#!/usr/local/bin/perl

## $Id: XrdOlbMonPerf,v 1.8 2004/09/10 12:01:20 elmer Exp $
## this script collects the informations on the server activity like:
## CPU, network I/O, memory usage ...
## modified to get rid of rperf.
## J-Y Nief - CCIN2P3 - 24/05/04
## modified to accept additional options and drop multi-home uf's.
#  Andy Hanushevsky - SLAC - 15/07/04
## modified to get right network I/O result, paging I/O and changes in paths to unix commands etc.
## Pavel Jakl - RCF/BNL - 20/08/05
#
# Usage: XrdOlbMonPerf [-I netintf] [-n netspeed] [-m <shmkey>] [<interval>]
# WARNING: if you are running this script on a Linux RH7.x server, 
#          the network metric is disabled as the netstat output is screwed, 
#          this info is useless. no problem for RH9 and RHEL3.

# get the name of the server + platform


undef($shmid);
$shmkey = '';
$rhost  = `/bin/uname -n`; chomp($rhost);
$enBps  = 131072000;
$systype= $^O;                #`/bin/uname`; chomp($systype);
$repval = 0;
$netif  = '';
$netmax = 0; # bits / s
$monint = 60;
$| = 1;                       # unbuffer STDOUT

$DEBUG  = 0;                  # switch to debug script

# Get options
#
  while(($argval = shift) && (substr($argval,0,1) eq '-'))
       {   if ($argval eq '-I')
              {Log("Network interface not specified.") if !($netif=shift);}
        elsif ($argval eq '-n')
              {Log("Network speed not specified.") if !($netmax=shift);}
        elsif ($argval eq '-m')
              {Log("Shared segment not specified.") if !($shmkey=shift);
               $shmid = shmget($shmkey, 4096, 0744) if (shmkey ne '.');
               Log("Unable to attach shared memory; $!") if !defined($shmid);
              }
       else   {Log("Unknown option, $argval, ignored", 1);}
      }

# Get the interval
#
if ($argval) 
   {$monint = $argval;
    Log("Invalid interval, '$monint'") if !($monint =~ /^\d+$/);
   }

# get the number of CPUs on this server
if ( $systype eq 'linux' ) {
  $numCPU = `/bin/grep -c cpu /proc/stat` - 1;
}

if ( $systype eq 'solaris' ) {
  $resp = `/bin/uname -X | /bin/grep NumCPU`;
  chomp($resp);
  @answer = split('= ', $resp);
  $numCPU = $answer[1];
}

# get the total memory of the server
if ($systype eq 'linux') {
  $resp = `/bin/grep MemTotal /proc/meminfo`;
  @answer = split('\s+', $resp);
  $TotMem = $answer[1]*1024;
}

if ($systype eq 'solaris' && -x "/etc/prtconf") {
  $resp = `/etc/prtconf | /bin/grep Memory`;
  ($TotMem) = $resp =~ /.+:\s*(\d+)/s;
  $TotMem *= 1024*1024;
}

# if it is a Linux, retrieve the distrib version.
# necessary for netstat which does not give the same output on RH 7.x, RH 9, 
# RHEL...
# netstat usable on RH 9 and RHEL 3 ==> distrib = "RH_OK", else "RH_WRONG"
if ($systype eq 'linux') {
  $distrib = "RH_OK";
  $resp = `/bin/cat /etc/redhat-release`;
  if ( $resp =~ /release 7./ ) { $distrib = "RH_WRONG"; }
}

# determine the column where the idle time and the free mem
# can be found in the 'vmstat' output.
# depends on the platform and on the 'vmstat' version, sigh... 
$ind_idle = 0;
$ind_free = 0;
@output = `/usr/bin/vmstat`;
chomp($output[1]);
@answer = split('\s+', $output[1]);
foreach $type(@answer) {
  last if ( $type eq 'id' );
  $ind_idle++;
}
foreach $type(@answer) {
  last if ( $type eq 'free' );
  $ind_free++;
}

# in the netstat output, the number of input and output packets is not in the 
# same columns whether it is a Linux or SunOS platform
if ( $systype eq 'solaris' ) {
  $ind_net1 = 5;
  $ind_net2 = 7;
} else {
  $ind_net1 = 3;
  $ind_net2 = 7;
}
$indx_net = 0;

# check the number of network interface on the server and their 
# capability (ethernet or gigabit)
$mtu = 1500;
if (!$netmax)
   {@com = `/bin/netstat -i`;
    foreach $line(@com) {
       if ( $line !~ /Kernel Interface/ && $line !~ /MTU/ ) {
          ( $line =~ /eth/ ) && ( $netmax = 1e8 );
          ( $line =~ /ge/ || $line =~ /ce/ ) && ( $netmax = 1e9 );
          }
      }
    if (!$netmax) {$netmax = 1e8;}
   }

# Get it in a sleep $monint time loop netstat result and count network I/O
$ipio_old = 0;
while(true) {
  @resp=`/bin/netstat -i`;
  
  # what's the CPU utilization ?
  @respCPU = `/usr/bin/vmstat 1 2`;
  chomp $respCPU[3];
  @resp_vmstat = split('\s+',$respCPU[3]);
  if ( ($resp_vmstat[$ind_idle] > 100) || ($resp_vmstat[$ind_idle] < 0) ) {
    $cpu = 0;
  } else {
    $cpu = $resp_vmstat[$ind_idle-2] + $resp_vmstat[$ind_idle-1];
  }

  # what's the runq load ?
  chomp($respLoad = `/usr/bin/uptime`);
  @respSplit = split(',',$respLoad);
  $load = int($respSplit[4]*25/$numCPU);  # Assumes some magic upper number i.e. 1 CPU load 4 = 100%
  $load = 100 if $load > 100;

  # what's the network I/O activity?
  foreach $resp (@resp){
      if ( ( $resp !~ /lo/ && $resp !~ /Iface/ && $systype eq 'linux' && $distrib ne 'RH_WRONG' )|| 
	   ( $systype eq 'solaris' ) ) {
       	@respSplit = split('\s+',$resp);

	print "DEBUG ".join("|",@respSplit)."\n" if ($DEBUG);

	if ( $systype eq 'solaris' ) {
	    $net_activity = ($respSplit[$ind_net1] + $respSplit[$ind_net2]) * $mtu * 8 / $monint;
	    $ipio = int ( $net_activity / $netmax * 100 );
	}else {
	    $measure[1] = $net[$indx_net] = $respSplit[$ind_net1] + $respSplit[$ind_net2];
	    print "DEBUG measure is $measure[1] $netmax\n" if ($DEBUG);
	    if ( $indx_net ) {
		$net_activity = ($measure[1] - $measure[0]) * $mtu * 8 / $monint;
		$ipio = int ( $net_activity / $netmax * 100 );
		$measure[0] = $measure[1];
	    }
	    $indx_net = $indx_net ^ 1;
	}
	$ipio_old = $ipio;
      } else {
	$ipio = $ipio_old;
      }
     }
  $ipio = 100 if $ipio > 100;
  $ipio_old = $ipio;

  # what's the memory load ?
  $used = $TotMem - $resp_vmstat[$ind_free]*1024;
  $mem = int($used/$TotMem*100);
  $mem = 100 if $mem > 100;
  #
  $repval++;

  # what's the paging I/O activity ?
  # useless as this metric is highly correlated with some of the others above.
  # being kept for backward compatibility with the load balancer.
  if ( -e "/proc/meminfo"){
      @items = split(" ",`/bin/cat /proc/meminfo | /bin/grep Swap:`);
      $pgio  = int($items[2]/$items[1]*100);
  } else {
      $pgio  = 0;
  }
  
  if (!defined($shmid)) {
      if ($DEBUG){ print "Load:$load CPU:$cpu MEM:$mem PGIO:$pgio IPIO:$ipio\n";}
      else       { print "$load $cpu $mem $pgio $ipio\n";}
  }
  else {
    $resp = pack('LLLLL',$load,$cpu,$mem,$pgio,$ipio);
    Log("Unable to write into shared memory; $!")
      if !shmwrite($shmid, $resp, 0, length($resp));
  }
   #Sleep some time
   sleep $monint;
}


sub Log {
  my($msg, $ret) = @_;
  print STDERR "XrdOlbMonPerf: $msg\n";
  system('/bin/logger', '-p', 'daemon.notice', "XrdOlbMonPerf: $msg");
  return 0 if $ret;
  exit(1);
}