--- loncom/loncnew 2004/10/05 11:16:57 1.65
+++ loncom/loncnew 2007/03/28 20:28:29 1.81
@@ -2,7 +2,7 @@
# The LearningOnline Network with CAPA
# lonc maintains the connections to remote computers
#
-# $Id: loncnew,v 1.65 2004/10/05 11:16:57 foxr Exp $
+# $Id: loncnew,v 1.81 2007/03/28 20:28:29 albertel Exp $
#
# Copyright Michigan State University Board of Trustees
#
@@ -60,7 +60,7 @@ use LONCAPA::Stack;
use LONCAPA::LondConnection;
use LONCAPA::LondTransaction;
use LONCAPA::Configuration;
-use LONCAPA::HashIterator;
+use Fcntl qw(:flock);
# Read the httpd configuration file to get perl variables
@@ -73,8 +73,6 @@ my %perlvar = %{$perlvarref};
# parent and shared variables.
my %ChildHash; # by pid -> host.
-my %HostToPid; # By host -> pid.
-my %HostHash; # by loncapaname -> IP.
my %listening_to; # Socket->host table for who the parent
# is listening to.
my %parent_dispatchers; # host-> listener watcher events.
@@ -95,6 +93,7 @@ my $executable = $0; # Get the full
# The variables below are only used by the child processes.
#
my $RemoteHost; # Name of host child is talking to.
+my $RemoteHostId; # default lonid of host child is talking to.
my $UnixSocketDir= $perlvar{'lonSockDir'};
my $IdleConnections = Stack->new(); # Set of idle connections
my %ActiveConnections; # Connections to the remote lond.
@@ -105,15 +104,14 @@ my $ConnectionCount = 0;
my $IdleSeconds = 0; # Number of seconds idle.
my $Status = ""; # Current status string.
my $RecentLogEntry = "";
-my $ConnectionRetries=2; # Number of connection retries allowed.
-my $ConnectionRetriesLeft=2; # Number of connection retries remaining.
+my $ConnectionRetries=5; # Number of connection retries allowed.
+my $ConnectionRetriesLeft=5; # Number of connection retries remaining.
my $LondVersion = "unknown"; # Version of lond we talk with.
my $KeyMode = ""; # e.g. ssl, local, insecure from last connect.
my $LondConnecting = 0; # True when a connection is being built.
-my $DieWhenIdle = 1; # When true children die when trimmed -> 0.
my $I_am_child = 0; # True if this is the child process.
#
@@ -151,6 +149,7 @@ sub UpdateStatus {
Makes an entry into the permanent log file.
=cut
+
sub LogPerm {
my $message=shift;
my $execdir=$perlvar{'lonDaemons'};
@@ -196,7 +195,7 @@ sub Log {
my $now = time;
my $local = localtime($now);
my $finalformat = "$local ($$) [$RemoteHost] [$Status] ";
- my $finalformat = $finalformat.$format."\n";
+ $finalformat = $finalformat.$format."\n";
# open the file and put the result.
@@ -270,6 +269,7 @@ sub SocketDump {
and as what we return in a SIGUSR1
=cut
+
sub ShowStatus {
my $state = shift;
my $now = time;
@@ -280,13 +280,14 @@ sub ShowStatus {
=pod
-=head 2 SocketTimeout
+=head2 SocketTimeout
Called when an action on the socket times out. The socket is
destroyed and any active transaction is failed.
=cut
+
sub SocketTimeout {
my $Socket = shift;
Log("WARNING", "A socket timeout was detected");
@@ -304,12 +305,13 @@ sub SocketTimeout {
}
}
+
#
# This function should be called by the child in all cases where it must
-# exit. If the child process is running with the DieWhenIdle turned on
-# it must create a lock file for the AF_UNIX socket in order to prevent
-# connection requests from lonnet in the time between process exit
-# and the parent picking up the listen again.
+# exit. The child process must create a lock file for the AF_UNIX socket
+# in order to prevent connection requests from lonnet in the time between
+# process exit and the parent picking up the listen again.
+#
# Parameters:
# exit_code - Exit status value, however see the next parameter.
# message - If this optional parameter is supplied, the exit
@@ -320,24 +322,20 @@ sub child_exit {
# Regardless of how we exit, we may need to do the lock thing:
- if($DieWhenIdle) {
- #
- # Create a lock file since there will be a time window
- # between our exit and the parent's picking up the listen
- # during which no listens will be done on the
- # lonnet client socket.
- #
- my $lock_file = GetLoncSocketPath().".lock";
- open(LOCK,">$lock_file");
- print LOCK "Contents not important";
- close(LOCK);
-
- exit(0);
- }
- # Now figure out how we exit:
+ #
+ # Create a lock file since there will be a time window
+ # between our exit and the parent's picking up the listen
+ # during which no listens will be done on the
+ # lonnet client socket.
+ #
+ my $lock_file = &GetLoncSocketPath().".lock";
+ open(LOCK,">$lock_file");
+ print LOCK "Contents not important";
+ close(LOCK);
+ unlink(&GetLoncSocketPath());
- if($message) {
- die $message;
+ if ($message) {
+ die($message);
} else {
exit($exit_code);
}
@@ -371,7 +369,7 @@ sub Tick {
KillSocket($Socket);
$IdleSeconds = 0; # Otherwise all connections get trimmed to fast.
UpdateStatus();
- if(($ConnectionCount == 0) && $DieWhenIdle) {
+ if(($ConnectionCount == 0)) {
&child_exit(0);
}
@@ -419,6 +417,7 @@ sub Tick {
$KeyMode = "";
$clock_watcher->cancel();
}
+ &UpdateStatus();
}
=pod
@@ -672,9 +671,9 @@ sub FailTransaction {
if ($ConnectionRetriesLeft > 0) {
Log("WARNING", "Failing transaction "
- .$transaction->getRequest());
+ .$transaction->getLoggableRequest());
}
- Debug(1, "Failing transaction: ".$transaction->getRequest());
+ Debug(1, "Failing transaction: ".$transaction->getLoggableRequest());
if (!$transaction->isDeferred()) { # If the transaction is deferred we'll get to it.
my $client = $transaction->getClient();
Debug(1," Replying con_lost to ".$transaction->getRequest());
@@ -684,12 +683,14 @@ sub FailTransaction {
}
=pod
+
=head1 EmptyQueue
Fails all items in the work queue with con_lost.
Note that each item in the work queue is a transaction.
=cut
+
sub EmptyQueue {
$ConnectionRetriesLeft--; # Counts as connection failure too.
while($WorkQueue->Count()) {
@@ -705,6 +706,7 @@ sub EmptyQueue {
Close all connections open on lond prior to exit e.g.
=cut
+
sub CloseAllLondConnections {
foreach my $Socket (keys %ActiveConnections) {
if(exists($ActiveTransactions{$Socket})) {
@@ -713,7 +715,6 @@ sub CloseAllLondConnections {
KillSocket($Socket);
}
}
-=cut
=pod
@@ -735,8 +736,8 @@ Parameters:
nonzero if we are allowed to create a new connection.
-
=cut
+
sub KillSocket {
my $Socket = shift;
@@ -948,7 +949,7 @@ sub LondReadable {
# We need to be writable for this and probably don't belong
# here inthe first place.
- Deubg(6, "SendingRequest state encountered in readable");
+ Debug(6, "SendingRequest state encountered in readable");
$Watcher->poll("w");
$Watcher->cb(\&LondWritable);
@@ -1146,9 +1147,12 @@ sub LondWritable {
}
}
+
=pod
=cut
+
+
sub QueueDelayed {
Debug(3,"QueueDelayed called");
@@ -1156,19 +1160,22 @@ sub QueueDelayed {
Debug(4, "Delayed path: ".$path);
opendir(DIRHANDLE, $path);
-
- my @alldelayed = grep /\.$RemoteHost$/, readdir DIRHANDLE;
+
+ use Apache::lonnet;
+ my @all_host_ids = &Apache::lonnet::machine_ids($RemoteHost);
+
+ my $host_id_re = '(?:'.join('|',@all_host_ids).')';
+ my @alldelayed = grep(/\.$host_id_re$/, readdir(DIRHANDLE));
closedir(DIRHANDLE);
- my $dfname;
- my $reqfile;
- foreach $dfname (sort @alldelayed) {
- $reqfile = "$path/$dfname";
- Debug(4, "queueing ".$reqfile);
+ foreach my $dfname (sort(@alldelayed)) {
+ my $reqfile = "$path/$dfname";
+ my ($host_id) = ($dfname =~ /\.([^.]*)$/);
+ Debug(4, "queueing ".$reqfile." for $host_id");
my $Handle = IO::File->new($reqfile);
my $cmd = <$Handle>;
chomp $cmd; # There may or may not be a newline...
$cmd = $cmd."\n"; # now for sure there's exactly one newline.
- my $Transaction = LondTransaction->new($cmd);
+ my $Transaction = LondTransaction->new("sethost:$host_id:$cmd");
$Transaction->SetDeferred($reqfile);
QueueTransaction($Transaction);
}
@@ -1192,7 +1199,8 @@ sub MakeLondConnection {
.GetServerPort());
my $Connection = LondConnection->new(&GetServerHost(),
- &GetServerPort());
+ &GetServerPort(),
+ &GetHostId());
if($Connection eq undef) { # Needs to be more robust later.
Log("CRITICAL","Failed to make a connection with lond.");
@@ -1393,7 +1401,7 @@ sub ClientRequest {
# Accept a connection request for a client (lonc child) and
# start up an event watcher to keep an eye on input from that
# Event. This can be called both from NewClient and from
-# ChildProcess if we are started in DieWhenIdle mode.
+# ChildProcess.
# Parameters:
# $socket - The listener socket.
# Returns:
@@ -1482,6 +1490,18 @@ sub GetServerHost {
=pod
+=head2 GetServerId
+
+Returns the hostid whose lond we talk with.
+
+=cut
+
+sub GetHostId {
+ return $RemoteHostId; # Setup by the fork.
+}
+
+=pod
+
=head2 GetServerPort
Returns the lond port number.
@@ -1509,15 +1529,14 @@ another event handler to subess requests
=cut
sub SetupLoncListener {
+ my ($host,$SocketName) = @_;
+ if (!$host) { $host = &GetServerHost(); }
+ if (!$SocketName) { $SocketName = &GetLoncSocketPath($host); }
- my $host = GetServerHost(); # Default host.
- if (@_) {
- ($host) = @_ # Override host with parameter.
- }
- my $socket;
- my $SocketName = GetLoncSocketPath($host);
unlink($SocketName);
+
+ my $socket;
unless ($socket =IO::Socket::UNIX->new(Local => $SocketName,
Listen => 250,
Type => SOCK_STREAM)) {
@@ -1557,6 +1576,7 @@ into the status file.
We also use this to reset the retries count in order to allow the
client to retry connections with a previously dead server.
+
=cut
sub ChildStatus {
@@ -1565,26 +1585,31 @@ sub ChildStatus {
Debug(2, "Reporting child status because : ".$watcher->data);
my $docdir = $perlvar{'lonDocRoot'};
- my $fh = IO::File->new(">>$docdir/lon-status/loncstatus.txt");
- print $fh $$."\t".$RemoteHost."\t".$Status."\t".
+
+ open(LOG,">>$docdir/lon-status/loncstatus.txt");
+ flock(LOG,LOCK_EX);
+ print LOG $$."\t".$RemoteHost."\t".$Status."\t".
$RecentLogEntry."\n";
#
# Write out information about each of the connections:
#
if ($DebugLevel > 2) {
- print $fh "Active connection statuses: \n";
+ print LOG "Active connection statuses: \n";
my $i = 1;
print STDERR "================================= Socket Status Dump:\n";
foreach my $item (keys %ActiveConnections) {
my $Socket = $ActiveConnections{$item}->data;
my $state = $Socket->GetState();
- print $fh "Connection $i State: $state\n";
+ print LOG "Connection $i State: $state\n";
print STDERR "---------------------- Connection $i \n";
$Socket->Dump(-1); # Ensure it gets dumped..
$i++;
}
}
+ flock(LOG,LOCK_UN);
+ close(LOG);
$ConnectionRetriesLeft = $ConnectionRetries;
+ UpdateStatus();
}
=pod
@@ -1605,12 +1630,14 @@ sub SignalledToDeath {
chomp($signal);
Log("CRITICAL", "Abnormal exit. Child $$ for $RemoteHost "
."died through "."\"$signal\"");
- LogPerm("F:lonc: $$ on $RemoteHost signalled to death: "
- ."\"$signal\"");
+ #LogPerm("F:lonc: $$ on $RemoteHost signalled to death: "
+# ."\"$signal\"");
exit 0;
}
+=pod
+
=head2 ToggleDebug
This sub toggles trace debugging on and off.
@@ -1626,6 +1653,8 @@ sub ToggleDebug {
}
+=pod
+
=head2 ChildProcess
This sub implements a child process for a single lonc daemon.
@@ -1636,7 +1665,7 @@ Optional parameter:
=cut
sub ChildProcess {
- # If we are in DieWhenIdle mode, we've inherited all the
+ # We've inherited all the
# events of our parent and those have to be cancelled or else
# all holy bloody chaos will result.. trust me, I already made
# >that< mistake.
@@ -1704,7 +1733,7 @@ sub ChildProcess {
desc => 'Lonc Listener Unix Socket',
fd => $socket);
- $Event::Debuglevel = $DebugLevel;
+ $Event::DebugLevel = $DebugLevel;
Debug(9, "Making initial lond connection for ".$RemoteHost);
@@ -1712,12 +1741,9 @@ sub ChildProcess {
# &MakeLondConnection(); // let first work request do it.
- # If We are in diwhenidle, need to accept the connection since the
- # event may not fire.
+ # need to accept the connection since the event may not fire.
- if ($DieWhenIdle) {
- &accept_client($socket);
- }
+ &accept_client($socket);
Debug(9,"Entering event loop");
my $ret = Event::loop(); # Start the main event loop.
@@ -1729,7 +1755,7 @@ sub ChildProcess {
# Create a new child for host passed in:
sub CreateChild {
- my ($host, $socket) = @_;
+ my ($host, $hostid) = @_;
my $sigset = POSIX::SigSet->new(SIGINT);
sigprocmask(SIG_BLOCK, $sigset);
@@ -1739,18 +1765,14 @@ sub CreateChild {
if($pid) { # Parent
$RemoteHost = "Parent";
$ChildHash{$pid} = $host;
- $HostToPid{$host}= $pid;
sigprocmask(SIG_UNBLOCK, $sigset);
} else { # child.
+ $RemoteHostId = $hostid;
ShowStatus("Connected to ".$RemoteHost);
$SIG{INT} = 'DEFAULT';
sigprocmask(SIG_UNBLOCK, $sigset);
- if(defined $socket) {
- &ChildProcess($socket);
- } else {
- ChildProcess; # Does not return.
- }
+ &ChildProcess(); # Does not return.
}
}
@@ -1778,25 +1800,46 @@ sub parent_client_connection {
my ($event) = @_;
my $watcher = $event->w;
my $socket = $watcher->fd;
+ my $connection = $socket->accept(); # Accept the client connection.
+ Event->io(cb => \&get_remote_hostname,
+ poll => 'r',
+ data => "",
+ fd => $connection);
+ }
+}
+
+sub get_remote_hostname {
+ my ($event) = @_;
+ my $watcher = $event->w;
+ my $socket = $watcher->fd;
- # Lookup the host associated with this socket:
-
- my $host = $listening_to{$socket};
-
- # Start the child:
-
-
+ my $thisread;
+ my $rv = $socket->recv($thisread, POSIX::BUFSIZ, 0);
+ Debug(8, "rcv: data length = ".length($thisread)." read =".$thisread);
+ if (!defined($rv) || length($thisread) == 0) {
+ # Likely eof on socket.
+ Debug(5,"Client Socket closed on lonc for p_c_c");
+ close($socket);
+ $watcher->cancel();
+ return;
+ }
+
+ my $data = $watcher->data().$thisread;
+ $watcher->data($data);
+ if($data =~ /\n$/) { # Request entirely read.
+ chomp($data);
+ } else {
+ return;
+ }
- &Debug(9,"Creating child for $host (parent_client_connection)");
- &CreateChild($host, $socket);
+ &Debug(5,"Creating child for $data (parent_client_connection)");
+ my ($hostname,$lonid) = split(':',$data,2);
+ &CreateChild($hostname,$lonid);
# Clean up the listen since now the child takes over until it exits.
-
$watcher->cancel(); # Nolonger listening to this event
- delete($listening_to{$socket});
- delete($parent_dispatchers{$host});
+ $socket->send("done\n");
$socket->close();
- }
}
# parent_listen:
@@ -1818,23 +1861,43 @@ sub parent_listen {
my ($loncapa_host) = @_;
Debug(5, "parent_listen: $loncapa_host");
- my $socket = &SetupLoncListener($loncapa_host);
+ my ($socket,$file);
+ if (!$loncapa_host) {
+ $loncapa_host = 'common_parent';
+ $file = $perlvar{'lonSockCreate'};
+ } else {
+ $file = &GetLoncSocketPath($loncapa_host);
+ }
+ $socket = &SetupLoncListener($loncapa_host,$file);
+
$listening_to{$socket} = $loncapa_host;
if (!$socket) {
die "Unable to create a listen socket for $loncapa_host";
}
- my $lock_file = &GetLoncSocketPath($loncapa_host).".lock";
+ my $lock_file = $file.".lock";
unlink($lock_file); # No problem if it doesn't exist yet [startup e.g.]
- my $watcher = Event->io(cb => \&parent_client_connection,
- poll => 'r',
- desc => "Parent listener unix socket ($loncapa_host)",
- fd => $socket);
+ my $watcher =
+ Event->io(cb => \&parent_client_connection,
+ poll => 'r',
+ desc => "Parent listener unix socket ($loncapa_host)",
+ data => "",
+ fd => $socket);
$parent_dispatchers{$loncapa_host} = $watcher;
}
+sub parent_clean_up {
+ my ($loncapa_host) = @_;
+ Debug(5, "parent_clean_up: $loncapa_host");
+
+ my $socket_file = &GetLoncSocketPath($loncapa_host);
+ unlink($socket_file); # No problem if it doesn't exist yet [startup e.g.]
+ my $lock_file = $socket_file.".lock";
+ unlink($lock_file); # No problem if it doesn't exist yet [startup e.g.]
+}
+
# listen_on_all_unix_sockets:
# This sub initiates a listen on all unix domain lonc client sockets.
@@ -1857,13 +1920,18 @@ sub listen_on_all_unix_sockets {
my $host_iterator = &LondConnection::GetHostIterator();
while (!$host_iterator->end()) {
my $host_entry_ref = $host_iterator->get();
- my $host_name = $host_entry_ref->[0];
+ my $host_name = $host_entry_ref->[3];
Debug(9, "Listen for $host_name");
&parent_listen($host_name);
$host_iterator->next();
}
}
+sub listen_on_common_socket {
+ Debug(5, "listen_on_common_socket");
+ &parent_listen();
+}
+
# server_died is called whenever a child process exits.
# Since this is dispatched via a signal, we must process all
# dead children until there are no more left. The action
@@ -1887,8 +1955,7 @@ sub server_died {
if($host) { # It's for real...
&Debug(9, "Caught sigchild for $host");
delete($ChildHash{$pid});
- delete($HostToPid{$host});
- &parent_listen($host);
+ &parent_clean_up($host);
} else {
&Debug(5, "Caught sigchild for pid not in hosts hash: $pid");
@@ -1945,21 +2012,9 @@ ShowStatus("Forking node servers");
Log("CRITICAL", "--------------- Starting children ---------------");
LondConnection::ReadConfig; # Read standard config files.
-my $HostIterator = LondConnection::GetHostIterator;
-if ($DieWhenIdle) {
- $RemoteHost = "[parent]";
- &listen_on_all_unix_sockets();
-} else {
-
- while (! $HostIterator->end()) {
-
- my $hostentryref = $HostIterator->get();
- CreateChild($hostentryref->[0]);
- $HostHash{$hostentryref->[0]} = $hostentryref->[4];
- $HostIterator->next();
- }
-}
+$RemoteHost = "[parent]";
+&listen_on_common_socket();
$RemoteHost = "Parent Server";
@@ -1968,68 +2023,38 @@ $RemoteHost = "Parent Server";
ShowStatus("Parent keeping the flock");
-if ($DieWhenIdle) {
- # We need to setup a SIGChild event to handle the exit (natural or otherwise)
- # of the children.
-
- Event->signal(cb => \&server_died,
- desc => "Child exit handler",
- signal => "CHLD");
-
-
- # Set up all the other signals we set up. We'll vector them off to the
- # same subs as we would for DieWhenIdle false and, if necessary, conditionalize
- # the code there.
-
- $parent_handlers{INT} = Event->signal(cb => \&Terminate,
- desc => "Parent INT handler",
- signal => "INT");
- $parent_handlers{TERM} = Event->signal(cb => \&Terminate,
- desc => "Parent TERM handler",
- signal => "TERM");
- $parent_handlers{HUP} = Event->signal(cb => \&Restart,
- desc => "Parent HUP handler.",
- signal => "HUP");
- $parent_handlers{USR1} = Event->signal(cb => \&CheckKids,
- desc => "Parent USR1 handler",
- signal => "USR1");
- $parent_handlers{USR2} = Event->signal(cb => \&UpdateKids,
- desc => "Parent USR2 handler.",
- signal => "USR2");
-
- # Start procdesing events.
-
- $Event::DebugLevel = $DebugLevel;
- Debug(9, "Parent entering event loop");
- my $ret = Event::loop();
- die "Main Event loop exited: $ret";
-
-
-} else {
- #
- # Set up parent signals:
- #
-
- $SIG{INT} = \&Terminate;
- $SIG{TERM} = \&Terminate;
- $SIG{HUP} = \&Restart;
- $SIG{USR1} = \&CheckKids;
- $SIG{USR2} = \&UpdateKids; # LonManage update request.
-
- while(1) {
- my $deadchild = wait();
- if(exists $ChildHash{$deadchild}) { # need to restart.
- my $deadhost = $ChildHash{$deadchild};
- delete($HostToPid{$deadhost});
- delete($ChildHash{$deadchild});
- Log("WARNING","Lost child pid= ".$deadchild.
- "Connected to host ".$deadhost);
- Log("INFO", "Restarting child procesing ".$deadhost);
- CreateChild($deadhost);
- }
- }
-}
+# We need to setup a SIGChild event to handle the exit (natural or otherwise)
+# of the children.
+Event->signal(cb => \&server_died,
+ desc => "Child exit handler",
+ signal => "CHLD");
+
+
+# Set up all the other signals we set up.
+
+$parent_handlers{INT} = Event->signal(cb => \&Terminate,
+ desc => "Parent INT handler",
+ signal => "INT");
+$parent_handlers{TERM} = Event->signal(cb => \&Terminate,
+ desc => "Parent TERM handler",
+ signal => "TERM");
+$parent_handlers{HUP} = Event->signal(cb => \&KillThemAll,
+ desc => "Parent HUP handler.",
+ signal => "HUP");
+$parent_handlers{USR1} = Event->signal(cb => \&CheckKids,
+ desc => "Parent USR1 handler",
+ signal => "USR1");
+$parent_handlers{USR2} = Event->signal(cb => \&UpdateKids,
+ desc => "Parent USR2 handler.",
+ signal => "USR2");
+
+# Start procdesing events.
+
+$Event::DebugLevel = $DebugLevel;
+Debug(9, "Parent entering event loop");
+my $ret = Event::loop();
+die "Main Event loop exited: $ret";
=pod
@@ -2056,7 +2081,6 @@ sub CheckKids {
foreach my $pid (keys %ChildHash) {
Debug(2, "Sending USR1 -> $pid");
kill 'USR1' => $pid; # Tell Child to report status.
- sleep 1; # Wait so file doesn't intermix.
}
}
@@ -2098,8 +2122,7 @@ sub UpdateKids {
# The down side is transactions that are in flight will get timed out
# (lost unless they are critical).
- &Restart();
-
+ &KillThemAll();
}
@@ -2139,8 +2162,6 @@ sub KillThemAll {
Log("CRITICAL", "Nicely Killing lonc for $serving pid = $pid");
kill 'QUIT' => $pid;
}
-
-
}
@@ -2162,6 +2183,7 @@ sub really_kill_them_all_dammit
unlink("$execdir/logs/lonc.pid");
}
}
+
=pod
=head1 Terminate
@@ -2184,6 +2206,14 @@ sub Terminate {
exit 0;
}
+
+sub my_hostname {
+ use Sys::Hostname;
+ my $name = &hostname();
+ &Debug(9,"Name is $name");
+ return $name;
+}
+
=pod
=head1 Theory