1QHOST(1) Grid Engine User Commands QHOST(1)
2
6 qhost - show the status of Grid Engine hosts, queues, jobs
7
9 qhost [ -F [resource_name,...] [ -help ] [ -h host_list ] [ -j ] [ -l
10 resource=val,... ] [ -u user,... ] [ -xml ].
11
13 qhost shows the current status of the available Grid Engine hosts,
14 queues and the jobs associated with the queues. Selection options allow
15 you to get information about specific hosts, queues, jobs or users.
16 Without any option qhost will display a list of all hosts without queue
17 or job information.
18
20 -F [ resource_name,... ]
21 qhost will present a detailed listing of the current resource
22 availability per host with respect to all resources (if the
23 option argument is omitted) or with respect to those resources
24 contained in the resource_name list. Please refer to the
25 description of the Full Format in section OUTPUT FORMATS below
26 for further detail.
27 -help Prints a listing of all options.
29 -h host_list
31 Prints a list of all hosts contained in host_list.
32 -j Prints all jobs running on the queues hosted by the shown hosts.
34 This switch calls -q implicitly.
35 -l resource[=value],...
37 Defines the resources required by the hosts on which information
38 is requested. Matching is performed on hosts.
39 -q Show information about the queues instances hosted by the dis‐
41 played hosts.
42 -u user,...
44 Display information only on those jobs and queues being associ‐
45 ated with the users from the given user list.
46 -xml This option can be used with all other options and changes the
48 output to XML. The used schemas are referenced in the XML out‐
49 put. The output is printed to stdout.
50
52 Depending on the presence or absence of the -q or -F and -j option
53 three output formats need to be differentiated. PP
54 Default Format (without -q, -F and -j)
56 For each host one line is printed. The output consists of consisting of
57 · the Hostname
59 · the Architecture.
61 · the Number of processors.
63 · the Load.
65 · the Total Memory.
67 · the Used Memory.
69 · the Total Swapspace.
71 · the Used Swapspace.
73 If the -q option is supplied, each host status line also contains extra
75 lines for every queue hosted by the host consisting of,
76 · the queue name.
78 · the queue type - one of B(atch), I(nteractive), C(heckpointing),
80 P(arallel), T(ransfer) or combinations thereof,
81 · the number of used and available job slots,
83 · the state of the queue - one of u(nknown) if the corresponding
85 sge_execd(8) cannot be contacted, a(larm), A(larm), C(alendar sus‐
86 pended), s(uspended), S(ubordinate), d(isabled), D(isabled), E(rror)
87 or combinations thereof.
88 If the state is a(alarm) at least one of the load thresholds defined in
90 the load_thresholds list of the queue configuration (see queue_conf(5))
91 is currently exceeded, which prevents from scheduling further jobs to
92 that queue.
93 As opposed to this, the state A(larm) indicates that at least one of
95 the suspend thresholds of the queue (see queue_conf(5)) is currently
96 exceeded. This will result in jobs running in that queue being succes‐
97 sively suspended until no threshold is violated.
98 The states s(uspended) and d(isabled) can be assigned to queues and
100 released via the qmod(1) command. Suspending a queue will cause all
101 jobs executing in that queue to be suspended.
102 The states D(isabled) and C(alendar suspended) indicate that the queue
104 has been disabled or suspended automatically via the calendar facility
105 of Grid Engine (see calendar_conf(5)), while the S(ubordinate) state
106 indicates, that the queue has been suspend via subordination to another
107 queue (see queue_conf(5) for details). When suspending a queue (regard‐
108 less of the cause) all jobs executing in that queue are suspended too.
109 If an E(rror) state is displayed for a queue, sge_execd(8) on that host
111 was unable to locate the sge_shepherd(8) executable on that host in
112 order to start a job. Please check the error logfile of that
113 sge_execd(8) for leads on how to resolve the problem. Please enable the
114 queue afterwards via the -c option of the qmod(1) command manually.
115 If the -F option was used, resource availability information is printed
117 following the host status line. For each resource (as selected in an
118 option argument to -F or for all resources if the option argument was
119 omitted) a single line is displayed with the following format:
120 · a one letter specifier indicating whether the current resource
122 availability value was dominated by either
123 `g' - a cluster global,
124 `h' - a host total or
125 · a second one letter specifier indicating the source for the current
127 resource availability value, being one of
128 `l' - a load value reported for the resource,
129 `L' - a load value for the resource after administrator defined load
130 scaling has been applied,
131 `c' - availability derived from the consumable resources facility
132 (see complexes(5)),
133 `f' - a fixed availability definition derived from a non-consumable
134 complex attribute or a fixed resource limit.
135 · after a colon the name of the resource on which information is dis‐
137 played.
138 · after an equal sign the current resource availability value.
140 The displayed availability values and the sources from which they
142 derive are always the minimum values of all possible combinations.
143 Hence, for example, a line of the form "qf:h_vmem=4G" indicates that a
144 queue currently has a maximum availability in virtual memory of 4 Giga‐
145 byte, where this value is a fixed value (e.g. a resource limit in the
146 queue configuration) and it is queue dominated, i.e. the host in total
147 may have more virtual memory available than this, but the queue doesn't
148 allow for more. Contrarily a line "hl:h_vmem=4G" would also indicate an
149 upper bound of 4 Gigabyte virtual memory availability, but the limit
150 would be derived from a load value currently reported for the host. So
151 while the queue might allow for jobs with higher virtual memory
152 requirements, the host on which this particular queue resides currently
153 only has 4 Gigabyte available.
154 After the queue status line (in case of -j) a single line is printed
156 for each job running currently in this queue. Each job status line con‐
157 tains
158 · the job ID,
160 · the job name,
162 · the job owner name,
164 · the status of the job - one of t(ransfering), r(unning),
166 R(estarted), s(uspended), S(uspended) or T(hreshold) (see the
167 Reduced Format section for detailed information),
168 · the start date and time and the function of the job (MASTER or SLAVE
170 - only meaningful in case of a parallel job) and
171 · the priority of the jobs.
173
175 SGE_ROOT Specifies the location of the Grid Engine standard con‐
176 figuration files.
177 SGE_CELL If set, specifies the default Grid Engine cell. To
179 address a Grid Engine cell qhost uses (in the order of
180 precedence):
181 The name of the cell specified in the environment
183 variable SGE_CELL, if it is set.
184 The name of the default cell, i.e. default.
186 SGE_DEBUG_LEVEL
189 If set, specifies that debug information should be writ‐
190 ten to stderr. In addition the level of detail in which
191 debug information is generated is defined.
192 SGE_QMASTER_PORT
194 If set, specifies the tcp port on which sge_qmaster(8)
195 is expected to listen for communication requests. Most
196 installations will use a services map entry for the ser‐
197 vice "sge_qmaster" instead to define that port.
198
200 $SGE_ROOT/$SGE_CELL/common/act_qmaster
201 Grid Engine master host file
202
204 sge_intro(1), qalter(1), qconf(1), qhold(1), qmod(1), qstat(1),
205 qsub(1), queue_conf(5), sge_execd(8), sge_qmaster(8), sge_shepherd(8).
206
208 See sge_intro(1) for a full statement of rights and permissions.
209GE 6.1 $Date: 2007/06/26 22:21:08 $ QHOST(1)