Skip site navigation (1)Skip section navigation (2)

FreeBSD Manual Pages

  
 
  

home | help
NAME
       dtop  --	display	and update information about processes on a cluster of
       machines

SYNOPSIS
       dtop [-bqtv] [-f	fanout]	 [-g  rungroup1,...,rungroupN]	[-l  username]
	    [-o	    porttimeout]    [-p	   portnum]    [-w    node1,...,nodeN]
	    [-x	node1,...,nodeN] [-m proc | load] [-i interval]	[command ...]

DESCRIPTION
       The dtop	command	can be used to remotely	monitor	a cluster of  machines
       for  CPU	 and process information.  It provides the same	information as
       the top program,	but rather than	showing	it just	for  one  machine,  it
       gathers	the  information  from a cluster of machines, and sorts	it all
       together	into a single, periodically updating  report.	The  following
       options are available:

       -b   The	 -b  flag  causes  dtop	to run one iteration on	each node, and
	    print out a	single report of the processes running on those	nodes,
	    rather than	continuously updating.

       -m   The	-m option determines if	the output is process output, or  load
	    average  output.   Load average output gives the load average, and
	    memory usage statistics for	the machines being monitored.  Process
	    output gives a list	of processes on	each machine,  sorted  by  cpu
	    usage.  The	default	mode is	proc.

       -i   The	 -i  flag  selects  the	interval of time between the update of
	    each nodes process or load information.  It	is  not	 wise  to  set
	    this  value	 too low, otherwise you	may produce uneccesary load on
	    the	target hosts.  The interval is specified in seconds.

       -f   If the -f option is	specified, followed by a number, it  sets  the
	    fanout  size  of  the  cluster.   The fanout size is the number of
	    nodes a command will run on	in parallel at one time.   Thus	 a  80
	    node cluster, with a fanout	size of	64, would run 64 nodes in par-
	    allel,  then, when all have	finished, it would execute the command
	    on the last	16 nodes.  The fanout size defaults to 64.   This  op-
	    tion overrides the FANOUT environment variable.

       -g   If	the -g option is specified, followed by	a comma	separated list
	    of group names, the	command	will only be  run  on  that  group  of
	    nodes.   A	node  may be a part of more than one group if desired,
	    however running without the	-g option will run the command on  the
	    same node as many times as it appears in the file specified	by the
	    CLUSTER  environment variable.  This option	is silently ignored if
	    used with the -w option.

       -l   If the -l option is	specified, followed by a  username,  the  com-
	    mands  will	be run under that userid on the	remote machines.  Con-
	    sideration must be taken for proper	authentication,	 for  this  to
	    work.

       -o   The	 -o  option  is	 used to set the timeout in seconds to be used
	    when testing remote	connections.  The default is five seconds.

       -p   The	-p option can be used to set  the  port	 number	 that  testing
	    should  occur on when testing remote connections.  The default be-
	    havior is to guess based on	the remote command name.

       -q   The	-q option does not issue any commands, but  displays  informa-
	    tion about the cluster, and	the fanout groupings.

       -t   The	 -t  option  causes  dtop to attempt a connection test to each
	    node prior to attempting to	run the	remote command.	 If  the  test
	    fails  for	any  reason, the remote	command	will not be attempted.
	    This can be	useful when clusterfiles have suffered bitrot and some
	    nodes no longer exist, or might be down for	maintenance.  The  de-
	    fault  timeout  is 5 seconds.  The timeout can be changed with the
	    -o option.	dtop will attempt to guess the port number of the  re-
	    mote  service  based on your RCMD_CMD setting.  It knows about ssh
	    and	rsh.  If dtop fails to guess your port correctly, you may  use
	    the	 -p  argument to set the remote	port number.  If the RCMD_TEST
	    environment	variable exists, the testing will  automatically  take
	    place.

       -v   Prints the version of ClusterIt to the stdout, and exits.

       -w   If	the -w option is specified, followed by	a comma	delimited list
	    of machine names, the command will be run  on  each	 node  in  the
	    list.   Without  this option, dtop runs on the nodes listed	in the
	    file pointed to by the CLUSTER environment variable.

       -x   The	-x option can be used to exclude specific nodes	from the clus-
	    ter.  The format is	the same as the	-w option, a  comma  delimited
	    list  of  machine  names.  This option is silently ignored if used
	    with the -w	option.

ENVIRONMENT
       dtop utilizes the following environment variables.

       CLUSTER		  Contains a filename, which is	 a  newline  separated
			  list of nodes	in the cluster.

       RCMD_CMD		  Command  to  use to connect to remote	machines.  The
			  command chosen must be able to connect with no pass-
			  word to the remote host.  Defaults to	rsh

       RCMD_CMD_ARGS	  Arguments to pass to the remote shell	command.   De-
			  faults to none.

       RCMD_PORT	  The  port  number  used  to test remote connections.
			  See the -p flag.

       RCMD_TEST	  When set, dtop will automatically test all hosts be-
			  fore launching the remote command. See the -t	option
			  for more information.

       RCMD_TEST_TIMEOUT  The timeout in seconds to use	when testing  for  re-
			  mote connections.

       RCMD_USER	  The username to connect to remote machines as	by de-
			  fault.

       FANOUT		  When	set,  limits  the maximum number of concurrent
			  commands sent	at once.  This can  be	used  to  keep
			  from	overloading a small host when sending out com-
			  mands	in parallel.  Defaults to 64.	This  environ-
			  ment setting can be overridden by the	-f option.

INTERACTIVE MODE
       When  dtop  is  running in interactive mode, it reads commands from the
       terminal	and acts upon  them  accordingly.   During  interactive	 mode,
       every  few seconds, depending on	the interval, dtop will	query the next
       few hosts in the	cluster, and merge the data from those hosts into  the
       display.	  The  number of hosts updated each interval, is determined by
       the fanout setting.

       Certain characters cause	immediate action by dtop.  These are

       p	   Switch the mode to the process mode,	sorted by the CPU  us-
		   age of each process.

       m	   Switch  the	mode to	the process mode, sorted by the	memory
		   usage of each process.

       l	   Switch the mode to the load average mode, sorted  by	 host-
		   name.

       v	   Switch  the	mode  to the load average mode,	sorted by load
		   average.

       a	   Switch the mode to the load average mode, sorted by	active
		   memory.

       i	   Switch  the	mode to	the load average mode, sorted by inac-
		   tive	memory.

       r	   Switch the mode to the load average mode,  sorted  by  file
		   cache/buffer	memory.

       f	   Switch  the	mode  to the load average mode,	sorted by free
		   memory.

       s	   Switch the mode to the load average mode,  sorted  by  swap
		   used.

       ?	   Display the interactive help	menu.

       q	   Quit	dtop

FILES
       The file	pointed	to by the CLUSTER environment variable has the follow-
       ing format:

	     pollux
	     castor
	     GROUP:alpha
	     rigel
	     kent
	     GROUP:sparc
	     alshain
	     altair
	     LUMP:alphasparc
	     alpha
	     sparc

       This  example would have	pollux and castor a member of no groups, rigel
       and kent	a member of group 'alpha', and alshain and altair a member  of
       group `sparc'.  Note the	format of the GROUP command, it	is in all cap-
       ital letters, followed by a colon, and the group	name.  There can be no
       spaces following	the GROUP command, or in the name of the group.

       There is	also a LUMP command, which is identical	in syntax to the GROUP
       command.	  This	command	 allows	you to create a	named group of groups.
       Each member of the lump is the name of a	group.	The  LUMP  command  is
       terminated by another LUMP or GROUP command, or the EOF marker.

       Any  line  beginning with a `#' symbol denotes a	comment	field, and the
       entire line will	be ignored.  Note that a  hash	mark  placed  anywhere
       other  than the first character of a line, will be considered part of a
       valid hostname or command.

SEE ALSO
       dsh(1), ssh(1), top(1)

HISTORY
       The dtop	command	appeared in clusterit 2.5.  Work on dtop was made pos-
       sible by	a generous donation from Mach1 Computing, LLC.

AUTHOR
       dtop was	written	by Tim Rightnour.

BUGS
       Solaris 2.5.1 has a maximum of 256 open file descriptors.   This	 means
       that dtop will fail on a	fanout size greater than about 32-40 nodes.

       dtop uses the top command in batch mode to collect data from remote ma-
       chines.	 Because  of  this,  the  top command must exist on the	remote
       node, and additionally, dtop must understand it's output.  dtop	should
       be  able	 to  understand	output from top	on NetBSD, Solaris, and	Linux,
       however,	it is possible that if the format were to change, or  be  dif-
       ferent, it would	break.	If dtop	fails to work for you, please send the
       output of:

	     top -Sb 20
       or

	     top -bn 1

       to root@garbled.net, or file a bug report on sourceforge.

       dtop  is	 still	rather	new, and is likely to still have a few display
       bugs and	parsing	issues.

				 July 23, 2007			       DTOP(1)

Want to link to this manual page? Use this URL:
<https://man.freebsd.org/cgi/man.cgi?query=dtop&sektion=1&manpath=FreeBSD+Ports+15.0>

home | help