@@ -447,12 +447,16 @@ Print huge (!) amount of debug during the migration process.
=item B<remus> [I<OPTIONS>] I<domain-id> I<host>
-Enable Remus HA for domain. By default B<xl> relies on ssh as a transport
-mechanism between the two hosts.
+Enable Remus HA or COLO HA for domain. By default B<xl> relies on ssh as a
+transport mechanism between the two hosts.
N.B: Remus support in xl is still in experimental (proof-of-concept) phase.
Disk replication support is limited to DRBD disks.
+ COLO support in xl is still in experimental (proof-of-concept) phase.
+ There is no support for network or disk, so the guest will corrupt its
+ disk and confuse its network peers at the moment.
+
B<OPTIONS>
=over 4
@@ -498,6 +502,11 @@ Disable network output buffering. Requires enabling unsafe mode.
Disable disk replication. Requires enabling unsafe mode.
+=item B<-c>
+
+Enable COLO HA. This conflicts with B<-i> and B<-b>, and memory
+checkpoint compression must be disabled.
+
=back
=item B<pause> I<domain-id>
@@ -848,12 +848,27 @@ int libxl_domain_remus_start(libxl_ctx *ctx, libxl_domain_remus_info *info,
goto out;
}
+ /* The caller must set this defbool */
+ if (libxl_defbool_is_default(info->colo)) {
+ LOG(ERROR, "colo mode must be enabled/disabled");
+ rc = ERROR_FAIL;
+ goto out;
+ }
+
libxl_defbool_setdefault(&info->allow_unsafe, false);
libxl_defbool_setdefault(&info->blackhole, false);
- libxl_defbool_setdefault(&info->compression, true);
+ libxl_defbool_setdefault(&info->compression,
+ !libxl_defbool_val(info->colo));
libxl_defbool_setdefault(&info->netbuf, true);
libxl_defbool_setdefault(&info->diskbuf, true);
+ if (libxl_defbool_val(info->colo) &&
+ libxl_defbool_val(info->compression)) {
+ LOG(ERROR, "cannot use memory checkpoint compression in COLO mode");
+ rc = ERROR_FAIL;
+ goto out;
+ }
+
if (!libxl_defbool_val(info->allow_unsafe) &&
(libxl_defbool_val(info->blackhole) ||
!libxl_defbool_val(info->netbuf) ||
@@ -875,7 +890,10 @@ int libxl_domain_remus_start(libxl_ctx *ctx, libxl_domain_remus_info *info,
dss->live = 1;
dss->debug = 0;
dss->remus = info;
- dss->checkpointed_stream = LIBXL_CHECKPOINTED_STREAM_REMUS;
+ if (libxl_defbool_val(info->colo))
+ dss->checkpointed_stream = LIBXL_CHECKPOINTED_STREAM_COLO;
+ else
+ dss->checkpointed_stream = LIBXL_CHECKPOINTED_STREAM_REMUS;
assert(info);
@@ -1893,7 +1893,6 @@ int libxl_domain_create_restore(libxl_ctx *ctx, libxl_domain_config *d_config,
const libxl_asyncop_how *ao_how,
const libxl_asyncprogress_how *aop_console_how)
{
- assert(send_back_fd == -1);
return do_domain_create(ctx, d_config, domid, restore_fd, send_back_fd,
params, ao_how, aop_console_how);
}
@@ -4740,6 +4740,8 @@ static void migrate_receive(int debug, int daemonize, int monitor,
char rc_buf;
char *migration_domname;
struct domain_create dom_info;
+ const char *ha = checkpointed == LIBXL_CHECKPOINTED_STREAM_COLO ?
+ "COLO" : "Remus";
signal(SIGPIPE, SIG_IGN);
/* if we get SIGPIPE we'd rather just have it as an error */
@@ -4757,7 +4759,7 @@ static void migrate_receive(int debug, int daemonize, int monitor,
dom_info.monitor = monitor;
dom_info.paused = 1;
dom_info.migrate_fd = recv_fd;
- dom_info.send_back_fd = -1;
+ dom_info.send_back_fd = send_fd;
dom_info.migration_domname_r = &migration_domname;
dom_info.checkpointed_stream = checkpointed;
@@ -4772,11 +4774,12 @@ static void migrate_receive(int debug, int daemonize, int monitor,
switch (checkpointed) {
case LIBXL_CHECKPOINTED_STREAM_REMUS:
+ case LIBXL_CHECKPOINTED_STREAM_COLO:
/* If we are here, it means that the sender (primary) has crashed.
* TODO: Split-Brain Check.
*/
- fprintf(stderr, "migration target: Remus Failover for domain %u\n",
- domid);
+ fprintf(stderr, "migration target: %s Failover for domain %u\n",
+ ha, domid);
/*
* If domain renaming fails, lets just continue (as we need the domain
@@ -4792,16 +4795,20 @@ static void migrate_receive(int debug, int daemonize, int monitor,
rc = libxl_domain_rename(ctx, domid, migration_domname,
common_domname);
if (rc)
- fprintf(stderr, "migration target (Remus): "
+ fprintf(stderr, "migration target (%s): "
"Failed to rename domain from %s to %s:%d\n",
- migration_domname, common_domname, rc);
+ 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 (Remus): "
+ fprintf(stderr, "migration target (%s): "
"Failed to unpause domain %s (id: %u):%d\n",
- common_domname, domid, rc);
+ ha, common_domname, domid, rc);
exit(rc ? -ERROR_FAIL: 0);
default:
@@ -4948,8 +4955,12 @@ int main_migrate_receive(int argc, char **argv)
int debug = 0, daemonize = 1, monitor = 1;
libxl_checkpointed_stream checkpointed = LIBXL_CHECKPOINTED_STREAM_NONE;
int opt;
+ static struct option opts[] = {
+ {"colo", 0, 0, 0x100},
+ COMMON_LONG_OPTS
+ };
- SWITCH_FOREACH_OPT(opt, "Fedr", NULL, "migrate-receive", 0) {
+ SWITCH_FOREACH_OPT(opt, "Fedr", opts, "migrate-receive", 0) {
case 'F':
daemonize = 0;
break;
@@ -4963,6 +4974,9 @@ int main_migrate_receive(int argc, char **argv)
case 'r':
checkpointed = LIBXL_CHECKPOINTED_STREAM_REMUS;
break;
+ case 0x100:
+ checkpointed = LIBXL_CHECKPOINTED_STREAM_COLO;
+ break;
}
if (argc-optind != 0) {
@@ -8338,11 +8352,8 @@ int main_remus(int argc, char **argv)
int config_len;
memset(&r_info, 0, sizeof(libxl_domain_remus_info));
- /* Defaults */
- r_info.interval = 200;
- libxl_defbool_setdefault(&r_info.blackhole, false);
- SWITCH_FOREACH_OPT(opt, "Fbundi:s:N:e", NULL, "remus", 2) {
+ SWITCH_FOREACH_OPT(opt, "Fbundi:s:N:ec", NULL, "remus", 2) {
case 'i':
r_info.interval = atoi(optarg);
break;
@@ -8370,11 +8381,32 @@ int main_remus(int argc, char **argv)
case 'e':
daemonize = 0;
break;
+ case 'c':
+ libxl_defbool_set(&r_info.colo, true);
}
domid = find_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)) {
+ perror("Option -c conflicts with -i 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)
r_info.netbufscript = default_remus_netbufscript;
@@ -8389,8 +8421,9 @@ int main_remus(int argc, char **argv)
if (!ssh_command[0]) {
rune = host;
} else {
- xasprintf(&rune, "exec %s %s xl migrate-receive -r %s",
+ xasprintf(&rune, "exec %s %s xl migrate-receive %s %s",
ssh_command, host,
+ libxl_defbool_val(r_info.colo) ? "-c" : "-r",
daemonize ? "" : " -e");
}
@@ -8418,7 +8451,8 @@ int main_remus(int argc, char **argv)
* domain to force failover
*/
if (libxl_domain_info(ctx, 0, domid)) {
- fprintf(stderr, "Remus: Primary domain has been destroyed.\n");
+ fprintf(stderr, "%s: Primary domain has been destroyed.\n",
+ libxl_defbool_val(r_info.colo) ? "COLO" : "Remus");
close(send_fd);
return 0;
}
@@ -8430,7 +8464,8 @@ int main_remus(int argc, char **argv)
if (rc == ERROR_GUEST_TIMEDOUT)
fprintf(stderr, "Failed to suspend domain at primary.\n");
else {
- fprintf(stderr, "Remus: Backup failed? resuming domain at primary.\n");
+ 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);
}
@@ -499,7 +499,9 @@ struct cmd_spec cmd_table[] = {
"-b Replicate memory checkpoints to /dev/null (blackhole).\n"
" Works only in unsafe mode.\n"
"-n Disable network output buffering. Works only in unsafe mode.\n"
- "-d Disable disk replication. Works only in unsafe mode."
+ "-d Disable disk replication. Works only in unsafe mode.\n"
+ "-c Enable COLO HA. It is conflict with -i and -b, and memory\n"
+ " checkpoint must be disabled"
},
#endif
{ "devd",