Re: [Xen-devel] [PATCH v10 22/31] implement the cmdline for COLO

[Wen Congyang <wency@xxxxxxxxxxxxxx>]

On 03/02/2016 11:03 PM, Wei Liu wrote:
> On Mon, Feb 22, 2016 at 10:52:26AM +0800, Wen Congyang wrote:
> [...]
>> +    if (libxl_defbool_val(info->colo)) {
>> +        if (libxl_defbool_val(info->compression)) {
> 
> This can be simplified as
> 
>        if (libxl_defbool_val(xxx) && libxl_defbool_val(yyy))

OK. will fix it in the next version.

> 
>> +            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) ||
>> @@ -876,7 +892,10 @@ 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 df7268b..0dc7220 100644
>> --- a/tools/libxl/xl_cmdimpl.c
>> +++ b/tools/libxl/xl_cmdimpl.c
>> @@ -4440,6 +4440,8 @@ 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 */
>> @@ -4460,6 +4462,9 @@ static void migrate_receive(int debug, int daemonize, 
>> int monitor,
>>      dom_info.send_back_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;
>>  
> 
> It seems that dom_info->quiet affects stderr, not stdout. See the only
> place that checks this in xl_cmdimpl.c.
> 
>>      rc = create_domain(&dom_info);
>>      if (rc < 0) {
>> @@ -4472,11 +4477,12 @@ 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
>> @@ -4492,16 +4498,20 @@ 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:
>> @@ -4649,7 +4659,7 @@ int main_migrate_receive(int argc, char **argv)
>>      libxl_checkpointed_stream 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;
>> @@ -4663,6 +4673,9 @@ 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) {
>> @@ -8032,11 +8045,8 @@ 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;
>> @@ -8064,11 +8074,32 @@ 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);
>> +        }
>> +    }
>> +
> 
> I don't think I'm entirely happy with how these things are arranged.
> Remus and COLO don't seem to have a set of consistent APIs that
> arbitrary users can call.
> 
> But for the sake of not growing this series any longer let's leave it
> like this for the moment. I think COLO at best is going to be (as you
> stated in manpage) experimental at this stage.

Yes, it is experimental now.

Thanks
Wen Congyang

> 
> 
>>      if (!r_info.netbufscript)
>>          r_info.netbufscript = default_remus_netbufscript;
>>  
>> @@ -8083,8 +8114,9 @@ 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");
>>          }
>>  
>> @@ -8112,7 +8144,8 @@ 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;
>>      }
>> @@ -8124,7 +8157,8 @@ 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 fdc1ac6..b6b630c 100644
>> --- a/tools/libxl/xl_cmdtable.c
>> +++ b/tools/libxl/xl_cmdtable.c
>> @@ -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",
>> -- 
>> 2.5.0
>>
>>
>>
>>
>> _______________________________________________
>> Xen-devel mailing list
>> Xen-devel@xxxxxxxxxxxxx
>> http://lists.xen.org/xen-devel
> 
> 
> .
> 




_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel