[PATCH 4 of 4 V5] tools/xl: Remus - Network buffering cmdline switch

[Shriram Rajagopalan <rshriram@cs.ubc.ca>]

# HG changeset patch
# User Shriram Rajagopalan <rshriram@cs.ubc.ca>
# Date 1384804015 28800
# Node ID 3c11efb5e8fef9f070272edefed47f31b7c619ef
# Parent  94eea030e0095ebd62bd6b40e02a819fdb778c82
tools/xl: Remus - Network buffering cmdline switch

Command line switch to 'xl remus' command, to enable network buffering.
Pass on this flag to libxl so that it can act accordingly.
Also update man pages to reflect the addition of a new option to
'xl remus' command.

Signed-off-by: Shriram Rajagopalan <rshriram@cs.ubc.ca>

diff -r 94eea030e009 -r 3c11efb5e8fe docs/man/xl.conf.pod.5
--- a/docs/man/xl.conf.pod.5	Mon Nov 18 11:10:02 2013 -0800
+++ b/docs/man/xl.conf.pod.5	Mon Nov 18 11:46:55 2013 -0800
@@ -105,6 +105,12 @@ Configures the default gateway device to
 
 Default: C<None>
 
+=item B<remus.default.netbufscript="PATH">
+
+Configures the default script used by Remus to setup network buffering.
+
+Default: C</etc/xen/scripts/remus-netbuf-setup>
+
 =item B<output_format="json|sxp">
 
 Configures the default output format used by xl when printing "machine
diff -r 94eea030e009 -r 3c11efb5e8fe docs/man/xl.pod.1
--- a/docs/man/xl.pod.1	Mon Nov 18 11:10:02 2013 -0800
+++ b/docs/man/xl.pod.1	Mon Nov 18 11:46:55 2013 -0800
@@ -398,8 +398,7 @@ Print huge (!) amount of debug during th
 Enable Remus 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.
-     There is no support for network or disk buffering at the moment.
+N.B: There is no support for disk buffering at the moment.
 
 B<OPTIONS>
 
@@ -418,6 +417,18 @@ Generally useful for debugging.
 
 Disable memory checkpoint compression.
 
+=item B<-n>
+
+Enable network output buffering.  The default script used to configure
+network buffering is /etc/xen/scripts/remus-netbuf-setup. If you wish to
+use a custom script, use the I<-N> option or set the global variable
+I<remus.default.netbufscript> in /etc/xen/xl.conf to point to your script.
+
+=item B<-N> I<netbufscript>
+
+Use <netbufscript> to setup network buffering instead of the instead of
+the default (/etc/xen/scripts/remus-netbuf-setup).
+
 =item B<-s> I<sshcommand>
 
 Use <sshcommand> instead of ssh.  String will be passed to sh.
diff -r 94eea030e009 -r 3c11efb5e8fe tools/libxl/xl.c
--- a/tools/libxl/xl.c	Mon Nov 18 11:10:02 2013 -0800
+++ b/tools/libxl/xl.c	Mon Nov 18 11:46:55 2013 -0800
@@ -46,6 +46,7 @@ char *default_vifscript = NULL;
 char *default_bridge = NULL;
 char *default_gatewaydev = NULL;
 char *default_vifbackend = NULL;
+char *default_remus_netbufscript = NULL;
 enum output_format default_output_format = OUTPUT_FORMAT_JSON;
 int claim_mode = 1;
 
@@ -177,6 +178,9 @@ static void parse_global_config(const ch
     if (!xlu_cfg_get_long (config, "claim_mode", &l, 0))
         claim_mode = l;
 
+    xlu_cfg_replace_string (config, "remus.default.netbufscript",
+                            &default_remus_netbufscript, 0);
+
     xlu_cfg_destroy(config);
 }
 
diff -r 94eea030e009 -r 3c11efb5e8fe tools/libxl/xl.h
--- a/tools/libxl/xl.h	Mon Nov 18 11:10:02 2013 -0800
+++ b/tools/libxl/xl.h	Mon Nov 18 11:46:55 2013 -0800
@@ -152,6 +152,7 @@ extern char *default_vifscript;
 extern char *default_bridge;
 extern char *default_gatewaydev;
 extern char *default_vifbackend;
+extern char *default_remus_netbufscript;
 extern char *blkdev_start;
 
 enum output_format {
diff -r 94eea030e009 -r 3c11efb5e8fe tools/libxl/xl_cmdimpl.c
--- a/tools/libxl/xl_cmdimpl.c	Mon Nov 18 11:10:02 2013 -0800
+++ b/tools/libxl/xl_cmdimpl.c	Mon Nov 18 11:46:55 2013 -0800
@@ -7116,8 +7116,9 @@ int main_remus(int argc, char **argv)
     r_info.interval = 200;
     r_info.blackhole = 0;
     r_info.compression = 1;
-
-    SWITCH_FOREACH_OPT(opt, "bui:s:e", NULL, "remus", 2) {
+    r_info.netbuf = 0;
+
+    SWITCH_FOREACH_OPT(opt, "buni:s:N:e", NULL, "remus", 2) {
     case 'i':
         r_info.interval = atoi(optarg);
         break;
@@ -7127,6 +7128,12 @@ int main_remus(int argc, char **argv)
     case 'u':
         r_info.compression = 0;
         break;
+    case 'n':
+        r_info.netbuf = 1;
+        break;
+    case 'N':
+        r_info.netbufscript = optarg;
+        break;
     case 's':
         ssh_command = optarg;
         break;
@@ -7138,6 +7145,9 @@ int main_remus(int argc, char **argv)
     domid = find_domain(argv[optind]);
     host = argv[optind + 1];
 
+    if(!r_info.netbufscript)
+        r_info.netbufscript = default_remus_netbufscript;
+
     if (r_info.blackhole) {
         send_fd = open("/dev/null", O_RDWR, 0644);
         if (send_fd < 0) {
@@ -7175,13 +7185,19 @@ int main_remus(int argc, char **argv)
     /* Point of no return */
     rc = libxl_domain_remus_start(ctx, &r_info, domid, send_fd, recv_fd, 0);
 
-    /* If we are here, it means backup has failed/domain suspend failed.
-     * Try to resume the domain and exit gracefully.
+    /* check if the domain exists. User may have xl destroyed the
+     * domain to force failover
+     */
+    if (libxl_domain_info(ctx, 0, domid)) {
+        fprintf(stderr, "Remus: Primary domain has been destroyed.\n");
+        close(send_fd);
+        return 0;
+    }
+
+    /* 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.
      */
-    fprintf(stderr, "remus sender: libxl_domain_suspend failed"
-            " (rc=%d)\n", rc);
-
     if (rc == ERROR_GUEST_TIMEDOUT)
         fprintf(stderr, "Failed to suspend domain at primary.\n");
     else {
diff -r 94eea030e009 -r 3c11efb5e8fe tools/libxl/xl_cmdtable.c
--- a/tools/libxl/xl_cmdtable.c	Mon Nov 18 11:10:02 2013 -0800
+++ b/tools/libxl/xl_cmdtable.c	Mon Nov 18 11:46:55 2013 -0800
@@ -481,6 +481,9 @@ struct cmd_spec cmd_table[] = {
       "-i MS                   Checkpoint domain memory every MS milliseconds (def. 200ms).\n"
       "-b                      Replicate memory checkpoints to /dev/null (blackhole)\n"
       "-u                      Disable memory checkpoint compression.\n"
+      "-n                      Enable network output buffering.\n"
+      "-N <netbufscript>       Use netbufscript to setup network buffering instead of the\n"
+      "                        instead of the default (/etc/xen/scripts/remus-netbuf-setup).\n"
       "-s <sshcommand>         Use <sshcommand> instead of ssh.  String will be passed\n"
       "                        to sh. If empty, run <host> instead of \n"
       "                        ssh <host> xl migrate-receive -r [-e]\n"