1sprio(1) Slurm Commands sprio(1)
2
3
4
6 sprio - view the factors that comprise a job's scheduling priority
7
8
10 sprio [OPTIONS...]
11
12
14 sprio is used to view the components of a job's scheduling priority
15 when the multi-factor priority plugin is installed. sprio is a
16 read-only utility that extracts information from the multi-factor pri‐
17 ority plugin. By default, sprio returns information for all pending
18 jobs. Options exist to display specific jobs by job ID and user name.
19
20
22 -M, --clusters=<string>
23 The cluster to issue commands to. Only one cluster name may be
24 specified. Note that the SlurmDBD must be up for this option to
25 work properly. This option implicitly sets the --local option.
26
27 --federation
28 Show jobs in federation if a member of one.
29
30 -o, --format=<output_format>
31 Specify the information to be displayed, its size and position
32 (right or left justified). The default formats when all factors
33 have been assigned non-zero weights are
34
35 default "%.15i %9r %.10Y %.10S %.10A %.10B %.10F %.10J
36 %.10P %.10Q %20T"
37
38 -l, --long "%.15i %9r %.8u %.10Y %.10S %.10A %.10B %.10F
39 %.10J %.10P %.10Q %.11N %.20T";
40
41 The format of each field is "%[.][size]type".
42
43 size is the minimum field size. If no size is specified,
44 whatever is needed to print the information will be
45 used.
46
47 . indicates the output should be left justified. By de‐
48 fault, output is right justified.
49
50 Valid type specifications include:
51
52 %a Normalized age priority
53
54 %A Weighted age priority
55
56 %b Normalized association priority
57
58 %B Weighted association priority
59
60 %c Cluster name. Only applicable for federated clusters
61
62 %f Normalized fair-share priority
63
64 %F Weighted fair-share priority
65
66 %i Job ID
67
68 %j Normalized job size priority
69
70 %J Weighted job size priority
71
72 %N Nice adjustment
73
74 %p Normalized partition priority
75
76 %P Weighted partition priority
77
78 %q Normalized quality of service priority
79
80 %Q Weighted quality of service priority
81
82 %r Partition name
83
84 %S Weighted admin priority.
85
86 %t Normalized TRES priorities
87
88 %T Weighted TRES priorities
89
90 %u User name for a job
91
92 %Y Job priority
93
94 %y Normalized job priority
95
96 --help Print a help message describing all options sprio.
97
98 -j, --jobs=<job_id_list>
99 Requests a comma separated list of job ids to display. Defaults
100 to all jobs. Since this option's argument is optional, for
101 proper parsing the single letter option must be followed immedi‐
102 ately with the value and not include a space between them. For
103 example "-j1008,1009" and not "-j 1008,1009".
104
105 --local
106 Show only jobs local to this cluster. Ignore other clusters in
107 this federation (if any). Overrides --federation.
108
109 -l, --long
110 Report more of the available information for the selected jobs.
111
112 -h, --noheader
113 Do not print a header on the output.
114
115 -n, --norm
116 Display the normalized priority factors for the selected jobs.
117
118 -p, --partition=<partition_list>
119 Requests a comma separated list of partitions to display. De‐
120 faults to all partitions.
121
122 --sibling
123 Show all sibling jobs on a federated cluster. Without this op‐
124 tion in a federated cluster, each job in each partition will
125 have its priority and its components reported for only one clus‐
126 ter. Each sibling job on the various clusters in the federation
127 may have different priority, which will not be reported without
128 using this option. Implicitly adds "%c" (cluster name) to the
129 output format.
130
131 -S, --sort=<sort_list>
132 Specification of the order in which jobs should be reported.
133 This uses the same field specification as <output_format>. Mul‐
134 tiple sorts may be performed by listing multiple sort fields
135 separated by commas. The field specifications may be preceded by
136 "+" or "-" for ascending (default) or descending respectively.
137 For example, a <sort_list> of "u,r,-y" will sort the job prior‐
138 ity reports by username, partition name, and descending job pri‐
139 ority, in that order. The default <sort_list> is "i" (ascending
140 job id).
141
142 --usage
143 Print a brief help message listing the sprio options.
144
145 -u, --user=<user_list>
146 Request jobs from a comma separated list of users. The list can
147 consist of user names or user id numbers.
148
149 -v, --verbose
150 Report details of sprios actions.
151
152 -V, --version
153 Print version information and exit.
154
155 -w, --weights
156 Display the configured weights for each factor. This is for in‐
157 formation purposes only. Actual job data is suppressed.
158
160 Executing sprio sends a remote procedure call to slurmctld. If enough
161 calls from sprio or other Slurm client commands that send remote proce‐
162 dure calls to the slurmctld daemon come in at once, it can result in a
163 degradation of performance of the slurmctld daemon, possibly resulting
164 in a denial of service.
165
166 Do not run sprio or other Slurm client commands that send remote proce‐
167 dure calls to slurmctld from loops in shell scripts or other programs.
168 Ensure that programs limit calls to sprio to the minimum necessary for
169 the information you are trying to gather.
170
171
173 If no corresponding command line option is specified, sprio will use
174 the value of the following environment variables.
175
176
177 SLURM_CLUSTERS Same as --clusters
178
179 SLURM_CONF The location of the Slurm configuration file.
180
181 SPRIO_FEDERATION Same as --federation
182
183 SPRIO_FORMAT Same as -o <output_format>, --format=<output_for‐
184 mat>
185
186 SPRIO_LOCAL Same as --local
187
188 SPRIO_SIBLING Same as --sibling
189
191 Print the list of all pending jobs with their weighted priorities
192
193 $ sprio
194 JOBID PRIORITY AGE FAIRSHARE JOBSIZE PARTITION QOS
195 65539 62664 0 51664 1000 10000 0
196 65540 62663 0 51663 1000 10000 0
197 65541 62662 0 51662 1000 10000 0
198
199
200 Print the list of all pending jobs with their normalized priorities
201
202 $ sprio -n
203 JOBID PRIORITY AGE FAIRSHARE JOBSIZE PARTITION QOS
204 65539 0.00001459 0.0007180 0.5166470 1.0000000 1.0000000 0.0000000
205 65540 0.00001459 0.0007180 0.5166370 1.0000000 1.0000000 0.0000000
206 65541 0.00001458 0.0007180 0.5166270 1.0000000 1.0000000 0.0000000
207
208
209 Print the job priorities for specific jobs
210
211 $ sprio --jobs=65548,65547
212 JOBID PRIORITY AGE FAIRSHARE JOBSIZE PARTITION QOS
213 65547 62078 0 51078 1000 10000 0
214 65548 62077 0 51077 1000 10000 0
215
216
217 Print the job priorities for jobs of specific users
218
219 $ sprio --users=fred,sally
220 JOBID USER PRIORITY AGE FAIRSHARE JOBSIZE PARTITION QOS
221 65548 fred 62079 1 51077 1000 10000 0
222 65549 sally 62080 1 51078 1000 10000 0
223
224
225 Print the configured weights for each priority component
226
227 $ sprio -w
228 JOBID PRIORITY AGE FAIRSHARE JOBSIZE PARTITION QOS
229 Weights 1000 100000 1000 10000 1
230
231
233 Copyright (C) 2009 Lawrence Livermore National Security. Produced at
234 Lawrence Livermore National Laboratory (cf, DISCLAIMER).
235 Copyright (C) 2010-2022 SchedMD LLC.
236
237 This file is part of Slurm, a resource management program. For de‐
238 tails, see <https://slurm.schedmd.com/>.
239
240 Slurm is free software; you can redistribute it and/or modify it under
241 the terms of the GNU General Public License as published by the Free
242 Software Foundation; either version 2 of the License, or (at your op‐
243 tion) any later version.
244
245 Slurm is distributed in the hope that it will be useful, but WITHOUT
246 ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
247 FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
248 for more details.
249
251 squeue(1), sshare(1)
252
253
254
255May 2021 Slurm Commands sprio(1)