1just-man-pages/condor_drain(1G)eneral Commands Manujaulst-man-pages/condor_drain(1)
2
3
4
6 condor_drain Control draining of an execute machine
7
9 condor_drain [ -help ]
10
11 condor_drain [ -debug ] [ -pool pool-name ] [ -graceful | -quick |
12 -fast ] [ -resume-on-completion ] [ -check expr ] machine-name
13
14 condor_drain [ -debug ] [ -pool pool-name ] -cancel [ -request-id id ]
15 machine-name
16
18 condor_drain is an administrative command used to control the draining
19 of all slots on an execute machine. When a machine is draining, it will
20 not accept any new jobs. Which machine to drain is specified by the
21 argument machine-name , and will be the same as the machine ClassAd
22 attribute Machine .
23
24 How currently running jobs are treated depends on the draining schedule
25 that is chosen with a command-line option:
26
27 -graceful
28
29 Initiate a graceful eviction of the job. This means all promises
30 that have been made to the job are honored, including MaxJobRetire‐
31 mentTime . The eviction of jobs is coordinated to reduce idle time.
32 This means that if one slot has a job with a long retirement time
33 and the other slots have jobs with shorter retirement times, the
34 effective retirement time for all of the jobs is the longer one. If
35 no draining schedule is specified, -graceful is chosen by default.
36
37
38
39
40
41 -quick
42
43
44 MaxJobRetirementTime is not honored. Eviction of jobs is immedi‐
45 ately initiated. Jobs are given time to shut down and produce check‐
46 points, according to the usual policy, that is, given by Machine‐
47 MaxVacateTime .
48
49
50
51
52
53 -fast
54
55 Jobs are immediately hard-killed, with no chance to gracefully shut
56 down or produce a checkpoint.
57
58
59
60
61
62 Once draining is complete, the machine will enter the Drained/Idle
63 state. To resume normal operation (negotiation) at that time or any
64 previous time during draining, the -cancel option may be used. The
65 -resume-on-completion option results in automatic resumption of normal
66 operation once draining has completed, and may be used when initiating
67 draining. This is useful for forcing a machine with a partitionable
68 slots to join all of the resources back together into one machine,
69 facilitating de-fragmentation and whole machine negotiation.
70
72 -help
73
74 Display brief usage information and exit.
75
76
77
78 -debug
79
80 Causes debugging information to be sent to stderr , based on the
81 value of the configuration variable TOOL_DEBUG .
82
83
84
85 -pool pool-name
86
87 Specify an alternate HTCondor pool, if the default one is not
88 desired.
89
90
91
92 -graceful
93
94 (the default) Honor the maximum vacate and retirement time policy.
95
96
97
98 -quick
99
100 Honor the maximum vacate time, but not the retirement time policy.
101
102
103
104 -fast
105
106 Honor neither the maximum vacate time policy nor the retirement time
107 policy.
108
109
110
111 -resume-on-completion
112
113 When done draining, resume normal operation, such that potentially
114 the whole machine could be claimed.
115
116
117
118 -check expr
119
120 Abort draining, if expr is not true for all slots to be drained.
121
122
123
124 -cancel
125
126 Cancel a prior draining request, to permit the condor_negotiator to
127 use the machine again.
128
129
130
131 -request-id id
132
133 Specify a specific draining request to cancel, where id is given by
134 the DrainingRequestId machine ClassAd attribute.
135
136
137
139 condor_drain will exit with a non-zero status value if it fails and
140 zero status if it succeeds.
141
143 Center for High Throughput Computing, University of Wisconsin-Madison
144
146 Copyright (C) 1990-2018 Center for High Throughput Computing, Computer
147 Sciences Department, University of Wisconsin-Madison, Madison, WI. All
148 Rights Reserved. Licensed under the Apache License, Version 2.0.
149
150
151
152 date just-man-pages/condor_drain(1)