10. Appendix A: ClassAd Attributes

ClassAd Types

ClassAd attributes vary, depending on the entity producing the ClassAd. Therefore, each ClassAd has an attribute named MyType, which describes the type of ClassAd. In addition, the condor_collector appends attributes to any daemon's ClassAd, whenever the condor_collector is queried. These additional attributes are listed in the unnumbered subsection labeled ClassAd Attributes Added by the condor_collector on page .

Here is a list of defined values for MyType, as well as a reference to a list attributes relevant to that type.

Job

Each submitted job describes its state, for use by the condor_negotiator daemon in finding a machine upon which to run the job. ClassAd attributes that appear in a job ClassAd are listed and described in the unnumbered subsection labeled Job ClassAd Attributes on page .

Machine

Each machine in the pool (and hence, the condor_startd daemon running on that machine) describes its state. ClassAd attributes that appear in a machine ClassAd are listed and described in the unnumbered subsection labeled Machine ClassAd Attributes on page .

DaemonMaster

Each condor_master daemon describes its state. ClassAd attributes that appear in a DaemonMaster ClassAd are listed and described in the unnumbered subsection labeled DaemonMaster ClassAd Attributes on page .

Scheduler

Each condor_schedd daemon describes its state. ClassAd attributes that appear in a Scheduler ClassAd are listed and described in the unnumbered subsection labeled Scheduler ClassAd Attributes on page .

Negotiator

Each condor_negotiator daemon describes its state. ClassAd attributes that appear in a Negotiator ClassAd are listed and described in the unnumbered subsection labeled Negotiator ClassAd Attributes on page .

Query

Job ClassAd Attributes

AllRemoteHosts:

String containing a comma-separated list of all the remote machines running a parallel or mpi universe job.

Args:

String representing the arguments passed to the job.

CkptArch:

String describing the architecture of the machine this job executed on at the time it last produced a checkpoint. If the job has never produced a checkpoint, this attribute is undefined.

CkptOpSys:

String describing the operating system of the machine this job executed on at the time it last produced a checkpoint. If the job has never produced a checkpoint, this attribute is undefined.

ClusterId:

Integer cluster identifier for this job. A cluster is a group of jobs that were submitted together. Each job has its own unique job identifier within the cluster, but shares a common cluster identifier. The value changes each time a job or set of jobs are queued for execution under Condor.

Cmd:

The path to and the file name of the job to be executed.

ConcurrencyLimits:

A string list, delimited by commas and space characters. The items in the list identify named resources that the job requires.

CommittedTime:

The number of seconds of wall clock time that the job has been allocated a machine, excluding the time spent on run attempts that were evicted without a checkpoint. Like RemoteWallClockTime, this includes time the job spent in a suspended state. In the case of RemoteWallClockTime, one can disregard suspended time by subtracting out CumulativeSuspensionTime. However, no analogous attribute representing committed suspension time exists, so it is not possible to compute how much of CommittedTime was actual time spent running.

CompletionDate:

The time when the job completed, or the value 0 if the job has not yet completed. Measured in the number of seconds since the epoch (00:00:00 UTC, Jan 1, 1970).

CumulativeSuspensionTime:

A running total of the number of seconds the job has spent in suspension for the life of the job.

CurrentHosts:

The number of hosts in the claimed state, due to this job.

DiskUsage:

Amount of disk space (Kbytes) in the Condor execute directory on the execute machine that this job has used. The initial estimate may be specified in the job submit file.

EmailAttributes:

A string containing a comma-separated list of job ClassAd attributes. For each attribute name in the list, its value will be included in the e-mail notification upon job completion.

EnteredCurrentStatus:

An integer containing the epoch time of when the job entered into its current status So for example, if the job is on hold, the ClassAd expression

    CurrentTime - EnteredCurrentStatus

will equal the number of seconds that the job has been on hold.

ExecutableSize:

Size of the executable in Kbytes.

ExitBySignal:

An attribute that is True when a user job exits via a signal and False otherwise. For some grid universe jobs, how the job exited is unavailable. In this case, ExitBySignal is set to False.

ExitCode:

When a user job exits by means other than a signal, this is the exit return code of the user job. For some grid universe jobs, how the job exited is unavailable. In this case, ExitCode is set to 0.

ExitSignal:

When a user job exits by means of an unhandled signal, this attribute takes on the numeric value of the signal. For some grid universe jobs, how the job exited is unavailable. In this case, ExitSignal will be undefined.

ExitStatus:

The way that Condor previously dealt with a job's exit status. This attribute should no longer be used. It is not always accurate in heterogeneous pools, or if the job exited with a signal. Instead, see the attributes: ExitBySignal, ExitCode, and ExitSignal.

GridJobStatus:

A string containing the job's status as reported by the remote job management system.

GridResource:

A string defined by the right hand side of the the submit description file command grid_resource. It specifies the target grid type, plus additional parameters specific to the grid type.

HoldKillSig:

Currently only for scheduler and local universe jobs, a string containing a name of a signal to be sent to the job if the job is put on hold.

HoldReasonCode:

An integer value that represents the reason that a job was put on hold.

Integer Code	Reason for Hold	HoldReasonSubCode
1	The user put the job on hold with condor_hold.
2	Globus middleware reported an error.	The GRAM error number.
3	The PERIODIC_HOLD expression evaluated to True.
4	The credentials for the job are invalid.
5	A job policy expression evaluated to Undefined.
6	The condor_starter failed to start the executable.	The Unix error number.
7	The standard output file for the job could not be opened.	The Unix error number.
8	The standard input file for the job could not be opened.	The Unix error number.
9	The standard output stream for the job could not be opened.	The Unix error number.
10	The standard input stream for the job could not be opened.	The Unix error number.
11	An internal Condor protocol error was encountered when transferring files.
12	The condor_starter failed to download input files.	The Unix error number.
13	The condor_starter failed to upload output files.	The Unix error number.
14	The initial working directory of the job cannot be accessed.	The Unix error number.
15	The user requested the job be submitted on hold.
16	Input files are being spooled.
17	A standard universe job is not compatible with the condor_shadow version available on the submitting machine.
18	An internal Condor protocol error was encountered when transferring files.
19	HOOK_PREPARE_JOB was defined but couldn't be executed or returned failure.
20	The job missed its deferred execution time and therefore failed to run.
21	The job was put on hold because WANT_HOLD in the machine policy was true.

HoldReasonSubCode:

An integer value that represents further information to go along with the HoldReasonCode, for some values of HoldReasonCode. See HoldReasonCode for the values.

HoldReason:

A string containing a human-readable message about why a job is on hold. This is the message that will be displayed in response to the command condor_q -hold. It can be used to determine if a job should be released or not.

HookKeyword:

A string that uniquely identifies a set of job hooks, and added to the ClassAd once a job is fetched.

ImageSize:

Estimate of the memory image size of the job in Kbytes. The initial estimate may be specified in the job submit file. Otherwise, the initial value is equal to the size of the executable. When the job checkpoints, the ImageSize attribute is set to the size of the checkpoint file (since the checkpoint file contains the job's memory image). A vanilla universe job's ImageSize is recomputed internally every 15 seconds.

JobLeaseDuration:

The number of seconds set for a job lease, the amount of time that a job may continue running on a remote resource, despite its submitting machine's lack of response. See section 2.15.4 for details on job leases.

JobPrio:

Integer priority for this job, set by condor_submit or condor_prio. The default value is 0. The higher the number, the greater (better) the priority.

JobRunCount:

This attribute is retained for backwards compatibility. It may go away in the future. It is equivalent to NumShadowStarts for all universes except scheduler. For the scheduler universe, this attribute is equivalent to NumJobStarts.

JobStartDate:

Time at which the job first began running. Measured in the number of seconds since the epoch (00:00:00 UTC, Jan 1, 1970).

JobStatus:

Integer which indicates the current status of the job.

Value	Status
0	Unexpanded (the job has never run)
1	Idle
2	Running
3	Removed
4	Completed
5	Held

JobUniverse:

Integer which indicates the job universe.

Value	Universe
1	standard
5	vanilla
7	scheduler
8	MPI
9	grid
10	java
11	parallel
12	local
13	vm

LastCheckpointPlatform:

An opaque string which is the CheckpointPlatform identifier from the last machine where this standard universe job had successfully produced a checkpoint.

LastCkptServer:

Host name of the last checkpoint server used by this job. When a pool is using multiple checkpoint servers, this tells the job where to find its checkpoint file.

LastCkptTime:

Time at which the job last performed a successful checkpoint. Measured in the number of seconds since the epoch (00:00:00 UTC, Jan 1, 1970).

LastMatchTime:

An integer containing the epoch time when the job was last successfully matched with a resource (gatekeeper) Ad.

LastRejMatchReason:

If, at any point in the past, this job failed to match with a resource ad, this attribute will contain a string with a human-readable message about why the match failed.

LastRejMatchTime:

An integer containing the epoch time when Condor-G last tried to find a match for the job, but failed to do so.

LastSuspensionTime:

Time at which the job last performed a successful suspension. Measured in the number of seconds since the epoch (00:00:00 UTC, Jan 1, 1970).

LastVacateTime:

Time at which the job was last evicted from a remote workstation. Measured in the number of seconds since the epoch (00:00:00 UTC, Jan 1, 1970).

LocalSysCpu:

An accumulated number of seconds of system CPU time that the job caused to the machine upon which the job was submitted.

LocalUserCpu:

An accumulated number of seconds of user CPU time that the job caused to the machine upon which the job was submitted.

MaxHosts:

The maximum number of hosts that this job would like to claim. As long as CurrentHosts is the same as MaxHosts, no more hosts are negotiated for.

MaxJobRetirementTime:

Maximum time in seconds to let this job run uninterrupted before kicking it off when it is being preempted. This can only decrease the amount of time from what the corresponding startd expression allows.

MinHosts:

The minimum number of hosts that must be in the claimed state for this job, before the job may enter the running state.

NextJobStartDelay:

An integer number of seconds delay time after this job starts until the next job is started. The value is limited by the configuration variable MAX_NEXT_JOB_START_DELAY .

NiceUser:

Boolean value which when True indicates that this job is a nice job, raising its user priority value, thus causing it to run on a machine only when no other Condor jobs want the machine.

NTDomain:

A string that identifies the NT domain under which a job's owner authenticates on a platform running Windows.

NumCkpts:

A count of the number of checkpoints written by this job during its lifetime.

NumGlobusSubmits:

An integer that is incremented each time the condor_gridmanager receives confirmation of a successful job submission into Globus.

NumJobMatches:

An integer that is incremented by the condor_schedd each time the job is matched with a resource ad by the negotiator.

NumJobStarts:

An integer count of the number of times the job started executing. This is not (yet) defined for standard universe jobs.

NumJobReconnects:

An integer count of the number of times a job successfully reconnected after being disconnected. This occurs when the condor_shadow and condor_starter lose contact, for example because of transient network failures or a condor_shadow or condor_schedd restart. This attribute is only defined for jobs that can reconnected: those in the vanilla and java universes.

NumRestarts:

A count of the number of restarts from a checkpoint attempted by this job during its lifetime.

NumShadowExceptions:

An integer count of the number of times the condor_shadow daemon had a fatal error for a given job.

NumShadowStarts:

An integer count of the number of times a condor_shadow daemon was started for a given job. This attribute is not defined for scheduler universe jobs, since they do not have a condor_shadow daemon associated with them. For local universe jobs, this attribute is defined, even though the process that manages the job is technically a condor_starter rather than a condor_shadow. This keeps the management of the local universe and other universes as similar as possible.

NumSystemHolds:

An integer that is incremented each time Condor-G places a job on hold due to some sort of error condition. This counter is useful, since Condor-G will always place a job on hold when it gives up on some error condition. Note that if the user places the job on hold using the condor_hold command, this attribute is not incremented.

Owner:

String describing the user who submitted this job.

ParallelShutdownPolicy:

A string that is only relevant to parallel universe jobs. Without this attribute defined, the default policy applied to parallel universe jobs is to consider the whole job completed when the first node exits, killing processes running on all remaining nodes. If defined to the following strings, Condor's behavior changes:

"WAIT_FOR_ALL"

Condor will wait until every node in the parallel job has completed to consider the job finished.

ProcId:

Integer process identifier for this job. Within a cluster of many jobs, each job has the same ClusterId, but will have a unique ProcId. Within a cluster, assignment of a ProcId value will start with the value 0. The job (process) identifier described here is unrelated to operating system PIDs.

QDate:

Time at which the job was submitted to the job queue. Measured in the number of seconds since the epoch (00:00:00 UTC, Jan 1, 1970).

ReleaseReason:

A string containing a human-readable message about why the job was released from hold.

RemoteIwd:

The path to the directory in which a job is to be executed on a remote machine.

RemoteSysCpu:

The total number of seconds of system CPU time (the time spent at system calls) the job used on remote machines. This does not count time spent on run attempts that were evicted without a checkpoint.

RemoteUserCpu:

The total number of seconds of user CPU time the job used on remote machines. This does not count time spent on run attempts that were evicted without a checkpoint.

RemoteWallClockTime:

Cumulative number of seconds the job has been allocated a machine. This also includes time spent in suspension (if any), so the total real time spent running is

RemoteWallClockTime - CumulativeSuspensionTime

Note that this number does not get reset to zero when a job is forced to migrate from one machine to another.

RemoveKillSig:

Currently only for scheduler universe jobs, a string containing a name of a signal to be sent to the job if the job is removed.

StreamErr:

An attribute utilized only for grid universe jobs. The default value is True. If True, and TransferErr is True, then standard error is streamed back to the submit machine, instead of doing the transfer (as a whole) after the job completes. If False, then standard error is transferred back to the submit machine (as a whole) after the job completes. If TransferErr is False, then this job attribute is ignored.

StreamOut:

An attribute utilized only for grid universe jobs. The default value is True. If True, and TransferOut is True, then job output is streamed back to the submit machine, instead of doing the transfer (as a whole) after the job completes. If False, then job output is transferred back to the submit machine (as a whole) after the job completes. If TransferOut is False, then this job attribute is ignored.

TotalSuspensions:

A count of the number of times this job has been suspended during its lifetime.

TransferErr:

An attribute utilized only for grid universe jobs. The default value is True. If True, then the error output from the job is transferred from the remote machine back to the submit machine. The name of the file after transfer is the file referred to by job attribute Err. If False, no transfer takes place (remote to submit machine), and the name of the file is the file referred to by job attribute Err.

TransferExecutable:

An attribute utilized only for grid universe jobs. The default value is True. If True, then the job executable is transferred from the submit machine to the remote machine. The name of the file (on the submit machine) that is transferred is given by the job attribute Cmd. If False, no transfer takes place, and the name of the file used (on the remote machine) will be as given in the job attribute Cmd.

TransferIn:

An attribute utilized only for grid universe jobs. The default value is True. If True, then the job input is transferred from the submit machine to the remote machine. The name of the file that is transferred is given by the job attribute In. If False, then the job's input is taken from a file on the remote machine (pre-staged), and the name of the file is given by the job attribute In.

TransferOut:

An attribute utilized only for grid universe jobs. The default value is True. If True, then the output from the job is transferred from the remote machine back to the submit machine. The name of the file after transfer is the file referred to by job attribute Out. If False, no transfer takes place (remote to submit machine), and the name of the file is the file referred to by job attribute Out.

WindowsBuildNumber:

An integer, extracted from the platform type of the machine upon which this job is submitted, representing a build number for a Windows operating system. This attribute only exists for jobs submitted from Windows machines.

WindowsMajorVersion:

An integer, extracted from the platform type of the machine upon which this job is submitted, representing a major version number (currently 5 or 6) for a Windows operating system. This attribute only exists for jobs submitted from Windows machines.

WindowsMinorVersion:

An integer, extracted from the platform type of the machine upon which this job is submitted, representing a minor version number (currently 0, 1, or 2) for a Windows operating system. This attribute only exists for jobs submitted from Windows machines.

The following job ClassAd attributes are relevant only for vm universe jobs.

VM_MACAddr:

The MAC address of the virtual machine's network interface, in the standard format of six groups of two hexadecimal digits separated by colons. This attribute is currently limited to apply only to Xen virtual machines.

Machine ClassAd Attributes

Activity:

String which describes Condor job activity on the machine. Can have one of the following values:

"Idle":

There is no job activity

"Busy":

A job is busy running

"Suspended":

A job is currently suspended

"Vacating":

A job is currently checkpointing

"Killing":

A job is currently being killed

"Benchmarking":

The startd is running benchmarks

Arch:

String with the architecture of the machine. Typically one of the following:

"ALPHA":

Digital Alpha CPU

"HPPA1":

Hewlett Packard PA-RISC 1.x CPU (i.e. PA-RISC 7000 series CPU) based workstation

"HPPA2":

Hewlett Packard PA-RISC 2.x CPU (i.e. PA-RISC 8000 series CPU) based workstation

"IA64":

Intel Itanium

"INTEL":

Intel x86 CPU (Pentium, Xeon, etc).

"SGI":

Silicon Graphics MIPS CPU

"SUN4u":

Sun UltraSparc CPU

"SUN4x":

A Sun Sparc CPU other than an UltraSparc, i.e. sun4m or sun4c CPU found in older Sparc workstations such as the Sparc 10, Sparc 20, IPC, IPX, etc.

"PPC":

Power Macintosh

"PPC64":

64-bit Power Macintosh

"X86_64":

AMD/Intel 64-bit X86

CheckpointPlatform:

A string which opaquely encodes various aspects about a machine's operating system, hardware, and kernel attributes. It is used to identify systems where previously taken checkpoints for the standard universe may resume.

ClockDay:

The day of the week, where 0 = Sunday, 1 = Monday, ... , 6 = Saturday.

ClockMin:

The number of minutes passed since midnight.

CondorLoadAvg:

The portion of the load average generated by Condor (either from remote jobs or running benchmarks).

ConsoleIdle:

The number of seconds since activity on the system console keyboard or console mouse has last been detected.

Cpus:

Number of CPUs in this machine, i.e. 1 = single CPU machine, 2 = dual CPUs, etc.

CurrentRank:

A float which represents this machine owner's affinity for running the Condor job which it is currently hosting. If not currently hosting a Condor job, CurrentRank is 0.0. When a machine is claimed, the attribute's value is computed by evaluating the machine's Rank expression with respect to the current job's ClassAd.

Disk:

The amount of disk space on this machine available for the job in Kbytes ( e.g. 23000 = 23 megabytes ). Specifically, this is the amount of disk space available in the directory specified in the Condor configuration files by the EXECUTE macro, minus any space reserved with the RESERVED_DISK macro.

DynamicSlot:

For SMP machines that allow dynamic partitioning of a slot, this boolean value identifies that this dynamic slot may be partitioned.

EnteredCurrentActivity:

Time at which the machine entered the current Activity (see Activity entry above). On all platforms (including NT), this is measured in the number of integer seconds since the Unix epoch (00:00:00 UTC, Jan 1, 1970).

FileSystemDomain:

A ``domain'' name configured by the Condor administrator which describes a cluster of machines which all access the same, uniformly-mounted, networked file systems usually via NFS or AFS. This is useful for Vanilla universe jobs which require remote file access.

KeyboardIdle:

The number of seconds since activity on any keyboard or mouse associated with this machine has last been detected. Unlike ConsoleIdle, KeyboardIdle also takes activity on pseudo-terminals into account (i.e. virtual ``keyboard'' activity from telnet and rlogin sessions as well). Note that KeyboardIdle will always be equal to or less than ConsoleIdle.

KFlops:

Relative floating point performance as determined via a Linpack benchmark.

LastHeardFrom:

Time when the Condor central manager last received a status update from this machine. Expressed as the number of integer seconds since the Unix epoch (00:00:00 UTC, Jan 1, 1970). Note: This attribute is only inserted by the central manager once it receives the ClassAd. It is not present in the condor_startd copy of the ClassAd. Therefore, you could not use this attribute in defining condor_startd expressions (and you would not want to).

LoadAvg:

A floating point number with the machine's current load average.

Machine:

A string with the machine's fully qualified host name.

Memory:

The amount of RAM in megabytes.

Mips:

Relative integer performance as determined via a Dhrystone benchmark.

MyType:

The ClassAd type; always set to the literal string "Machine".

Name:

The name of this resource; typically the same value as the Machine attribute, but could be customized by the site administrator. On SMP machines, the condor_startd will divide the CPUs up into separate slots, each with with a unique name. These names will be of the form ``slot#@full.hostname'', for example, ``slot1@vulture.cs.wisc.edu'', which signifies slot number 1 from vulture.cs.wisc.edu.

OpSys:

String describing the operating system running on this machine. For Condor Version 7.3.2 typically one of the following:

"HPUX10":

for HPUX 10.20

"HPUX11":

for HPUX B.11.00

"LINUX":

for LINUX 2.0.x, LINUX 2.2.x, LINUX 2.4.x, or LINUX 2.6.x kernel systems

"OSF1":

for Digital Unix 4.x

"OSX":

for Darwin

"OSX10_2":

for Darwin 6.4

"SOLARIS25":

for Solaris 2.4 or 5.5

"SOLARIS251":

for Solaris 2.5.1 or 5.5.1

"SOLARIS26":

for Solaris 2.6 or 5.6

"SOLARIS27":

for Solaris 2.7 or 5.7

"SOLARIS28":

for Solaris 2.8 or 5.8

"SOLARIS29":

for Solaris 2.9 or 5.9

"WINNT50":

for Windows 2000

"WINNT51":

for Windows XP

"WINNT52":

for Windows Server 2003

"WINNT60":

for Windows Vista

Requirements:

A boolean, which when evaluated within the context of the machine ClassAd and a job ClassAd, must evaluate to TRUE before Condor will allow the job to use this machine.

MaxJobRetirementTime:

An expression giving the maximum time in seconds that the startd will wait for the job to finish before kicking it off if it needs to do so. This is evaluated in the context of the job ClassAd, so it may refer to job attributes as well as machine attributes.

PartitionableSlot:

For SMP machines, a boolean value identifying that this slot may be partitioned.

SlotID:

For SMP machines, the integer that identifies the slot. The value will be X for the slot with

name="slotX@full.hostname"

For non-SMP machines with one slot, the value will be 1. NOTE: This attribute was added in Condor version 6.9.3. For older versions of Condor, see VirtualMachineID below.

SlotWeight:

This specifies the weight of the slot when calculating usage, computing fair shares, and enforcing group quotas. For example, claiming a slot with SlotWeight = 2 is equivalent to claiming two SlotWeight = 1 slots. See the description of SlotWeight on page .

StartdIpAddr:

String with the IP and port address of the condor_startd daemon which is publishing this machine ClassAd.

State:

String which publishes the machine's Condor state. Can be:

"Owner":

The machine owner is using the machine, and it is unavailable to Condor.

"Unclaimed":

The machine is available to run Condor jobs, but a good match is either not available or not yet found.

"Matched":

The Condor central manager has found a good match for this resource, but a Condor scheduler has not yet claimed it.

"Claimed":

The machine is claimed by a remote condor_schedd and is probably running a job.

"Preempting":

A Condor job is being preempted (possibly via checkpointing) in order to clear the machine for either a higher priority job or because the machine owner wants the machine back.

TargetType:

Describes what type of ClassAd to match with. Always set to the string literal "Job", because machine ClassAds always want to be matched with jobs, and vice-versa.

TotalTimeBackfillBusy:

The number of seconds that this machine (slot) has accumulated within the backfill busy state and activity pair since the condor_startd began executing. This attribute will only be defined if it has a value greater than 0.

TotalTimeBackfillIdle:

The number of seconds that this machine (slot) has accumulated within the backfill idle state and activity pair since the condor_startd began executing. This attribute will only be defined if it has a value greater than 0.

TotalTimeBackfillKilling:

The number of seconds that this machine (slot) has accumulated within the backfill killing state and activity pair since the condor_startd began executing. This attribute will only be defined if it has a value greater than 0.

TotalTimeClaimedBusy:

The number of seconds that this machine (slot) has accumulated within the claimed busy state and activity pair since the condor_startd began executing. This attribute will only be defined if it has a value greater than 0.

TotalTimeClaimedIdle:

The number of seconds that this machine (slot) has accumulated within the claimed idle state and activity pair since the condor_startd began executing. This attribute will only be defined if it has a value greater than 0.

TotalTimeClaimedRetiring:

The number of seconds that this machine (slot) has accumulated within the claimed retiring state and activity pair since the condor_startd began executing. This attribute will only be defined if it has a value greater than 0.

TotalTimeClaimedSuspended:

The number of seconds that this machine (slot) has accumulated within the claimed suspended state and activity pair since the condor_startd began executing. This attribute will only be defined if it has a value greater than 0.

TotalTimeMatchedIdle:

The number of seconds that this machine (slot) has accumulated within the matched idle state and activity pair since the condor_startd began executing. This attribute will only be defined if it has a value greater than 0.

TotalTimeOwnerIdle:

The number of seconds that this machine (slot) has accumulated within the owner idle state and activity pair since the condor_startd began executing. This attribute will only be defined if it has a value greater than 0.

TotalTimePreemptingKilling:

The number of seconds that this machine (slot) has accumulated within the preempting killing state and activity pair since the condor_startd began executing. This attribute will only be defined if it has a value greater than 0.

TotalTimePreemptingVacating:

The number of seconds that this machine (slot) has accumulated within the preempting vacating state and activity pair since the condor_startd began executing. This attribute will only be defined if it has a value greater than 0.

TotalTimeUnclaimedBenchmarking:

The number of seconds that this machine (slot) has accumulated within the unclaimed benchmarking state and activity pair since the condor_startd began executing. This attribute will only be defined if it has a value greater than 0.

TotalTimeUnclaimedIdle:

The number of seconds that this machine (slot) has accumulated within the unclaimed idle state and activity pair since the condor_startd began executing. This attribute will only be defined if it has a value greater than 0.

UidDomain:

a domain name configured by the Condor administrator which describes a cluster of machines which all have the same passwd file entries, and therefore all have the same logins.

VirtualMachineID:

Starting with Condor version 6.9.3, this attribute is now longer used. Instead, use SlotID, as described above. This will only be present if ALLOW_VM_CRUFT is TRUE.

VirtualMemory:

The amount of currently available virtual memory (swap space) expressed in Kbytes.

WindowsBuildNumber:

An integer, extracted from the platform type, representing a build number for a Windows operating system. This attribute only exists on Windows machines.

WindowsMajorVersion:

An integer, extracted from the platform type, representing a major version number (currently 5 or 6) for a Windows operating system. This attribute only exists on Windows machines.

WindowsMinorVersion:

An integer, extracted from the platform type, representing a minor version number (currently 0, 1, or 2) for a Windows operating system. This attribute only exists on Windows machines.

In addition, there are a few attributes that are automatically inserted into the machine ClassAd whenever a resource is in the Claimed state:

ClientMachine:

The host name of the machine that has claimed this resource

RemoteOwner:

The name of the user who originally claimed this resource.

RemoteUser:

The name of the user who is currently using this resource. In general, this will always be the same as the RemoteOwner, but in some cases, a resource can be claimed by one entity that hands off the resource to another entity which uses it. In that case, RemoteUser would hold the name of the entity currently using the resource, while RemoteOwner would hold the name of the entity that claimed the resource.

PreemptingOwner:

The name of the user who is preempting the job that is currently running on this resource.

PreemptingUser:

The name of the user who is preempting the job that is currently running on this resource. The relationship between PreemptingUser and PreemptingOwner is the same as the relationship between RemoteUser and RemoteOwner.

PreemptingRank:

A float which represents this machine owner's affinity for running the Condor job which is waiting for the current job to finish or be preempted. If not currently hosting a Condor job, PreemptingRank is undefined. When a machine is claimed and there is already a job running, the attribute's value is computed by evaluating the machine's Rank expression with respect to the preempting job's ClassAd.

TotalClaimRunTime:

A running total of the amount of time (in seconds) that all jobs (under the same claim) ran (have spent in the Claimed/Busy state).

TotalClaimSuspendTime:

A running total of the amount of time (in seconds) that all jobs (under the same claim) have been suspended (in the Claimed/Suspended state).

TotalJobRunTime:

A running total of the amount of time (in seconds) that a single job ran (has spent in the Claimed/Busy state).

TotalJobSuspendTime:

A running total of the amount of time (in seconds) that a single job has been suspended (in the Claimed/Suspended state).

There are a few attributes that are only inserted into the machine ClassAd if a job is currently executing. If the resource is claimed but no job are running, none of these attributes will be defined.

JobId:

The job's identifier (for example, 152.3), as seen from condor_q on the submitting machine.

JobStart:

The time stamp in integer seconds of when the job began executing, since the Unix epoch (00:00:00 UTC, Jan 1, 1970). For idle machines, the value is UNDEFINED.

LastPeriodicCheckpoint:

If the job has performed a periodic checkpoint, this attribute will be defined and will hold the time stamp of when the last periodic checkpoint was begun. If the job has yet to perform a periodic checkpoint, or cannot checkpoint at all, the LastPeriodicCheckpoint attribute will not be defined.

There are a few attributes that are applicable to machines that are offline (i.e. hibernating).

MachineLastMatchTime:

The Unix epoch time when this offline ad would have been matched to a job if the machine were online. In addition, the slot1 ad of a multi-slot machine will have slot<X>_MachineLastMatchTime where X is replaced by the slot id of each of the slots with MachineLastMatchTime defined.

Offline:

true for ads that are in an offline state in the collector. Such ads are stored persistently so that they will still be there after the collector restarts.

Unhibernate:

a boolean expression that specifies when a hibernating machine should be woken up (e.g. by condor_rooster).

Finally, the single attribute, CurrentTime, is defined by the ClassAd environment.

CurrentTime:

Evaluates to the the number of integer seconds since the Unix epoch (00:00:00 UTC, Jan 1, 1970).

DaemonMaster ClassAd Attributes

CkptServer:

A string with with the fully qualified host name of the machine running a checkpoint server.

DaemonStartTime:

The time that this daemon was started, represented as the number of second elapsed since the Unix epoch (00:00:00 UTC, Jan 1, 1970).

Machine:

A string with the machine's fully qualified host name.

MasterIpAddr:

String with the IP and port address of the condor_master daemon which is publishing this DaemonMaster ClassAd.

MyAddress:

Description is not yet written.

MyCurrentTime:

The time, represented as the number of second elapsed since the Unix epoch (00:00:00 UTC, Jan 1, 1970), at which the condor_master daemon last sent a ClassAd update to the condor_collector.

Name:

The name of this resource; typically the same value as the Machine attribute, but could be customized by the site administrator. On SMP machines, the condor_startd will divide the CPUs up into separate slots, each with with a unique name. These names will be of the form ``slot#@full.hostname'', for example, ``slot1@vulture.cs.wisc.edu'', which signifies slot number 1 from vulture.cs.wisc.edu.

PublicNetworkIpAddr:

Description is not yet written.

RealUid:

The UID under which the condor_master is started.

UpdateSequenceNumber:

An integer, starting at zero, and incremented with each ClassAd update sent to the condor_collector. The condor_collector uses this value to sequence the updates it receives.

Scheduler ClassAd Attributes

DaemonStartTime:

The time that this daemon was started, represented as the number of second elapsed since the Unix epoch (00:00:00 UTC, Jan 1, 1970).

JobQueueBirthdate:

Description is not yet written.

Machine:

A string with the machine's fully qualified host name.

MaxJobsRunning:

The same integer value as set in the configuration variable MAX_JOBS_RUNNING . See the definition at section 3.3.11 on page .

MyAddress:

Description is not yet written.

MyCurrentTime:

The time, represented as the number of second elapsed since the Unix epoch (00:00:00 UTC, Jan 1, 1970), at which the condor_schedd daemon last sent a ClassAd update to the condor_collector.

Name:

The name of this resource; typically the same value as the Machine attribute, but could be customized by the site administrator. On SMP machines, the condor_startd will divide the CPUs up into separate slots, each with with a unique name. These names will be of the form ``slot#@full.hostname'', for example, ``slot1@vulture.cs.wisc.edu'', which signifies slot number 1 from vulture.cs.wisc.edu.

NumUsers:

The integer number of distinct users with jobs in this condor_schedd's queue.

PublicNetworkIpAddr:

Description is not yet written.

QuillEnabled:

The same boolean value as set in the configuration variable QUILL_ENABLED . See the definition at section 3.3.30 on page .

ScheddIpAddr:

String with the IP and port address of the condor_schedd daemon which is publishing this Scheduler ClassAd.

ServerTime:

Description is not yet written.

StartLocalUniverse:

The same boolean value as set in the configuration variable START_LOCAL_UNIVERSE . See the definition at section 3.3.11 on page .

StartSchedulerUniverse:

The same boolean value as set in the configuration variable START_SCHEDULER_UNIVERSE . See the definition at section 3.3.11 on page .

TotalFlockedJobs:

The total number of jobs from this condor_schedd daemon that are currently flocked to other pools.

TotalHeldJobs:

The total number of jobs from this condor_schedd daemon that are currently on hold.

TotalIdleJobs:

The total number of jobs from this condor_schedd daemon that are currently idle.

TotalJobAds:

The total number of all jobs (in all states) from this condor_schedd daemon.

TotalRemovedJobs:

The current number of all running jobs from this condor_schedd daemon that have remove requests.

TotalRunningJobs:

The total number of jobs from this condor_schedd daemon that are currently running.

UpdateSequenceNumber:

An integer, starting at zero, and incremented with each ClassAd update sent to the condor_collector. The condor_collector uses this value to sequence the updates it receives.

VirtualMemory:

Description is not yet written.

WantResAd:

A boolean value that when True causes the condor_negotiator daemon to send to this condor_schedd daemon a full machine ClassAd corresponding to a matched job.

Negotiator ClassAd Attributes

DaemonStartTime:

The time that this daemon was started, represented as the number of second elapsed since the Unix epoch (00:00:00 UTC, Jan 1, 1970).

Machine:

A string with the machine's fully qualified host name.

MyAddress:

Description is not yet written.

MyCurrentTime:

The time, represented as the number of second elapsed since the Unix epoch (00:00:00 UTC, Jan 1, 1970), at which the condor_schedd daemon last sent a ClassAd update to the condor_collector.

Name:

The name of this resource; typically the same value as the Machine attribute, but could be customized by the site administrator. On SMP machines, the condor_startd will divide the CPUs up into separate slots, each with with a unique name. These names will be of the form ``slot#@full.hostname'', for example, ``slot1@vulture.cs.wisc.edu'', which signifies slot number 1 from vulture.cs.wisc.edu.

NegotiatorIpAddr:

String with the IP and port address of the condor_negotiator daemon which is publishing this Negotiator ClassAd.

PublicNetworkIpAddr:

Description is not yet written.

UpdateSequenceNumber:

An integer, starting at zero, and incremented with each ClassAd update sent to the condor_collector. The condor_collector uses this value to sequence the updates it receives.

ClassAd Attributes Added by the condor_collector

These attributes are only added if COLLECTOR_DAEMON_STATS is True. See page  for more information on configuration variable COLLECTOR_DAEMON_STATS.

LastHeardFrom:

The time inserted into a daemon's ClassAd representing the time that this condor_collector last received a message from the daemon. Time is represented as the number of second elapsed since the Unix epoch (00:00:00 UTC, Jan 1, 1970).

UpdatesHistory:

A bitmap representing the status of the most recent updates received from the daemon. This attribute is only added if COLLECTOR_DAEMON_HISTORY_SIZE is non-zero. See page  for more information on this setting.

UpdatesLost:

An integer count of the number of updates from the daemon that were lost since the condor_collector started running.

UpdatesSequenced:

An integer count of the number of updates received from the daemon for which the condor_collector can tell how many were lost, since the condor_collector started running.

UpdatesTotal:

An integer count started when the condor_collector started running, representing the sum of the number of updates actually received from the daemon plus the number of updates that the condor_collector determined were lost.