1ACCOUNTING(5) Grid Engine File Formats ACCOUNTING(5)
2
3
4
6 accounting - Grid Engine accounting file format
7
9 An accounting record is written to the Grid Engine accounting file for
10 each job having finished. The accounting file is processed by qacct(1)
11 to derive accounting statistics.
12
14 Each job is represented by a line in the accounting file. Empty lines
15 and lines which contain one character or less are ignored. Accounting
16 record entries are separated by colon (':'). The entries denote in
17 their order of appearance:
18
19 qname
20 Name of the cluster queue in which the job has run.
21
22 hostname
23 Name of the execution host.
24
25 group
26 The effective group id of the job owner when executing the job.
27
28 owner
29 Owner of the Grid Engine job.
30
31 job_name
32 Job name.
33
34 job_number
35 Job identifier - job number.
36
37 account
38 An account string as specified by the qsub(1) or qalter(1) -A option.
39
40 priority
41 Priority value assigned to the job corresponding to the priority
42 parameter in the queue configuration (see queue_conf(5)).
43
44 submission_time
45 Submission time (GMT Unix time stamp). For slave tasks of tightly
46 integrated parallel jobs, the submission_time is always set to 0.
47
48 start_time
49 Start time (GMT Unix time stamp).
50
51 end_time
52 End time (GMT Unix time stamp).
53
54 failed
55 Indicates the problem which occurred in case a job could not be started
56 on the execution host (e.g. because the owner of the job did not have a
57 valid account on that machine). If Grid Engine tries to start a job
58 multiple times, this may lead to multiple entries in the accounting
59 file corresponding to the same job ID.
60
61 exit_status
62 Exit status of the job script (or Grid Engine specific status in case
63 of certain error conditions).
64
65 ru_wallclock
66 Difference between end_time and start_time (see above).
67
68 The remainder of the accounting entries follows the contents of the
69 standard UNIX rusage structure as described in getrusage(2). Depending
70 on the operating system where the job was executed some of the fields
71 may be 0. The following entries are provided:
72
73 ru_utime
74 ru_stime
75 ru_maxrss
76 ru_ixrss
77 ru_ismrss
78 ru_idrss
79 ru_isrss
80 ru_minflt
81 ru_majflt
82 ru_nswap
83 ru_inblock
84 ru_oublock
85 ru_msgsnd
86 ru_msgrcv
87 ru_nsignals
88 ru_nvcsw
89 ru_nivcsw
90
91 project
92 The project which was assigned to the job.
93
94 department
95 The department which was assigned to the job.
96
97 granted_pe
98 The parallel environment which was selected for that job.
99
100 slots
101 The number of slots which were dispatched to the job by the scheduler.
102
103 task_number
104 Array job task index number.
105
106 cpu
107 The cpu time usage in seconds.
108
109 mem
110 The integral memory usage in Gbytes cpu seconds.
111
112 io
113 The amount of data transferred in input/output operations.
114
115 category
116 A string specifying the job category.
117
118 iow
119 The io wait time in seconds.
120
121 pe_taskid
122 If this identifier is set the task was part of a parallel job and was
123 passed to Grid Engine via the qrsh -inherit interface.
124
125 maxvmem
126 The maximum vmem size in bytes.
127
129 sge_intro(1), qacct(1), qalter(1), qsub(1), getrusage(2),
130 queue_conf(5).
131
133 See sge_intro(1) for a full statement of rights and permissions.
134
135
136
137GE 6.1 $Date: 2007/06/26 22:21:10 $ ACCOUNTING(5)