipe[1], 1);
- close(sendpipe[0]); close(sendpipe[1]);
- close(recvpipe[0]); close(recvpipe[1]);
- execlp("sh","sh","-c",rune,(char*)0);
- perror("failed to exec sh");
- exit(EXIT_FAILURE);
- }
-
- close(sendpipe[0]);
- close(recvpipe[1]);
- *send_fd = sendpipe[1];
- *recv_fd = recvpipe[0];
-
- /* if receiver dies, we get an error and can clean up
- rather than just dying */
- signal(SIGPIPE, SIG_IGN);
-
- return child;
-}
-
-static int migrate_read_fixedmessage(int fd, const void *msg, int msgsz,
- const char *what, const char *rune) {
- char buf[msgsz];
- const char *stream;
- int rc;
-
- stream = rune ? "migration receiver stream" : "migration stream";
- rc = libxl_read_exactly(ctx, fd, buf, msgsz, stream, what);
- if (rc) return 1;
-
- if (memcmp(buf, msg, msgsz)) {
- fprintf(stderr, "%s contained unexpected data instead of %s\n",
- stream, what);
- if (rune)
- fprintf(stderr, "(command run was: %s )\n", rune);
- return 1;
- }
- return 0;
-}
-
-static void migration_child_report(int recv_fd) {
- pid_t child;
- int status, sr;
- struct timeval now, waituntil, timeout;
- static const struct timeval pollinterval = { 0, 1000 }; /* 1ms */
-
- if (!xl_child_pid(child_migration)) return;
-
- CHK_SYSCALL(gettimeofday(&waituntil, 0));
- waituntil.tv_sec += 2;
-
- for (;;) {
- pid_t migration_child = xl_child_pid(child_migration);
- child = xl_waitpid(child_migration, &status, WNOHANG);
-
- if (child == migration_child) {
- if (status)
- xl_report_child_exitstatus(XTL_INFO, child_migration,
- migration_child, status);
- break;
- }
- if (child == -1) {
- fprintf(stderr, "wait for migration child [%ld] failed: %s\n",
- (long)migration_child, strerror(errno));
- break;
- }
- assert(child == 0);
-
- CHK_SYSCALL(gettimeofday(&now, 0));
- if (timercmp(&now, &waituntil, >)) {
- fprintf(stderr, "migration child [%ld] not exiting, no longer"
- " waiting (exit status will be unreported)\n",
- (long)migration_child);
- break;
- }
- timersub(&waituntil, &now, &timeout);
-
- if (recv_fd >= 0) {
- fd_set readfds, exceptfds;
- FD_ZERO(&readfds);
- FD_ZERO(&exceptfds);
- FD_SET(recv_fd, &readfds);
- FD_SET(recv_fd, &exceptfds);
- sr = select(recv_fd+1, &readfds,0,&exceptfds, &timeout);
- } else {
- if (timercmp(&timeout, &pollinterval, >))
- timeout = pollinterval;
- sr = select(0,0,0,0, &timeout);
- }
- if (sr > 0) {
- recv_fd = -1;
- } else if (sr == 0) {
- } else if (sr == -1) {
- if (errno != EINTR) {
- fprintf(stderr, "migration child [%ld] exit wait select"
- " failed unexpectedly: %s\n",
- (long)migration_child, strerror(errno));
- break;
- }
- }
- }
-}
-
-static void migrate_do_preamble(int send_fd, int recv_fd, pid_t child,
- uint8_t *config_data, int config_len,
- const char *rune)
-{
- int rc = 0;
-
- if (send_fd < 0 || recv_fd < 0) {
- fprintf(stderr, "migrate_do_preamble: invalid file descriptors\n");
- exit(EXIT_FAILURE);
- }
-
- rc = migrate_read_fixedmessage(recv_fd, migrate_receiver_banner,
- sizeof(migrate_receiver_banner)-1,
- "banner", rune);
- if (rc) {
- close(send_fd);
- migration_child_report(recv_fd);
- exit(EXIT_FAILURE);
- }
-
- save_domain_core_writeconfig(send_fd, "migration stream",
- config_data, config_len);
-
-}
-
-static void migrate_domain(uint32_t domid, const char *rune, int debug,
- const char *override_config_file)
-{
- pid_t child = -1;
- int rc;
- int send_fd = -1, recv_fd = -1;
- char *away_domname;
- char rc_buf;
- uint8_t *config_data;
- int config_len, flags = LIBXL_SUSPEND_LIVE;
-
- save_domain_core_begin(domid, override_config_file,
- &config_data, &config_len);
-
- if (!config_len) {
- fprintf(stderr, "No config file stored for running domain and "
- "none supplied - cannot migrate.\n");
- exit(EXIT_FAILURE);
- }
-
- child = create_migration_child(rune, &send_fd, &recv_fd);
-
- migrate_do_preamble(send_fd, recv_fd, child, config_data, config_len,
- rune);
-
- xtl_stdiostream_adjust_flags(logger, XTL_STDIOSTREAM_HIDE_PROGRESS, 0);
-
- if (debug)
- flags |= LIBXL_SUSPEND_DEBUG;
- rc = libxl_domain_suspend(ctx, domid, send_fd, flags, NULL);
- if (rc) {
- fprintf(stderr, "migration sender: libxl_domain_suspend failed"
- " (rc=%d)\n", rc);
- if (rc == ERROR_GUEST_TIMEDOUT)
- goto failed_suspend;
- else
- goto failed_resume;
- }
-
- //fprintf(stderr, "migration sender: Transfer complete.\n");
- // Should only be printed when debugging as it's a bit messy with
- // progress indication.
-
- rc = migrate_read_fixedmessage(recv_fd, migrate_receiver_ready,
- sizeof(migrate_receiver_ready),
- "ready message", rune);
- if (rc) goto failed_resume;
-
- xtl_stdiostream_adjust_flags(logger, 0, XTL_STDIOSTREAM_HIDE_PROGRESS);
-
- /* right, at this point we are about give the destination
- * permission to rename and resume, so we must first rename the
- * domain away ourselves */
-
- fprintf(stderr, "migration sender: Target has acknowledged transfer.\n");
-
- if (common_domname) {
- xasprintf(&away_domname, "%s--migratedaway", common_domname);
- rc = libxl_domain_rename(ctx, domid, common_domname, away_domname);
- if (rc) goto failed_resume;
- }
-
- /* point of no return - as soon as we have tried to say
- * "go" to the receiver, it's not safe to carry on. We leave
- * the domain renamed to %s--migratedaway in case that's helpful.
- */
-
- fprintf(stderr, "migration sender: Giving target permission to start.\n");
-
- rc = libxl_write_exactly(ctx, send_fd,
- migrate_permission_to_go,
- sizeof(migrate_permission_to_go),
- "migration stream", "GO message");
- if (rc) goto failed_badly;
-
- rc = migrate_read_fixedmessage(recv_fd, migrate_report,
- sizeof(migrate_report),
- "success/failure report message", rune);
- if (rc) goto failed_badly;
-
- rc = libxl_read_exactly(ctx, recv_fd,
- &rc_buf, 1,
- "migration ack stream", "success/failure status");
- if (rc) goto failed_badly;
-
- if (rc_buf) {
- fprintf(stderr, "migration sender: Target reports startup failure"
- " (status code %d).\n", rc_buf);
-
- rc = migrate_read_fixedmessage(recv_fd, migrate_permission_to_go,
- sizeof(migrate_permission_to_go),
- "permission for sender to resume",
- rune);
- if (rc) goto failed_badly;
-
- fprintf(stderr, "migration sender: Trying to resume at our end.\n");
-
- if (common_domname) {
- libxl_domain_rename(ctx, domid, away_domname, common_domname);
- }
- rc = libxl_domain_resume(ctx, domid, 1, 0);
- if (!rc) fprintf(stderr, "migration sender: Resumed OK.\n");
-
- fprintf(stderr, "Migration failed due to problems at target.\n");
- exit(EXIT_FAILURE);
- }
-
- fprintf(stderr, "migration sender: Target reports successful startup.\n");
- libxl_domain_destroy(ctx, domid, 0); /* bang! */
- fprintf(stderr, "Migration successful.\n");
- exit(EXIT_SUCCESS);
-
- failed_suspend:
- close(send_fd);
- migration_child_report(recv_fd);
- fprintf(stderr, "Migration failed, failed to suspend at sender.\n");
- exit(EXIT_FAILURE);
-
- failed_resume:
- close(send_fd);
- migration_child_report(recv_fd);
- fprintf(stderr, "Migration failed, resuming at sender.\n");
- libxl_domain_resume(ctx, domid, 1, 0);
- exit(EXIT_FAILURE);
-
- failed_badly:
- fprintf(stderr,
- "** Migration failed during final handshake **\n"
- "Domain state is now undefined !\n"
- "Please CHECK AT BOTH ENDS for running instances, before renaming and\n"
- " resuming at most one instance. Two simultaneous instances of the domain\n"
- " would probably result in SEVERE DATA LOSS and it is now your\n"
- " responsibility to avoid that. Sorry.\n");
-
- close(send_fd);
- migration_child_report(recv_fd);
- exit(EXIT_FAILURE);
-}
-
-static void migrate_receive(int debug, int daemonize, int monitor,
- int pause_after_migration,
- int send_fd, int recv_fd,
- libxl_checkpointed_stream checkpointed,
- char *colo_proxy_script)
-{
- uint32_t domid;
- int rc, rc2;
- char rc_buf;
- char *migration_domname;
- struct domain_create dom_info;
-
- signal(SIGPIPE, SIG_IGN);
- /* if we get SIGPIPE we'd rather just have it as an error */
-
- fprintf(stderr, "migration target: Ready to receive domain.\n");
-
- CHK_ERRNOVAL(libxl_write_exactly(
- ctx, send_fd, migrate_receiver_banner,
- sizeof(migrate_receiver_banner)-1,
- "migration ack stream", "banner") );
-
- memset(&dom_info, 0, sizeof(dom_info));
- dom_info.debug = debug;
- dom_info.daemonize = daemonize;
- dom_info.monitor = monitor;
- dom_info.paused = 1;
- dom_info.migrate_fd = recv_fd;
- dom_info.send_back_fd = send_fd;
- dom_info.migration_domname_r = &migration_domname;
- dom_info.checkpointed_stream = checkpointed;
- dom_info.colo_proxy_script = colo_proxy_script;
-
- rc = create_domain(&dom_info);
- if (rc < 0) {
- fprintf(stderr, "migration target: Domain creation failed"
- " (code %d).\n", rc);
- exit(EXIT_FAILURE);
- }
-
- domid = rc;
-
- switch (checkpointed) {
- case LIBXL_CHECKPOINTED_STREAM_REMUS:
- case LIBXL_CHECKPOINTED_STREAM_COLO:
- {
- const char *ha = checkpointed == LIBXL_CHECKPOINTED_STREAM_COLO ?
- "COLO" : "Remus";
- /* If we are here, it means that the sender (primary) has crashed.
- * TODO: Split-Brain Check.
- */
- fprintf(stderr, "migration target: %s Failover for domain %u\n",
- ha, domid);
-
- /*
- * If domain renaming fails, lets just continue (as we need the domain
- * to be up & dom names may not matter much, as long as its reachable
- * over network).
- *
- * If domain unpausing fails, destroy domain ? Or is it better to have
- * a consistent copy of the domain (memory, cpu state, disk)
- * on atleast one physical host ? Right now, lets just leave the domain
- * as is and let the Administrator decide (or troubleshoot).
- */
- if (migration_domname) {
- rc = libxl_domain_rename(ctx, domid, migration_domname,
- common_domname);
- if (rc)
- fprintf(stderr, "migration target (%s): "
- "Failed to rename domain from %s to %s:%d\n",
- ha, migration_domname, common_domname, rc);
- }
-
- if (checkpointed == LIBXL_CHECKPOINTED_STREAM_COLO)
- /* The guest is running after failover in COLO mode */
- exit(rc ? -ERROR_FAIL: 0);
-
- rc = libxl_domain_unpause(ctx, domid);
- if (rc)
- fprintf(stderr, "migration target (%s): "
- "Failed to unpause domain %s (id: %u):%d\n",
- ha, common_domname, domid, rc);
-
- exit(rc ? EXIT_FAILURE : EXIT_SUCCESS);
- }
- default:
- /* do nothing */
- break;
- }
-
- fprintf(stderr, "migration target: Transfer complete,"
- " requesting permission to start domain.\n");
-
- rc = libxl_write_exactly(ctx, send_fd,
- migrate_receiver_ready,
- sizeof(migrate_receiver_ready),
- "migration ack stream", "ready message");
- if (rc) exit(EXIT_FAILURE);
-
- rc = migrate_read_fixedmessage(recv_fd, migrate_permission_to_go,
- sizeof(migrate_permission_to_go),
- "GO message", 0);
- if (rc) goto perhaps_destroy_notify_rc;
-
- fprintf(stderr, "migration target: Got permission, starting domain.\n");
-
- if (migration_domname) {
- rc = libxl_domain_rename(ctx, domid, migration_domname,
common_domname);
- if (rc) goto perhaps_destroy_notify_rc;
- }
-
- if (!pause_after_migration) {
- rc = libxl_domain_unpause(ctx, domid);
- if (rc) goto perhaps_destroy_notify_rc;
- }
-
- fprintf(stderr, "migration target: Domain started successsfully.\n");
- rc = 0;
-
- perhaps_destroy_notify_rc:
- rc2 = libxl_write_exactly(ctx, send_fd,
- migrate_report, sizeof(migrate_report),
- "migration ack stream",
- "success/failure report");
- if (rc2) exit(EXIT_FAILURE);
-
- rc_buf = -rc;
- assert(!!rc_buf == !!rc);
- rc2 = libxl_write_exactly(ctx, send_fd, &rc_buf, 1,
- "migration ack stream",
- "success/failure code");
- if (rc2) exit(EXIT_FAILURE);
-
- if (rc) {
- fprintf(stderr, "migration target: Failure, destroying our copy.\n");
-
- rc2 = libxl_domain_destroy(ctx, domid, 0);
- if (rc2) {
- fprintf(stderr, "migration target: Failed to destroy our copy"
- " (code %d).\n", rc2);
- exit(EXIT_FAILURE);
- }
-
- fprintf(stderr, "migration target: Cleanup OK, granting sender"
- " permission to resume.\n");
-
- rc2 = libxl_write_exactly(ctx, send_fd,
- migrate_permission_to_go,
- sizeof(migrate_permission_to_go),
- "migration ack stream",
- "permission to sender to have domain back");
- if (rc2) exit(EXIT_FAILURE);
- }
-
- exit(EXIT_SUCCESS);
-}
-
-
-int main_migrate_receive(int argc, char **argv)
-{
- int debug = 0, daemonize = 1, monitor = 1, pause_after_migration = 0;
- libxl_checkpointed_stream checkpointed = LIBXL_CHECKPOINTED_STREAM_NONE;
- int opt;
- char *script = NULL;
- static struct option opts[] = {
- {"colo", 0, 0, 0x100},
- /* It is a shame that the management code for disk is not here. */
- {"coloft-script", 1, 0, 0x200},
- COMMON_LONG_OPTS
- };
-
- SWITCH_FOREACH_OPT(opt, "Fedrp", opts, "migrate-receive", 0) {
- case 'F':
- daemonize = 0;
- break;
- case 'e':
- daemonize = 0;
- monitor = 0;
- break;
- case 'd':
- debug = 1;
- break;
- case 'r':
- checkpointed = LIBXL_CHECKPOINTED_STREAM_REMUS;
- break;
- case 0x100:
- checkpointed = LIBXL_CHECKPOINTED_STREAM_COLO;
- break;
- case 0x200:
- script = optarg;
- break;
- case 'p':
- pause_after_migration = 1;
- break;
- }
-
- if (argc-optind != 0) {
- help("migrate-receive");
- return EXIT_FAILURE;
- }
- migrate_receive(debug, daemonize, monitor, pause_after_migration,
- STDOUT_FILENO, STDIN_FILENO,
- checkpointed, script);
-
- return EXIT_SUCCESS;
-}
-
-int main_migrate(int argc, char **argv)
-{
- uint32_t domid;
- const char *config_filename = NULL;
- const char *ssh_command = "ssh";
- char *rune = NULL;
- char *host;
- int opt, daemonize = 1, monitor = 1, debug = 0, pause_after_migration = 0;
- static struct option opts[] = {
- {"debug", 0, 0, 0x100},
- {"live", 0, 0, 0x200},
- COMMON_LONG_OPTS
- };
-
- SWITCH_FOREACH_OPT(opt, "FC:s:ep", opts, "migrate", 2) {
- case 'C':
- config_filename = optarg;
- break;
- case 's':
- ssh_command = optarg;
- break;
- case 'F':
- daemonize = 0;
- break;
- case 'e':
- daemonize = 0;
- monitor = 0;
- break;
- case 'p':
- pause_after_migration = 1;
- break;
- case 0x100: /* --debug */
- debug = 1;
- break;
- case 0x200: /* --live */
- /* ignored for compatibility with xm */
- break;
- }
-
- domid = xfind_domain(argv[optind]);
- host = argv[optind + 1];
-
- bool pass_tty_arg = progress_use_cr || (isatty(2) > 0);
-
- if (!ssh_command[0]) {
- rune= host;
- } else {
- char verbose_buf[minmsglevel_default+3];
- int verbose_len;
- verbose_buf[0] = ' ';
- verbose_buf[1] = '-';
- memset(verbose_buf+2, 'v', minmsglevel_default);
- verbose_buf[sizeof(verbose_buf)-1] = 0;
- if (minmsglevel == minmsglevel_default) {
- verbose_len = 0;
- } else {
- verbose_len = (minmsglevel_default - minmsglevel) + 2;
- }
- xasprintf(&rune, "exec %s %s xl%s%.*s migrate-receive%s%s%s",
- ssh_command, host,
- pass_tty_arg ? " -t" : "",
- verbose_len, verbose_buf,
- daemonize ? "" : " -e",
- debug ? " -d" : "",
- pause_after_migration ? " -p" : "");
- }
-
- migrate_domain(domid, rune, debug, config_filename);
- return EXIT_SUCCESS;
-}
-#endif
-
-#ifndef LIBXL_HAVE_NO_SUSPEND_RESUME
-int main_remus(int argc, char **argv)
-{
- uint32_t domid;
- int opt, rc, daemonize = 1;
- const char *ssh_command = "ssh";
- char *host = NULL, *rune = NULL;
- libxl_domain_remus_info r_info;
- int send_fd = -1, recv_fd = -1;
- pid_t child = -1;
- uint8_t *config_data;
- int config_len;
-
- memset(&r_info, 0, sizeof(libxl_domain_remus_info));
-
- SWITCH_FOREACH_OPT(opt, "Fbundi:s:N:ec", NULL, "remus", 2) {
- case 'i':
- r_info.interval = atoi(optarg);
- break;
- case 'F':
- libxl_defbool_set(&r_info.allow_unsafe, true);
- break;
- case 'b':
- libxl_defbool_set(&r_info.blackhole, true);
- break;
- case 'u':
- libxl_defbool_set(&r_info.compression, false);
- break;
- case 'n':
- libxl_defbool_set(&r_info.netbuf, false);
- break;
- case 'N':
- r_info.netbufscript = optarg;
- break;
- case 'd':
- libxl_defbool_set(&r_info.diskbuf, false);
- break;
- case 's':
- ssh_command = optarg;
- break;
- case 'e':
- daemonize = 0;
- break;
- case 'c':
- libxl_defbool_set(&r_info.colo, true);
- }
-
- domid = xfind_domain(argv[optind]);
- host = argv[optind + 1];
-
- /* Defaults */
- libxl_defbool_setdefault(&r_info.blackhole, false);
- libxl_defbool_setdefault(&r_info.colo, false);
- if (!libxl_defbool_val(r_info.colo) && !r_info.interval)
- r_info.interval = 200;
-
- if (libxl_defbool_val(r_info.colo)) {
- if (r_info.interval || libxl_defbool_val(r_info.blackhole) ||
- !libxl_defbool_is_default(r_info.netbuf) ||
- !libxl_defbool_is_default(r_info.diskbuf)) {
- perror("option -c is conflict with -i, -d, -n or -b");
- exit(-1);
- }
-
- if (libxl_defbool_is_default(r_info.compression)) {
- perror("COLO can't be used with memory compression. "
- "Disable memory checkpoint compression now...");
- libxl_defbool_set(&r_info.compression, false);
- }
- }
-
- if (!r_info.netbufscript) {
- if (libxl_defbool_val(r_info.colo))
- r_info.netbufscript = default_colo_proxy_script;
- else
- r_info.netbufscript = default_remus_netbufscript;
- }
-
- if (libxl_defbool_val(r_info.blackhole)) {
- send_fd = open("/dev/null", O_RDWR, 0644);
- if (send_fd < 0) {
- perror("failed to open /dev/null");
- exit(EXIT_FAILURE);
- }
- } else {
-
- if (!ssh_command[0]) {
- rune = host;
- } else {
- if (!libxl_defbool_val(r_info.colo)) {
- xasprintf(&rune, "exec %s %s xl migrate-receive %s %s",
- ssh_command, host,
- "-r",
- daemonize ? "" : " -e");
- } else {
- xasprintf(&rune, "exec %s %s xl migrate-receive %s %s %s %s",
- ssh_command, host,
- "--colo",
- r_info.netbufscript ? "--coloft-script" : "",
- r_info.netbufscript ? r_info.netbufscript : "",
- daemonize ? "" : " -e");
- }
- }
-
- save_domain_core_begin(domid, NULL, &config_data, &config_len);
-
- if (!config_len) {
- fprintf(stderr, "No config file stored for running domain and "
- "none supplied - cannot start remus.\n");
- exit(EXIT_FAILURE);
- }
-
- child = create_migration_child(rune, &send_fd, &recv_fd);
-
- migrate_do_preamble(send_fd, recv_fd, child, config_data, config_len,
- rune);
-
- if (ssh_command[0])
- free(rune);
- }
-
- /* Point of no return */
- rc = libxl_domain_remus_start(ctx, &r_info, domid, send_fd, recv_fd, 0);
-
- /* check if the domain exists. User may have xl destroyed the
- * domain to force failover
- */
- if (libxl_domain_info(ctx, 0, domid)) {
- fprintf(stderr, "%s: Primary domain has been destroyed.\n",
- libxl_defbool_val(r_info.colo) ? "COLO" : "Remus");
- close(send_fd);
- return EXIT_SUCCESS;
- }
-
- /* If we are here, it means remus setup/domain suspend/backup has
- * failed. Try to resume the domain and exit gracefully.
- * TODO: Split-Brain check.
- */
- if (rc == ERROR_GUEST_TIMEDOUT)
- fprintf(stderr, "Failed to suspend domain at primary.\n");
- else {
- fprintf(stderr, "%s: Backup failed? resuming domain at primary.\n",
- libxl_defbool_val(r_info.colo) ? "COLO" : "Remus");
- libxl_domain_resume(ctx, domid, 1, 0);
- }
-
- close(send_fd);
- return EXIT_FAILURE;
-}
-#endif
-
/*
* Local variables:
* mode: C
diff --git a/tools/xl/xl_migrate.c b/tools/xl/xl_migrate.c
new file mode 100644
index 0000000000..6b5dff2d1a
--- /dev/null
+++ b/tools/xl/xl_migrate.c
@@ -0,0 +1,754 @@
+/*
+ * Copyright 2009-2017 Citrix Ltd and other contributors
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published
+ * by the Free Software Foundation; version 2.1 only. with the special
+ * exception on linking described in file LICENSE.
+ *
+ * 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 Lesser General Public License for more details.
+ */
+
+#include <fcntl.h>
+#include <inttypes.h>
+#include <stdlib.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/utsname.h>
+#include <time.h>
+#include <unistd.h>
+
+#include <libxl.h>
+#include <libxl_utils.h>
+#include <libxlutil.h>
+
+#include "xl.h"
+#include "xl_utils.h"
+#include "xl_parse.h"
+
+extern const char *common_domname;
+
+#ifndef LIBXL_HAVE_NO_SUSPEND_RESUME
+
+static pid_t create_migration_child(const char *rune, int *send_fd,
+ int *recv_fd)
+{
+ int sendpipe[2], recvpipe[2];
+ pid_t child;
+
+ if (!rune || !send_fd || !recv_fd)
+ return -1;
+
+ MUST( libxl_pipe(ctx, sendpipe) );
+ MUST( libxl_pipe(ctx, recvpipe) );
+
+ child = xl_fork(child_migration, "migration transport process");
+
+ if (!child) {
+ dup2(sendpipe[0], 0);
+ dup2(recvpipe[1], 1);
+ close(sendpipe[0]); close(sendpipe[1]);
+ close(recvpipe[0]); close(recvpipe[1]);
+ execlp("sh","sh","-c",rune,(char*)0);
+ perror("failed to exec sh");
+ exit(EXIT_FAILURE);
+ }
+
+ close(sendpipe[0]);
+ close(recvpipe[1]);
+ *send_fd = sendpipe[1];
+ *recv_fd = recvpipe[0];
+
+ /* if receiver dies, we get an error and can clean up
+ rather than just dying */
+ signal(SIGPIPE, SIG_IGN);
+
+ return child;
+}
+
+static int migrate_read_fixedmessage(int fd, const void *msg, int msgsz,
+ const char *what, const char *rune) {
+ char buf[msgsz];
+ const char *stream;
+ int rc;
+
+ stream = rune ? "migration receiver stream" : "migration stream";
+ rc = libxl_read_exactly(ctx, fd, buf, msgsz, stream, what);
+ if (rc) return 1;
+
+ if (memcmp(buf, msg, msgsz)) {
+ fprintf(stderr, "%s contained unexpected data instead of %s\n",
+ stream, what);
+ if (rune)
+ fprintf(stderr, "(command run was: %s )\n", rune);
+ return 1;
+ }
+ return 0;
+}
+
+static void migration_child_report(int recv_fd) {
+ pid_t child;
+ int status, sr;
+ struct timeval now, waituntil, timeout;
+ static const struct timeval pollinterval = { 0, 1000 }; /* 1ms */
+
+ if (!xl_child_pid(child_migration)) return;
+
+ CHK_SYSCALL(gettimeofday(&waituntil, 0));
+ waituntil.tv_sec += 2;
+
+ for (;;) {
+ pid_t migration_child = xl_child_pid(child_migration);
+ child = xl_waitpid(child_migration, &status, WNOHANG);
+
+ if (child == migration_child) {
+ if (status)
+ xl_report_child_exitstatus(XTL_INFO, child_migration,
+ migration_child, status);
+ break;
+ }
+ if (child == -1) {
+ fprintf(stderr, "wait for migration child [%ld] failed: %s\n",
+ (long)migration_child, strerror(errno));
+ break;
+ }
+ assert(child == 0);
+
+ CHK_SYSCALL(gettimeofday(&now, 0));
+ if (timercmp(&now, &waituntil, >)) {
+ fprintf(stderr, "migration child [%ld] not exiting, no longer"
+ " waiting (exit status will be unreported)\n",
+ (long)migration_child);
+ break;
+ }
+ timersub(&waituntil, &now, &timeout);
+
+ if (recv_fd >= 0) {
+ fd_set readfds, exceptfds;
+ FD_ZERO(&readfds);
+ FD_ZERO(&exceptfds);
+ FD_SET(recv_fd, &readfds);
+ FD_SET(recv_fd, &exceptfds);
+ sr = select(recv_fd+1, &readfds,0,&exceptfds, &timeout);
+ } else {
+ if (timercmp(&timeout, &pollinterval, >))
+ timeout = pollinterval;
+ sr = select(0,0,0,0, &timeout);
+ }
+ if (sr > 0) {
+ recv_fd = -1;
+ } else if (sr == 0) {
+ } else if (sr == -1) {
+ if (errno != EINTR) {
+ fprintf(stderr, "migration child [%ld] exit wait select"
+ " failed unexpectedly: %s\n",
+ (long)migration_child, strerror(errno));
+ break;
+ }
+ }
+ }
+}
+
+static void migrate_do_preamble(int send_fd, int recv_fd, pid_t child,
+ uint8_t *config_data, int config_len,
+ const char *rune)
+{
+ int rc = 0;
+
+ if (send_fd < 0 || recv_fd < 0) {
+ fprintf(stderr, "migrate_do_preamble: invalid file descriptors\n");
+ exit(EXIT_FAILURE);
+ }
+
+ rc = migrate_read_fixedmessage(recv_fd, migrate_receiver_banner,
+ sizeof(migrate_receiver_banner)-1,
+ "banner", rune);
+ if (rc) {
+ close(send_fd);
+ migration_child_report(recv_fd);
+ exit(EXIT_FAILURE);
+ }
+
+ save_domain_core_writeconfig(send_fd, "migration stream",
+ config_data, config_len);
+
+}
+
+static void migrate_domain(uint32_t domid, const char *rune, int debug,
+ const char *override_config_file)
+{
+ pid_t child = -1;
+ int rc;
+ int send_fd = -1, recv_fd = -1;
+ char *away_domname;
+ char rc_buf;
+ uint8_t *config_data;
+ int config_len, flags = LIBXL_SUSPEND_LIVE;
+
+ save_domain_core_begin(domid, override_config_file,
+ &config_data, &config_len);
+
+ if (!config_len) {
+ fprintf(stderr, "No config file stored for running domain and "
+ "none supplied - cannot migrate.\n");
+ exit(EXIT_FAILURE);
+ }
+
+ child = create_migration_child(rune, &send_fd, &recv_fd);
+
+ migrate_do_preamble(send_fd, recv_fd, child, config_data, config_len,
+ rune);
+
+ xtl_stdiostream_adjust_flags(logger, XTL_STDIOSTREAM_HIDE_PROGRESS, 0);
+
+ if (debug)
+ flags |= LIBXL_SUSPEND_DEBUG;
+ rc = libxl_domain_suspend(ctx, domid, send_fd, flags, NULL);
+ if (rc) {
+ fprintf(stderr, "migration sender: libxl_domain_suspend failed"
+ " (rc=%d)\n", rc);
+ if (rc == ERROR_GUEST_TIMEDOUT)
+ goto failed_suspend;
+ else
+ goto failed_resume;
+ }
+
+ //fprintf(stderr, "migration sender: Transfer complete.\n");
+ // Should only be printed when debugging as it's a bit messy with
+ // progress indication.
+
+ rc = migrate_read_fixedmessage(recv_fd, migrate_receiver_ready,
+ sizeof(migrate_receiver_ready),
+ "ready message", rune);
+ if (rc) goto failed_resume;
+
+ xtl_stdiostream_adjust_flags(logger, 0, XTL_STDIOSTREAM_HIDE_PROGRESS);
+
+ /* right, at this point we are about give the destination
+ * permission to rename and resume, so we must first rename the
+ * domain away ourselves */
+
+ fprintf(stderr, "migration sender: Target has acknowledged transfer.\n");
+
+ if (common_domname) {
+ xasprintf(&away_domname, "%s--migratedaway", common_domname);
+ rc = libxl_domain_rename(ctx, domid, common_domname, away_domname);
+ if (rc) goto failed_resume;
+ }
+
+ /* point of no return - as soon as we have tried to say
+ * "go" to the receiver, it's not safe to carry on. We leave
+ * the domain renamed to %s--migratedaway in case that's helpful.
+ */
+
+ fprintf(stderr, "migration sender: Giving target permission to start.\n");
+
+ rc = libxl_write_exactly(ctx, send_fd,
+ migrate_permission_to_go,
+ sizeof(migrate_permission_to_go),
+ "migration stream", "GO message");
+ if (rc) goto failed_badly;
+
+ rc = migrate_read_fixedmessage(recv_fd, migrate_report,
+ sizeof(migrate_report),
+ "success/failure report message", rune);
+ if (rc) goto failed_badly;
+
+ rc = libxl_read_exactly(ctx, recv_fd,
+ &rc_buf, 1,
+ "migration ack stream", "success/failure status");
+ if (rc) goto failed_badly;
+
+ if (rc_buf) {
+ fprintf(stderr, "migration sender: Target reports startup failure"
+ " (status code %d).\n", rc_buf);
+
+ rc = migrate_read_fixedmessage(recv_fd, migrate_permission_to_go,
+ sizeof(migrate_permission_to_go),
+ "permission for sender to resume",
+ rune);
+ if (rc) goto failed_badly;
+
+ fprintf(stderr, "migration sender: Trying to resume at our end.\n");
+
+ if (common_domname) {
+ libxl_domain_rename(ctx, domid, away_domname, common_domname);
+ }
+ rc = libxl_domain_resume(ctx, domid, 1, 0);
+ if (!rc) fprintf(stderr, "migration sender: Resumed OK.\n");
+
+ fprintf(stderr, "Migration failed due to problems at target.\n");
+ exit(EXIT_FAILURE);
+ }
+
+ fprintf(stderr, "migration sender: Target reports successful startup.\n");
+ libxl_domain_destroy(ctx, domid, 0); /* bang! */
+ fprintf(stderr, "Migration successful.\n");
+ exit(EXIT_SUCCESS);
+
+ failed_suspend:
+ close(send_fd);
+ migration_child_report(recv_fd);
+ fprintf(stderr, "Migration failed, failed to suspend at sender.\n");
+ exit(EXIT_FAILURE);
+
+ failed_resume:
+ close(send_fd);
+ migration_child_report(recv_fd);
+ fprintf(stderr, "Migration failed, resuming at sender.\n");
+ libxl_domain_resume(ctx, domid, 1, 0);
+ exit(EXIT_FAILURE);
+
+ failed_badly:
+ fprintf(stderr,
+ "** Migration failed during final handshake **\n"
+ "Domain state is now undefined !\n"
+ "Please CHECK AT BOTH ENDS for running instances, before renaming and\n"
+ " resuming at most one instance. Two simultaneous instances of the domain\n"
+ " would probably result in SEVERE DATA LOSS and it is now your\n"
+ " responsibility to avoid that. Sorry.\n");
+
+ close(send_fd);
+ migration_child_report(recv_fd);
+ exit(EXIT_FAILURE);
+}
+
+static void migrate_receive(int debug, int daemonize, int monitor,
+ int pause_after_migration,
+ int send_fd, int recv_fd,
+ libxl_checkpointed_stream checkpointed,
+ char *colo_proxy_script)
+{
+ uint32_t domid;
+ int rc, rc2;
+ char rc_buf;
+ char *migration_domname;
+ struct domain_create dom_info;
+
+ signal(SIGPIPE, SIG_IGN);
+ /* if we get SIGPIPE we'd rather just have it as an error */
+
+ fprintf(stderr, "migration target: Ready to receive domain.\n");
+
+ CHK_ERRNOVAL(libxl_write_exactly(
+ ctx, send_fd, migrate_receiver_banner,
+ sizeof(migrate_receiver_banner)-1,
+ "migration ack stream", "banner") );
+
+ memset(&dom_info, 0, sizeof(dom_info));
+ dom_info.debug = debug;
+ dom_info.daemonize = daemonize;
+ dom_info.monitor = monitor;
+ dom_info.paused = 1;
+ dom_info.migrate_fd = recv_fd;
+ dom_info.send_back_fd = send_fd;
+ dom_info.migration_domname_r = &migration_domname;
+ dom_info.checkpointed_stream = checkpointed;
+ dom_info.colo_proxy_script = colo_proxy_script;
+
+ rc = create_domain(&dom_info);
+ if (rc < 0) {
+ fprintf(stderr, "migration target: Domain creation failed"
+ " (code %d).\n", rc);
+ exit(EXIT_FAILURE);
+ }
+
+ domid = rc;
+
+ switch (checkpointed) {
+ case LIBXL_CHECKPOINTED_STREAM_REMUS:
+ case LIBXL_CHECKPOINTED_STREAM_COLO:
+ {
+ const char *ha = checkpointed == LIBXL_CHECKPOINTED_STREAM_COLO ?
+ "COLO" : "Remus";
+ /* If we are here, it means that the sender (primary) has crashed.
+ * TODO: Split-Brain Check.
+ */
+ fprintf(stderr, "migration target: %s Failover for domain %u\n",
+ ha, domid);
+
+ /*
+ * If domain renaming fails, lets just continue (as we need the domain
+ * to be up & dom names may not matter much, as long as its reachable
+ * over network).
+ *
+ * If domain unpausing fails, destroy domain ? Or is it better to have
+ * a consistent copy of the domain (memory, cpu state, disk)
+ * on atleast one physical host ? Right now, lets just leave the domain
+ * as is and let the Administrator decide (or troubleshoot).
+ */
+ if (migration_domname) {
+ rc = libxl_domain_rename(ctx, domid, migration_domname,
+ common_domname);
+ if (rc)
+ fprintf(stderr, "migration target (%s): "
+ "Failed to rename domain from %s to %s:%d\n",
+ ha, migration_domname, common_domname, rc);
+ }
+
+ if (checkpointed == LIBXL_CHECKPOINTED_STREAM_COLO)
+ /* The guest is running after failover in COLO mode */
+ exit(rc ? -ERROR_FAIL: 0);
+
+ rc = libxl_domain_unpause(ctx, domid);
+ if (rc)
+ fprintf(stderr, "migration target (%s): "
+ "Failed to unpause domain %s (id: %u):%d\n",
+ ha, common_domname, domid, rc);
+
+ exit(rc ? EXIT_FAILURE : EXIT_SUCCESS);
+ }
+ default:
+ /* do nothing */
+ break;
+ }
+
+ fprintf(stderr, "migration target: Transfer complete,"
+ " requesting permission to start domain.\n");
+
+ rc = libxl_write_exactly(ctx, send_fd,
+ migrate_receiver_ready,
+ sizeof(migrate_receiver_ready),
+ "migration ack stream", "ready message");
+ if (rc) exit(EXIT_FAILURE);
+
+ rc = migrate_read_fixedmessage(recv_fd, migrate_permission_to_go,
+ sizeof(migrate_permission_to_go),
+ "GO message", 0);
+ if (rc) goto perhaps_destroy_notify_rc;
+
+ fprintf(stderr, "migration target: Got permission, starting domain.\n");
+
+ if (migration_domname) {
+ rc = libxl_domain_rename(ctx, domid, migration_domname,
common_domname);
+ if (rc) goto perhaps_destroy_notify_rc;
+ }
+
+ if (!pause_after_migration) {
+ rc = libxl_domain_unpause(ctx, domid);
+ if (rc) goto perhaps_destroy_notify_rc;
+ }
+
+ fprintf(stderr, "migration target: Domain started successsfully.\n");
+ rc = 0;
+
+ perhaps_destroy_notify_rc:
+ rc2 = libxl_write_exactly(ctx, send_fd,
+ migrate_report, sizeof(migrate_report),
+ "migration ack stream",
+ "success/failure report");
+ if (rc2) exit(EXIT_FAILURE);
+
+ rc_buf = -rc;
+ assert(!!rc_buf == !!rc);
+ rc2 = libxl_write_exactly(ctx, send_fd, &rc_buf, 1,
+ "migration ack stream",
+ "success/failure code");
+ if (rc2) exit(EXIT_FAILURE);
+
+ if (rc) {
+ fprintf(stderr, "migration target: Failure, destroying our copy.\n");
+
+ rc2 = libxl_domain_destroy(ctx, domid, 0);
+ if (rc2) {
+ fprintf(stderr, "migration target: Failed to destroy our copy"
+ " (code %d).\n", rc2);
+ exit(EXIT_FAILURE);
+ }
+
+ fprintf(stderr, "migration target: Cleanup OK, granting sender"
+ " permission to resume.\n");
+
+ rc2 = libxl_write_exactly(ctx, send_fd,
+ migrate_permission_to_go,
+ sizeof(migrate_permission_to_go),
+ "migration ack stream",
+ "permission to sender to have domain back");
+ if (rc2) exit(EXIT_FAILURE);
+ }
+
+ exit(EXIT_SUCCESS);
+}
+
+
+int main_migrate_receive(int argc, char **argv)
+{
+ int debug = 0, daemonize = 1, monitor = 1, pause_after_migration = 0;
+ libxl_checkpointed_stream checkpointed = LIBXL_CHECKPOINTED_STREAM_NONE;
+ int opt;
+ char *script = NULL;
+ static struct option opts[] = {
+ {"colo", 0, 0, 0x100},
+ /* It is a shame that the management code for disk is not here. */
+ {"coloft-script", 1, 0, 0x200},
+ COMMON_LONG_OPTS
+ };
+
+ SWITCH_FOREACH_OPT(opt, "Fedrp", opts, "migrate-receive", 0) {
+ case 'F':
+ daemonize = 0;
+ break;
+ case 'e':
+ daemonize = 0;
+ monitor = 0;
+ break;
+ case 'd':
+ debug = 1;
+ break;
+ case 'r':
+ checkpointed = LIBXL_CHECKPOINTED_STREAM_REMUS;
+ break;
+ case 0x100:
+ checkpointed = LIBXL_CHECKPOINTED_STREAM_COLO;
+ break;
+ case 0x200:
+ script = optarg;
+ break;
+ case 'p':
+ pause_after_migration = 1;
+ break;
+ }
+
+ if (argc-optind != 0) {
+ help("migrate-receive");
+ return EXIT_FAILURE;
+ }
+ migrate_receive(debug, daemonize, monitor, pause_after_migration,
+ STDOUT_FILENO, STDIN_FILENO,
+ checkpointed, script);
+
+ return EXIT_SUCCESS;
+}
+
+int main_migrate(int argc, char **argv)
+{
+ uint32_t domid;
+ const char *config_filename = NULL;
+ const char *ssh_command = "ssh";
+ char *rune = NULL;
+ char *host;
+ int opt, daemonize = 1, monitor = 1, debug = 0, pause_after_migration = 0;
+ static struct option opts[] = {
+ {"debug", 0, 0, 0x100},
+ {"live", 0, 0, 0x200},
+ COMMON_LONG_OPTS
+ };
+
+ SWITCH_FOREACH_OPT(opt, "FC:s:ep", opts, "migrate", 2) {
+ case 'C':
+ config_filename = optarg;
+ break;
+ case 's':
+ ssh_command = optarg;
+ break;
+ case 'F':
+ daemonize = 0;
+ break;
+ case 'e':
+ daemonize = 0;
+ monitor = 0;
+ break;
+ case 'p':
+ pause_after_migration = 1;
+ break;
+ case 0x100: /* --debug */
+ debug = 1;
+ break;
+ case 0x200: /* --live */
+ /* ignored for compatibility with xm */
+ break;
+ }
+
+ domid = xfind_domain(argv[optind]);
+ host = argv[optind + 1];
+
+ bool pass_tty_arg = progress_use_cr || (isatty(2) > 0);
+
+ if (!ssh_command[0]) {
+ rune= host;
+ } else {
+ char verbose_buf[minmsglevel_default+3];
+ int verbose_len;
+ verbose_buf[0] = ' ';
+ verbose_buf[1] = '-';
+ memset(verbose_buf+2, 'v', minmsglevel_default);
+ verbose_buf[sizeof(verbose_buf)-1] = 0;
+ if (minmsglevel == minmsglevel_default) {
+ verbose_len = 0;
+ } else {
+ verbose_len = (minmsglevel_default - minmsglevel) + 2;
+ }
+ xasprintf(&rune, "exec %s %s xl%s%.*s migrate-receive%s%s%s",
+ ssh_command, host,
+ pass_tty_arg ? " -t" : "",
+ verbose_len, verbose_buf,
+ daemonize ? "" : " -e",
+ debug ? " -d" : "",
+ pause_after_migration ? " -p" : "");
+ }
+
+ migrate_domain(domid, rune, debug, config_filename);
+ return EXIT_SUCCESS;
+}
+
+int main_remus(int argc, char **argv)
+{
+ uint32_t domid;
+ int opt, rc, daemonize = 1;
+ const char *ssh_command = "ssh";
+ char *host = NULL, *rune = NULL;
+ libxl_domain_remus_info r_info;
+ int send_fd = -1, recv_fd = -1;
+ pid_t child = -1;
+ uint8_t *config_data;
+ int config_len;
+
+ memset(&r_info, 0, sizeof(libxl_domain_remus_info));
+
+ SWITCH_FOREACH_OPT(opt, "Fbundi:s:N:ec", NULL, "remus", 2) {
+ case 'i':
+ r_info.interval = atoi(optarg);
+ break;
+ case 'F':
+ libxl_defbool_set(&r_info.allow_unsafe, true);
+ break;
+ case 'b':
+ libxl_defbool_set(&r_info.blackhole, true);
+ break;
+ case 'u':
+ libxl_defbool_set(&r_info.compression, false);
+ break;
+ case 'n':
+ libxl_defbool_set(&r_info.netbuf, false);
+ break;
+ case 'N':
+ r_info.netbufscript = optarg;
+ break;
+ case 'd':
+ libxl_defbool_set(&r_info.diskbuf, false);
+ break;
+ case 's':
+ ssh_command = optarg;
+ break;
+ case 'e':
+ daemonize = 0;
+ break;
+ case 'c':
+ libxl_defbool_set(&r_info.colo, true);
+ }
+
+ domid = xfind_domain(argv[optind]);
+ host = argv[optind + 1];
+
+ /* Defaults */
+ libxl_defbool_setdefault(&r_info.blackhole, false);
+ libxl_defbool_setdefault(&r_info.colo, false);
+ if (!libxl_defbool_val(r_info.colo) && !r_info.interval)
+ r_info.interval = 200;
+
+ if (libxl_defbool_val(r_info.colo)) {
+ if (r_info.interval || libxl_defbool_val(r_info.blackhole) ||
+ !libxl_defbool_is_default(r_info.netbuf) ||
+ !libxl_defbool_is_default(r_info.diskbuf)) {
+ perror("option -c is conflict with -i, -d, -n or -b");
+ exit(-1);
+ }
+
+ if (libxl_defbool_is_default(r_info.compression)) {
+ perror("COLO can't be used with memory compression. "
+ "Disable memory checkpoint compression now...");
+ libxl_defbool_set(&r_info.compression, false);
+ }
+ }
+
+ if (!r_info.netbufscript) {
+ if (libxl_defbool_val(r_info.colo))
+ r_info.netbufscript = default_colo_proxy_script;
+ else
+ r_info.netbufscript = default_remus_netbufscript;
+ }
+
+ if (libxl_defbool_val(r_info.blackhole)) {
+ send_fd = open("/dev/null", O_RDWR, 0644);
+ if (send_fd < 0) {
+ perror("failed to open /dev/null");
+ exit(EXIT_FAILURE);
+ }
+ } else {
+
+ if (!ssh_command[0]) {
+ rune = host;
+ } else {
+ if (!libxl_defbool_val(r_info.colo)) {
+ xasprintf(&rune, "exec %s %s xl migrate-receive %s %s",
+ ssh_command, host,
+ "-r",
+ daemonize ? "" : " -e");
+ } else {
+ xasprintf(&rune, "exec %s %s xl migrate-receive %s %s %s %s",
+ ssh_command, host,
+ "--colo",
+ r_info.netbufscript ? "--coloft-script" : "",
+ r_info.netbufscript ? r_info.netbufscript : "",
+ daemonize ? "" : " -e");
+ }
+ }
+
+ save_domain_core_begin(domid, NULL, &config_data, &config_len);
+
+ if (!config_len) {
+ fprintf(stderr, "No config file stored for running domain and "
+ "none supplied - cannot start remus.\n");
+ exit(EXIT_FAILURE);
+ }
+
+ child = create_migration_child(rune, &send_fd, &recv_fd);
+
+ migrate_do_preamble(send_fd, recv_fd, child, config_data, config_len,
+ rune);
+
+ if (ssh_command[0])
+ free(rune);
+ }
+
+ /* Point of no return */
+ rc = libxl_domain_remus_start(ctx, &r_info, domid, send_fd, recv_fd, 0);
+
+ /* check if the domain exists. User may have xl destroyed the
+ * domain to force failover
+ */
+ if (libxl_domain_info(ctx, 0, domid)) {
+ fprintf(stderr, "%s: Primary domain has been destroyed.\n",
+ libxl_defbool_val(r_info.colo) ? "COLO" : "Remus");
+ close(send_fd);
+ return EXIT_SUCCESS;
+ }
+
+ /* If we are here, it means remus setup/domain suspend/backup has
+ * failed. Try to resume the domain and exit gracefully.
+ * TODO: Split-Brain check.
+ */
+ if (rc == ERROR_GUEST_TIMEDOUT)
+ fprintf(stderr, "Failed to suspend domain at primary.\n");
+ else {
+ fprintf(stderr, "%s: Backup failed? resuming domain at primary.\n",
+ libxl_defbool_val(r_info.colo) ? "COLO" : "Remus");
+ libxl_domain_resume(ctx, domid, 1, 0);
+ }
+
+ close(send_fd);
+ return EXIT_FAILURE;
+}
+#endif
+
+
+/*
+ * Local variables:
+ * mode: C
+ * c-basic-offset: 4
+ * indent-tabs-mode: nil
+ * End:
+ */
--
2.11.0
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
https://lists.xen.org/xen-devel
|
 |
Lists.xenproject.org is hosted with RackSpace, monitoring our |