1CONDOR_STATS(1) HTCondor Manual CONDOR_STATS(1)
2
6 condor_stats - HTCondor Manual
7 Display historical information about the HTCondor pool
9
13 condor_stats [-f filename] [-orgformat ] [-pool centralmanagerhost‐
14 name[:portnumber]] [time-range ] query-type
15
17 condor_stats displays historic information about an HTCondor pool.
18 Based on the type of information requested, a query is sent to the con‐
19 dor_collector daemon, and the information received is displayed using
20 the standard output. If the -f option is used, the information will be
21 written to a file instead of to standard output. The -pool option can
22 be used to get information from other pools, instead of from the local
23 (default) pool. The condor_stats tool is used to query resource infor‐
24 mation (single or by platform), submitter and user information, and
25 checkpoint server information. If a time range is not specified, the
26 default query provides information for the previous 24 hours. Other‐
27 wise, information can be retrieved for other time ranges such as the
28 last specified number of hours, last week, last month, or a specified
29 date range.
30 The information is displayed in columns separated by tabs. The first
32 column always represents the time, as a percentage of the range of the
33 query. Thus the first entry will have a value close to 0.0, while the
34 last will be close to 100.0. If the -orgformat option is used, the time
35 is displayed as number of seconds since the Unix epoch. The information
36 in the remainder of the columns depends on the query type.
37 Note that logging of pool history must be enabled in the condor_collec‐
39 tor daemon, otherwise no information will be available.
40 One query type is required. If multiple queries are specified, only the
42 last one takes effect.
43
45 -lastday
46 Get information for the last day.
47 -lastweek
49 Get information for the last week.
50 -lastmonth
52 Get information for the last month.
53 -lasthours n
55 Get information for the n last hours.
56 -from m d y
58 Get information for the time since the beginning of the spec‐
59 ified date. A start date prior to the Unix epoch causes con‐
60 dor_stats to print its usage information and quit.
61 -to m d y
63 Get information for the time up to the beginning of the spec‐
64 ified date, instead of up to now. A finish date in the future
65 causes condor_stats to print its usage information and quit.
66
68 The query types that do not list all of a category require further
69 specification as given by an argument.
70 -resourcequery hostname
72 A single resource query provides information about a single
73 machine. The information also includes the keyboard idle
74 time (in seconds), the load average, and the machine state.
75 -resourcelist
77 A query of a single list of resources to provide a list of
78 all the machines for which the condor_collector daemon has
79 historic information within the query's time range.
80 -resgroupquery arch/opsys | "Total"
82 A query of a specified group to provide information about a
83 group of machines based on their platform (operating system
84 and architecture). The architecture is defined by the machine
85 ClassAd Arch, and the operating system is defined by the ma‐
86 chine ClassAd OpSys. The string "Total" ask for information
87 about all platforms.
88 The columns displayed are the number of machines that are un‐
90 claimed, matched, claimed, preempting, owner, shutdown,
91 delete, backfill, and drained state.
92 -resgrouplist
94 Queries for a list of all the group names for which the con‐
95 dor_collector has historic information within the query's
96 time range.
97 -userquery email_address/submit_machine
99 Query for a specific submitter on a specific machine. The in‐
100 formation displayed includes the number of running jobs and
101 the number of idle jobs. An example argument appears as
102 -userquery jondoe@sample.com/onemachine.sample.com
104 -userlist
106 Queries for the list of all submitters for which the con‐
107 dor_collector daemon has historic information within the
108 query's time range.
109 -usergroupquery email_address | "Total"
111 Query for all jobs submitted by the specific user, regardless
112 of the machine they were submitted from, or all jobs. The in‐
113 formation displayed includes the number of running jobs and
114 the number of idle jobs.
115 -usergrouplist
117 Queries for the list of all users for which the condor_col‐
118 lector has historic information within the query's time
119 range.
120 -ckptquery hostname
122 Query about a checkpoint server given its host name. The in‐
123 formation displayed includes the number of MiB received, MiB
124 sent, average receive bandwidth (in KiB/sec), and average
125 send bandwidth (in KiB/sec).
126 -ckptlist
128 Query for the entire list of checkpoint servers for which the
129 condor_collector has historic information in the query's time
130 range.
131
133 -f filename
134 Write the information to a file instead of the standard out‐
135 put.
136 -pool centralmanagerhostname[:portnumber]
138 Contact the specified central manager instead of the local
139 one.
140 -orgformat
142 Display the information in an alternate format for timing,
143 which presents timestamps since the Unix epoch. This argument
144 only affects the display of resoursequery, resgroupquery,
145 userquery, usergroupquery, and ckptquery.
146
148 condor_stats will exit with a status value of 0 (zero) upon success,
149 and it will exit with the value 1 (one) upon failure.
150
152 HTCondor Team
153
155 1990-2021, Center for High Throughput Computing, Computer Sciences De‐
156 partment, University of Wisconsin-Madison, Madison, WI, US. Licensed
157 under the Apache License, Version 2.0.
1588.8 Aug 23, 2021 CONDOR_STATS(1)