1QACCT(1)                   Grid Engine User Commands                  QACCT(1)
2
3
4

NAME

6       qacct - report and account for Grid Engine usage
7

SYNOPSIS

9       qacct  [ -ar [ar_id] ] [ -A Account ] [ -b BeginTime ] [ -d Days ] [ -e
10       EndTime ] [ -g [GroupId|GroupName] ] [ -h [HostName] ] [ -help ]  [  -j
11       [job_id|job_name|pattern]  ]  [ -l attr=val,...  ] [ -o [Owner] ] [ -pe
12       [PEname]  ]  [  -q  [wc_queue]  ]  [  -slots  [SlotNumber]   ]   [   -t
13       task_id_range_list  ]  [  -P [Project] ] [ -D [Department] ] [ -f Acct‐
14       FileName ]
15

DESCRIPTION

17       The qacct utility scans the accounting data  file  (see  accounting(5))
18       and  produces  a  summary of information for wall-clock time, cpu-time,
19       and system time for the categories of hostname, queue-name, group-name,
20       owner-name,  job-name,  job-ID  and for the queues meeting the resource
21       requirements as specified with the -l  switch.   Combinations  of  each
22       category  are  permitted.  Alternatively,  all  or specific jobs can be
23       listed with the -j switch.   For  example  the  search  criteria  could
24       include summarizing for a queue and an owner, but not for two queues in
25       the same request.
26

OPTIONS

28       -ar [ar_id]
29              The ID of the advance reservation for which usage is summarized.
30              If  ar_id  is  not  given,  accounting  data  is listed for each
31              advance reservation separately.
32
33       -A Account
34              The account for jobs to be summarized.
35
36       -b BeginTime
37              The earliest start time for jobs to be summarized, in the format
38              [[CC]YY]MMDDhhmm[.SS].  See  also -d option. If CC is not speci‐
39              fied, a YY of < 70 means 20YY.
40
41       -d Days
42              The number of days to summarize and print accounting information
43              on.  If  used together with the -b BeginTime option (see above),
44              jobs started within BeginTime to BeginTime + Days  are  counted.
45              If  used  together with the -e EndTime (see below) option, count
46              starts at EndTime - Days.
47
48       -e EndTime
49              The latest start time for jobs to be summarized, in  the  format
50              [[CC]YY]MMDDhhmm[.SS].  See  also -d option. If CC is not speci‐
51              fied, a YY of < 70 means 20YY.
52
53       [-f AcctFileName]
54              The accounting file to be used. If omitted, the  system  default
55              accounting file is processed.
56
57       -g [GroupId|GroupName]
58              The  numeric  system  group id or the group alphanumeric name of
59              the  job  owners  to  be  included   in   the   accounting.   If
60              GroupId/GroupName is omitted, all groups are accounted.
61
62       -h [HostName]
63              The  case-insensitive  name  of  the  host upon which accounting
64              information is requested. If the name  is  omitted,  totals  for
65              each host are listed separately.
66
67       -help  Display help information for the qacct command.
68
69       -j [job_id|job_name|pattern]
70              The name, a expression for matching names, or ID of the job dur‐
71              ing execution for which accounting information  is  printed.  If
72              neither a name nor an ID is given all jobs are enlisted.
73              This  option  changes  the output format of qacct. If activated,
74              CPU times are no longer accumulated  but  the  "raw"  accounting
75              information  is  printed  in  a  formatted  form  instead.   See
76              accounting(5) for an explanation of the displayed information.
77
78       -l attr=val,...
79              A resource requirement specification which must be  met  by  the
80              queues  in  which  the  jobs being accounted were executing. The
81              resource request  is  very  similar  to  the  one  described  in
82              qsub(1).
83
84       -o [Owner]
85              The  name  of the owner of the jobs for which accounting statis‐
86              tics are assembled. If the optional Owner argument is omitted, a
87              listing  of  the  accounting  statistics of all job owners being
88              present in the accounting file is produced.
89
90       -pe [PEname]
91              The name of the parallel environment for which usage  is  summa‐
92              rized.   If  PEname  is not given, accounting data is listed for
93              each parallel environment separately.
94
95       -q [wc_queue_name]
96              A expression for queues for which usage is summarized. All queue
97              instances  matching the expression will be listed. If no expres‐
98              sion is specified, a cluster queue summary will be given.
99
100       -slots [SlotNumber]
101              The number of queue slots for which  usage  is  summarized.   If
102              SlotNumber is not given, accounting data is listed for each num‐
103              ber of queue slots separately.
104
105       -t task_id_range_list
106              Only available together with the -j option described above.
107
108              The -t switch specifies the array  job  task  range,  for  which
109              accounting  information  should be printed. Syntax and semantics
110              of task_id_range_list are identical to that one described  under
111              the  -t  option  to  qsub(1).  Please see there also for further
112              information on array jobs.
113
114       -P [Project]
115              The name of the project  for  which  usage  is  summarized.   If
116              Project  is not given, accounting data is listed for each owning
117              project separately.
118
119       -D [Department]
120              The name of the department for which usage  is  summarized.   If
121              Department is not given, accounting data is listed for each own‐
122              ing department separately.
123

ENVIRONMENTAL VARIABLES

125       GE_ROOT        Specifies the location of the Grid Engine standard  con‐
126                      figuration files.
127
128       GE_CELL        If  set,  specifies  the  default  Grid  Engine cell. To
129                      address a Grid Engine cell qacct uses (in the  order  of
130                      precedence):
131
132                             The name of the cell specified in the environment
133                             variable GE_CELL, if it is set.
134
135                             The name of the default cell, i.e. default.
136
137
138       GE_DEBUG_LEVEL If set, specifies that debug information should be writ‐
139                      ten  to stderr. In addition the level of detail in which
140                      debug information is generated is defined.
141
142       GE_QMASTER_PORT
143                      If set, specifies the tcp port on which ge_qmaster(8) is
144                      expected  to  listen  for  communication requests.  Most
145                      installations will use a services map entry for the ser‐
146                      vice "sge_qmaster" instead to define that port.
147
148       GE_EXECD_PORT  If  set,  specifies the tcp port on which ge_execd(8) is
149                      expected to listen  for  communication  requests.   Most
150                      installations will use a services map entry for the ser‐
151                      vice "sge_execd" instead to define that port.
152

FILES

154       <ge_root>/<cell>/common/accounting
155                      Grid Engine default accounting file
156       <xxqs_nam_sexx_root>/<cell>/common/act_qmaster
157                      Grid Engine master host file
158

SEE ALSO

160       ge_intro(1), qsub(1), accounting(5), ge_qmaster(8),
161
163       See ge_intro(1) for a full statement of rights and permissions.
164
165
166
167GE 6.2u5                 $Date: 2009/02/12 14:32:28 $                 QACCT(1)
Impressum