[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Xen-devel] [PATCH 2 of 2] libxl: Remus - xl remus command



# HG changeset patch
# User Shriram Rajagopalan <rshriram@xxxxxxxxx>
# Date 1327972788 28800
# Node ID 070f78ba4244cf8239ded3a69ccd54ac6e1bd24d
# Parent  0129989da2cda789f86f2bc83d9c642a0bcebe60
libxl: Remus - xl remus command

xl remus acts as a frontend to enable remus for a given domain.
 * At the moment, only memory checkpointing and blackhole replication is
   supported. Support for disk checkpointing and network buffering will
   be added in future.
 * Replication is done over ssh connection currently (like live migration
   with xl). Future versions will have an option to use simple tcp socket
   based replication channel (for both Remus & live migration).

Signed-off-by: Shriram Rajagopalan <rshriram@xxxxxxxxx>

diff -r 0129989da2cd -r 070f78ba4244 tools/libxl/libxl.c
--- a/tools/libxl/libxl.c       Mon Jan 30 17:19:46 2012 -0800
+++ b/tools/libxl/libxl.c       Mon Jan 30 17:19:48 2012 -0800
@@ -471,6 +471,40 @@ libxl_vminfo * libxl_list_vm(libxl_ctx *
     return ptr;
 }
 
+int libxl_domain_remus_start(libxl_ctx *ctx, libxl_domain_remus_info *info,
+                             uint32_t domid, int fd)
+{
+    GC_INIT(ctx);
+    libxl_domain_type type = libxl__domain_type(gc, domid);
+    int rc = 0;
+
+    if (info == NULL) {
+        LIBXL__LOG(ctx, LIBXL__LOG_ERROR,
+                   "No remus_info structure supplied for domain %d", domid);
+        rc = -1;
+        goto remus_fail;
+    }
+
+    /* TBD: Remus setup - i.e. attach qdisc, enable disk buffering, etc */
+
+    /* Point of no return */
+    rc = libxl__domain_suspend_common(gc, domid, fd, type, /* live */ 1,
+                                      /* debug */ 0, info);
+
+    /* 
+     * With Remus, if we reach this point, it means either
+     * backup died or some network error occurred preventing us
+     * from sending checkpoints.
+     */
+
+    /* TBD: Remus cleanup - i.e. detach qdisc, release other
+     * resources.
+     */
+ remus_fail:
+    GC_FREE;
+    return rc;
+}
+
 int libxl_domain_suspend(libxl_ctx *ctx, libxl_domain_suspend_info *info,
                          uint32_t domid, int fd)
 {
diff -r 0129989da2cd -r 070f78ba4244 tools/libxl/libxl.h
--- a/tools/libxl/libxl.h       Mon Jan 30 17:19:46 2012 -0800
+++ b/tools/libxl/libxl.h       Mon Jan 30 17:19:48 2012 -0800
@@ -266,6 +266,8 @@ typedef int (*libxl_console_ready)(libxl
 int libxl_domain_create_new(libxl_ctx *ctx, libxl_domain_config *d_config, 
libxl_console_ready cb, void *priv, uint32_t *domid);
 int libxl_domain_create_restore(libxl_ctx *ctx, libxl_domain_config *d_config, 
libxl_console_ready cb, void *priv, uint32_t *domid, int restore_fd);
 void libxl_domain_config_dispose(libxl_domain_config *d_config);
+int libxl_domain_remus_start(libxl_ctx *ctx, libxl_domain_remus_info *info,
+                             uint32_t domid, int fd);
 int libxl_domain_suspend(libxl_ctx *ctx, libxl_domain_suspend_info *info,
                           uint32_t domid, int fd);
 int libxl_domain_resume(libxl_ctx *ctx, uint32_t domid, int fast);
diff -r 0129989da2cd -r 070f78ba4244 tools/libxl/xl.h
--- a/tools/libxl/xl.h  Mon Jan 30 17:19:46 2012 -0800
+++ b/tools/libxl/xl.h  Mon Jan 30 17:19:48 2012 -0800
@@ -94,6 +94,7 @@ int main_cpupoolnumasplit(int argc, char
 int main_getenforce(int argc, char **argv);
 int main_setenforce(int argc, char **argv);
 int main_loadpolicy(int argc, char **argv);
+int main_remus(int argc, char **argv);
 
 void help(const char *command);
 
diff -r 0129989da2cd -r 070f78ba4244 tools/libxl/xl_cmdimpl.c
--- a/tools/libxl/xl_cmdimpl.c  Mon Jan 30 17:19:46 2012 -0800
+++ b/tools/libxl/xl_cmdimpl.c  Mon Jan 30 17:19:48 2012 -0800
@@ -2846,7 +2846,7 @@ static void core_dump_domain(const char 
  * an ssh channel.
  */
 static void migrate_receive(int debug, int daemonize, int monitor,
-                            int send_fd, int recv_fd)
+                            int send_fd, int recv_fd, int remus)
 {
     int rc, rc2;
     char rc_buf;
@@ -2881,6 +2881,41 @@ static void migrate_receive(int debug, i
         exit(-rc);
     }
 
+    if (remus) {
+        /* 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);
+
+        /*
+         * 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 (Remus): "
+                        "Failed to rename domain from %s to %s:%d\n",
+                        migration_domname, common_domname, rc);
+        }
+
+        rc = libxl_domain_unpause(ctx, domid);
+        if (rc)
+            fprintf(stderr, "migration target (Remus): "
+                    "Failed to unpause domain %s (id: %u):%d\n",
+                    common_domname, domid, rc);
+
+        exit(rc ? -ERROR_FAIL: 0);
+    }
+
     fprintf(stderr, "migration target: Transfer complete,"
             " requesting permission to start domain.\n");
 
@@ -3007,10 +3042,10 @@ int main_restore(int argc, char **argv)
 
 int main_migrate_receive(int argc, char **argv)
 {
-    int debug = 0, daemonize = 1, monitor = 1;
+    int debug = 0, daemonize = 1, monitor = 1, remus = 0;
     int opt;
 
-    while ((opt = def_getopt(argc, argv, "Fed", "migrate-receive", 0)) != -1) {
+    while ((opt = def_getopt(argc, argv, "Fedr", "migrate-receive", 0)) != -1) 
{
         switch (opt) {
         case 0: case 2:
             return opt;
@@ -3024,6 +3059,9 @@ int main_migrate_receive(int argc, char 
         case 'd':
             debug = 1;
             break;
+        case 'r':
+            remus = 1;
+            break;
         }
     }
 
@@ -3032,7 +3070,8 @@ int main_migrate_receive(int argc, char 
         return 2;
     }
     migrate_receive(debug, daemonize, monitor,
-                    /* write to stdout */1, /* read from stdin */0);
+                    /* write to stdout */ 1, /* read from stdin */ 0,
+                    remus);
     return 0;
 }
 
@@ -5968,6 +6007,91 @@ done:
     return ret;
 }
 
+int main_remus(int argc, char **argv)
+{
+    int opt, rc, daemonize = 1;
+    const char *ssh_command = "ssh";
+    char *host = NULL, *rune = NULL, *domain = NULL;
+    libxl_domain_remus_info r_info;
+    int send_fd = -1, recv_fd = -1;
+
+    memset(&r_info, 0, sizeof(libxl_domain_remus_info));
+    /* Defaults */
+    r_info.interval = 200;
+    r_info.blackhole = 0;
+    r_info.compression = 1;
+
+    while ((opt = def_getopt(argc, argv, "bui:s:e", "remus", 2)) != -1) {
+        switch (opt) {
+        case 0: case 2:
+            return opt;
+
+        case 'i':
+           r_info.interval = atoi(optarg);
+            break;
+        case 'b':
+            r_info.blackhole = 1;
+            break;
+        case 'u':
+           r_info.compression = 0;
+            break;
+        case 's':
+            ssh_command = optarg;
+            break;
+        case 'e':
+            daemonize = 0;
+            break;
+        }
+    }
+
+    domain = argv[optind];
+    host = argv[optind + 1];
+
+    if (r_info.blackhole) {
+        find_domain(domain);
+        send_fd = open("/dev/null", O_RDWR, 0644);
+        if (send_fd < 0) {
+            perror("failed to open /dev/null");
+            exit(-1);
+        }
+    } else {
+
+        /*
+         * TODO: change this to plain TCP socket based channel
+         * instead of SSH. For both live-migration and Remus.
+         */
+        if (!ssh_command[0]) {
+            rune = host;
+        } else {
+            if (asprintf(&rune, "exec %s %s xl migrate-receive -r %s",
+                         ssh_command, host,
+                         daemonize ? "" : " -e") < 0)
+                return 1;
+        }
+        migrate_do_preamble(domain, rune, NULL, &send_fd, &recv_fd, NULL);
+    }
+
+    /* Point of no return */
+    rc = libxl_domain_remus_start(ctx, &r_info, domid, send_fd);
+
+    /* If we are here, it means backup has failed/domain suspend 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 {
+        fprintf(stderr, "Remus: Backup failed? resuming domain at primary.\n");
+        libxl_domain_resume(ctx, domid, 1);
+    }
+
+    close(send_fd);
+    return -ERROR_FAIL;
+}
+
 /*
  * Local variables:
  * mode: C
diff -r 0129989da2cd -r 070f78ba4244 tools/libxl/xl_cmdtable.c
--- a/tools/libxl/xl_cmdtable.c Mon Jan 30 17:19:46 2012 -0800
+++ b/tools/libxl/xl_cmdtable.c Mon Jan 30 17:19:48 2012 -0800
@@ -412,6 +412,20 @@ struct cmd_spec cmd_table[] = {
       "Loads a new policy int the Flask Xen security module",
       "<policy file>",
     },
+    { "remus",
+      &main_remus, 0,
+      "Enable Remus HA for domain",
+      "[options] <Domain> [<host>]",
+      "-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"
+      "-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\n"
+      "-e                      Do not wait in the background (on <host>) for 
the death\n"
+      "                        of the domain."
+
+    },
 };
 
 int cmdtable_len = sizeof(cmd_table)/sizeof(struct cmd_spec);

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel


 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.