1pbs_server_attributes(7B) PBS pbs_server_attributes(7B)
2
6 pbs_server_attributes - pbs server attributes
7
9 Server attributes can be read by any client; privilege is not required.
10 Most server attributes are alterable by a privileged client, run by a
11 user with administrator or operator privilege. Certain attributes re‐
12 quire the user to have full administrator privilege. The following is
13 a list of the server attributes.
14 accounting_keep_days
16 This defines the number of days that accounting files will be
17 kept. Default value: unset - pbs_server will never delete ac‐
18 counting files Format: integer
19 acl_group_hosts
21 List of group/host combinations that authorize users to submit
22 jobs. Groups are expanded on the server. Format:
23 "group@hostname.domain[,...]"; default value: defer to
24 acl_users.
25 acl_group_sloppy
27 This is a default value for the queue attribute of the same
28 name. Format: boolean, "TRUE", "True", "true", "Y", "y", "1",
29 "FALSE", "False", "false", "N", "n", "0"; default value: false
30 = disabled.
31 acl_host_enable
33 Attribute which when true directs the server to use the
34 acl_hosts access control lists. Requires full manager privi‐
35 lege to set or alter. Format: boolean, "TRUE", "True",
36 "true", "Y", "y", "1", "FALSE", "False", "false", "N", "n",
37 "0"; default value: false = disabled.
38 acl_hosts
40 List of hosts which may request services from this server.
41 This list contains the network name of the hosts. Local re‐
42 quests, i.e. from the server's host itself, are aways accepted
43 even if the host is not included in the list. See section
44 10.1, Authorization, in the PBS External Reference Specifica‐
45 tion. Requires full manager privilege to set or alter. For‐
46 mat: "[+|-]hostname.domain[,...]"; default value: all hosts.
47 acl_logic_or
49 This is a default value for the queue attribute of the same
50 name. Format: boolean, "TRUE", "True", "true", "Y", "y", "1",
51 "FALSE", "False", "false", "N", "n", "0"; default value: false
52 = disabled.
53 acl_user_enable
55 Attribute which when true directs the server to use the server
56 level acl_users access list. Requires full manager privilege
57 to set or alter. Format: boolean (see acl_group_enable); de‐
58 fault value: disabled.
59 acl_user_hosts
61 List of user/host combinations that authorize users to submit
62 jobs. Format: "user@hostname.domain[,...]"; default value:
63 defer to acl_users.
64 acl_users
66 List of users allowed or denied the ability to make any re‐
67 quests of this server. See section 10.1, Authorization, in
68 the PBS External Reference Specification. If acl_user_enable
69 is set to true, only users listed in acl_users may submit to
70 or execute jobs in the queue. Requires full manager privilege
71 to set or alter. Format: "[+|-]user[@host][,...]"; default
72 value: all users allowed.
73 acl_roots
75 List of super users who may submit to and execute jobs at this
76 server. If the job execution id would be zero (0), then the
77 job owner, root@host, must be listed in this access control
78 list or the job is rejected. Format:
79 "[+|-]user[@host][,...]"; default value: no root jobs allowed.
80 allow_node_submit
82 Allow job submissions from compute nodes regardless of
83 ruserok(). Requires full manager privilege to set or alter.
84 Format: boolean; default value: disabled.
85 allow_proxy_user
87 Specifies users can proxy from one user to another. Proxy re‐
88 quests will be either validated by ruserok() or by the sched‐
89 uler. Format: boolean; default value: false.
90 auto_node_np
92 Automatically configure a node's np value based on the ncpus
93 value from the status update. Requires full manager privilege
94 to set or alter. Format: boolean; default value: disabled.
95 automatic_requeue_exit_code
97 This is an exit code, defined by the admin, that tells
98 pbs_server to requeue the job instead of considering it as
99 completed. This allows the user to add some additional checks
100 that the job can run meaningfully, and if not, then the job
101 script exits with the specified code to be requeued. Format:
102 long; default value: none.
103 clone_batch_delay
105 Number of seconds to delay between cloning a batch for a job
106 array. Format: integer; default value: 1.
107 clone_batch_size
109 Number of jobs to clone in a batch for a job array. Format:
110 integer; default value: 256.
111 credential_lifetime
113 The number of a seconds that a client connection may stay con‐
114 nected without re-authenticating. Default is 3600 seconds.
115 comment
117 A text string which may be set by the scheduler or other priv‐
118 ileged client to provide information to the batch system
119 users. Format: any string; default value: none.
120 copy_on_rerun
122 When set to true, copy the output and error files over to the
123 user-specified directory when a job is rerun. Format: bool‐
124 ean; default value: false.
125 cray_enabled
127 When set to true, specifies that this instance of pbs_server
128 has Cray hardware that reports to it. Format: boolean; de‐
129 fault value: false.
130 default_node
132 A node specification to use if there is no other supplied
133 specification. This attribute is only used by servers where a
134 nodes file exist in the server_priv directory providing a list
135 of nodes to the server. If the nodes file does not exist,
136 this attribute is not set by default and is ignored if set.
137 The default value allows for jobs to share a single node.
138 Format: a node specification string; default value: 1#shared.
139 default_queue
141 The queue which is the target queue when a request does not
142 specify a queue name. Format: a queue name; default value:
143 none, must be set to an existing queue.
144 disable_automatic_requeue
146 Normally, if a job cannot start due to a transient error, the
147 MOM returns a special exit code to the server so that the job
148 is requeued instead of completed. When this parameter is set,
149 the special exit code is ignored and the job is completed.
150 Format: boolean; default value: false.
151 display_job_server_suffix
153 When set to TRUE, Torque will display both the job ID and the
154 host name. When set to FALSE, only the job ID will be dis‐
155 played. Format: boolean; default value: true.
156 dont_write_nodes_file
158 When set to TRUE, the nodes file cannot be overwritten for any
159 reason; qmgr commands to edit nodes will be rejected. Format:
160 boolean; default value: false.
161 note_append_on_error
163 Append the error string to the end of the current nodes note
164 if MOM reports a message beginning with the string "ERROR".
165 Format: boolean; default value: true.
166 down_on_error
168 Set a node's state to "down" if MOM reports a message begin‐
169 ning with the string "ERROR". This might interfere with
170 moab's node error handling. See the HEALTH CHECK section in
171 pbs_mom(8B). This is an EXPERIMENTAL feature and may be re‐
172 moved in the future. Format: boolean; default value: true.
173 disable_server_id_check
175 Makes it so the user for the job doesn't have to exist on the
176 server. The user must still exist on all the compute nodes or
177 the job will fail when it tries to execute. Format: boolean;
178 default value: false
179 extra_resc
181 Add additional string-type job resources. They have no effect
182 within TORQUE and are only advisible to the scheduler. They
183 can not be used for resources_default/min/max. Format: list;
184 default value: none.
185 interactive_jobs_can_roam
187 By default, interactive jobs run from the login node that they
188 submitted from. When TRUE, interactive jobs may run on login
189 nodes other than the one where the jobs were submitted to.
190 Only applies when cray_enabled is set. Format: boolean; de‐
191 fault value: false.
192 job_exclusive_on_use
194 When job_exclusive_on_use is set to TRUE, pbsnodes will show
195 job-exclusive on a node when there's at least one of its pro‐
196 cessors running a job. This differs with the default behavior
197 which is to show job-exclusive on a node when all of its pro‐
198 cessors are running a job. Format: boolean; default value:
199 false.
200 job_force_cancel_time
202 If configured, number of seconds after a delete where a job
203 will be purged by the server. If not configured, no such thing
204 happens. Format: integer; default value: not used.
205 job_full_report_time
207 Sets the time in seconds that a job should be fully reported
208 after any kind of change to the job, even if condensed output
209 was requested. Format: integer; default value: 300 seconds.
210 job_log_file_max_size
212 This specifies a soft limit (in kilobytes) for the job log's
213 maximum size. The file size is checked every five minutes and
214 if the current day file size is greater than or equal to this
215 value, it is rolled from <filename> to <filename.1> and a new
216 empty log is opened. If the current day file size exceeds the
217 maximum size a second time, the <filename.1> log file is
218 rolled to <filename.2>, the current log is rolled to <file‐
219 name.1>, and a new empty log is opened. Each new log causes
220 all other logs to roll to an extension that is one greater
221 than its current number. Any value less than 0 is ignored by
222 pbs_server (meaning the log will not be rolled). Format: in‐
223 teger; default value: none.
224 job_log_file_roll_depth
226 This sets the maximum number of new log files that are kept in
227 a day if the job_log_file_max_size parameter is set. For exam‐
228 ple, if the roll depth is set to 3, no file can roll higher
229 than <filename.3>. If a file is already at the specified
230 depth, such as <filename.3>, the file is deleted so it can be
231 replaced by the incoming file roll, <filename.2>. Format: in‐
232 teger; default value: none.
233 job_log_keep_days
235 This maintains job logs for the number of days designated. If
236 set to 4, any job log file older than 4 days old is deleted.
237 Format: integer; default value: none.
238 job_nanny
240 Enables the "job deletion nanny" feature. All job cancels
241 will create a repeating task that will resend KILL signals if
242 the initial job cancel failed. Further job cancels will be
243 rejected with the message "job cancel in progress." This is
244 useful for temporary failures with a job's execution node dur‐
245 ing a job delete request. It is possible that the job nanny
246 might interfere with job restarts, migrations, and checkpoint‐
247 ing. Format: boolean; default value: false.
248 job_start_timeout
250 Specifies the pbs_server to pbs_mom TCP socket timeout in sec‐
251 onds that is used when the pbs_server sends a job start to the
252 pbs_mom. It is useful when the mom has extra overhead in‐
253 volved in starting jobs. If not specified then the tcp_time‐
254 out value is used.
255 job_stat_rate
257 Moderates how often job stat requests will be issued from
258 pbs_server to the MOM daemons. If poll_jobs is unset or
259 false, then all jobs that haven't been updated in
260 job_stat_rate seconds will trigger a stat request. If
261 poll_jobs is true, then all jobs will be updated every
262 job_stat_rate.
263 (see poll_jobs) On active clusters, 60 or 120 might be rea‐
264 sonable. Default value: 45 seconds (PBS_RESTAT_JOB in
265 server_limits.h) Minimum value: 4 seconds (PBS_JOBSTAT_MIN in
266 server_limits.h)
267 job_sync_timeout
269 When a stray job is reported on multiple nodes, the server
270 sends a kill signal to one node at a time. This timeout deter‐
271 mines how long the server waits between kills if the job is
272 still being reported on any nodes. Format: integer; default
273 value: 60.
274 keep_completed
276 Number of seconds to retain completed jobs in the C state.
277 This is overridden by the execution queue attribute of the
278 same name. Format: integer; default value: 0.
279 kill_delay
281 The amount of the time delay between the sending of SIGTERM
282 and SIGKILL when a qdel command is issued against a running
283 job. This is overridden by the execution queue attribute of
284 the same name. Format: integer seconds; default value: 2 sec‐
285 onds.
286 lock_file
288 Specifies the name and location of the lock file used to de‐
289 termine which high availability server should be active.
290 If a full path is specified, it is used verbatim by TORQUE. If
291 a relative path is specified, TORQUE will prefix it with
292 $TORQUE_HOME/server_priv. Format: string; default value:
293 $TORQUE_HOME/server_priv/server.lock
294 lock_file_update_time
296 Specifies how often (in seconds) the thread will update the
297 lockfile. (for threaded high availability) Format: integer;
298 default value: 3
299 lock_file_check_time
301 Specifies how often (in seconds) a high availability server
302 will check to see if it should become active. (for threaded
303 high availability) Must be greater than lock_file_update_time.
304 Format: integer; default value: 9
305 log_events
307 A bit string which specifies the type of events which are
308 logged, see the section on Event Logging in chapter 3 of the
309 ERS. Format: integer; default value: 511, all events.
310 log_file_max_size
312 If this is set to a value > 0 then pbs_server will roll the
313 current log file to logfile.1 when its size is greater than or
314 equal to the value of log_file_max_size. This value is inter‐
315 preted as kilobytes.
316 log_file_roll_depth
318 If this is set to a value >=1 and log_file_max_size is set
319 then pbs_server will continue rolling the log files to log‐
320 file.log_file_roll_depth.
321 log_keep_days
323 If this is set then logs older than X days will be removed by
324 the server. Format: integer; default value: not enforced;
325 log_level
327 Controls the verbosity of server logs. This value ranges from
328 0 to 7 with 7 representing maximum verbosity. Format: inte‐
329 ger; default value: 0, minimum verbosity.
330 mail_body_fmt
332 Override the default format for the body of outgoing mail mes‐
333 sages. A number of printf-like format specifiers and escape
334 sequences can be used:
335 \n new line
337 \t horizontal tab
339 \\ backslash
341 \' single quote
343 \" double quote
345 %d details concerning the message
347 %h PBS host name
349 %i PBS job identifier
351 %j PBS job name
353 %m long reason for message
355 %r short reason for message
357 %% a single %
359 Format: a printf-like format string; Default value: "PBS Job Id:
361 %i\nJob Name: %j\nExec host: %h\n%m\n%d\n".
362 mail_domain
364 Override the default domain for outgoing mail messages. If
365 set, emails will be addressed to "euser@mail_domain". If un‐
366 set, the job's Job_Owner attribute will be used. If set to
367 "never", TORQUE will never send emails. Format: a domain
368 name; Default value: none.
369 mail_from
371 Set the From: header for all outgoing emails from pbs_server.
372 Format: an email address; Default value: "adm".
373 mail_subject_fmt
375 Override the default format for the subject of outgoing mail
376 messages. A number of printf-like format specifiers and escape
377 sequences can be used:
378 \n new line
380 \t horizontal tab
382 \\ backslash
384 \' single quote
386 \" double quote
388 %d details concerning the message
390 %h PBS host name
392 %i PBS job identifier
394 %j PBS job name
396 %m long reason for message
398 %r short reason for message
400 %% a single %
402 Format: a printf-like format string; Default value: "PBS JOB %i".
404 mail_uid
406 The uid from which server generated mail is sent to users.
407 Format: integer uid; default value: 0 for root.
408 managers
410 List of users granted batch administrator privileges. Format:
411 user@host.sub.domain[,user@host.sub.domain...]. The host,
412 sub-domain, or domain name may be wild carded by the use of an
413 * character, see the description of user access control lists
414 in chapter 10.1.1 of the ERS. Requires full manager privilege
415 to set or alter. Default value: root on the local host.
416 max_job_array_size
418 Specifies the maximum number of jobs that can be in any re‐
419 quested job array. Arrays requesting more jobs than configured
420 will be rejected. Format: integer; default value: Unlimited.
421 max_slot_limit
423 No array can request a slot limit greater than 10. Any array
424 that does not request a slot limit receives a slot limit of
425 10. Using the example above, slot requests greater than 10 are
426 rejected. A slot limit is the maximum number of jobs from an
427 array that can run concurrently. Format: integer; default
428 value: Unlimited.
429 max_running
431 The maximum number of jobs allowed to be selected for execu‐
432 tion at any given time. Advisory to the Scheduler, not en‐
433 forced by the server. Format: integer.
434 max_user_run
436 The maximum number of jobs owned by a single user that are al‐
437 lowed to be running from this queue at one time. This attri‐
438 bute is advisory to the Scheduler, it is not enforced by the
439 server. Format: integer; default value: none.
440 max_group_run
442 The maximum number of jobs owned by any users in a single
443 group that are allowed to be running from this queue at one
444 time. This attribute is advisory to the Scheduler, it is not
445 enforced by the server. Format: integer; default value: none.
446 max_threads
448 This is the maximum number of threads that should exist in the
449 thread pool at any time. Format: integer; default value: ((2
450 * the number of procs listed in /proc/cpuinfo) + 1) * 20
451 max_user_queuable
453 When set, max_user_queuable places a system-wide limit on the
454 amount of jobs that an individual user can queue. Format: in‐
455 teger; default value: unlimited.
456 min_threads
458 This is the minimum number of threads that should exist in the
459 thread pool at any time. Format: integer; default value: (2 *
460 the number of procs listed in /proc/cpuinfo) + 1.
461 moab_array_compatible
463 This parameter places a hold on jobs that exceed the slot
464 limit in a job array. When one of the active jobs is completed
465 or deleted, one of the held jobs goes to a queued state. For‐
466 mat: boolean; default value: true.
467 mom_job_sync
469 Enables the "job sync on MOM" feature. When MOMs send a sta‐
470 tus update, and it includes a list of jobs, server will issue
471 job deletes for any jobs that don't actually exist. Format:
472 boolean; default value: true.
473 next_job_number
475 This hidden attribute is used to allow a manager to set the
476 value of the next job ID via qmgr. This attribute should
477 rarely be modified. Some sites may find it useful if they need
478 to recreate their pbs_server database (perhaps due to a format
479 change between major TORQUE versions) and they keep a database
480 of job information indexed by the job ID. The manager should
481 be careful to avoid setting the value to something that would
482 allow the next job number to conflict with a job already
483 queued, however Torque will handle this in a sane manner: the
484 job submission will be rejected and the next job number will
485 be incremented.
486 net_counter
488 Lists the 3 numbers representing the number of connections in
489 the last 5 seconds, 30 seconds, and 60 seconds. This is a
490 read-only attribute. Format: string; default value: none.
491 no_mail_force
493 This attribute can be set by a manager via qmgr. When set
494 true, Torque will not force mail to be sent to the user when
495 the jobs mail_points is set to "n". User will not receive no‐
496 tice of job failures or deletions. Format: boolean; default
497 value: false.
498 node_check_rate
500 In OpenPBS, this was the rate at which pbs_server would poll
501 each node. In TORQUE, nodes periodically send updates without
502 solicitation from pbs_server; this attribute is now used as
503 the maximum number of seconds allowed without an update before
504 pbs_server will consider the node down. Format: integer; de‐
505 fault value: 150
506 node_ping_rate
508 Specifies the maximum interval (in seconds) between successive
509 pings sent from the pbs_server daemon to the pbs_mom daemon to
510 determine node/daemon health. Format: integer; default value:
511 300
512 node_pack
514 Controls how multiple processor nodes are allocated to jobs.
515 If this attribute is set to true, jobs will be assigned to the
516 multiple processor nodes with the fewest free processors.
517 This packs jobs into the fewest possible nodes leaving multi‐
518 ple processor nodes free for jobs which need many processors
519 on a node. If set to false, jobs will be scattered across
520 nodes reducing conflicts over memory between jobs. If unset,
521 the jobs are packed on nodes in the order that the nodes are
522 declared to the server (in the nodes file). Default value:
523 unset - assigned to nodes as nodes in order that were de‐
524 clared.
525 node_suffix
527 Adds a domainname to node names before IP lookups. Format:
528 string; default value: none.
529 np_default
531 np_default allows the administrator to unify the number of
532 processors (np) on all nodes. The value can be dynamically
533 changed. A value of 0 tells pbs_server to use the value of np
534 found in the nodes file. The maximum value is 32767. Format:
535 integer; default value: not used.
536 operators
538 List of users granted batch operator privileges. Format of
539 the list is identical with managers above. Requires full man‐
540 ager privilege to set or alter. Default value: root on the
541 local host.
542 owner_purge
544 Allows job owners to forcibly purge their own jobs from the
545 server. This short-circuits the normal flow of events and is
546 hightly discouraged. Default value: unset
547 pass_cpuclock
549 If set to TRUE, the pbs_server daemon passes the option and
550 its value to the pbs_mom daemons for direct implementation by
551 the daemons, making the CPU frequency adjustable as part of a
552 resource request by a job submission. If set to FALSE, the
553 pbs_server daemon creates and passes a PBS_CPUCLOCK job
554 environment variable to the pbs_mom daemons that contains the
555 value of the cpuclock attribute used as part of a resource re‐
556 quest by a job submission. The CPU frequencies on the MOMs
557 are not adjusted. The environment variable is for use by pro‐
558 logue and epilogue scripts, enabling administrators to log and
559 research when users are making cpuclock requests, as well as
560 researchers and developers to perform CPU clock frequency
561 changes using a method outside of that employed by the Torque
562 pbs_mom daemons. Format: boolean; default value: true.
563 poll_jobs
565 Controls how pbs_server will send job status requests to MOMs.
566 When unset or false, statjob requests from clients (ie: qs‐
567 tat(1B) or the scheduler) may trigger job status requests to
568 MOMs and and must wait until the MOMs have replied; this is
569 suitable for small to medium sized clusters. When set to
570 true, pbs_server will send periodic job status requests; this
571 is suitable for busy clusters with lots of jobs, lots of
572 clients, qstat(1B) is too slow, or your scheduler times out.
573 (see job_stat_rate) Default value: TRUE
574 query_other_jobs
576 The setting of this attribute controls if general users, other
577 than the job owner, are allowed to query the status of or se‐
578 lect the job. Format: boolean (see acl_host_enable); Requires
579 full manager privilege to set or alter. default value: false
580 - users may not query or select jobs owned by other users.
581 record_job_info
583 This must be set to TRUE in order for job logging to be en‐
584 abled. Format: boolean; default value: false.
585 record_job_script
587 If set to TRUE, this adds the contents of the script executed
588 by a job to the log. For record_job_script to take effect,
589 record_job_info must be set to TRUE. Format: boolean; de‐
590 fault value: false.
591 resources_available
593 The list of resource and amounts available to jobs run by this
594 server. The sum of the resource of each type used by all jobs
595 running by this server cannot exceed the total amount listed
596 here. Advisory to the Scheduler, not enforced by the server.
597 Format: "resources_available.resource_name=value[,...]".
598 resources_cost
600 The cost factors of various types of resources. These values
601 are used in determining the order of releasing members of syn‐
602 chronous job sets, see the section on Synchronize Job Starts.
603 For the most part, these value are purely arbitrary and have
604 meaning only in the relative values between systems. The cost
605 of the resources requested by a job is the sum of the products
606 of the various resources_cost s and the amount of each re‐
607 source requested by the job. It is not necessary to assign a
608 cost for each possible resource, only those which the site
609 wishes to be considered in synchronous job scheduling. For‐
610 mat: "resources_cost.resource_name=value[,...]"; default
611 value: none, cost of resource is not computed.
612 resources_default
614 The list of default resource values that are set as limits for
615 a job executing on this server when the job does not specify a
616 limit, and there is no queue default. Format: "resources_de‐
617 fault.resource_name=value[,...]"; default value: no limit.
618 resources_max
620 The maximum amount of each resource which can be requested by
621 a single job executing on this server if there is not a re‐
622 sources_max valued defined for the queue in which the job re‐
623 sides. Format: "resources_max.resource_name=value[,...]"; de‐
624 fault value: infinite usage.
625 sched_version
627 A string specifying the scheduler version. Schedulers should
628 check this string when starting and not become active if the
629 wrong string is found. This is ignored by pbs_server.
630 scheduler_iteration
632 Has no effect.
633 scheduling
635 Controls if the server will request job scheduling by the PBS
636 job scheduler. If true, the scheduler will be called as re‐
637 quired; if false, the scheduler will not be called and no job
638 will be placed into execution unless the server is directed to
639 do so by an operator or administrator. Setting or resetting
640 this attribute to true results in an immediate call to the
641 scheduler. For more information, see the section Scheduler -
642 Server Interaction in the PBS Administrator Guide. Format:
643 boolean (see acl_host_enable); default value: value of -a op‐
644 tion when server is invoked, if -a is not specified, the value
645 is recovered from the prior server run. If it has never been
646 set, the value is "false".
647 server_name
649 The name of the server which is the same as the host name. If
650 the hostname resolves to an external IP address, then set this
651 to a name that resolves to the internal IP.
652 submit_hosts
654 A list of hostnames allowed to submit jobs to this batch
655 server regardless of ruserok().
656 system_cost
658 An arbitrary value factored into the resource cost of any job
659 managed by this server for the purpose of selecting which mem‐
660 ber of synchronous set is released first, see resources_cost
661 and section 3.2.2, Synchronize Job Starts. [default value:
662 none, cost of resource is not computed]
663 tcp_timeout
665 Specifies the pbs_server to pbs_mom TCP socket timeout in sec‐
666 onds. Format: integer; default value: 6.
667 thread_idle_seconds
669 This is the number of seconds a thread can be idle in the
670 thread pool before it is deleted. If threads should not be
671 deleted, set to -1. Torque will always maintain at least
672 min_threads number of threads, even if all are idle. Format:
673 integer; default value: 300.
674 timeout_for_job_delete
676 The specific timeout used when deleting jobs because the node
677 they are executing on is being deleted. Format: integer; de‐
678 fault value: 120.
679 timeout_for_job_requeue
681 The specific timeout used when requeuing jobs because the node
682 they are executing on is being deleted. Format: integer; de‐
683 fault value: 120.
684 use_jobs_subdirs
686 Lets an administrator direct the way pbs_server will store its
687 job-related files. When use_jobs_subdirs is unset (or set to
688 FALSE), job and job array files will be stored directly under
689 $PBS_HOME/server_priv/jobs and $PBS_HOME/server_priv/arrays.
690 When use_job_subdirs is set to TRUE, job and job array files
691 will be distributed over 10 subdirectories under their respec‐
692 tive parent directories. This method helps to keep a smaller
693 number of files in a given directory. Format: boolean; de‐
694 fault value: false.
695 The following attributes are read-only, they are maintained by the
697 server and cannot be changed by a client.
698 pbs_version
700 The release version number of the server.
701 resources_assigned
703 The total amount of certain types of resources allocated to
704 running jobs.
705 server_state
707 The current state of the server:
708 Active The server is running and will invoke the job scheduler
710 as required to schedule jobs for execution.
711 Idle The server is running but will not invoke the job
713 scheduler.
714 Scheduling
716 The server is running and there is an outstanding re‐
717 quest to the job scheduler.
718 Terminating
720 The server is terminating. No additional jobs will be
721 scheduled.
722 Terminating, Delayed
724 The server is terminating in delayed mode. The server
725 will not run any new jobs and will shutdown when the
726 last currently executing job completes.
727 state_count
729 The total number of jobs managed by the server currently in
730 each state.
731 total_jobs
733 The total number of jobs currently managed by the server.
734
736 the PBS ERS, qmgr(1B), pbs_resources(7B)
737Local pbs_server_attributes(7B)