Sun Cluster 3.1 10/03 Data Services Developer's Guide

xfnts_probe Method

The xfnts_probe method checks the availability of the application and decides whether to failover or restart the data service. The xfnts_monitor_start callback method launches this program and the xfnts_monitor_stop callback method stops it.


Example C–5 xfnts_probe.c+

/*
 * Copyright (c) 1998-2003 by Sun Microsystems, Inc.
 * All rights reserved.
 *
 * xfnts_probe.c - Probe for HA-XFS
 */

#pragma ident “@(#)xfnts_probe.c 1.26 01/01/18 SMI”

#include <stdio.h>
#include <stdlib.h>
#include <strings.h>
#include <unistd.h>
#include <signal.h>
#include <sys/time.h>
#include <sys/socket.h>
#include <strings.h>
#include <rgm/libdsdev.h>
#include “xfnts.h”


/*
 * main():
 * Just an infinite loop which sleep()s for sometime, waiting for
 * the PMF action script to interrupt the sleep(). When interrupted
 * It calls the start method for HA-XFS to restart it.
 *
 */

int
main(int argc, char *argv[])
{
   int         timeout;
   int         port, ip, probe_result;
   scds_handle_t      scds_handle;

   hrtime_t      ht1, ht2;
   unsigned long      dt;

   scds_netaddr_list_t *netaddr;
   char   *hostname;

   if (scds_initialize(&scds_handle, argc, argv) != SCHA_ERR_NOERR)
{
      scds_syslog(LOG_ERR, “Failed to initialize the handle.”);
      return (1);
   }


   /* Get the ip addresses available for this resource */
   if (scds_get_netaddr_list(scds_handle, &netaddr)) {
      scds_syslog(LOG_ERR,
          “No network address resource in resource group.”);
      scds_close(&scds_handle);
      return (1);
   }

   /* Return an error if there are no network resources */
   if (netaddr == NULL || netaddr->num_netaddrs == 0) {
      scds_syslog(LOG_ERR,
          “No network address resource in resource group.”);
      return (1);
   }


   /*
    * Set the timeout from the X props. This means that each probe
    * iteration will get a full timeout on each network resource
    * without chopping up the timeout between all of the network
    * resources configured for this resource.
    */
   timeout = scds_get_ext_probe_timeout(scds_handle);

   for (;;) {

      /*
       * sleep for a duration of thorough_probe_interval between
       *  successive probes.
       */
      (void) scds_fm_sleep(scds_handle,
          scds_get_rs_thorough_probe_interval(scds_handle));

      /*
       * Now probe all ipaddress we use. Loop over
       * 1. All net resources we use.
       * 2. All ipaddresses in a given resource.
       * For each of the ipaddress that is probed,
       * compute the failure history.
       */
      probe_result = 0;
      /*
       * Iterate through the all resources to get each
       * IP address to use for calling svc_probe()
       */
      for (ip = 0; ip < netaddr->num_netaddrs; ip++) {
         /*
          * Grab the hostname and port on which the
          * health has to be monitored.
          */
         hostname = netaddr->netaddrs[ip].hostname;
         port = netaddr->netaddrs[ip].port_proto.port;
         /*
          * HA-XFS supports only one port and
          * hence obtain the port value from the
          * first entry in the array of ports.
          */
         ht1 = gethrtime(); /* Latch probe start time */
         scds_syslog(LOG_INFO, “Probing the service on “
             “port: %d.”, port);

         probe_result =
         svc_probe(scds_handle, hostname, port, timeout);

         /*
          * Update service probe history,
          * take action if necessary.
          * Latch probe end time.
          */
         ht2 = gethrtime();

         /* Convert to milliseconds */
         dt = (ulong_t)((ht2 - ht1) / 1e6);

         /*
          * Compute failure history and take
          * action if needed
          */
         (void) scds_fm_action(scds_handle,
             probe_result, (long)dt);
      }   /* Each net resource */
   }    /* Keep probing forever */
}