mirror of
https://github.com/xcat2/xcat-core.git
synced 2025-10-31 11:22:27 +00:00
411 lines
15 KiB
Perl
Executable File
411 lines
15 KiB
Perl
Executable File
#!/usr/bin/perl
|
|
# IBM(c) 2016 EPL license http://www.eclipse.org/legal/epl-v10.html
|
|
|
|
#--------------------------------------------------------
|
|
#This is a template for developing a probe sub_command.
|
|
#This template mainly implement the sub_comamd dispatch in hierarchical structure
|
|
#Developer only need to focus on main probe job (by implement do_main_job function) and friendly output (by implement summary_all_jobs_output function) for user
|
|
#This template can also be used in flat structure. but if developer think it's too heavy in flat, it's fine to develop sub command directly.
|
|
#But in hierarchical structure, we strongly recommand using this template.
|
|
#The main dispatch policy are:
|
|
#1. if there isn't noderange input from commmand line. if there are service nodes defined in current MN,
|
|
# we dispatch exact same command input from STDIN to all SNs and current MN. if there isn't service nodes defined,
|
|
# just hanld command input from STDIN in current MN
|
|
#2. If there is noderange input from command line by opion "-n", we will dispatch the command input from STDIN to SN which can hanle these ndoes
|
|
# For example, if we got command from STDIN like "probecommand -n test[1-15] -V" and test[1-5] 's SN is SN1, test[6-10]'s SN is SN2
|
|
# The dispatch result will be:
|
|
# For MN run: probecommand -n test[11-15] -V
|
|
# For SN1 run: probecommand -n test[1-5] -V
|
|
# For SN2 run: probecommand -n test[6-10] -V
|
|
#3. All the return message from SNs and MN will be saved in hash %summaryoutput, develper can use it while implement summary_all_jobs_output function
|
|
#--------------------------------------------------------
|
|
|
|
|
|
BEGIN { $::XCATROOT = $ENV{'XCATROOT'} ? $ENV{'XCATROOT'} : -d '/opt/xcat' ? '/opt/xcat' : '/usr'; }
|
|
|
|
use lib "$::XCATROOT/probe/lib/perl";
|
|
use probe_utils;
|
|
use xCAT::ServiceNodeUtils;
|
|
use File::Basename;
|
|
use Getopt::Long qw(:config no_ignore_case);
|
|
use IO::Select;
|
|
use Data::Dumper;
|
|
|
|
my $program_name = basename("$0"); #current sub_command name
|
|
my $help = 0; #command line attribute '-h', get usage information
|
|
my $test = 0; #command line attribute '-T'
|
|
my $verbose = 0; #command line attribute '-V'
|
|
my $noderange; #command line attribute '-n'
|
|
my $output = "stdout"; #used by probe_utils->send_msg("$output", "o", "xxxxxxxxxx"); print output to STDOUT
|
|
my $is_sn = 0; #flag current server is SN
|
|
my $rst = 0; #the exit code of current command
|
|
my $terminal = 0; #means get INT signal from STDIN
|
|
|
|
#save all output from commands running on SNs and MN
|
|
# one example:
|
|
# $summaryoutput{mn} = @mn_output_history
|
|
# $summaryoutput{SN1} = @SN1_output_history
|
|
my %summaryoutput;
|
|
|
|
#a map of SNs and command which will be dispatched to current SN
|
|
# one example:
|
|
# $dispatchcmd{SN1} = "probecommand -n test[1-5] -V"
|
|
# $dispatchcmd{SN2} = "probecommand -n test[6-10] -V"
|
|
my %dispatchcmd;
|
|
|
|
#save command line attributes from STDIN
|
|
my @tmpargv;
|
|
|
|
#--------------------------------
|
|
# below are some options rules used by default
|
|
# -h : Get usage information of current sub command
|
|
# -V : Output more information for debug
|
|
# -T : To verify if $program_name can work, reserve option for probe framework, dosen't use by customer
|
|
# -n : In xCAT probe, -n is uesd to specify node range uniformly
|
|
#--------------------------------
|
|
$::USAGE = "Usage:
|
|
$program_name -h
|
|
$program_name [-V]
|
|
|
|
Description:
|
|
This is a template for developing a probe sub_command.
|
|
<# ADD DESCRIPTION FOR YOUR COMMAND #>
|
|
|
|
Options:
|
|
-h : Get usage information of $program_name
|
|
-V : Output more information for debug
|
|
";
|
|
|
|
#------------------------------------
|
|
# Please implement the main checking job of current command in do_main_job function
|
|
# If $outputtarget has input value, that means do_main_job is running on MN, so every message needed to print on STDOUT should be written into pipe $outputtarget.
|
|
# If $outputtarget has no value, that means do_main_job is running on SN, all message just need to print on STDOUT
|
|
# Recommand to use probe_utils->send_msg() to handle message you plan to print out
|
|
# A simple example has been written in funciton.
|
|
#------------------------------------
|
|
sub do_main_job {
|
|
my $outputtarget = shift;
|
|
$outputtarget = "stdout" if (!$outputtarget);
|
|
my $rst = 0;
|
|
|
|
probe_utils->send_msg($outputtarget, "o", "I reveive node range is $noderange");
|
|
|
|
#<#DO YOUR OWN CHECKING JOB1#>
|
|
probe_utils->send_msg($outputtarget, "o", "first checking point");
|
|
|
|
#<#DO YOUR OWN CHECKING JOB2#>
|
|
probe_utils->send_msg($outputtarget, "f", "second checking point");
|
|
|
|
return $rst;
|
|
}
|
|
|
|
#-------------------------------------
|
|
# When this command return from all SNs and MN, you need to generate a summary
|
|
# All history outpout from SNs and MN are saved in globle hash %summaryoutput.
|
|
# $summaryoutput{mn} = @mnhistory
|
|
# $summaryoutput{snname1} = @snname1history;
|
|
# The entry in each histroy array isn't categorized, the message coming early is arranged before the one coming later.
|
|
# A simple example of how to dump %summaryoutput has been written in function
|
|
#-------------------------------------
|
|
sub summary_all_jobs_output {
|
|
my $rst = 0;
|
|
|
|
#DO SUMMARY DEPENDING ON YOUR SUB_COMMAND NEED
|
|
probe_utils->send_msg("$output", "d", "======================do summary=====================");
|
|
foreach my $sn (keys %summaryoutput) {
|
|
probe_utils->send_msg("$output", "d", "[$sn]");
|
|
foreach my $log (@{ $summaryoutput{$sn} }) {
|
|
probe_utils->send_msg("$output", "d", "$log");
|
|
}
|
|
}
|
|
return $rst;
|
|
}
|
|
|
|
#-------------------------------------
|
|
# Each probe sub command is supposed to support hierarchical.
|
|
# This funtion is used to calclulate which SN should be dispatched which command
|
|
#-------------------------------------
|
|
sub calculate_dispatch_cmd {
|
|
my @snlist = xCAT::ServiceNodeUtils->getAllSN();
|
|
if ($noderange) {
|
|
my @nodes = `nodels $noderange 2>&1`;
|
|
|
|
#if there is error in noderange
|
|
if ($?) {
|
|
my $error = join(" ", @nodes);
|
|
if ($error =~ /Error: Invalid nodes and\/or groups in noderange: (.+)/) {
|
|
probe_utils->send_msg("$output", "f", "There are invaild nodes ($1) in command line attribute node range");
|
|
} else {
|
|
probe_utils->send_msg("$output", "f", "There is error in command line attribute node range, please using nodels to check");
|
|
}
|
|
return 1;
|
|
} else {
|
|
|
|
#calculate the mapping between SN and the nodes which belong to it.
|
|
chomp foreach (@nodes);
|
|
my $snnodemap = xCAT::ServiceNodeUtils->get_ServiceNode(\@nodes, "xcat", "MN");
|
|
|
|
#print Dumper $snnodemap;
|
|
my %newsnnodemap;
|
|
foreach my $sn (keys %$snnodemap) {
|
|
if (grep(/^$sn$/, @snlist)) { # the node just belong to one SN
|
|
push(@{ $newsnnodemap{$sn} }, @{ $snnodemap->{$sn} });
|
|
} elsif ($sn =~ /(\w+),.+/) { # the node belong to more than one SN, count it into first SN
|
|
if(grep(/^$1$/, @snlist)){
|
|
push(@{ $newsnnodemap{$1} }, @{ $snnodemap->{$sn} });
|
|
}else{
|
|
probe_utils->send_msg("$output", "f", "The value $1 of 'servicenode' isn't a service node");
|
|
}
|
|
} else { # the nodes don't belong to any SN will be handled by MN
|
|
push(@{ $newsnnodemap{mn} }, @{ $snnodemap->{$sn} });
|
|
}
|
|
}
|
|
|
|
#print Dumper \%newsnnodemap;
|
|
#generate new command for each SN, replace noderange
|
|
foreach my $sn (keys %newsnnodemap) {
|
|
my $nodes = join(",", @{ $newsnnodemap{$sn} });
|
|
if ($sn eq "mn") {
|
|
$noderange = $nodes;
|
|
} else {
|
|
for (my $i = 0 ; $i <= $#tmpargv ; $i++) {
|
|
if ($tmpargv[$i] eq "-n") {
|
|
$tmpargv[ $i + 1 ] = $nodes;
|
|
last;
|
|
}
|
|
}
|
|
my $args = join(" ", @tmpargv);
|
|
$dispatchcmd{$sn} = "$::XCATROOT/probe/subcmds/$program_name $args 2>&1";
|
|
}
|
|
}
|
|
}
|
|
} else {
|
|
|
|
#there isn't noderange input from STDIN, dispatch command to all SN if there are SN defined in MN
|
|
if (@snlist) {
|
|
my $args = join(" ", @tmpargv);
|
|
my $sns = join(",", @snlist);
|
|
$dispatchcmd{$sns} = "$::XCATROOT/probe/subcmds/$program_name $args 2>&1" if (!$?);
|
|
}
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
|
|
|
|
#-------------------------------------
|
|
# main process start
|
|
#-------------------------------------
|
|
@tmpargv = @ARGV;
|
|
if (
|
|
!GetOptions("--help|h" => \$help,
|
|
"T" => \$test,
|
|
"n=s" => \$noderange,
|
|
"V" => \$verbose))
|
|
{
|
|
probe_utils->send_msg("$output", "f", "Invalid parameter for $program_name");
|
|
probe_utils->send_msg("$output", "d", "$::USAGE");
|
|
exit 1;
|
|
}
|
|
|
|
if ($help) {
|
|
if ($output ne "stdout") {
|
|
probe_utils->send_msg("$output", "d", "$::USAGE");
|
|
} else {
|
|
print "$::USAGE";
|
|
}
|
|
exit 0;
|
|
}
|
|
|
|
if ($test) {
|
|
probe_utils->send_msg("$output", "o", "This isn't a probe tool, this is just a template for sub command coding. Using it to develop sub command which need to cover hierarchical cluster");
|
|
exit 0;
|
|
}
|
|
|
|
#Handle the interrupt signal from STDIN
|
|
$SIG{TERM} = $SIG{INT} = sub {
|
|
$terminal = 1;
|
|
};
|
|
|
|
#--------------------------------------------
|
|
# To confirm what current node is, MN or SN
|
|
#--------------------------------------------
|
|
$is_sn = 1 if (-e "/etc/xCATSN");
|
|
|
|
#if this node is SN, just run job, not to do dispatch
|
|
if ($is_sn) {
|
|
$rst = do_main_job();
|
|
exit $rst;
|
|
}
|
|
|
|
#--------------------------------------------
|
|
# calculate which command should be dispatched to which SN
|
|
#--------------------------------------------
|
|
$rst = calculate_dispatch_cmd();
|
|
|
|
#print Dumper \%dispatchcmd;
|
|
#print "nodes left to mn : $noderange\n";
|
|
#print "========================\n";
|
|
exit $rst if ($rst);
|
|
|
|
#--------------------------------------------
|
|
# dispatch job to MN and SN
|
|
#--------------------------------------------
|
|
my $mnjobpid = 0;
|
|
my @snsjobpids = ();
|
|
my @snsjobfds = ();
|
|
my $pipe_parent_read;
|
|
my $pipe_child_write;
|
|
pipe $pipe_parent_read, $pipe_child_write;
|
|
{
|
|
#handle job in MN
|
|
$mnjobpid = fork();
|
|
if (!defined($mnjobpid)) {
|
|
probe_utils->send_msg("$output", "f", "fork process to handle MN job failed: $!");
|
|
$rst = 1;
|
|
last;
|
|
} elsif ($mnjobpid == 0) {
|
|
$SIG{TERM} = $SIG{INT} = sub {
|
|
exit 1;
|
|
};
|
|
|
|
close $pipe_parent_read;
|
|
$rst = do_main_job($pipe_child_write);
|
|
exit $rst;
|
|
}
|
|
$SIG{CHLD} = sub { waitpid($mnjobpid, WNOHANG) };
|
|
close $pipe_child_write;
|
|
|
|
#handle job dispatch to SN
|
|
foreach my $sn (keys %dispatchcmd) {
|
|
my $snjobcmd = "xdsh $sn -s \"$dispatchcmd{$sn}\" 2>&1";
|
|
|
|
#print "$sn = $snjobcmd\n";
|
|
my $snjobfd;
|
|
my $snjobpid;
|
|
if (!($snjobpid = open($snjobfd, "$snjobcmd |"))) {
|
|
probe_utils->send_msg("$output", "f", "fork process to dispatch cmd $snjobcmd to $sn failed: $!");
|
|
next;
|
|
}
|
|
push(@snsjobpids, $snjobpid);
|
|
push(@snsjobfds, $snjobfd);
|
|
}
|
|
|
|
my $select = new IO::Select;
|
|
$select->add(\*$pipe_parent_read) if ($pipe_parent_read);
|
|
$select->add(\*$_) foreach (@snsjobfds);
|
|
$| = 1;
|
|
|
|
my $line;
|
|
my %pipeisnonull;
|
|
$pipeisnonull{mn} = 1;
|
|
$pipeisnonull{$_} = 1 foreach (@snsjobfds);
|
|
my $onepipeisnonull = 1;
|
|
while ($onepipeisnonull) {
|
|
if (@hdls = $select->can_read(0)) {
|
|
foreach $hdl (@hdls) {
|
|
if ($pipeisnonull{mn} && $hdl == \*$pipe_parent_read) {
|
|
if (eof($pipe_parent_read)) {
|
|
$pipeisnonull{mn} = 0;
|
|
} else {
|
|
chomp($line = <$pipe_parent_read>);
|
|
print "$line\n";
|
|
push @{ $summaryoutput{mn} }, $line;
|
|
}
|
|
} else {
|
|
foreach my $fd (@snsjobfds) {
|
|
if ($pipeisnonull{$fd} && $hdl == \*$fd) {
|
|
if (eof($fd)) {
|
|
$pipeisnonull{$fd} = 0;
|
|
} else {
|
|
chomp($line = <$fd>);
|
|
if ($line =~ /(Error:)\s+(\w+)\s+(.+)/i) {
|
|
push @{ $summaryoutput{$2} }, $line;
|
|
#if need to print to STDIN in real time, can make below line available
|
|
#print "[failed] :$2: $line\n";
|
|
} elsif ($line =~ /^(\w+)\s*:\s(.*)/) {
|
|
push @{ $summaryoutput{$1} }, $2;
|
|
#if need to print to STDIN in real time, can make below lines available
|
|
#$line = "$2:$1: $3" if ($line =~ /^(\w+)\s*:\s*(\[\w+\]\s*):\s*(.*)/);
|
|
#print "$line\n";
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
$onepipeisnonull = 0;
|
|
$onepipeisnonull |= $pipeisnonull{$_} foreach (keys %pipeisnonull);
|
|
}
|
|
last if ($terminal);
|
|
sleep 1;
|
|
}
|
|
}
|
|
close($pipe_child_write) if ($pipe_child_write);
|
|
close($pipe_parent_read) if ($pipe_parent_read);
|
|
close($_) foreach (@snsjobfds);
|
|
|
|
#start to clear up all sub processes
|
|
my %runningpid;
|
|
$runningpid{$mnjobpid} = 1 if ($mnjobpid);
|
|
$runningpid{$_} = 1 foreach (@snsjobpids);
|
|
my $existrunningpid = 0;
|
|
$existrunningpid = 1 if (%runningpid);
|
|
|
|
my $trytime = 0;
|
|
while ($existrunningpid) {
|
|
|
|
#send terminal signal to all running process at same time
|
|
#try INT 5 up to 5 times
|
|
if ($try < 5) {
|
|
foreach my $pid (keys %runningpid) {
|
|
kill 'INT', $pid if ($runningpid{$pid});
|
|
}
|
|
|
|
#try TERM 5 up to 5 times
|
|
} elsif ($try < 10) {
|
|
foreach my $pid (keys %runningpid) {
|
|
kill 'TERM', $pid if ($runningpid{$pid});
|
|
}
|
|
|
|
#try KILL 1 time
|
|
} else {
|
|
foreach my $pid (keys %runningpid) {
|
|
kill 'KILL', $pid if ($runningpid{$pid});
|
|
}
|
|
}
|
|
++$try;
|
|
|
|
sleep 1;
|
|
|
|
#To check how many process exit, set the flag of exited process to 0
|
|
foreach my $pid (keys %runningpid) {
|
|
$runningpid{$pid} = 0 if (waitpid($pid, WNOHANG));
|
|
}
|
|
|
|
#To check if there are processes still running, if there are, try kill again in next loop
|
|
$existrunningpid = 0;
|
|
$existrunningpid |= $runningpid{$_} foreach (keys %runningpid);
|
|
|
|
#just try 10 times, if still can't kill some process, give up
|
|
if ($try > 10) {
|
|
my $leftpid;
|
|
foreach my $pid (keys %runningpid) {
|
|
$leftpid .= "$pid " if ($runningpid{$pid});
|
|
}
|
|
print "Can't stop process $leftpid, please handle manually.\n";
|
|
last;
|
|
}
|
|
}
|
|
|
|
#-------------------------------------
|
|
# summary all jobs output to display
|
|
#-------------------------------------
|
|
$rst = summary_all_jobs_output();
|
|
|
|
exit $rst;
|
|
|
|
|
|
|
|
|