xen-devel.lists.xenproject.org archive mirror
 help / color / mirror / Atom feed
From: Yang Hongyang <yanghy@cn.fujitsu.com>
To: xen-devel@lists.xen.org
Cc: wei.liu2@citrix.com, ian.campbell@citrix.com,
	wency@cn.fujitsu.com, andrew.cooper3@citrix.com,
	yunhong.jiang@intel.com, eddie.dong@intel.com,
	guijianfeng@cn.fujitsu.com, rshriram@cs.ubc.ca,
	ian.jackson@eu.citrix.com
Subject: [PATCH v7 COLO 10/18] implement the cmdline for COLO
Date: Thu, 25 Jun 2015 14:31:04 +0800	[thread overview]
Message-ID: <1435213872-10698-11-git-send-email-yanghy@cn.fujitsu.com> (raw)
In-Reply-To: <1435213872-10698-1-git-send-email-yanghy@cn.fujitsu.com>

From: Wen Congyang <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>
Signed-off-by: Yang Hongyang <yanghy@cn.fujitsu.com>
---
 docs/man/xl.pod.1         | 12 ++++++++--
 tools/libxl/libxl.c       | 23 ++++++++++++++++--
 tools/libxl/xl_cmdimpl.c  | 61 ++++++++++++++++++++++++++++++++++++-----------
 tools/libxl/xl_cmdtable.c |  4 +++-
 4 files changed, 81 insertions(+), 19 deletions(-)

diff --git a/docs/man/xl.pod.1 b/docs/man/xl.pod.1
index 4eb929d..4260c60 100644
--- a/docs/man/xl.pod.1
+++ b/docs/man/xl.pod.1
@@ -447,12 +447,15 @@ 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
-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 at the moment.
+
 B<OPTIONS>
 
 =over 4
@@ -498,6 +501,11 @@ 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>
diff --git a/tools/libxl/libxl.c b/tools/libxl/libxl.c
index 8b866f4..08ae7a7 100644
--- a/tools/libxl/libxl.c
+++ b/tools/libxl/libxl.c
@@ -811,12 +811,28 @@ 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)) {
+        if (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) ||
@@ -838,7 +854,10 @@ 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);
 
diff --git a/tools/libxl/xl_cmdimpl.c b/tools/libxl/xl_cmdimpl.c
index 83164bc..eb1b45f 100644
--- a/tools/libxl/xl_cmdimpl.c
+++ b/tools/libxl/xl_cmdimpl.c
@@ -4259,6 +4259,8 @@ 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 */
@@ -4279,6 +4281,9 @@ 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 = checkpointed;
+    if (checkpointed == 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) {
@@ -4293,8 +4298,8 @@ 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",
-                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
@@ -4310,16 +4315,20 @@ 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);
     }
@@ -4465,7 +4474,7 @@ int main_migrate_receive(int argc, char **argv)
     int checkpointed = LIBXL_CHECKPOINTED_STREAM_NONE;
     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;
@@ -4479,6 +4488,9 @@ int main_migrate_receive(int argc, char **argv)
     case 'r':
         checkpointed = LIBXL_CHECKPOINTED_STREAM_REMUS;
         break;
+    case 'c':
+        checkpointed = LIBXL_CHECKPOINTED_STREAM_COLO;
+        break;
     }
 
     if (argc-optind != 0) {
@@ -7967,11 +7979,8 @@ 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;
@@ -7999,11 +8008,32 @@ 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;
 
@@ -8018,8 +8048,9 @@ 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,
+                         libxl_defbool_val(r_info.colo) ? "-c" : "-r",
                          daemonize ? "" : " -e") < 0)
                 return 1;
         }
@@ -8048,7 +8079,8 @@ 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;
     }
@@ -8060,7 +8092,8 @@ 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);
     }
 
diff --git a/tools/libxl/xl_cmdtable.c b/tools/libxl/xl_cmdtable.c
index 7f4759b..611accf 100644
--- a/tools/libxl/xl_cmdtable.c
+++ b/tools/libxl/xl_cmdtable.c
@@ -515,7 +515,9 @@ 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",
-- 
1.9.1

  parent reply	other threads:[~2015-06-25  6:31 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-06-25  6:30 [PATCH v7 COLO 00/18] COarse-grain LOck-stepping Virtual Machines for Non-stop Service Yang Hongyang
2015-06-25  6:30 ` [PATCH v7 COLO 01/18] docs: add colo readme Yang Hongyang
2015-07-14 15:15   ` Ian Campbell
2015-06-25  6:30 ` [PATCH v7 COLO 02/18] tools/libxl: handle colo_context records in a libxl migration v2 stream Yang Hongyang
2015-07-14 15:19   ` Ian Campbell
2015-07-15  0:34     ` Yang Hongyang
2015-06-25  6:30 ` [PATCH v7 COLO 03/18] tools/libxl: write colo_context records into the stream Yang Hongyang
2015-06-25  6:30 ` [PATCH v7 COLO 04/18] secondary vm suspend/resume/checkpoint code Yang Hongyang
2015-06-25  6:30 ` [PATCH v7 COLO 05/18] primary " Yang Hongyang
2015-06-25  6:31 ` [PATCH v7 COLO 06/18] libxc/restore: support COLO restore Yang Hongyang
2015-06-25  6:31 ` [PATCH v7 COLO 07/18] libxc/restore: send dirty bitmap to primary when checkpoint under colo Yang Hongyang
2015-06-25  6:31 ` [PATCH v7 COLO 08/18] send store mfn and console mfn to xl before resuming secondary vm Yang Hongyang
2015-06-25  6:31 ` [PATCH v7 COLO 09/18] libxc/save: support COLO save Yang Hongyang
2015-06-25  6:31 ` Yang Hongyang [this message]
2015-06-25  6:31 ` [PATCH v7 COLO 11/18] Support colo mode for qemu disk Yang Hongyang
2015-06-25  6:31 ` [PATCH v7 COLO 12/18] COLO: use qemu block replication Yang Hongyang
2015-06-25  6:31 ` [PATCH v7 COLO 13/18] COLO proxy: implement setup/teardown of COLO proxy module Yang Hongyang
2015-06-25  6:31 ` [PATCH v7 COLO 14/18] COLO proxy: preresume, postresume and checkpoint Yang Hongyang
2015-06-25  6:31 ` [PATCH v7 COLO 15/18] COLO nic: implement COLO nic subkind Yang Hongyang
2015-06-25  6:31 ` [PATCH v7 COLO 16/18] setup and control colo proxy on primary side Yang Hongyang
2015-06-25  6:31 ` [PATCH v7 COLO 17/18] setup and control colo proxy on secondary side Yang Hongyang
2015-06-25  6:31 ` [PATCH v7 COLO 18/18] cmdline switches and config vars to control colo-proxy Yang Hongyang
2015-07-14 15:55 ` [PATCH v7 COLO 00/18] COarse-grain LOck-stepping Virtual Machines for Non-stop Service Ian Campbell
2015-07-15  0:41   ` Yang Hongyang

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=1435213872-10698-11-git-send-email-yanghy@cn.fujitsu.com \
    --to=yanghy@cn.fujitsu.com \
    --cc=andrew.cooper3@citrix.com \
    --cc=eddie.dong@intel.com \
    --cc=guijianfeng@cn.fujitsu.com \
    --cc=ian.campbell@citrix.com \
    --cc=ian.jackson@eu.citrix.com \
    --cc=rshriram@cs.ubc.ca \
    --cc=wei.liu2@citrix.com \
    --cc=wency@cn.fujitsu.com \
    --cc=xen-devel@lists.xen.org \
    --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).