1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
|
job "${job_name}" {
# The "datacenters" parameter specifies the list of datacenters which should
# be considered when placing this task. This must be provided.
datacenters = "${datacenters}"
# The "type" parameter controls the type of job, which impacts the scheduler's
# decision on placement. For a full list of job types and their differences,
# please see the online documentation.
#
# https://www.nomadproject.io/docs/jobspec/schedulers
#
type = "${type}"
# The periodic stanza allows a job to run at fixed times, dates, or intervals.
# The easiest way to think about the periodic scheduler is "Nomad cron" or
# "distributed cron".
#
# https://www.nomadproject.io/docs/job-specification/periodic
#
periodic {
cron = "${cron}"
prohibit_overlap = "${prohibit_overlap}"
time_zone = "${time_zone}"
}
# The "group" stanza defines a series of tasks that should be co-located on
# the same Nomad client. Any task within a group will be placed on the same
# client.
#
# https://www.nomadproject.io/docs/job-specification/group
#
group "${job_name}-master" {
# The restart stanza configures a tasks's behavior on task failure. Restarts
# happen on the client that is running the task.
#
# https://www.nomadproject.io/docs/job-specification/restart
#
restart {
mode = "fail"
}
# The constraint allows restricting the set of eligible nodes. Constraints
# may filter on attributes or client metadata.
#
# For more information and examples on the "volume" stanza, please see
# the online documentation at:
#
# https://www.nomadproject.io/docs/job-specification/constraint
#
constraint {
attribute = "$${attr.cpu.arch}"
operator = "!="
value = "arm64"
}
constraint {
attribute = "$${node.class}"
value = "builder"
}
# The "task" stanza creates an individual unit of work, such as a Docker
# container, web application, or batch processing.
#
# https://www.nomadproject.io/docs/job-specification/task.html
#
task "${job_name}-trending" {
# The artifact stanza instructs Nomad to fetch and unpack a remote
# resource, such as a file, tarball, or binary.
#
# https://www.nomadproject.io/docs/job-specification/artifact
#
artifact {
source = "git::https://github.com/FDio/csit"
destination = "local/csit"
}
# The "driver" parameter specifies the task driver that should be used to
# run the task.
driver = "docker"
# The "config" stanza specifies the driver configuration, which is passed
# directly to the driver to start the task. The details of configurations
# are specific to each driver, so please see specific driver
# documentation for more information.
config {
image = "${image}"
command = "gluesparksubmit"
args = [
"--driver-memory", "20g",
"--executor-memory", "20g",
"trending.py"
]
work_dir = "/local/csit/csit.infra.etl"
}
# The env stanza configures a list of environment variables to populate
# the task's environment before starting.
env {
AWS_ACCESS_KEY_ID = "${aws_access_key_id}"
AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}"
AWS_DEFAULT_REGION = "${aws_default_region}"
OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}"
OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}"
OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}"
${ envs }
}
# The "resources" stanza describes the requirements a task needs to
# execute. Resource requirements include memory, network, cpu, and more.
# This ensures the task will execute on a machine that contains enough
# resource capacity.
#
# https://www.nomadproject.io/docs/job-specification/resources
#
resources {
cpu = ${cpu}
memory = ${memory}
}
}
task "${job_name}-stats" {
# The artifact stanza instructs Nomad to fetch and unpack a remote
# resource, such as a file, tarball, or binary.
#
# https://www.nomadproject.io/docs/job-specification/artifact
#
artifact {
source = "git::https://github.com/FDio/csit"
destination = "local/csit"
}
# The "driver" parameter specifies the task driver that should be used to
# run the task.
driver = "docker"
# The "config" stanza specifies the driver configuration, which is passed
# directly to the driver to start the task. The details of configurations
# are specific to each driver, so please see specific driver
# documentation for more information.
config {
image = "${image}"
command = "gluesparksubmit"
args = [
"--driver-memory", "10g",
"--executor-memory", "10g",
"stats.py"
]
work_dir = "/local/csit/csit.infra.etl"
}
# The env stanza configures a list of environment variables to populate
# the task's environment before starting.
env {
AWS_ACCESS_KEY_ID = "${aws_access_key_id}"
AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}"
AWS_DEFAULT_REGION = "${aws_default_region}"
OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}"
OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}"
OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}"
${ envs }
}
# The "resources" stanza describes the requirements a task needs to
# execute. Resource requirements include memory, network, cpu, and more.
# This ensures the task will execute on a machine that contains enough
# resource capacity.
#
# https://www.nomadproject.io/docs/job-specification/resources
#
resources {
cpu = ${cpu}
memory = ${memory}
}
}
}
# group "${job_name}-rls2202" {
# # The restart stanza configures a tasks's behavior on task failure. Restarts
# # happen on the client that is running the task.
# #
# # https://www.nomadproject.io/docs/job-specification/restart
# #
# restart {
# mode = "fail"
# }
#
# # The constraint allows restricting the set of eligible nodes. Constraints
# # may filter on attributes or client metadata.
# #
# # For more information and examples on the "volume" stanza, please see
# # the online documentation at:
# #
# # https://www.nomadproject.io/docs/job-specification/constraint
# #
# constraint {
# attribute = "$${attr.cpu.arch}"
# operator = "!="
# value = "arm64"
# }
#
# constraint {
# attribute = "$${node.class}"
# value = "builder"
# }
#
# # The "task" stanza creates an individual unit of work, such as a Docker
# # container, web application, or batch processing.
# #
# # https://www.nomadproject.io/docs/job-specification/task.html
# #
# task "${job_name}-coverage" {
# # The artifact stanza instructs Nomad to fetch and unpack a remote
# # resource, such as a file, tarball, or binary.
# #
# # https://www.nomadproject.io/docs/job-specification/artifact
# #
# artifact {
# source = "git::https://github.com/FDio/csit"
# destination = "local/csit"
# }
#
# # The "driver" parameter specifies the task driver that should be used to
# # run the task.
# driver = "docker"
#
# # The "config" stanza specifies the driver configuration, which is passed
# # directly to the driver to start the task. The details of configurations
# # are specific to each driver, so please see specific driver
# # documentation for more information.
# config {
# image = "${image}"
# command = "gluesparksubmit"
# args = [
# "--driver-memory", "20g",
# "--executor-memory", "20g",
# "coverage_rls2202.py"
# ]
# work_dir = "/local/csit/csit.infra.etl"
# }
#
# # The env stanza configures a list of environment variables to populate
# # the task's environment before starting.
# env {
# AWS_ACCESS_KEY_ID = "${aws_access_key_id}"
# AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}"
# AWS_DEFAULT_REGION = "${aws_default_region}"
# OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}"
# OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}"
# OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}"
# ${ envs }
# }
#
# # The "resources" stanza describes the requirements a task needs to
# # execute. Resource requirements include memory, network, cpu, and more.
# # This ensures the task will execute on a machine that contains enough
# # resource capacity.
# #
# # https://www.nomadproject.io/docs/job-specification/resources
# #
# resources {
# cpu = ${cpu}
# memory = ${memory}
# }
# }
# task "${job_name}-iterative" {
# # The artifact stanza instructs Nomad to fetch and unpack a remote
# # resource, such as a file, tarball, or binary.
# #
# # https://www.nomadproject.io/docs/job-specification/artifact
# #
# artifact {
# source = "git::https://github.com/FDio/csit"
# destination = "local/csit"
# }
#
# # The "driver" parameter specifies the task driver that should be used to
# # run the task.
# driver = "docker"
#
# # The "config" stanza specifies the driver configuration, which is passed
# # directly to the driver to start the task. The details of configurations
# # are specific to each driver, so please see specific driver
# # documentation for more information.
# config {
# image = "${image}"
# command = "gluesparksubmit"
# args = [
# "--driver-memory", "20g",
# "--executor-memory", "20g",
# "iterative_rls2202.py"
# ]
# work_dir = "/local/csit/csit.infra.etl"
# }
#
# # The env stanza configures a list of environment variables to populate
# # the task's environment before starting.
# env {
# AWS_ACCESS_KEY_ID = "${aws_access_key_id}"
# AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}"
# AWS_DEFAULT_REGION = "${aws_default_region}"
# OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}"
# OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}"
# OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}"
# ${ envs }
# }
#
# # The "resources" stanza describes the requirements a task needs to
# # execute. Resource requirements include memory, network, cpu, and more.
# # This ensures the task will execute on a machine that contains enough
# # resource capacity.
# #
# # https://www.nomadproject.io/docs/job-specification/resources
# #
# resources {
# cpu = ${cpu}
# memory = ${memory}
# }
# }
# }
}
|
