From: Wen Congyang <wency@cn.fujitsu.com>
To: xen devel <xen-devel@lists.xen.org>
Cc: Ian Campbell <Ian.Campbell@citrix.com>,
Wen Congyang <wency@cn.fujitsu.com>,
Ian Jackson <Ian.Jackson@eu.citrix.com>,
Jiang Yunhong <yunhong.jiang@intel.com>,
Dong Eddie <eddie.dong@intel.com>,
Yang Hongyang <yanghy@cn.fujitsu.com>,
Lai Jiangshan <laijs@cn.fujitsu.com>
Subject: [RFC Patch 22/25] implement the cmdline for COLO
Date: Fri, 18 Jul 2014 19:39:07 +0800 [thread overview]
Message-ID: <1405683551-12579-23-git-send-email-wency@cn.fujitsu.com> (raw)
In-Reply-To: <1405683551-12579-1-git-send-email-wency@cn.fujitsu.com>
Add a new option -c to the command 'xl remus'. If you want
to use COLO HA instead of Remus HA, please use -c option.
Update man pages to reflect the addition of a new option to
'xl remus' command.
Also add a new option -c to the internal command 'xl migrate-receive'.
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
---
docs/man/xl.pod.1 | 9 ++++++++-
tools/libxl/xl_cmdimpl.c | 47 ++++++++++++++++++++++++++++++++++++++---------
tools/libxl/xl_cmdtable.c | 3 ++-
3 files changed, 48 insertions(+), 11 deletions(-)
diff --git a/docs/man/xl.pod.1 b/docs/man/xl.pod.1
index 547e8a2..accdbe5 100644
--- a/docs/man/xl.pod.1
+++ b/docs/man/xl.pod.1
@@ -427,12 +427,15 @@ 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
+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 buffering 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 at the moment.
+
B<OPTIONS>
=over 4
@@ -473,6 +476,10 @@ If empty, run <host> instead of ssh <host> xl migrate-receive -r [-e].
On the new host, do not wait in the background (on <host>) for the death
of the domain. See the corresponding option of the I<create> subcommand.
+=item B<-c>
+
+Enable COLO HA. It is conflict with B<-i> and B<-b>.
+
=back
=item B<pause> I<domain-id>
diff --git a/tools/libxl/xl_cmdimpl.c b/tools/libxl/xl_cmdimpl.c
index 22b7964..1839555 100644
--- a/tools/libxl/xl_cmdimpl.c
+++ b/tools/libxl/xl_cmdimpl.c
@@ -3710,6 +3710,9 @@ static void migrate_receive(int debug, int daemonize, int monitor,
dom_info.send_fd = send_fd;
dom_info.migration_domname_r = &migration_domname;
dom_info.checkpointed_stream = remus;
+ if (remus == LIBXL_CHECKPOINTED_STREAM_COLO)
+ /* COLO uses stdout to send control message to master */
+ dom_info.quiet = 1;
rc = create_domain(&dom_info);
if (rc < 0) {
@@ -3724,7 +3727,8 @@ static void migrate_receive(int debug, int daemonize, int monitor,
/* 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",
+ fprintf(stderr, "migration target: %s Failover for domain %u\n",
+ remus == LIBXL_CHECKPOINTED_STREAM_COLO ? "COLO" : "Remus",
domid);
/*
@@ -3741,15 +3745,21 @@ 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",
+ remus == LIBXL_CHECKPOINTED_STREAM_COLO ? "COLO" : "Remus",
migration_domname, common_domname, rc);
}
+ if (remus == 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",
+ remus == LIBXL_CHECKPOINTED_STREAM_COLO ? "COLO" : "Remus",
common_domname, domid, rc);
exit(rc ? -ERROR_FAIL: 0);
@@ -3895,7 +3905,7 @@ int main_migrate_receive(int argc, char **argv)
int debug = 0, daemonize = 1, monitor = 1, remus = 0;
int opt;
- SWITCH_FOREACH_OPT(opt, "Fedr", NULL, "migrate-receive", 0) {
+ SWITCH_FOREACH_OPT(opt, "Fedrc", NULL, "migrate-receive", 0) {
case 'F':
daemonize = 0;
break;
@@ -3907,8 +3917,10 @@ int main_migrate_receive(int argc, char **argv)
debug = 1;
break;
case 'r':
- remus = 1;
+ remus = LIBXL_CHECKPOINTED_STREAM_REMUS;
break;
+ case 'c':
+ remus = LIBXL_CHECKPOINTED_STREAM_COLO;
}
if (argc-optind != 0) {
@@ -7176,6 +7188,7 @@ int main_remus(int argc, char **argv)
pid_t child = -1;
uint8_t *config_data;
int config_len;
+ int interval = 0;
memset(&r_info, 0, sizeof(libxl_domain_remus_info));
/* Defaults */
@@ -7185,9 +7198,10 @@ int main_remus(int argc, char **argv)
r_info.netbuf = 1;
r_info.diskbuf = 1;
- SWITCH_FOREACH_OPT(opt, "bundi:s:N:e", NULL, "remus", 2) {
+ SWITCH_FOREACH_OPT(opt, "bundi:s:N:ec", NULL, "remus", 2) {
case 'i':
r_info.interval = atoi(optarg);
+ interval = 1;
break;
case 'b':
r_info.blackhole = 1;
@@ -7210,11 +7224,23 @@ int main_remus(int argc, char **argv)
case 'e':
daemonize = 0;
break;
+ case 'c':
+ r_info.colo = 1;
}
domid = find_domain(argv[optind]);
host = argv[optind + 1];
+ if (r_info.colo) {
+ if (!interval)
+ r_info.interval = 0;
+
+ if (r_info.interval + r_info.blackhole > 0) {
+ perror("option c is conflict with i or b");
+ exit(-1);
+ }
+ }
+
if (!r_info.netbufscript)
r_info.netbufscript = default_remus_netbufscript;
@@ -7229,8 +7255,9 @@ int main_remus(int argc, char **argv)
if (!ssh_command[0]) {
rune = host;
} else {
- if (asprintf(&rune, "exec %s %s xl migrate-receive -r %s",
+ if (asprintf(&rune, "exec %s %s xl migrate-receive %s %s",
ssh_command, host,
+ r_info.colo ? "-c" : "-r",
daemonize ? "" : " -e") < 0)
return 1;
}
@@ -7259,7 +7286,8 @@ 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",
+ r_info.colo ? "COLO" : "Remus");
close(send_fd);
return 0;
}
@@ -7271,7 +7299,8 @@ 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",
+ r_info.colo ? "COLO" : "Remus");
libxl_domain_resume(ctx, domid, 1, 0);
}
diff --git a/tools/libxl/xl_cmdtable.c b/tools/libxl/xl_cmdtable.c
index 246aa11..b91b638 100644
--- a/tools/libxl/xl_cmdtable.c
+++ b/tools/libxl/xl_cmdtable.c
@@ -495,7 +495,8 @@ struct cmd_spec cmd_table[] = {
" to sh. If empty, run <host> instead of \n"
" ssh <host> xl migrate-receive -r [-e]\n"
"-e Do not wait in the background (on <host>) for the death\n"
- " of the domain."
+ " of the domain.\n"
+ "-c Enable COLO HA. It is conflict with -i and -b"
},
#endif
{ "devd",
--
1.9.3
next prev parent reply other threads:[~2014-07-18 11:39 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-07-18 11:38 [RFC Patch 00/25] COarse-grain LOck-stepping Virtual Machines for Non-stop Service Wen Congyang
2014-07-18 11:38 ` [RFC Patch 01/25] copy the correct page to memory Wen Congyang
2014-07-18 11:38 ` [RFC Patch 02/25] csum the correct page Wen Congyang
2014-07-18 11:38 ` [RFC Patch 03/25] don't zero out ioreq page Wen Congyang
2014-07-18 11:38 ` [RFC Patch 04/25] don't touch remus in remus_device Wen Congyang
2014-07-18 11:38 ` [RFC Patch 05/25] rename remus device to checkpoint device Wen Congyang
2014-07-18 11:38 ` [RFC Patch 06/25] adjust the indentation Wen Congyang
2014-07-18 11:38 ` [RFC Patch 07/25] Refactor domain_suspend_callback_common() Wen Congyang
2014-07-18 11:38 ` [RFC Patch 08/25] Update libxl__domain_resume() for colo Wen Congyang
2014-07-18 11:38 ` [RFC Patch 09/25] Update libxl__domain_suspend_common_switch_qemu_logdirty() " Wen Congyang
2014-07-18 11:38 ` [RFC Patch 10/25] Introduce a new internal API libxl__domain_unpause() Wen Congyang
2014-07-18 11:38 ` [RFC Patch 11/25] Update libxl__domain_unpause() to support qemu-xen Wen Congyang
2014-07-18 11:38 ` [RFC Patch 12/25] support to resume uncooperative HVM guests Wen Congyang
2014-07-18 11:38 ` [RFC Patch 13/25] update datecopier to support sending data only Wen Congyang
2014-07-18 11:38 ` [RFC Patch 14/25] introduce a new API to aync read data from fd Wen Congyang
2014-07-18 11:39 ` [RFC Patch 15/25] Update libxl_save_msgs_gen.pl to support return data from xl to xc Wen Congyang
2014-07-18 11:39 ` [RFC Patch 16/25] Allow slave sends data to master Wen Congyang
2014-07-18 11:39 ` [RFC Patch 17/25] secondary vm suspend/resume/checkpoint code Wen Congyang
2014-07-18 11:39 ` [RFC Patch 18/25] primary vm suspend/get_dirty_pfn/resume/checkpoint code Wen Congyang
2014-07-18 11:39 ` [RFC Patch 19/25] xc_domain_save: flush cache before calling callbacks->postcopy() in colo mode Wen Congyang
2014-07-18 11:39 ` [RFC Patch 20/25] COLO: xc related codes Wen Congyang
2014-07-18 11:39 ` [RFC Patch 21/25] send store mfn and console mfn to xl before resuming secondary vm Wen Congyang
2014-07-18 11:39 ` Wen Congyang [this message]
2014-07-18 11:39 ` [RFC Patch 23/25] HACK: do checkpoint per 20ms Wen Congyang
2014-07-18 11:39 ` [RFC Patch 24/25] fix vm entry fail Wen Congyang
2014-07-24 10:40 ` Tim Deegan
2014-07-25 5:39 ` Wen Congyang
2014-08-07 6:52 ` Wen Congyang
2014-07-18 11:39 ` [RFC Patch 25/25] sync mmu before resuming secondary vm Wen Congyang
2014-07-24 10:59 ` Tim Deegan
2014-07-25 5:46 ` Wen Congyang
2014-08-07 7:46 ` Wen Congyang
2014-07-18 11:39 ` [RFC Patch 26/25] Introduce "xen-load-devices-state" Wen Congyang
2014-07-18 11:43 ` [RFC Patch 00/25] COarse-grain LOck-stepping Virtual Machines for Non-stop Service Wen Congyang
2014-07-18 14:18 ` Andrew Cooper
2014-07-18 14:30 ` Wen Congyang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1405683551-12579-23-git-send-email-wency@cn.fujitsu.com \
--to=wency@cn.fujitsu.com \
--cc=Ian.Campbell@citrix.com \
--cc=Ian.Jackson@eu.citrix.com \
--cc=eddie.dong@intel.com \
--cc=laijs@cn.fujitsu.com \
--cc=xen-devel@lists.xen.org \
--cc=yanghy@cn.fujitsu.com \
--cc=yunhong.jiang@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).