This is an outdated version of the HTCondor Manual. You can find current documentation at http://htcondor.org/manual.

Next: 13. Appendix B: Codes Up: HTCondor^{^TM} Version 8.1.6 Manual Previous: procd_ctl Contents Index

12. 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 .
Submitter: Each submitter is described by a ClassAd. ClassAd attributes that appear in a Submitter ClassAd are listed and described in the unnumbered subsection labeled Submitter ClassAd Attributes on page .
Defrag: Each condor_defrag daemon describes its state. ClassAd attributes that appear in a Defrag ClassAd are listed and described in the unnumbered subsection labeled Defrag ClassAd Attributes on page .
Collector: Each condor_collector daemon describes its state. ClassAd attributes that appear in a Collector ClassAd are listed and described in the unnumbered subsection labeled Collector ClassAd Attributes on page .
Query: $\fbox{This section has not yet been written}$

In addition, statistics are published for each DaemonCore daemon. These attributes are listed and described in the unnumbered subsection labeled DaemonCore Statistics Attributes on page .

Job ClassAd Attributes

Absent:

Boolean set to true True if the ad is absent.

AcctGroup:

The accounting group name, as set in the submit description file via the accounting_group command. This attribute is only present if an accounting group was requested by the submission. See section 3.4.7 for more information about accounting groups.

AcctGroupUser:

The user name associated with the accounting group. This attribute is only present if an accounting group was requested by the submission.

AllRemoteHosts:

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

Args:

A string representing the command line arguments passed to the job, when those arguments are specified using the old syntax, as specified in section 11.

Arguments:

A string representing the command line arguments passed to the job, when those arguments are specified using the new syntax, as specified in section 11.

BatchQueue:

For grid universe jobs destined for PBS, LSF or SGE, the name of the queue in the remote batch system.

BoincAuthenticatorFile:

Used for grid type boinc jobs; a string taken from the definition of the submit description file command boinc_authenticator_file. Defines the path and file name of the file containing the authenticator string to use to authenticate to the BOINC service.

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 HTCondor.

Cmd:

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

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, so the total committed wall time spent running is

CommittedTime - CommittedSuspensionTime

CommittedSlotTime:

This attribute is identical to CommittedTime except that the time is multiplied by the SlotWeight of the machine(s) that ran the job. This relies on SlotWeight being listed in SYSTEM_JOB_MACHINE_ATTRS .

CommittedSuspensionTime:

A running total of the number of seconds the job has spent in suspension during time in which the job was not evicted without a checkpoint. This number is updated when the job is checkpointed and when it exits.

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).

ConcurrencyLimits:

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

CumulativeSlotTime:

This attribute is identical to RemoteWallClockTime except that the time is multiplied by the SlotWeight of the machine(s) that ran the job. This relies on SlotWeight being listed in SYSTEM_JOB_MACHINE_ATTRS .

CumulativeSuspensionTime:

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

CumulativeTransferTime:

The total time, in seconds, that condor has spent transferring the input and output sandboxes for the life of the job.

CurrentHosts:

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

DAGManJobId:

For a DAGMan node job only, the ClusterId job ClassAd attribute of the condor_dagman job which is the parent of this node job. For nested DAGs, this attribute holds only the ClusterId of the job's immediate parent.

DAGParentNodeNames:

For a DAGMan node job only, a comma separated list of each JobName which is a parent node of this job's node. This attribute is passed through to the job via the condor_submit command line, if it does not exceed the line length defined with _POSIX_ARG_MAX. For example, if a node job has two parents with JobNames B and C, the condor_submit command line will contain

  -append +DAGParentNodeNames=B,C

DAGManNodesLog:

For a DAGMan node job only, gives the path to an event log used exclusively by DAGMan to monitor the state of the DAG's jobs. Events are written to this log file in addition to any log file specified in the job's submit description file.

DAGManNodesMask:

For a DAGMan node job only, a comma-separated list of the event codes that should be written to the log specified by DAGManNodesLog, known as the auxiliary log. All events not specified in the DAGManNodesMask string are not written to the auxiliary event log. The value of this attribute is determined by DAGMan, and it is passed to the job via the condor_submit command line. By default, the following events are written to the auxiliary job log:

Submit, event code is 0
Execute, event code is 1
Executable error, event code is 2
Job evicted, event code is 4
Job terminated, event code is 5
Shadow exception, event code is 7
Job aborted, event code is 9
Job suspended, event code is 10
Job unsuspended, event code is 11
Job held, event code is 12
Job released, event code is 13
Post script terminated, event code is 16
Globus submit, event code is 17
Grid submit, event code is 27

If DAGManNodesLog is not defined, it has no effect. The value of DAGManNodesMask does not affect events recorded in the job event log file referred to by UserLog.

DelegateJobGSICredentialsLifetime:

An integer that specifies the maximum number of seconds for which delegated proxies should be valid. The default behavior is determined by the configuration setting DELEGATE_JOB_GSI_CREDENTIALS_LIFETIME , which defaults to one day. A value of 0 indicates that the delegated proxy should be valid for as long as allowed by the credential used to create the proxy. This setting currently only applies to proxies delegated for non-grid jobs and HTCondor-C jobs. It does not currently apply to globus grid jobs, which always behave as though this setting were 0. This setting has no effect if the configuration setting DELEGATE_JOB_GSI_CREDENTIALS is false, because in that case the job proxy is copied rather than delegated.

DeltacloudAvailableActions:

Used for grid-type deltacloud jobs. For a running job, HTCondor sets this string to contain a comma-separated list of actions that can be performed on a Deltacloud instance, as given by the selected service.

DeltacloudHardwareProfile:

String taken from the submit description file command deltacloud_hardware_profile. Specifies the hardware configuration to be used for a grid-type deltacloud job.

DeltacloudHardwareProfileCpu:

String taken from the submit description file command deltacloud_hardware_profile_cpu. Specifies CPU details in the hardware configuration to be used for a grid-type deltacloud job.

DeltacloudHardwareProfileMemory:

String taken from the submit description file command deltacloud_hardware_profile_memory. Specifies memory (RAM) details in the hardware configuration to be used for a grid-type deltacloud job.

DeltacloudHardwareProfileStorage:

String taken from the submit description file command deltacloud_hardware_profile_storage. Specifies memory (disk) details in the hardware configuration to be used for a grid-type deltacloud job.

DeltacloudImageId:

String taken from the submit description file command deltacloud_image_id. Specifies the virtual machine image to use for a grid-type deltacloud job.

DeltacloudKeyname:

String taken from the submit description file command deltacloud_keyname. Specifies the SSH key pair to use for a grid-type deltacloud job.

DeltacloudPasswordFile:

String taken from the submit description file command deltacloud_password_file. Specifies a file containing the secret key to be used to authenticate with the Deltacloud service for a grid-type deltacloud job.

DeltacloudPrivateNetworkAddresses:

For a running Deltacloud instance, HTCondor receives and sets this comma-separated list of the private IP addresses allocated to the running virtual machine.

DeltacloudPublicNetworkAddresses:

For a running Deltacloud instance, HTCondor receives and sets this comma-separated list of the public IP addresses allocated to the running virtual machine.

DeltacloudRealmId:

String taken from the submit description file command deltacloud_ream_id. Specifies the realm to be used for a grid-type deltacloud job.

DeltacloudUserData:

String taken from the submit description file command deltacloud_user_data. Specifies a block of data to be provided to the instance for a grid-type deltacloud job.

DeltacloudUsername:

String taken from the submit description file command deltacloud_username. Specifies the user name to be used to authenticate with the Deltacloud service for a grid-type deltacloud job.

DiskUsage:

Amount of disk space (Kbytes) in the HTCondor execute directory on the execute machine that this job has used. An initial value may be set at the job's request, placing into the job's submit description file a setting such as

  # 1 megabyte initial value
  +DiskUsage = 1024

vm universe jobs will default to an initial value of the disk image size. If not initialized by the job, non-vm universe jobs will default to an initial value of the sum of the job's executable and all input files.

EC2AccessKeyId:

Used for grid type ec2 jobs; a string taken from the definition of the submit description file command ec2_access_key_id. Defines the path and file name of the file containing the EC2 Query API's access key.

EC2AmiID:

Used for grid type ec2 jobs; a string taken from the definition of the submit description file command ec2_ami_id. Identifies the machine image of the instance.

EC2ElasticIp:

Used for grid type ec2 jobs; a string taken from the definition of the submit description file command ec2_elastic_ip. Specifies an Elastic IP address to associate with the instance.

EC2InstanceName:

Used for grid type ec2 jobs; a string set for the job once the instance starts running, as assigned by the EC2 service, that represents the unique ID assigned to the instance by the EC2 service.

EC2InstanceType:

Used for grid type ec2 jobs; a string taken from the definition of the submit description file command ec2_instance_type. Specifies a service-specific instance type.

EC2KeyPair:

Used for grid type ec2 jobs; a string taken from the definition of the submit description file command ec2_key_pair. Defines the key pair associated with the EC2 instance.

EC2SpotPrice:

Used for grid type ec2 jobs; a string taken from the definition of the submit description file command ec2_spot_price. Defines the maximum amount per hour a job submitter is willing to pay to run this job.

EC2SpotRequestID:

Used for grid type ec2 jobs; identifies the spot request HTCondor made on behalf of this job.

EC2StatusReasonCode:

Used for grid type ec2 jobs; reports the reason for the most recent EC2-level state transition. Can be used to determine if a spot request was terminated due to a rise in the spot price.

EC2TagNames:

Used for grid type ec2 jobs; a string taken from the definition of the submit description file command ec2_tag_names. Defines the set, and case, of tags associated with the EC2 instance.

EC2KeyPairFile:

Used for grid type ec2 jobs; a string taken from the definition of the submit description file command ec2_key_pair_file. Defines the path and file name of the file into which to write the SSH key used to access the image, once it is running.

EC2RemoteVirtualMachineName:

Used for grid type ec2 jobs; a string set for the job once the instance starts running, as assigned by the EC2 service, that represents the host name upon which the instance runs, such that the user can communicate with the running instance.

EC2SecretAccessKey:

Used for grid type ec2 jobs; a string taken from the definition of the submit description file command ec2_secret_access_key. Defines that path and file name of the file containing the EC2 Query API's secret access key.

EC2SecurityGroups:

Used for grid type ec2 jobs; a string taken from the definition of the submit description file command ec2_security_groups. Defines the list of EC2 security groups which should be associated with the job.

EC2UserData:

Used for grid type ec2 jobs; a string taken from the definition of the submit description file command ec2_user_data. Defines a block of data that can be accessed by the virtual machine.

EC2UserDataFile:

Used for grid type ec2 jobs; a string taken from the definition of the submit description file command ec2_user_data_file. Specifies a path and file name of a file containing data that can be accessed by the virtual machine.

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

    time() - EnteredCurrentStatus

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

Args:

A string representing the environment variables passed to the job, when those arguments are specified using the old syntax, as specified in section 11.

Arguments:

A string representing the environment variables passed to the job, when those arguments are specified using the new syntax, as specified in section 11.

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 HTCondor 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.

GceAuthFile:

Used for grid type gce jobs; a string taken from the definition of the submit description file command gce_auth_file. Defines the path and file name of the file containing authorization credentials to use the GCE service.

GceImage:

Used for grid type gce jobs; a string taken from the definition of the submit description file command gce_image. Identifies the machine image of the instance.

GceMachineType:

Used for grid type gce jobs; a string taken from the definition of the submit description file command gce_machine_type. Specifies the hardward profile that should be used for a GCE instance.

GceMetadata:

Used for grid type gce jobs; a string taken from the definition of the submit description file command gce_metadata. Defines a set of name/value pairs that can be accessed by the virtual machine.

GceMetadataFile:

Used for grid type gce jobs; a string taken from the definition of the submit description file command gce_metadata_file. Specifies a path and file name of a file containing a set of name/value pairs that can be accessed by the virtual machine.

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.

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.

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 errno number.
7	The standard output file for the job could not be opened.	The Unix errno number.
8	The standard input file for the job could not be opened.	The Unix errno number.
9	The standard output stream for the job could not be opened.	The Unix errno number.
10	The standard input stream for the job could not be opened.	The Unix errno number.
11	An internal HTCondor protocol error was encountered when transferring files.
12	The condor_starter or condor_shadow failed to receive or write job files.	The Unix errno number.
13	The condor_starter or condor_shadow failed to read or send job files.	The Unix errno number.
14	The initial working directory of the job cannot be accessed.	The Unix errno 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 HTCondor protocol error was encountered when transferring files.
19	`<Keyword>_HOOK_PREPARE_JOB` was defined but could not 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.
22	Unable to initialize job event log.
23	Failed to access user account.
24	No compatible shadow.
25	Invalid cron settings.
26	`SYSTEM_PERIODIC_HOLD` evaluated to true.
27	The system periodic job policy evaluated to undefined.
28	Failed while using glexec to set up the job's working directory (chown sandbox to the user).
30	Failed while using glexec to prepare output for transfer (chown sandbox to condor).
32	The maximum total input file transfer size was exceeded. (See `MAX_TRANSFER_INPUT_MB` .)
33	The maximum total output file transfer size was exceeded. (See `MAX_TRANSFER_OUTPUT_MB` .)
34	Memory usage exceeds a memory limit.

HoldReasonSubCode:

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

HookKeyword:

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

ImageSize:

Maximum observed memory image size (i.e. virtual memory) of the job in Kbytes. The initial value is equal to the size of the executable for non-vm universe jobs, and 0 for vm universe jobs. When the job writes a checkpoint, 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. How quickly this updated information becomes visible to condor_q is controlled by SHADOW_QUEUE_UPDATE_INTERVAL and STARTER_UPDATE_INTERVAL.

Under Linux, ProportionalSetSize is a better indicator of memory usage for jobs with significant sharing of memory between processes, because ImageSize is simply the sum of virtual memory sizes across all of the processes in the job, which may count the same memory pages more than once.

IwdFlushNFSCache:

A boolean expression that controls whether or not HTCondor attempts to flush a submit machine's NFS cache, in order to refresh an HTCondor job's initial working directory. The value will be True, unless a job explicitly adds this attribute, setting it to False.

JobAdInformationAttrs:

A comma-separated list of attribute names. The named attributes and their values are written in the job event log whenever any event is being written to the log. This is the same as the configuration setting EVENT_LOG_INFORMATION_ATTRS (see page

) but it applies to the job event log instead of the system event log.

JobDescription:

A string that may be defined for a job by setting description in the submit description file. When set, tools which display the executable such as condor_q will instead use this string. For interactive jobs that do not have a submit description file, this string will default to "Interactive job".

JobCurrentStartDate:

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

JobCurrentStartExecutingDate:

Time at which the job most recently finished transferring its input sandbox and began executing. Measured in the number of seconds since the epoch (00:00:00 UTC, Jan 1, 1970)

JobCurrentStartTransferOutputDate:

Time at which the job most recently finished executing and began transferring its output sandbox. Measured in the number of seconds since the epoch (00:00:00 UTC, Jan 1, 1970)

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 2.13.4 for details on job leases.

JobMaxVacateTime:

An integer expression that specifies the time in seconds requested by the job for being allowed to gracefully shut down.

JobNotification:

An integer indicating what events should be emailed to the user. The integer values correspond to the user choices for the submit command notification.

Value	Notification value
0	Never
1	Always
2	Complete
3	Error

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
1	Idle
2	Running
3	Removed
4	Completed
5	Held
6	Transferring Output
7	Suspended

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

KeepClaimIdle:

An integer value that represents the number of seconds that the condor_schedd will continue to keep a claim, in the Claimed Idle state, after the job with this attribute defined completes, and there are no other jobs ready to run from this user. This attribute may improve the performance of linear DAGs, in the case when a dependent job can not be scheduled until its parent has completed. Extending the claim on the machine may permit the dependent job to be scheduled with less delay than with waiting for the condor_negotiator to match with a new machine.

KillSig:

The Unix signal number that the job wishes to be sent before being forcibly killed. It is relevant only for jobs running on Unix machines.

KillSigTimeout:

This attribute is replaced by the functionality in JobMaxVacateTime as of HTCondor version 7.7.3. The number of seconds that the job (other than the standard universe) requests the condor_starter wait after sending the signal defined as KillSig and before forcibly removing the job. The actual amount of time will be the minimum of this value and the execute machine's configuration variable KILLING_TIMEOUT .

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 HTCondor-G last tried to find a match for the job, but failed to do so.

LastRemotePool:

The name of the condor_collector of the pool in which a job ran via flocking in the most recent run attempt. This attribute is not defined if the job did not run via flocking.

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).

LeaveJobInQueue:

A boolean expression that defaults to False, causing the job to be removed from the queue upon completion. An exception is if the job is submitted using condor_submit -spool. For this case, the default expression causes the job to be kept in the queue for 10 days after completion.

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.

MachineAttr<X><N>:

Machine attribute of name <X> that is placed into this job ClassAd, as specified by the configuration variable SYSTEM_JOB_MACHINE_ATTRS. With the potential for multiple run attempts, <N> represents an integer value providing historical values of this machine attribute for multiple runs. The most recent run will have a value of <N> equal to 0. The next most recent run will have a value of <N> equal to 1.

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.

MaxTransferInputMB:

This integer expression specifies the maximum allowed total size in Mbytes of the input files that are transferred for a job. This expression does not apply to grid universe, standard universe, or files transferred via file transfer plug-ins. The expression may refer to attributes of the job. The special value -1 indicates no limit. If not set, the system setting MAX_TRANSFER_INPUT_MB is used. If the observed size of all input files at submit time is larger than the limit, the job will be immediately placed on hold with a HoldReasonCode value of 32. If the job passes this initial test, but the size of the input files increases or the limit decreases so that the limit is violated, the job will be placed on hold at the time when the file transfer is attempted.

MaxTransferOutputMB:

This integer expression specifies the maximum allowed total size in Mbytes of the output files that are transferred for a job. This expression does not apply to grid universe, standard universe, or files transferred via file transfer plug-ins. The expression may refer to attributes of the job. The special value -1 indicates no limit. If not set, the system setting MAX_TRANSFER_OUTPUT_MB is used. If the total size of the job's output files to be transferred is larger than the limit, the job will be placed on hold with a HoldReasonCode value of 33. The output will be transferred up to the point when the limit is hit, so some files may be fully transferred, some partially, and some not at all.

MemoryUsage:

An integer expression in units of Mbytes that represents the peak memory usage for the job. Its purpose is to be compared with the value defined by a job with the request_memory submit command, for purposes of policy evaluation.

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 HTCondor jobs want the machine.

Nonessential:

A boolean value only relevant to grid universe jobs, which when True tells HTCondor to simply abort (remove) any problematic job, instead of putting the job on hold. It is the equivalent of doing condor_rm followed by condor_rm -forcex any time the job would have otherwise gone on hold. If not explicitly set to True, the default value will be False.

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.

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.

NumJobStarts:

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

NumPids:

A count of the number of child processes that this job has.

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 HTCondor-G places a job on hold due to some sort of error condition. This counter is useful, since HTCondor-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.

OtherJobRemoveRequirements:

A string that defines a list of jobs. When the job with this attribute defined is removed, all other jobs defined by the list are also removed. The string is an expression that defines a constraint equivalent to the one implied by the command

  condor_rm -constraint <constraint>

This attribute is used for jobs managed with condor_dagman to ensure that node jobs of the DAG are removed when the condor_dagman job itself is removed. Note that the list of jobs defined by this attribute must not form a cyclic removal of jobs, or the condor_schedd will go into an infinite loop when any of the jobs is removed.

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, HTCondor's behavior changes:

"WAIT_FOR_ALL": HTCondor will wait until every node in the parallel job has completed to consider the job finished.

PreserveRelativeExecutable:

When True, the condor_starter will not prepend Iwd to Cmd, when Cmd is a relative path name and TransferExecutable is False. The default value is False. This attribute is primarily of interest for users of USER_JOB_WRAPPER for the purpose of allowing an executable's location to be resolved by the user's path in the job wrapper.

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.

ProportionalSetSizeKb:

On Linux execute machines with kernel version more recent than 2.6.27, this is the maximum observed proportional set size (PSS) in Kbytes, summed across all processes in the job. If the execute machine does not support monitoring of PSS or PSS has not yet been measured, this attribute will be undefined. PSS differs from ImageSize in how memory shared between processes is accounted. The PSS for one process is the sum of that process' memory pages divided by the number of processes sharing each of the pages. ImageSize is the same, except there is no division by the number of processes sharing the pages.

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.

RemotePool:

The name of the condor_collector of the pool in which a job is running via flocking. This attribute is not defined if the job is not running via flocking.

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. A job in the virtual machine universe will only report this attribute if run on a KVM hypervisor.

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. CommittedTime, on the other hand, is just like RemoteWallClockTime except it does get reset to 0 whenever the job is evicted without a checkpoint.

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.

RequestCpus:

The number of CPUs requested for this job. If dynamic condor_startd provisioning is enabled, it is the minimum number of CPUs that are needed in the created dynamic slot.

RequestDisk:

The amount of disk space in Kbytes requested for this job. If dynamic condor_startd provisioning is enabled, it is the minimum amount of disk space needed in the created dynamic slot.

RequestedChroot:

A full path to the directory that the job requests the condor_starter use as an argument to chroot().

RequestMemory:

The amount of memory space in Mbytes requested for this job. If dynamic condor_startd provisioning is enabled, it is the minimum amount of memory needed in the created dynamic slot. If not set by the job, its definition is specified by configuration variable JOB_DEFAULT_REQUESTMEMORY .

ResidentSetSize:

Maximum observed physical memory in use by the job in Kbytes while running.

StackSize:

Utilized for Linux jobs only, the number of bytes allocated for stack space for this job. This number of bytes replaces the default allocation of 512 Mbytes.

StageOutFinish:

An attribute representing a Unix epoch time that is defined for a job that is spooled to a remote site using condor_submit -spool or HTCondor-C and causes HTCondor to hold the output in the spool while the job waits in the queue in the Completed state. This attribute is defined when retrieval of the output finishes.

StageOutStart:

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.

SubmitterAutoregroup:

A boolean attribute defined by the condor_negotiator when it makes a match. It will be True if the resource was claimed via negotiation when the configuration variable GROUP_AUTOREGROUP was True. It will be False otherwise.

SubmitterGroup:

The accounting group name defined by the condor_negotiator when it makes a match.

SubmitterNegotiatingGroup:

The accounting group name under which the resource negotiated when it was claimed, as set by the condor_negotiator.

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.

TransferInputSizeMB:

The total size in Mbytes of input files to be transferred for the job. Files transferred via file transfer plug-ins are not included. This attribute is automatically set by condor_submit; jobs submitted via other submission methods, such as SOAP, may not define this attribute.

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.

TransferringInput:

A boolean value that indicates whether the job is currently transferring input files. The value is Undefined if the job is not scheduled to run or has not yet attempted to start transferring input. When this value is True, to see whether the transfer is active or queued, check TransferQueued.

TransferringOutput:

A boolean value that indicates whether the job is currently transferring output files. The value is Undefined if the job is not scheduled to run or has not yet attempted to start transferring output. When this value is True, to see whether the transfer is active or queued, check TransferQueued.

TransferQueued:

A boolean value that indicates whether the job is currently waiting to transfer files because of limits placed by MAX_CONCURRENT_DOWNLOADS or MAX_CONCURRENT_UPLOADS .

UserLog:

The full path and file name on the submit machine of the log file of job events.

WantGracefulRemoval:

A boolean expression that, when True, specifies that a graceful shutdown of the job should be done when the job is removed or put on hold.

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.

X509UserProxy:

The full path and file name of the file containing the X.509 user proxy.

X509UserProxyEmail:

For a job with an X.509 proxy credential, this is the email address extracted from the proxy.

X509UserProxyExpiration:

For a job that defines the submit description file command x509userproxy, this is the time at which the indicated X.509 proxy credential will expire, measured in the number of seconds since the epoch (00:00:00 UTC, Jan 1, 1970).

X509UserProxyFirstFQAN:

For a vanilla or grid universe job that defines the submit description file command x509userproxy, this is the VOMS Fully Qualified Attribute Name (FQAN) of the primary role of the credential. A credential may have multiple roles defined, but by convention the one listed first is the primary role.

X509UserProxyFQAN:

For a vanilla or grid universe job that defines the submit description file command x509userproxy, this is a serialized list of the DN and all FQAN. A comma is used as a separator, and any existing commas in the DN or FQAN are replaced with the string ,. Likewise, any ampersands in the DN or FQAN are replaced with &.

X509UserProxySubject:

For a vanilla or grid universe job that defines the submit description file command x509userproxy, this attribute contains the Distinguished Name (DN) of the credential used to submit the job.

X509UserProxyVOName:

For a vanilla or grid universe job that defines the submit description file command x509userproxy, this is the name of the VOMS virtual organization (VO) that the user's credential is part of.

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.

The following job ClassAd attributes appear in the job ClassAd only for the condor_dagman job submitted under DAGMan. They represent status information for the DAG.

DAG_InRecovery:

The value 1 if the DAG is in recovery mode, and The value 0 otherwise.

DAG_NodesDone:

The number of DAG nodes that have finished successfully. This means that the entire node has finished, not only an actual HTCondor job or jobs.

DAG_NodesFailed:

The number of DAG nodes that have failed. This value includes all retries, if there are any.

DAG_NodesPostrun:

The number of DAG nodes for which a POST script is running or has been deferred because of a POST script throttle setting.

DAG_NodesPrerun:

The number of DAG nodes for which a PRE script is running or has been deferred because of a PRE script throttle setting.

DAG_NodesQueued:

The number of DAG nodes for which the actual HTCondor job or jobs are queued. The queued jobs may be in any state.

DAG_NodesReady:

The number of DAG nodes that are ready to run, but which have not yet started running.

DAG_NodesTotal:

The total number of nodes in the DAG, including the FINAL node, if there is a FINAL node.

DAG_NodesUnready:

The number of DAG nodes that are not ready to run. This is a node in which one or more of the parent nodes has not yet finished.

DAG_Status:

The overall status of the DAG, with the same values as the _DAG_STATUS macro.

Value	Status
0	OK
1	error; an error condition different than those listed here
2	one or more nodes in the DAG have failed
3	the DAG has been aborted by an ABORT-DAG-ON specification
4	removed; the DAG has been removed by condor_rm
5	a cycle was found in the DAG
6	the DAG has been suspended (see section 2.10.7)

Machine ClassAd Attributes

Activity:

String which describes HTCondor 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
"Retiring":: Waiting for a job to finish or for the maximum retirement time to expire

Arch:

String with the architecture of the machine. Currently supported architectures have the following string definitions:

"INTEL":: Intel x86 CPU (Pentium, Xeon, etc).
"X86_64":: AMD/Intel 64-bit X86

These strings show definitions for architectures no longer supported:

"IA64":: Intel Itanium
"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":: 32-bit PowerPC
"PPC64":: 64-bit PowerPC

CanHibernate:

The condor_startd has the capability to shut down or hibernate a machine when certain configurable criteria are met. However, before the condor_startd can shut down a machine, the hardware itself must support hibernation, as must the operating system. When the condor_startd initializes, it checks for this support. If the machine has the ability to hibernate, then this boolean ClassAd attribute will be True. By default, it is False.

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, ... , and 6 = Saturday.

ClockMin:

The number of minutes passed since midnight.

CondorLoadAvg:

The load average contributed by HTCondor, either from remote jobs or running benchmarks.

CondorVersion:

A string containing the HTCondor version number for the condor_startd daemon, the release date, and the build identification number.

ConsoleIdle:

The number of seconds since activity on the system console keyboard or console mouse has last been detected. The value can be modified with SLOTS_CONNECTED_TO_CONSOLE as defined at 3.3.10.

Cpus:

The number of CPUs in this slot. It is 1 for a single CPU slot, 2 for a dual CPU slot, etc.

CurrentRank:

A float which represents this machine owner's affinity for running the HTCondor job which it is currently hosting. If not currently hosting an HTCondor 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 HTCondor configuration files by the EXECUTE macro, minus any space reserved with the RESERVED_DISK macro.

Draining:

This attribute is True when the slot is draining and undefined if not.

DrainingRequestId:

This attribute contains a string that is the request id of the draining request that put this slot in a draining state. It is undefined if the slot is not draining.

DotNetVersions:

The .NET framework versions currently installed on this computer. Default format is a comma delimited list. Current definitions:

"1.1":: for .Net Framework 1.1
"2.0":: for .Net Framework 2.0
"3.0":: for .Net Framework 3.0
"3.5":: for .Net Framework 3.5
"4.0Client":: for .Net Framework 4.0 Client install
"4.0Full":: for .Net Framework 4.0 Full install

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).

ExpectedMachineGracefulDrainingBadput:

The job run time in cpu-seconds that would be lost if graceful draining were initiated at the time this ClassAd was published. This calculation assumes that jobs will run for the full retirement time and then be evicted without saving a checkpoint.

ExpectedMachineGracefulDrainingCompletion:

The estimated time at which graceful draining of the machine could complete if it were initiated at the time this ClassAd was published and there are no active claims. This is measured in the number of integer seconds since the Unix epoch (00:00:00 UTC, Jan 1, 1970). This value is computed with the assumption that the machine policy will not suspend jobs during draining while the machine is waiting for the job to use up its retirement time. If suspension happens, the upper bound on how long draining could take is unlimited. To avoid suspension during draining, the SUSPEND and CONTINUE expressions could be configured to pay attention to the Draining attribute.

ExpectedMachineGracefulQuickBadput:

The job run time in cpu-seconds that would be lost if quick or fast draining were initiated at the time this ClassAd was published. This calculation assumes that all evicted jobs will not save a checkpoint.

ExpectedMachineQuickDrainingCompletion:

Time at which quick or fast draining of the machine could complete if it were initiated at the time this ClassAd was published and there are no active claims. 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 HTCondor 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.

Has_sse4_1:

A boolean value set to True if the machine being advertised supports the SSE 4.1 instructions, and Undefined otherwise.

Has_sse4_2:

A boolean value set to True if the machine being advertised supports the SSE 4.2 instructions, and Undefined otherwise.

has_ssse3:

A boolean value set to True if the machine being advertised supports the SSSE 3 instructions, and Undefined otherwise.

HasVM:

A boolean value added to the machine ClassAd when the configuration triggers the detection of virtual machine software.

IsWakeAble:

A boolean value that when True identifies that the machine has the capability to be woken into a fully powered and running state by receiving a Wake On LAN (WOL) packet. This ability is a function of the operating system, the network adapter in the machine (notably, wireless network adapters usually do not have this function), and BIOS settings. When the condor_startd initializes, it tries to detect if the operating system and network adapter both support waking from hibernation by receipt of a WOL packet. The default value is False.

IsWakeEnabled:

If the hardware and software have the capacity to be woken into a fully powered and running state by receiving a Wake On LAN (WOL) packet, this feature can still be disabled via the BIOS or software. If BIOS or the operating system have disabled this feature, the condor_startd sets this boolean attribute to False.

JobPreemptions:

The total number of times a running job has been preempted on this machine.

JobRankPreemptions:

The total number of times a running job has been preempted on this machine due to the machine's rank of jobs since the condor_startd started running.

JobStarts:

The total number of jobs which have been started on this machine since the condor_startd started running.

JobUserPrioPreemptions:

The total number of times a running job has been preempted on this machine based on a fair share allocation of the pool since the condor_startd started running.

JobVM_VCPUS:

An attribute defined if a vm universe job is running on this slot. Defined by the number of virtualized CPUs in the virtual machine.

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. Pseudo-terminals have virtual keyboard activity from telnet and rlogin sessions. Note that KeyboardIdle will always be equal to or less than ConsoleIdle. The value can be modified with SLOTS_CONNECTED_TO_KEYBOARD as defined at 3.3.10.

KFlops:

Relative floating point performance as determined via a Linpack benchmark.

LastDrainStartTime:

Time when draining of this condor_startd was last initiated (e.g. due to condor_defrag or condor_drain).

LastHeardFrom:

Time when the HTCondor 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 representing the current load average.

Machine:

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

MachineMaxVacateTime:

An integer expression that specifies the time in seconds the machine will allow the job to gracefully shut down.

MaxJobRetirementTime:

When the condor_startd wants to kick the job off, a job which has run for less than this number of seconds will not be hard-killed. The condor_startd will wait for the job to finish or to exceed this amount of time, whichever comes sooner. If the job vacating policy grants the job X seconds of vacating time, a preempted job will be soft-killed X seconds before the end of its retirement time, so that hard-killing of the job will not happen until the end of the retirement time if the job does not finish shutting down before then. This is an expression evaluated in the context of the job ClassAd, so it may refer to job attributes as well as machine attributes.

Memory:

The amount of RAM in megabytes.

Mips:

Relative integer performance as determined via a Dhrystone benchmark.

MonitorSelfAge:

The number of seconds that this daemon has been running.

MonitorSelfCPUUsage:

The fraction of recent CPU time utilized by this daemon.

MonitorSelfImageSize:

The amount of virtual memory consumed by this daemon in Kbytes.

MonitorSelfRegisteredSocketCount:

The current number of sockets registered by this daemon.

MonitorSelfResidentSetSize:

The amount of resident memory used by this daemon in Kbytes.

MonitorSelfSecuritySessions:

The number of open (cached) security sessions for this daemon.

MonitorSelfTime:

The time, represented as the number of second elapsed since the Unix epoch (00:00:00 UTC, Jan 1, 1970), at which this daemon last checked and set the attributes with names that begin with the string MonitorSelf.

MyAddress:

String with the IP and port address of the condor_startd daemon which is publishing this machine ClassAd. When using CCB, condor_shared_port, and/or an additional private network interface, that information will be included here as well.

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.

Offline<name>:

A string that lists specific instances of a user-defined machine resource, identified by name. Each instance is currently unavailable for purposes of match making.

OpSys:

String describing the operating system running on this machine. Currently supported operating systems have the following string definitions:

"LINUX":: for LINUX 2.0.x, LINUX 2.2.x, LINUX 2.4.x, LINUX 2.6.x, or LINUX 3.10.0 kernel systems, as well as Scientific Linux and Ubuntu 12.04
"OSX":: for Darwin
"FREEBSD7":: for FreeBSD 7
"FREEBSD8":: for FreeBSD 8
"WINDOWS":: for all versions of Windows
"SOLARIS5.10":: for Solaris 2.10 or 5.10
"SOLARIS5.11":: for Solaris 2.11 or 5.11

These strings show definitions for operating systems no longer supported:

"SOLARIS28":: for Solaris 2.8 or 5.8
"SOLARIS29":: for Solaris 2.9 or 5.9

OpSysAndVer:

A string indicating an operating system and a version number.

For Linux operating systems, it is the value of the OpSysName attribute concatenated with the string version of the OpSysMajorVersion attribute:

"RedHat5":: for RedHat Linux version 5
"RedHat6":: for RedHat Linux version 6
"RedHat7":: for RedHat Linux version 7 Beta
"Fedora16":: for Fedora Linux version 16
"Debian5":: for Debian Linux version 5
"Debian6":: for Debian Linux version 6
"Ubuntu12":: for Ubuntu 12.04
"SL5":: for Scientific Linux version 5
"SL6":: for Scientific Linux version 6
"SLFermi5":: for Fermi's Scientific Linux version 5
"SLFermi6":: for Fermi's Scientific Linux version 6
"SLCern5":: for CERN's Scientific Linux version 5
"SLCern6":: for CERN's Scientific Linux version 6

For MacOS operating systems, it is the value of the OpSysShortName attribute concatenated with the string version of the OpSysVer attribute:

"MacOSX605":: for MacOS version 10.6.5 (Snow Leopard)
"MacOSX703":: for MacOS version 10.7.3 (Lion)

For BSD operating systems, it is the value of the OpSysName attribute concatenated with the string version of the OpSysMajorVersion attribute:

"FREEBSD7":: for FreeBSD version 7
"FREEBSD8":: for FreeBSD version 8

For Solaris Unix operating systems, it is the same value as the OpSys attribute:

"SOLARIS5.10":: for Solaris 2.10 or 5.10
"SOLARIS5.11":: for Solaris 2.11 or 5.11

For Windows operating systems, it is the value of the OpSys attribute concatenated with the string version of the OpSysMajorVersion attribute:

"WINDOWS500":: for Windows 2000
"WINDOWS501":: for Windows XP
"WINDOWS502":: for Windows Server 2003
"WINDOWS600":: for Windows Vista
"WINDOWS601":: for Windows 7

OpSysLegacy:

A string that holds the long-standing values for the OpSys attribute. Currently supported operating systems have the following string definitions:

"LINUX":: for LINUX 2.0.x, LINUX 2.2.x, LINUX 2.4.x, LINUX 2.6.x, or LINUX 3.10.0 kernel systems, as well as Scientific Linux and Ubuntu 12.04 versions
"OSX":: for Darwin
"FREEBSD7":: for FreeBSD version 7
"FREEBSD8":: for FreeBSD version 8
"SOLARIS5.10":: for Solaris 2.10 or 5.10
"SOLARIS5.11":: for Solaris 2.11 or 5.11
"WINDOWS":: for all versions of Windows

OpSysLongName:

A string giving a full description of the operating system. For Linux platforms, this is generally the string taken from /etc/hosts, with extra characters stripped off Debian versions.

"Red Hat Enterprise Linux Server release 5.7 (Tikanga)":: for RedHat Linux version 5
"Red Hat Enterprise Linux Server release 6.2 (Santiago)":: for RedHat Linux version 6
"Red Hat Enterprise Linux Everything release 7.0 (Maipo)":: for RedHat Linux version 7.0 Beta
"Ubuntu 12.04.3 LTS":: for Ubuntu 12.04 point release 3
"Fedora release 16 (Verne)":: for Fedora Linux version 16
"MacOSX 6.5":: for MacOS version 10.6.5 (Snow Leopard)
"MacOSX 7.3":: for MacOS version 10.7.3 (Lion)
"FreeBSD8.2-RELEASE-p3":: for FreeBSD version 8
"SOLARIS5.10":: for Solaris 2.10 or 5.10
"SOLARIS5.11":: for Solaris 2.11 or 5.11
"Windows XP SP3":: for Windows XP
"Windows 7 SP2":: for Windows 7

OpSysMajorVersion:

An integer value representing the major version of the operating system.

5:: for RedHat Linux version 5 and derived platforms such as Scientific Linux
6:: for RedHat Linux version 6 and derived platforms such as Scientific Linux
7:: for RedHat Linux version 7 Beta
12:: for Ubuntu 12.04
16:: for Fedora Linux version 16
6:: for MacOS version 10.6.5 (Snow Leopard)
7:: for MacOS version 10.7.3 (Lion)
7:: for FreeBSD version 7
8:: for FreeBSD version 8
5:: for Solaris 2.10, 5.10, 2.11, or 5.11
501:: for Windows XP
600:: for Windows Vista
601:: for Windows 7

OpSysName:

A string containing a terse description of the operating system.

"RedHat":: for RedHat Linux version 6 and 7 Beta
"Fedora":: for Fedora Linux version 16
"Ubuntu":: for Ubuntu 12.04
"SnowLeopard":: for MacOS version 10.6.5 (Snow Leopard)
"Lion":: for MacOS version 10.7.3 (Lion)
"FREEBSD":: for FreeBSD version 7 or 8
"SOLARIS5.10":: for Solaris 2.10 or 5.10
"SOLARIS5.11":: for Solaris 2.11 or 5.11
"WindowsXP":: for Windows XP
"WindowsVista":: for Windows Vista
"Windows7":: for Windows 7
"SL":: for Scientific Linux
"SLFermi":: for Fermi's Scientific Linux
"SLCern":: for CERN's Scientific Linux

OpSysShortName:

A string containing a short name for the operating system.

"RedHat":: for RedHat Linux version 5, 6 or 7 Beta
"Fedora":: for Fedora Linux version 16
"Debian":: for Debian Linux version 5 or 6
"Ubuntu":: for Ubuntu 12.04
"MacOSX":: for MacOS version 10.6.5 (Snow Leopard) or for MacOS version 10.7.3 (Lion)
"FreeBSD":: for FreeBSD version 7 or 8
"SOLARIS5.10":: for Solaris 2.10 or 5.10
"SOLARIS5.11":: for Solaris 2.11 or 5.11
"XP":: for Windows XP
"Vista":: for Windows Vista
"7":: for Windows 7
"SL":: for Scientific Linux
"SLFermi":: for Fermi's Scientific Linux
"SLCern":: for CERN's Scientific Linux

OpSysVer:

An integer value representing the operating system version number.

700:: for RedHat Linux version 7.0 Beta
602:: for RedHat Linux version 6.2
1600:: for Fedora Linux version 16.0
1204:: for Ubuntu 12.04
704:: for FreeBSD version 7.4
802:: for FreeBSD version 8.2
605:: for MacOS version 10.6.5 (Snow Leopard)
703:: for MacOS version 10.7.3 (Lion)
500:: for Windows 2000
501:: for Windows XP
502:: for Windows Server 2003
600:: for Windows Vista or Windows Server 2008
601:: for Windows 7 or Windows Server 2008

RecentJobPreemptions:

The total number of jobs which have been preempted from this machine in the last twenty minutes.

RecentJobRankPreemptions:

The total number of times a running job has been preempted on this machine due to the machine's rank of jobs in the last twenty minutes.

RecentJobStarts:

The total number of jobs which have been started on this machine in the last twenty minutes.

RecentJobUserPrio:

The total number of times a running job has been preempted on this machine based on a fair share allocation of the pool in the last twenty minutes.

Requirements:

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

RetirementTimeRemaining:

An integer number of seconds after MyCurrentTime when the running job can be evicted. MaxJobRetirementTime is the expression of how much retirement time the machine offers to new jobs, whereas RetirementTimeRemaining is the negotiated amount of time remaining for the current running job. This may be less than the amount offered by the machine's MaxJobRetirementTime expression, because the job may ask for less.

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 HTCondor version 6.9.3. For older versions of HTCondor, 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:

State:

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

"Owner":: The machine owner is using the machine, and it is unavailable to HTCondor.
"Unclaimed":: The machine is available to run HTCondor jobs, but a good match is either not available or not yet found.
"Matched":: The HTCondor central manager has found a good match for this resource, but an HTCondor scheduler has not yet claimed it.
"Claimed":: The machine is claimed by a remote condor_schedd and is probably running a job.
"Preempting":: An HTCondor 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.
"Drained":: This slot is not accepting jobs, because the machine is being drained.

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.

TotalCondorLoadAvg:

The load average contributed by HTCondor summed across all slots on the machine, either from remote jobs or running benchmarks.

TotalCpus:

The number of CPUs that are on the machine. This is in contrast with Cpus, which is the number of CPUs in the slot.

TotalLoadAvg:

A floating point number representing the current load average summed across all slots on the machine.

TotalMachineDrainingBadput:

The total job runtime in cpu-seconds that has been lost due to job evictions caused by draining since this condor_startd began executing. In this calculation, it is assumed that jobs are evicted without checkpointing.

TotalMachineDrainingUnclaimedTime:

The total machine-wide time in cpu-seconds that has not been used (i.e. not matched to a job submitter) due to draining since this condor_startd began executing.

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 HTCondor 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 HTCondor 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. On Linux platforms, it is the sum of paging space and physical memory, which more accurately represents the virtual memory size of the machine.

VM_AvailNum:

The maximum number of vm universe jobs that can be started on this machine. This maximum is set by the configuration variable VM_MAX_NUMBER .

VM_Guest_Mem:

An attribute defined if a vm universe job is running on this slot. Defined by the amount of memory in use by the virtual machine, given in Mbytes.

VM_Memory:

Gives the amount of memory available for starting additional VM jobs on this machine, given in Mbytes. The maximum value is set by the configuration variable VM_MEMORY .

VM_Networking:

A boolean value indicating whether networking is allowed for virtual machines on this machine.

VM_Type:

The type of virtual machine software that can run on this machine. The value is set by the configuration variable VM_TYPE .

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
RemoteAutoregroup:: A boolean attribute which is True if this resource was claimed via negotiation when the configuration variable GROUP_AUTOREGROUP is True. It is False otherwise.
RemoteGroup:: The accounting group name corresponding to the submitter that claimed this resource.
RemoteNegotiatingGroup:: The accounting group name under which this resource negotiated when it was claimed. This attribute will frequently be the same as attribute RemoteGroup, but it may differ in cases such as when configuration variable GROUP_AUTOREGROUP is True, in which case it will have the name of the root group, identified as <none>.
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 HTCondor job which is waiting for the current job to finish or be preempted. If not currently hosting an HTCondor 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, that is, hibernating.

MachineLastMatchTime:: The Unix epoch time when this offline ClassAd would have been matched to a job, if the machine were online. In addition, the slot1 ClassAd of a multi-slot machine will have slot<X>_MachineLastMatchTime defined, where <X> is replaced by the slot id of each of the slots with MachineLastMatchTime defined.
Offline:: A boolean value, that when True, indicates this machine is in an offline state in the condor_collector. Such ClassAds are stored persistently, such that they will continue to exist after the condor_collector restarts.
Unhibernate:: A boolean expression that specifies when a hibernating machine should be woken up, for example, by condor_rooster.

For machines with user-defined or custom resource specifications, including GPUs, the following attributes will be in the ClassAd for each slot. In the name of the attribute, <name> is substituted with the configured name given to the resource.

Assigned<name>:: A space separated list that identifies which of these resources are currently assigned to slots.
Offline<name>:: A space separated list that indicates which of these resources is unavailable for match making.
Total<name>:: An integer quantity of the total number of these resources.

For machines with custom resource specifications that include GPUs, the following attributes may be in the ClassAd for each slot, depending on the value of configuration variable MACHINE_RESOURCE_INVENTORY_GPUs and what GPUs are detected. In the name of the attribute, <name> is substituted with the prefix string assigned for the GPU.

<name>BoardTempC:: For NVIDIA devices, a dynamic attribute representing the temperature in Celsius of the board containing the GPU.
<name>Capability:: The CUDA-defined capability for the GPU.
<name>ClockMhz:: For CUDA or Open CL devices, the integer clocking speed of the GPU in MHz.
<name>ComputeUnits:: For CUDA or Open CL devices, the integer number of compute units per GPU.
<name>CoresPerCU:: For CUDA devices, the integer number of cores per compute unit.
<name>DeviceName:: For CUDA or Open CL devices, a string representing the manufacturer's proprietary device name.
<name>DieTempC:: For NVIDIA devices, a dynamic attribute representing the temperature in Celsius of the GPU die.
<name>DriverVersion:: For CUDA devices, a string representing the manufacturer's driver version.
<name>ECCEnabled:: For CUDA or Open CL devices, a boolean value representing whether error correction is enabled.
<name>EccErrorsDoubleBit:: For NVIDIA devices, a count of the number of double bit errors detected for this GPU.
<name>EccErrorsSingleBit:: For NVIDIA devices, a count of the number of single bit errors detected for this GPU.
<name>FanSpeedPct:: For NVIDIA devices, a value between 0 and 100 (inclusive), used to represent the level of fan operation as percentage of full fan speed.
<name>GlobalMemoryMb:: For CUDA or Open CL devices, the quantity of memory in Mbytes in this GPU.
<name>OpenCLVersion:: For Open CL devices, a string representing the manufacturer's version number.
<name>RuntimeVersion:: For CUDA devices, a string representing the manufacturer's version number.

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.
CondorVersion:: A string containing the HTCondor version number, the release date, and the build identification number.
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.
MonitorSelfAge:: The number of seconds that this daemon has been running.
MonitorSelfCPUUsage:: The fraction of recent CPU time utilized by this daemon.
MonitorSelfImageSize:: The amount of virtual memory consumed by this daemon in Kbytes.
MonitorSelfRegisteredSocketCount:: The current number of sockets registered by this daemon.
MonitorSelfResidentSetSize:: The amount of resident memory used by this daemon in Kbytes.
MonitorSelfSecuritySessions:: The number of open (cached) security sessions for this daemon.
MonitorSelfTime:: The time, represented as the number of second elapsed since the Unix epoch (00:00:00 UTC, Jan 1, 1970), at which this daemon last checked and set the attributes with names that begin with the string MonitorSelf.
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

Autoclusters:

A Statistics attribute defining the number of active autoclusters.

CollectorHost:

The name of the main condor_collector which this condor_schedd daemon reports to, as copied from COLLECTOR_HOST . If a condor_schedd flocks to other condor_collector daemons, this attribute still represents the "home" condor_collector, so this value can be used to discover if a condor_schedd is currently flocking.

CondorVersion:

A string containing the HTCondor version number, the release date, and the build identification number.

DaemonCoreDutyCycle:

A Statistics attribute defining the ratio of the time spent handling messages and events to the elapsed time for the time period defined by StatsLifetime of this condor_schedd. A value near 0.0 indicates an idle daemon, while a value near 1.0 indicates a daemon running at or above capacity.

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).

DetectedCpus:

The number of detected machine CPUs/cores.

DetectedMemory:

The amount of detected machine RAM in MBytes.

JobQueueBirthdate:

Description is not yet written.

JobsAccumBadputTime:

A Statistics attribute defining the sum of the all of the time jobs which did not complete successfully have spent running over the lifetime of this condor_schedd.

JobsAccumRunningTime:

A Statistics attribute defining the sum of the all of the time jobs have spent running in the time interval defined by attribute StatsLifetime.

JobsAccumTimeToStart:

A Statistics attribute defining the sum of all the time jobs have spent waiting to start in the time interval defined by attribute StatsLifetime.

JobsBadputRuntimes:

A Statistics attribute defining a histogram count of jobs that did not complete successfully, as classified by time spent running, over the lifetime of this condor_schedd. Counts within the histogram are separated by a comma and a space, where the time interval classification is defined in the ClassAd attribute JobsRuntimesHistogramBuckets.

JobsBadputSizes:

A Statistics attribute defining a histogram count of jobs that did not complete successfully, as classified by image size, over the lifetime of this condor_schedd. Counts within the histogram are separated by a comma and a space, where the size classification is defined in the ClassAd attribute JobsSizesHistogramBuckets.

JobsCheckpointed:

A Statistics attribute defining the number of times jobs that have exited with a condor_shadow exit code of JOB_CKPTED in the time interval defined by attribute StatsLifetime.

JobsCompleted:

A Statistics attribute defining the number of jobs successfully completed in the time interval defined by attribute StatsLifetime.

JobsCompletedRuntimes:

A Statistics attribute defining a histogram count of jobs that completed successfully as classified by time spent running, over the lifetime of this condor_schedd. Counts within the histogram are separated by a comma and a space, where the time interval classification is defined in the ClassAd attribute JobsRuntimesHistogramBuckets.

JobsCompletedSizes:

A Statistics attribute defining a histogram count of jobs that completed successfully as classified by image size, over the lifetime of this condor_schedd. Counts within the histogram are separated by a comma and a space, where the size classification is defined in the ClassAd attribute JobsSizesHistogramBuckets.

JobsCoredumped:

A Statistics attribute defining the number of times that jobs have exited with a condor_shadow exit code of JOB_COREDUMPED in the time interval defined by attribute StatsLifetime.

JobsDebugLogError:

A Statistics attribute defining the number of times that jobs have exited with a condor_shadow exit code of DPRINTF_ERROR in the time interval defined by attribute StatsLifetime.

JobsExecFailed:

A Statistics attribute defining the number of times that jobs have exited with a condor_shadow exit code of JOB_EXEC_FAILED in the time interval defined by attribute StatsLifetime.

JobsExited:

A Statistics attribute defining the number of times that jobs that exited (successfully or not) in the time interval defined by attribute StatsLifetime.

JobsExitedAndClaimClosing:

A Statistics attribute defining the number of times jobs have exited with a condor_shadow exit code of JOB_EXITED_AND_CLAIM_CLOSING in the time interval defined by attribute StatsLifetime.

JobsExitedNormally:

A Statistics attribute defining the number of times that jobs have exited with a condor_shadow exit code of JOB_EXITED or with an exit code of JOB_EXITED_AND_CLAIM_CLOSING in the time interval defined by attribute StatsLifetime.

JobsExitException:

A Statistics attribute defining the number of times that jobs have exited with a condor_shadow exit code of JOB_EXCEPTION or with an unknown status in the time interval defined by attribute StatsLifetime.

JobsKilled:

A Statistics attribute defining the number of times that jobs have exited with a condor_shadow exit code of JOB_KILLED in the time interval defined by attribute StatsLifetime.

JobsMissedDeferralTime:

A Statistics attribute defining the number of times that jobs have exited with a condor_shadow exit code of JOB_MISSED_DEFERRAL_TIME in the time interval defined by attribute StatsLifetime.

JobsNotStarted:

A Statistics attribute defining the number of times that jobs have exited with a condor_shadow exit code of JOB_NOT_STARTED in the time interval defined by attribute StatsLifetime.

JobsRunningRuntimes:

A Statistics attribute defining a histogram count of jobs currently running, as classified by elapsed runtime. Counts within the histogram are separated by a comma and a space, where the time interval classification is defined in the ClassAd attribute JobsRuntimesHistogramBuckets.

JobsRunningSizes:

A Statistics attribute defining a histogram count of jobs currently running, as classified by image size. Counts within the histogram are separated by a comma and a space, where the size classification is defined in the ClassAd attribute JobsSizesHistogramBuckets.

JobsRuntimesHistogramBuckets:

A Statistics attribute defining the predefined bucket boundaries for histogram statistics that classify run times. Defined as

  JobsRuntimesHistogramBuckets = "30Sec, 1Min, 3Min, 10Min, 30Min, 1Hr, 3Hr, 
          6Hr, 12Hr, 1Day, 2Day, 4Day, 8Day, 16Day"

JobsShadowNoMemory:

A Statistics attribute defining the number of times that jobs have exited because there was not enough memory to start the condor_shadow in the time interval defined by attribute StatsLifetime.

JobsShouldHold:

A Statistics attribute defining the number of times that jobs have exited with a condor_shadow exit code of JOB_SHOULD_HOLD in the time interval defined by attribute StatsLifetime.

JobsShouldRemove:

A Statistics attribute defining the number of times that jobs have exited with a condor_shadow exit code of JOB_SHOULD_REMOVE in the time interval defined by attribute StatsLifetime.

JobsShouldRequeue:

A Statistics attribute defining the number of times that jobs have exited with a condor_shadow exit code of JOB_SHOULD_REQUEUE in the time interval defined by attribute StatsLifetime.

JobsSizesHistogramBuckets:

A Statistics attribute defining the predefined bucket boundaries for histogram statistics that classify image sizes. Defined as

  JobsSizesHistogramBuckets = "64Kb, 256Kb, 1Mb, 4Mb, 16Mb, 64Mb, 256Mb,
          1Gb, 4Gb, 16Gb, 64Gb, 256Gb"

JobsStarted:

A Statistics attribute defining the number of jobs started in the time interval defined by attribute StatsLifetime.

JobsSubmitted:

A Statistics attribute defining the number of jobs submitted in the time interval defined by attribute StatsLifetime.

Machine:

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

MaxJobsRunning:

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

MonitorSelfAge:

The number of seconds that this daemon has been running.

MonitorSelfCPUUsage:

The fraction of recent CPU time utilized by this daemon.

MonitorSelfImageSize:

The amount of virtual memory consumed by this daemon in Kbytes.

MonitorSelfRegisteredSocketCount:

The current number of sockets registered by this daemon.

MonitorSelfResidentSetSize:

The amount of resident memory used by this daemon in Kbytes.

MonitorSelfSecuritySessions:

The number of open (cached) security sessions for this daemon.

MonitorSelfTime:

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:

NumUsers:

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

PublicNetworkIpAddr:

Description is not yet written.

RecentDaemonCoreDutyCycle:

A Statistics attribute defining the ratio of the time spent handling messages and events to the elapsed time in the previous time interval defined by attribute RecentStatsLifetime.

RecentJobsAccumBadputTime:

A Statistics attribute defining the sum of the all of the time that jobs which did not complete successfully have spent running in the previous time interval defined by attribute RecentStatsLifetime.

RecentJobsAccumRunningTime:

A Statistics attribute defining the sum of the all of the time jobs which have exited in the previous time interval defined by attribute RecentStatsLifetime spent running.

RecentJobsAccumTimeToStart:

A Statistics attribute defining the sum of all the time jobs which have exited in the previous time interval defined by attribute RecentStatsLifetime had spent waiting to start.

RecentJobsBadputRuntimes:

A Statistics attribute defining a histogram count of jobs that did not complete successfully, as classified by time spent running, in the previous time interval defined by attribute RecentStatsLifetime. Counts within the histogram are separated by a comma and a space, where the time interval classification is defined in the ClassAd attribute JobsRuntimesHistogramBuckets.

RecentJobsBadputSizes:

A Statistics attribute defining a histogram count of jobs that did not complete successfully, as classified by image size, in the previous time interval defined by attribute RecentStatsLifetime. Counts within the histogram are separated by a comma and a space, where the size classification is defined in the ClassAd attribute JobsSizesHistogramBuckets.

RecentJobsCheckpointed:

A Statistics attribute defining the number of times jobs that have exited with a condor_shadow exit code of JOB_CKPTED in the previous time interval defined by attribute RecentStatsLifetime.

RecentJobsCompleted:

A Statistics attribute defining the number of jobs successfully completed in the previous time interval defined by attribute RecentStatsLifetime.

RecentJobsCompletedRuntimes:

A Statistics attribute defining a histogram count of jobs that completed successfully, as classified by time spent running, in the previous time interval defined by attribute RecentStatsLifetime. Counts within the histogram are separated by a comma and a space, where the time interval classification is defined in the ClassAd attribute JobsRuntimesHistogramBuckets.

RecentJobsCompletedSizes:

A Statistics attribute defining a histogram count of jobs that completed successfully, as classified by image size, in the previous time interval defined by attribute RecentStatsLifetime. Counts within the histogram are separated by a comma and a space, where the size classification is defined in the ClassAd attribute JobsSizesHistogramBuckets.

RecentJobsCoredumped:

A Statistics attribute defining the number of times that jobs have exited with a condor_shadow exit code of JOB_COREDUMPED in the previous time interval defined by attribute RecentStatsLifetime.

RecentJobsDebugLogError:

A Statistics attribute defining the number of times that jobs have exited with a condor_shadow exit code of DPRINTF_ERROR in the previous time interval defined by attribute RecentStatsLifetime.

RecentJobsExecFailed:

A Statistics attribute defining the number of times that jobs have exited with a condor_shadow exit code of JOB_EXEC_FAILED in the previous time interval defined by attribute RecentStatsLifetime.

RecentJobsExited:

A Statistics attribute defining the number of times that jobs have exited normally in the previous time interval defined by attribute RecentStatsLifetime.

RecentJobsExitedAndClaimClosing:

A Statistics attribute defining the number of times that jobs have exited with a condor_shadow exit code of JOB_EXITED_AND_CLAIM_CLOSING in the previous time interval defined by attribute RecentStatsLifetime.

RecentJobsExitedNormally:

A Statistics attribute defining the number of times that jobs have exited with a condor_shadow exit code of JOB_EXITED or with an exit code of JOB_EXITED_AND_CLAIM_CLOSING in the previous time interval defined by attribute RecentStatsLifetime.

RecentJobsExitException:

A Statistics attribute defining the number of times that jobs have exited with a condor_shadow exit code of JOB_EXCEPTION or with an unknown status in the previous time interval defined by attribute RecentStatsLifetime.

RecentJobsKilled:

A Statistics attribute defining the number of times that jobs have exited with a condor_shadow exit code of JOB_KILLED in the previous time interval defined by attribute RecentStatsLifetime.

RecentJobsMissedDeferralTime:

A Statistics attribute defining the number of times that jobs have exited with a condor_shadow exit code of JOB_MISSED_DEFERRAL_TIME in the previous time interval defined by attribute RecentStatsLifetime.

RecentJobsNotStarted:

A Statistics attribute defining the number of times that jobs have exited with a condor_shadow exit code of JOB_NOT_STARTED in the previous time interval defined by attribute RecentStatsLifetime.

RecentJobsShadowNoMemory:

A Statistics attribute defining the number of times that jobs have exited because there was not enough memory to start the condor_shadow in the previous time interval defined by attribute RecentStatsLifetime.

RecentJobsShouldHold:

A Statistics attribute defining the number of times that jobs have exited with a condor_shadow exit code of JOB_SHOULD_HOLD in the previous time interval defined by attribute RecentStatsLifetime.

RecentJobsShouldRemove:

A Statistics attribute defining the number of times that jobs have exited with a condor_shadow exit code of JOB_SHOULD_REMOVE in the previous time interval defined by attribute RecentStatsLifetime.

RecentJobsShouldRequeue:

A Statistics attribute defining the number of times that jobs have exited with a condor_shadow exit code of JOB_SHOULD_REQUEUE in the previous time interval defined by attribute RecentStatsLifetime.

RecentJobsStarted:

A Statistics attribute defining the number of jobs started in the previous time interval defined by attribute RecentStatsLifetime.

RecentJobsSubmitted:

A Statistics attribute defining the number of jobs submitted in the previous time interval defined by attribute RecentStatsLifetime.

RecentShadowsReconnections:

A Statistics attribute defining the number of times that condor_shadow daemons lost connection to their condor_starter daemons and successfully reconnected in the previous time interval defined by attribute RecentStatsLifetime. This statistic only appears in the Scheduler ClassAd if the level of verbosity set by the configuration variable STATISTICS_TO_PUBLISH is set to 2 or higher.

RecentShadowsRecycled:

A Statistics attribute defining the number of times condor_shadow processes have been recycled for use with a new job in the previous time interval defined by attribute RecentStatsLifetime. This statistic only appears in the Scheduler ClassAd if the level of verbosity set by the configuration variable STATISTICS_TO_PUBLISH is set to 2 or higher.

RecentShadowsStarted:

A Statistics attribute defining the number of condor_shadow daemons started in the previous time interval defined by attribute RecentStatsLifetime.

RecentStatsLifetime:

A Statistics attribute defining the time in seconds over which statistics values have been collected for attributes with names that begin with Recent. This value starts at 0, and it may grow to a value as large as the value defined for attribute RecentWindowMax.

RecentStatsTickTime:

A Statistics attribute defining the time that attributes with names that begin with Recent were last updated, represented as the number of seconds elapsed since the Unix epoch (00:00:00 UTC, Jan 1, 1970). This statistic only appears in the Scheduler ClassAd if the level of verbosity set by the configuration variable STATISTICS_TO_PUBLISH is set to 2 or higher.

RecentWindowMax:

A Statistics attribute defining the maximum time in seconds over which attributes with names that begin with Recent are collected. The value is set by the configuration variable STATISTICS_WINDOW_SECONDS , which defaults to 1200 seconds (20 minutes). This statistic only appears in the Scheduler ClassAd if the level of verbosity set by the configuration variable STATISTICS_TO_PUBLISH is set to 2 or higher.

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.

ShadowsReconnections:

A Statistics attribute defining the number of times condor_shadows lost connection to their condor_starters and successfully reconnected in the previous StatsLifetime seconds. This statistic only appears in the Scheduler ClassAd if the level of verbosity set by the configuration variable STATISTICS_TO_PUBLISH is set to 2 or higher.

ShadowsRecycled:

A Statistics attribute defining the number of times condor_shadow processes have been recycled for use with a new job in the previous StatsLifetime seconds. This statistic only appears in the Scheduler ClassAd if the level of verbosity set by the configuration variable STATISTICS_TO_PUBLISH is set to 2 or higher.

ShadowsRunning:

A Statistics attribute defining the number of condor_shadow daemons currently running that are owned by this condor_schedd.

ShadowsRunningPeak:

A Statistics attribute defining the maximum number of condor_shadow daemons running at one time that were owned by this condor_schedd over the lifetime of this condor_schedd.

ShadowsStarted:

A Statistics attribute defining the number of condor_shadow daemons started in the previous time interval defined by attribute StatsLifetime.

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

StatsLastUpdateTime:

A Statistics attribute defining the time that statistics about jobs were last updated, represented as the number of seconds elapsed since the Unix epoch (00:00:00 UTC, Jan 1, 1970). This statistic only appears in the Scheduler ClassAd if the level of verbosity set by the configuration variable STATISTICS_TO_PUBLISH is set to 2 or higher.

StatsLifetime:

A Statistics attribute defining the time in seconds over which statistics have been collected for attributes with names that do not begin with Recent. This statistic only appears in the Scheduler ClassAd if the level of verbosity set by the configuration variable STATISTICS_TO_PUBLISH is set to 2 or higher.

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, not including local or scheduler universe jobs.

TotalJobAds:

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

TotalLocalIdleJobs:

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

TotalLocalRunningJobs:

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

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, not including local or scheduler universe jobs.

TotalSchedulerIdleJobs:

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

TotalSchedulerRunningJobs:

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

TransferQueueUserExpr

A ClassAd expression that provides the name of the transfer queue that the condor_schedd will be using for job file transfer.

UpdateInterval:

The interval, in seconds, between publication of this condor_schedd ClassAd and the previous publication.

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.

When using file transfer concurrency limits, the following additional I/O usage statistics are published. These includes the sum and rate of bytes transferred as well as time spent reading and writing to files and to the network. These statistics are reported for the sum of all users and may also be reported individually for recently active users by increasing the verbosity level STATISTICS_TO_PUBLISH = TRANSFER:2. Each of the per-user statistics is prefixed by a user name in the form Owner_<username>_FileTransferUploadBytes. In this case, the attribute represents activity by the specified user. The published user name is actually the file transfer queue name, as defined by configuration variable TRANSFER_QUEUE_USER_EXPR . This expression defaults to Owner_ followed by the name of the job owner. The attributes that are rates have a suffix that specifies the time span of the exponential moving average. By default the time spans that are published are 1m, 5m, 1h, and 1d. This can be changed by configuring configuration variable TRANSFER_IO_REPORT_TIMESPANS . These attributes are only reported once a full time span has accumulated.

FileTransferDiskThrottleExcess_<timespan>: The exponential moving average of the disk load that exceeds the upper limit set for the disk load throttle. Periods of time in which there is no excess and no waiting transfers do not contribute to the average. This attribute is published only if configuration variable FILE_TRANSFER_DISK_LOAD_THROTTLE is defined.
FileTransferDiskThrottleHigh: The desired upper limit for the disk load from file transfers, as configured by FILE_TRANSFER_DISK_LOAD_THROTTLE . This attribute is published only if configuration variable FILE_TRANSFER_DISK_LOAD_THROTTLE is defined.
FileTransferDiskThrottleLevel: The current concurrency limit set by the disk load throttle. The limit is applied to the sum of uploads and downloads. This attribute is published only if configuration variable FILE_TRANSFER_DISK_LOAD_THROTTLE is defined.
FileTransferDiskThrottleLow: The lower limit for the disk load from file transfers, as configured by FILE_TRANSFER_DISK_LOAD_THROTTLE . This attribute is published only if configuration variable FILE_TRANSFER_DISK_LOAD_THROTTLE is defined.
FileTransferDiskThrottleShortfall_<timespan>: The exponential moving average of the disk load that falls below the upper limit set for the disk load throttle. Periods of time in which there is no excess and no waiting transfers do not contribute to the average. This attribute is published only if configuration variable FILE_TRANSFER_DISK_LOAD_THROTTLE is defined.
FileTransferDownloadBytes: Total number of bytes downloaded as output from jobs since this condor_schedd was started. If STATISTICS_TO_PUBLISH contains TRANSFER:2, for each active user, this attribute is also published prefixed by the user name, with the name Owner_<username>_FileTransferDownloadBytes. The published user name is actually the file transfer queue name, as defined by configuration variable TRANSFER_QUEUE_USER_EXPR .
FileTransferDownloadBytesPerSecond_<timespan>: Exponential moving average over the specified time span of the rate at which bytes have been downloaded as output from jobs. The time spans that are published are configured by TRANSFER_IO_REPORT_TIMESPANS , which defaults to 1m, 5m, 1h, and 1d. When less than one full time span has accumulated, the attribute is not published. If STATISTICS_TO_PUBLISH contains TRANSFER:2, for each active user, this attribute is also published prefixed by the user name, with the name Owner_<username>_FileTransferDownloadBytesPerSecond_<timespan>. The published user name is actually the file transfer queue name, as defined by configuration variable TRANSFER_QUEUE_USER_EXPR .
FileTransferFileReadLoad_<timespan>: Exponential moving average over the specified time span of the rate at which submit-side file transfer processes have spent time reading from files to be transferred as input to jobs. One file transfer process spending nearly all of its time reading files will generate a load close to 1.0. The time spans that are published are configured by TRANSFER_IO_REPORT_TIMESPANS , which defaults to 1m, 5m, 1h, and 1d. When less than one full time span has accumulated, the attribute is not published. If STATISTICS_TO_PUBLISH contains TRANSFER:2, for each active user, this attribute is also published prefixed by the user name, with the name Owner_<username>_FileTransferFileReadLoad_<timespan>. The published user name is actually the file transfer queue name, as defined by configuration variable TRANSFER_QUEUE_USER_EXPR .
FileTransferFileReadSeconds: Total number of submit-side transfer process seconds spent reading from files to be transferred as input to jobs since this condor_schedd was started. If STATISTICS_TO_PUBLISH contains TRANSFER:2, for each active user, this attribute is also published prefixed by the user name, with the name Owner_<username>_FileTransferFileReadSeconds. The published user name is actually the file transfer queue name, as defined by configuration variable TRANSFER_QUEUE_USER_EXPR .
FileTransferFileWriteLoad_<timespan>: Exponential moving average over the specified time span of the rate at which submit-side file transfer processes have spent time writing to files transferred as output from jobs. One file transfer process spending nearly all of its time writing to files will generate a load close to 1.0. The time spans that are published are configured by TRANSFER_IO_REPORT_TIMESPANS , which defaults to 1m, 5m, 1h, and 1d. When less than one full time span has accumulated, the attribute is not published. If STATISTICS_TO_PUBLISH contains TRANSFER:2, for each active user, this attribute is also published prefixed by the user name, with the name Owner_<username>_FileTransferFileWriteLoad_<timespan>. The published user name is actually the file transfer queue name, as defined by configuration variable TRANSFER_QUEUE_USER_EXPR .
FileTransferFileWriteSeconds: Total number of submit-side transfer process seconds spent writing to files transferred as output from jobs since this condor_schedd was started. If STATISTICS_TO_PUBLISH contains TRANSFER:2, for each active user, this attribute is also published prefixed by the user name, with the name Owner_<username>_FileTransferFileWriteSeconds. The published user name is actually the file transfer queue name, as defined by configuration variable TRANSFER_QUEUE_USER_EXPR .
FileTransferNetReadLoad_<timespan>: Exponential moving average over the specified time span of the rate at which submit-side file transfer processes have spent time reading from the network when transferring output from jobs. One file transfer process spending nearly all of its time reading from the network will generate a load close to 1.0. The reason a file transfer process may spend a long time writing to the network could be a network bottleneck on the path between the submit and execute machine. It could also be caused by slow reads from the disk on the execute side. The time spans that are published are configured by TRANSFER_IO_REPORT_TIMESPANS , which defaults to 1m, 5m, 1h, and 1d. When less than one full time span has accumulated, the attribute is not published. If STATISTICS_TO_PUBLISH contains TRANSFER:2, for each active user, this attribute is also published prefixed by the user name, with the name Owner_<username>_FileTransferNetReadLoad_<timespan>. The published user name is actually the file transfer queue name, as defined by configuration variable TRANSFER_QUEUE_USER_EXPR .
FileTransferNetReadSeconds: Total number of submit-side transfer process seconds spent reading from the network when transferring output from jobs since this condor_schedd was started. The reason a file transfer process may spend a long time writing to the network could be a network bottleneck on the path between the submit and execute machine. It could also be caused by slow reads from the disk on the execute side. If STATISTICS_TO_PUBLISH contains TRANSFER:2, for each active user, this attribute is also published prefixed by the user name, with the name Owner_<username>_FileTransferNetReadSeconds. The published user name is actually the file transfer queue name, as defined by configuration variable TRANSFER_QUEUE_USER_EXPR .
FileTransferNetWriteLoad_<timespan>: Exponential moving average over the specified time span of the rate at which submit-side file transfer processes have spent time writing to the network when transferring input to jobs. One file transfer process spending nearly all of its time writing to the network will generate a load close to 1.0. The reason a file transfer process may spend a long time writing to the network could be a network bottleneck on the path between the submit and execute machine. It could also be caused by slow writes to the disk on the execute side. The time spans that are published are configured by TRANSFER_IO_REPORT_TIMESPANS , which defaults to 1m, 5m, 1h, and 1d. When less than one full time span has accumulated, the attribute is not published. If STATISTICS_TO_PUBLISH contains TRANSFER:2, for each active user, this attribute is also published prefixed by the user name, with the name Owner_<username>_FileTransferNetWriteLoad_<timespan>. The published user name is actually the file transfer queue name, as defined by configuration variable TRANSFER_QUEUE_USER_EXPR .
FileTransferNetWriteSeconds: Total number of submit-side transfer process seconds spent writing to the network when transferring input to jobs since this condor_schedd was started. The reason a file transfer process may spend a long time writing to the network could be a network bottleneck on the path between the submit and execute machine. It could also be caused by slow writes to the disk on the execute side. The time spans that are published are configured by TRANSFER_IO_REPORT_TIMESPANS , which defaults to 1m, 5m, 1h, and 1d. When less than one full time span has accumulated, the attribute is not published. If STATISTICS_TO_PUBLISH contains TRANSFER:2, for each active user, this attribute is also published prefixed by the user name, with the name Owner_<username>_FileTransferNetWriteSeconds. The published user name is actually the file transfer queue name, as defined by configuration variable TRANSFER_QUEUE_USER_EXPR .
FileTransferUploadBytes: Total number of bytes uploaded as input to jobs since this condor_schedd was started. If STATISTICS_TO_PUBLISH contains TRANSFER:2, for each active user, this attribute is also published prefixed by the user name, with the name Owner_<username>_FileTransferUploadBytes. The published user name is actually the file transfer queue name, as defined by configuration variable TRANSFER_QUEUE_USER_EXPR .
FileTransferUploadBytesPerSecond_<timespan>: Exponential moving average over the specified time span of the rate at which bytes have been uploaded as input to jobs. The time spans that are published are configured by TRANSFER_IO_REPORT_TIMESPANS , which defaults to 1m, 5m, 1h, and 1d. When less than one full time span has accumulated, the attribute is not published. If STATISTICS_TO_PUBLISH contains TRANSFER:2, for each active user, this attribute is also published prefixed by the user name, with the name Owner_<username>_FileTransferUploadBytesPerSecond_<timespan>. The published user name is actually the file transfer queue name, as defined by configuration variable TRANSFER_QUEUE_USER_EXPR .
TransferQueueMBWaitingToDownload: Number of megabytes of output files waiting to be downloaded.
TransferQueueMBWaitingToUpload: Number of megabytes of input files waiting to be uploaded.
TransferQueueNumWaitingToDownload: Number of jobs waiting to transfer output files.
TransferQueueNumWaitingToUpload: Number of jobs waiting to transfer input files.

Negotiator ClassAd Attributes

CondorVersion:: A string containing the HTCondor version number, the release date, and the build identification number.
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).
LastNegotiationCycleActiveSubmitterCount<X>:: The integer number of submitters the condor_negotiator attempted to negotiate with in the negotiation cycle. The number <X> appended to the attribute name indicates how many negotiation cycles ago this cycle happened.
LastNegotiationCycleCandidateSlots<X>:: The number of slot ClassAds after filtering by NEGOTIATOR_SLOT_POOLSIZE_CONSTRAINT . This is the number of slots actually considered for matching. The number <X> appended to the attribute name indicates how many negotiation cycles ago this cycle happened.
LastNegotiationCycleDuration<X>:: The number of seconds that it took to complete the negotiation cycle. The number <X> appended to the attribute name indicates how many negotiation cycles ago this cycle happened.
LastNegotiationCycleEnd<X>:: The time, represented as the number of seconds since the Unix epoch, at which the negotiation cycle ended. The number <X> appended to the attribute name indicates how many negotiation cycles ago this cycle happened.
LastNegotiationCycleMatches<X>:: The number of successful matches that were made in the negotiation cycle. The number <X> appended to the attribute name indicates how many negotiation cycles ago this cycle happened.
LastNegotiationCycleMatchRate<X>:: The number of matched jobs divided by the duration of this cycle giving jobs per second. The number <X> appended to the attribute name indicates how many negotiation cycles ago this cycle happened.
LastNegotiationCycleMatchRateSustained<X>:: The number of matched jobs divided by the period of this cycle giving jobs per second. The period is the time elapsed between the end of the previous cycle and the end of this cycle, and so this rate includes the interval between cycles. The number <X> appended to the attribute name indicates how many negotiation cycles ago this cycle happened.
LastNegotiationCycleNumIdleJobs<X>:: The number of idle jobs considered for matchmaking. The number <X> appended to the attribute name indicates how many negotiation cycles ago this cycle happened.
LastNegotiationCycleNumJobsConsidered<X>:: The number of jobs requests returned from the schedulers for consideration. The number <X> appended to the attribute name indicates how many negotiation cycles ago this cycle happened.
LastNegotiationCycleNumSchedulers<X>:: The number of individual schedulers negotiated with during matchmaking. The number <X> appended to the attribute name indicates how many negotiation cycles ago this cycle happened.
LastNegotiationCyclePeriod<X>:: The number of seconds elapsed between the end of the previous negotiation cycle and the end of this cycle. The number <X> appended to the attribute name indicates how many negotiation cycles ago this cycle happened.
LastNegotiationCyclePhase1Duration<X>:: The duration, in seconds, of Phase 1 of the negotiation cycle: the process of getting submitter and machine ClassAds from the condor_collector. The number <X> appended to the attribute name indicates how many negotiation cycles ago this cycle happened.
LastNegotiationCyclePhase2Duration<X>:: The duration, in seconds, of Phase 2 of the negotiation cycle: the process of filtering slots and processing accounting group configuration. The number <X> appended to the attribute name indicates how many negotiation cycles ago this cycle happened.
LastNegotiationCyclePhase3Duration<X>:: The duration, in seconds, of Phase 3 of the negotiation cycle: sorting submitters by priority. The number <X> appended to the attribute name indicates how many negotiation cycles ago this cycle happened.
LastNegotiationCyclePhase4Duration<X>:: The duration, in seconds, of Phase 4 of the negotiation cycle: the process of matching slots to jobs in conjunction with the schedulers. The number <X> appended to the attribute name indicates how many negotiation cycles ago this cycle happened.
LastNegotiationCycleRejections<X>:: The number of rejections that occurred in the negotiation cycle. The number <X> appended to the attribute name indicates how many negotiation cycles ago this cycle happened.
LastNegotiationCycleSlotShareIter<X>:: The number of iterations performed during the negotiation cycle. Each iteration includes the reallocation of remaining slots to accounting groups, as defined by the implementation of hierarchical group quotas, together with the negotiation for those slots. The maximum number of iterations is limited by the configuration variable GROUP_QUOTA_MAX_ALLOCATION_ROUNDS . The number <X> appended to the attribute name indicates how many negotiation cycles ago this cycle happened.
LastNegotiationCycleSubmittersFailed<X>:: A string containing a space and comma-separated list of the names of all submitters who failed to negotiate in the negotiation cycle. One possible cause of failure is a communication timeout. This list does not include submitters who ran out of time due to NEGOTIATOR_MAX_TIME_PER_SUBMITTER . Those are listed separately in LastNegotiationCycleSubmittersOutOfTime<X>. The number <X> appended to the attribute name indicates how many negotiation cycles ago this cycle happened.
LastNegotiationCycleSubmittersOutOfTime<X>:: A string containing a space and comma separated list of the names of all submitters who ran out of time due to NEGOTIATOR_MAX_TIME_PER_SUBMITTER in the negotiation cycle. The number <X> appended to the attribute name indicates how many negotiation cycles ago this cycle happened.
LastNegotiationCycleSubmittersShareLimit:: A string containing a space and comma separated list of names of submitters who encountered their fair-share slot limit during the negotiation cycle. The number <X> appended to the attribute name indicates how many negotiation cycles ago this cycle happened.
LastNegotiationCycleTime<X>:: The time, represented as the number of second elapsed since the Unix epoch (00:00:00 UTC, Jan 1, 1970), at which the negotiation cycle started. The number <X> appended to the attribute name indicates how many negotiation cycles ago this cycle happened.
LastNegotiationCycleTotalSlots<X>:: The total number of slot ClassAds received by the condor_negotiator. The number <X> appended to the attribute name indicates how many negotiation cycles ago this cycle happened.
LastNegotiationCycleTrimmedSlots<X>:: The number of slot ClassAds left after trimming currently claimed slots (when enabled). The number <X> appended to the attribute name indicates how many negotiation cycles ago this cycle happened.
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.

Submitter ClassAd Attributes

CondorVersion:: A string containing the HTCondor version number, the release date, and the build identification number.
FlockedJobs:: The number of jobs from this submitter that are running in another pool.
HeldJobs:: The number of jobs from this submitter that are in the hold state.
IdleJobs:: The number of jobs from this submitter that are now idle.
Name:: The fully qualified name of the user or accounting group. It will be of the form name@submit.domain.
RunningJobs:: The number of jobs from this submitter that are running now.
ScheddIpAddr:: The IP address associated with the condor_schedd daemon used by the submitter.
ScheddName:: The fully qualified host name of the machine that the submitter submitted from. It will be of the form submit.domain.
SubmitterTag:: The fully qualified host name of the central manager of the pool used by the submitter, if the job flocked to the local pool. Or, it will be the empty string if submitter submitted from within the local pool.
WeightedIdleJobs:: A total number of requested cores across all Idle jobs from the submitter, weighted by the slot weight. So, if the slot weight is cpus, and a job requests two cpus, the weight of that job is two.
WeightedRunningJobs:: A total number of requested cores across all Running jobs from the submitter.

Defrag ClassAd Attributes

AvgDrainingBadput:: Fraction of time CPUs in the pool have spent on jobs that were killed during draining of the machine. This is calculated in each polling interval by looking at TotalMachineDrainingBadput. Therefore, it treats evictions of jobs that do and do not produce checkpoints the same. When the condor_startd restarts, its counters start over from 0, so the average is only over the time since the daemons have been alive.
AvgDrainingUnclaimedTime:: Fraction of time CPUs in the pool have spent unclaimed by a user during draining of the machine. This is calculated in each polling interval by looking at TotalMachineDrainingUnclaimedTime. When the condor_startd restarts, its counters start over from 0, so the average is only over the time since the daemons have been alive.
DaemonStartTime:: The time that this daemon was started, represented as the number of seconds elapsed since the Unix epoch (00:00:00 UTC, Jan 1, 1970).
DrainedMachines:: A count of the number of fully drained machines which have arrived during the run time of this condor_defrag daemon.
DrainFailures:: Total count of failed attempts to initiate draining during the lifetime of this condor_defrag daemon.
DrainSuccesses:: Total count of successful attempts to initiate draining during the lifetime of this condor_defrag daemon.
Machine:: A string with the machine's fully qualified host name.
MachinesDraining:: Number of machines that were observed to be draining in the last polling interval.
MachinesDrainingPeak:: Largest number of machines that were ever observed to be draining.
MeanDrainedArrived:: The mean time in seconds between arrivals of fully drained machines.
MonitorSelfAge:: The number of seconds that this daemon has been running.
MonitorSelfCPUUsage:: The fraction of recent CPU time utilized by this daemon.
MonitorSelfImageSize:: The amount of virtual memory consumed by this daemon in Kbytes.
MonitorSelfRegisteredSocketCount:: The current number of sockets registered by this daemon.
MonitorSelfResidentSetSize:: The amount of resident memory used by this daemon in Kbytes.
MonitorSelfSecuritySessions:: The number of open (cached) security sessions for this daemon.
MonitorSelfTime:: The time, represented as the number of seconds elapsed since the Unix epoch (00:00:00 UTC, Jan 1, 1970), at which this daemon last checked and set the attributes with names that begin with the string MonitorSelf.
MyAddress:: Description is not yet written.
MyCurrentTime:: The time, represented as the number of seconds elapsed since the Unix epoch (00:00:00 UTC, Jan 1, 1970), at which the condor_defrag daemon last sent a ClassAd update to the condor_collector.
Name:: The name of this daemon; typically the same value as the Machine attribute, but could be customized by the site administrator via the configuration variable DEFRAG_NAME .
RecentDrainFailures:: Count of failed attempts to initiate draining during the past RecentStatsLifetime seconds.
RecentDrainSuccesses:: Count of successful attempts to initiate draining during the past RecentStatsLifetime seconds.
RecentStatsLifetime:: A Statistics attribute defining the time in seconds over which statistics values have been collected for attributes with names that begin with Recent.
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.
WholeMachines:: Number of machines that were observed to be defragmented in the last polling interval.
WholeMachinesPeak:: Largest number of machines that were ever observed to be simultaneously defragmented.

Collector ClassAd Attributes

CollectorIpAddr:

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

CondorVersion:

A string containing the HTCondor version number, the release date, and the build identification number.

CurrentJobsRunningAll:

An integer value representing the sum of all jobs running under all universes.

CurrentJobsRunning<universe>:

An integer value representing the current number of jobs running under the universe which forms the attribute name. For example

  CurrentJobsRunningVanilla = 567

identifies that the condor_collector counts 567 vanilla universe jobs currently running. <universe> is one of Unknown, Standard, Vanilla, Scheduler, Java, Parallel, VM, or Local. There are other universes, but they are not listed here, as they represent ones that are no longer used in Condor.

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).

HostsClaimed:

Description is not yet written.

HostsOwner:

Description is not yet written.

HostsTotal:

Description is not yet written.

HostsUnclaimed:

Description is not yet written.

IdleJobs:

Description is not yet written.

Machine:

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

MaxJobsRunning<universe:

An integer value representing the sum of all MaxJobsRunning<universe> values.

MaxJobsRunning<universe>:

An integer value representing largest number of currently running jobs ever seen under the universe which forms the attribute name, over the life of this condor_collector process. For example

  MaxJobsRunningVanilla = 401

identifies that the condor_collector saw 401 vanilla universe jobs currently running at one point in time, and that was the largest number it had encountered. <universe> is one of Unknown, Standard, Vanilla, Scheduler, Java, Parallel, VM, or Local. There are other universes, but they are not listed here, as they represent ones that are no longer used in Condor.

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:

RunningJobs:

Description is not yet written.

UpdateInterval:

Description is not yet written.

UpdateSequenceNumber:

An integer that begins at 0, and increments by one each time the same ClassAd is again advertised.

ClassAd Attributes Added by the condor_collector

AuthenticatedIdentity:: The authenticated name assigned by the condor_collector to the daemon that published the ClassAd.
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). This attribute is added if COLLECTOR_DAEMON_STATS is True.
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. This attribute is added if COLLECTOR_DAEMON_STATS is True.
UpdatesLost:: An integer count of the number of updates from the daemon that the condor_collector can definitively determine were lost since the condor_collector started running. This attribute is added if COLLECTOR_DAEMON_STATS is True.
UpdatesSequenced:: An integer count of the number of updates received from the daemon, for which the condor_collector can tell how many were or were not lost, since the condor_collector started running. This attribute is added if COLLECTOR_DAEMON_STATS is True.
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. This attribute is added if COLLECTOR_DAEMON_STATS is True.

DaemonCore Statistics Attributes

DebugOuts:: Description not yet written.
PipeMessages:: Description not yet written.
PipeRuntime:: Description not yet written.
SelectWaittime:: Description not yet written.
SignalRuntime:: Description not yet written.
Signals:: Description not yet written.
SocketRuntime:: Description not yet written.
SockMessages:: Description not yet written.
TimerRuntime:: Description not yet written.
TimersFired:: Description not yet written.

Subsections

Next: 13. Appendix B: Codes Up: HTCondor^{^TM} Version 8.1.6 Manual Previous: procd_ctl Contents Index