forked from broadinstitute/cromwell
-
Notifications
You must be signed in to change notification settings - Fork 0
/
cromwell.examples.conf
809 lines (714 loc) · 28.7 KB
/
cromwell.examples.conf
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
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
# This line is required. It pulls in default overrides from the embedded cromwell `application.conf` needed for proper
# performance of cromwell.
include required(classpath("application"))
# Cromwell HTTP server settings
webservice {
#port = 8000
#interface = 0.0.0.0
#binding-timeout = 5s
#instance.name = "reference"
}
akka {
# Optionally set / override any akka settings
}
# Cromwell "system" settings
system {
# If 'true', a SIGINT will trigger Cromwell to attempt to abort all currently running jobs before exiting
#abort-jobs-on-terminate = false
# If 'true', a SIGTERM or SIGINT will trigger Cromwell to attempt to gracefully shutdown in server mode,
# in particular clearing up all queued database writes before letting the JVM shut down.
# The shutdown is a multi-phase process, each phase having its own configurable timeout. See the Dev Wiki for more details.
#graceful-server-shutdown = true
# If 'true' then when Cromwell starts up, it tries to restart incomplete workflows
#workflow-restart = true
# Cromwell will cap the number of running workflows at N
#max-concurrent-workflows = 5000
# Cromwell will launch up to N submitted workflows at a time, regardless of how many open workflow slots exist
#max-workflow-launch-count = 50
# Number of seconds between workflow launches
#new-workflow-poll-rate = 20
# Since the WorkflowLogCopyRouter is initialized in code, this is the number of workers
#number-of-workflow-log-copy-workers = 10
# Default number of cache read workers
#number-of-cache-read-workers = 25
io {
# Global Throttling - This is mostly useful for GCS and can be adjusted to match
# the quota availble on the GCS API
#number-of-requests = 100000
#per = 100 seconds
# Number of times an I/O operation should be attempted before giving up and failing it.
#number-of-attempts = 5
}
# Maximum number of input file bytes allowed in order to read each type.
# If exceeded a FileSizeTooBig exception will be thrown.
input-read-limits {
#lines = 128000
#bool = 7
#int = 19
#float = 50
#string = 128000
#json = 128000
#tsv = 128000
#map = 128000
#object = 128000
}
}
workflow-options {
# These workflow options will be encrypted when stored in the database
#encrypted-fields: []
# AES-256 key to use to encrypt the values in `encrypted-fields`
#base64-encryption-key: "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA="
# Directory where to write per workflow logs
#workflow-log-dir: "cromwell-workflow-logs"
# When true, per workflow logs will be deleted after copying
#workflow-log-temporary: true
# Workflow-failure-mode determines what happens to other calls when a call fails. Can be either ContinueWhilePossible or NoNewCalls.
# Can also be overridden in workflow options. Defaults to NoNewCalls. Uncomment to change:
#workflow-failure-mode: "ContinueWhilePossible"
default {
# When a workflow type is not provided on workflow submission, this specifies the default type.
#workflow-type: WDL
# When a workflow type version is not provided on workflow submission, this specifies the default type version.
#workflow-type-version: "draft-2"
}
}
# Optional call-caching configuration.
call-caching {
# Allows re-use of existing results for jobs you've already run
# (default: false)
#enabled = false
# Whether to invalidate a cache result forever if we cannot reuse them. Disable this if you expect some cache copies
# to fail for external reasons which should not invalidate the cache (e.g. auth differences between users):
# (default: true)
#invalidate-bad-cache-results = true
}
# Google configuration
google {
#application-name = "cromwell"
# Default: just application default
#auths = [
# Application default
#{
# name = "application-default"
# scheme = "application_default"
#},
# Use a refresh token
#{
# name = "user-via-refresh"
# scheme = "refresh_token"
# client-id = "secret_id"
# client-secret = "secret_secret"
#},
# Use a static service account
#{
# name = "service-account"
# scheme = "service_account"
# Choose between PEM file and JSON file as a credential format. They're mutually exclusive.
# PEM format:
# service-account-id = "my-service-account"
# pem-file = "/path/to/file.pem"
# JSON format:
# json-file = "/path/to/file.json"
#}
# Use service accounts provided through workflow options
#{
# name = "user-service-account"
# scheme = "user_service_account"
#}
#]
}
docker {
hash-lookup {
# Set this to match your available quota against the Google Container Engine API
#gcr-api-queries-per-100-seconds = 1000
# Time in minutes before an entry expires from the docker hashes cache and needs to be fetched again
#cache-entry-ttl = "20 minutes"
# Maximum number of elements to be kept in the cache. If the limit is reached, old elements will be removed from the cache
#cache-size = 200
# How should docker hashes be looked up. Possible values are "local" and "remote"
# "local": Lookup hashes on the local docker daemon using the cli
# "remote": Lookup hashes on docker hub and gcr
#method = "remote"
}
}
engine {
# This instructs the engine which filesystems are at its disposal to perform any IO operation that it might need.
# For instance, WDL variables declared at the Workflow level will be evaluated using the filesystems declared here.
# If you intend to be able to run workflows with this kind of declarations:
# workflow {
# String str = read_string("gs://bucket/my-file.txt")
# }
# You will need to provide the engine with a gcs filesystem
# Note that the default filesystem (local) is always available.
filesystems {
# gcs {
# auth = "application-default"
# # Google project which will be billed for the requests
# project = "google-billing-project"
# }
# oss {
# auth {
# endpoint = ""
# access-id = ""
# access-key = ""
# security-token = ""
# }
# }
local {
#enabled: true
}
}
}
# You probably don't want to override the language factories here, but the strict-validation and enabled fields might be of interest:
#
# `enabled`: Defaults to `true`. Set to `false` to disallow workflows of this language/version from being run.
# `strict-validation`: Specifies whether workflows fail if the inputs JSON (or YAML) file contains values which the workflow did not ask for (and will therefore have no effect).
languages {
WDL {
versions {
"draft-2" {
# language-factory = "languages.wdl.draft2.WdlDraft2LanguageFactory"
# config {
# strict-validation: true
# enabled: true
# }
}
# draft-3 is the same as 1.0 so files should be able to be submitted to Cromwell as 1.0
# "draft-3" {
# language-factory = "languages.wdl.draft3.WdlDraft3LanguageFactory"
# config {
# strict-validation: true
# enabled: true
# }
# }
"1.0" {
# 1.0 is just a rename of draft-3, so yes, they really do use the same factory:
# language-factory = "languages.wdl.draft3.WdlDraft3LanguageFactory"
# config {
# strict-validation: true
# enabled: true
# }
}
}
}
CWL {
versions {
"v1.0" {
# language-factory = "languages.cwl.CwlV1_0LanguageFactory"
# config {
# strict-validation: false
# enabled: true
# }
}
}
}
}
backend {
# Override the default backend.
#default = "LocalExample"
# The list of providers.
providers {
# The local provider is included by default in the reference.conf. This is an example.
# Define a new backend provider.
LocalExample {
# The actor that runs the backend. In this case, it's the Shared File System (SFS) ConfigBackend.
actor-factory = "cromwell.backend.impl.sfs.config.ConfigBackendLifecycleActorFactory"
# The backend custom configuration.
config {
# Optional limits on the number of concurrent jobs
#concurrent-job-limit = 5
# If true submits scripts to the bash background using "&". Only usefull for dispatchers that do NOT submit
# the job and then immediately return a scheduled job id.
run-in-background = true
# `temporary-directory` creates the temporary directory for commands.
#
# If this value is not set explicitly, the default value creates a unique temporary directory, equivalent to:
# temporary-directory = "mktemp -d \"$PWD\"/tmp.XXXXXX"
#
# The expression is run from the execution directory for the script. The expression must create the directory
# if it does not exist, and then return the full path to the directory.
#
# To create and return a non-random temporary directory, use something like:
# temporary-directory = "mkdir -p /tmp/mydir && echo /tmp/mydir"
# `script-epilogue` configures a shell command to run after the execution of every command block.
#
# If this value is not set explicitly, the default value is `sync`, equivalent to:
# script-epilogue = "sync"
#
# To turn off the default `sync` behavior set this value to an empty string:
# script-epilogue = ""
# The list of possible runtime custom attributes.
runtime-attributes = """
String? docker
String? docker_user
"""
# Submit string when there is no "docker" runtime attribute.
submit = "/usr/bin/env bash ${script}"
# Submit string when there is a "docker" runtime attribute.
submit-docker = """
docker run \
--rm -i \
${"--user " + docker_user} \
--entrypoint ${job_shell} \
-v ${cwd}:${docker_cwd} \
${docker} ${script}
"""
# Root directory where Cromwell writes job results. This directory must be
# visible and writeable by the Cromwell process as well as the jobs that Cromwell
# launches.
root = "cromwell-executions"
# File system configuration.
filesystems {
# For SFS backends, the "local" configuration specifies how files are handled.
local {
# Try to hard link (ln), then soft-link (ln -s), and if both fail, then copy the files.
localization: [
"hard-link", "soft-link", "copy"
]
# Call caching strategies
caching {
# When copying a cached result, what type of file duplication should occur. Attempted in the order listed below:
duplication-strategy: [
"hard-link", "soft-link", "copy"
]
# Possible values: file, path
# "file" will compute an md5 hash of the file content.
# "path" will compute an md5 hash of the file path. This strategy will only be effective if the duplication-strategy (above) is set to "soft-link",
# in order to allow for the original file path to be hashed.
hashing-strategy: "file"
# When true, will check if a sibling file with the same name and the .md5 extension exists, and if it does, use the content of this file as a hash.
# If false or the md5 does not exist, will proceed with the above-defined hashing strategy.
check-sibling-md5: false
}
}
}
# The defaults for runtime attributes if not provided.
default-runtime-attributes {
failOnStderr: false
continueOnReturnCode: 0
}
}
}
# Other backend examples. Uncomment the block/stanza for your configuration. May need more tweaking/configuration
# for your specific environment.
#TES {
# actor-factory = "cromwell.backend.impl.tes.TesBackendLifecycleActorFactory"
# config {
# root = "cromwell-executions"
# dockerRoot = "/cromwell-executions"
# endpoint = "http://127.0.0.1:9000/v1/tasks"
# default-runtime-attributes {
# cpu: 1
# failOnStderr: false
# continueOnReturnCode: 0
# memory: "2 GB"
# disk: "2 GB"
# }
# }
#}
#BCS {
# actor-factory = "cromwell.backend.impl.bcs.BcsBackendLifecycleActorFactory"
# config {
# root = "oss://your-bucket/cromwell-exe"
# dockerRoot = "/cromwell-executions"
# region = ""
# #access-id = ""
# #access-key = ""
# #security-token = ""
# filesystems {
# oss {
# auth {
# #endpoint = ""
# #access-id = ""
# #access-key = ""
# #security-token = ""
# }
# }
# }
# default-runtime-attributes {
# #failOnStderr: false
# #continueOnReturnCode: 0
# #cluster: "cls-mycluster"
# #mounts: "oss://bcs-bucket/bcs-dir/ /home/inputs/ false"
# #docker: "ubuntu/latest oss://bcs-reg/ubuntu/"
# #userData: "key value"
# #reserveOnFail: true
# #autoReleaseJob: true
# #verbose: false
# #workerPath: "oss://bcs-bucket/workflow/worker.tar.gz"
# #systemDisk: "cloud 50"
# #dataDisk: "cloud 250 /home/data/"
# #timeout: 3000
# #vpc: "192.168.0.0/16 vpc-xxxx"
# }
# }
#}
#SGE {
# actor-factory = "cromwell.backend.impl.sfs.config.ConfigBackendLifecycleActorFactory"
# config {
#
# # Limits the number of concurrent jobs
# concurrent-job-limit = 5
#
# runtime-attributes = """
# Int cpu = 1
# Float? memory_gb
# String? sge_queue
# String? sge_project
# """
#
# submit = """
# qsub \
# -terse \
# -V \
# -b y \
# -N ${job_name} \
# -wd ${cwd} \
# -o ${out}.qsub \
# -e ${err}.qsub \
# -pe smp ${cpu} \
# ${"-l mem_free=" + memory_gb + "g"} \
# ${"-q " + sge_queue} \
# ${"-P " + sge_project} \
# /usr/bin/env bash ${script}
# """
#
# kill = "qdel ${job_id}"
# check-alive = "qstat -j ${job_id}"
# job-id-regex = "(\\d+)"
# }
#}
#LSF {
# actor-factory = "cromwell.backend.impl.sfs.config.ConfigBackendLifecycleActorFactory"
# config {
# submit = "bsub -J ${job_name} -cwd ${cwd} -o ${out} -e ${err} /usr/bin/env bash ${script}"
# kill = "bkill ${job_id}"
# check-alive = "bjobs ${job_id}"
# job-id-regex = "Job <(\\d+)>.*"
# }
#}
#SLURM {
# actor-factory = "cromwell.backend.impl.sfs.config.ConfigBackendLifecycleActorFactory"
# config {
# runtime-attributes = """
# Int runtime_minutes = 600
# Int cpus = 2
# Int requested_memory_mb_per_core = 8000
# String queue = "short"
# """
#
# submit = """
# sbatch -J ${job_name} -D ${cwd} -o ${out} -e ${err} -t ${runtime_minutes} -p ${queue} \
# ${"-n " + cpus} \
# --mem-per-cpu=${requested_memory_mb_per_core} \
# --wrap "/usr/bin/env bash ${script}"
# """
# kill = "scancel ${job_id}"
# check-alive = "squeue -j ${job_id}"
# job-id-regex = "Submitted batch job (\\d+).*"
# }
#}
# Example backend that _only_ runs workflows that specify docker for every command.
#Docker {
# actor-factory = "cromwell.backend.impl.sfs.config.ConfigBackendLifecycleActorFactory"
# config {
# run-in-background = true
# runtime-attributes = "String docker"
# submit-docker = "docker run --rm -v ${cwd}:${docker_cwd} -i ${docker} /bin/bash < ${script}"
# }
#}
#HtCondor {
# actor-factory = "cromwell.backend.impl.sfs.config.ConfigBackendLifecycleActorFactory"
# config {
# runtime-attributes = """
# Int cpu = 1
# Float memory_mb = 512.0
# Float disk_kb = 256000.0
# String? nativeSpecs
# String? docker
# """
#
# submit = """
# chmod 755 ${script}
# cat > ${cwd}/execution/submitFile <<EOF
# Iwd=${cwd}/execution
# requirements=${nativeSpecs}
# leave_in_queue=true
# request_memory=${memory_mb}
# request_disk=${disk_kb}
# error=${err}
# output=${out}
# log_xml=true
# request_cpus=${cpu}
# executable=${script}
# log=${cwd}/execution/execution.log
# queue
# EOF
# condor_submit ${cwd}/execution/submitFile
# """
#
# submit-docker = """
# chmod 755 ${script}
# cat > ${cwd}/execution/dockerScript <<EOF
# #!/bin/bash
# docker run --rm -i -v ${cwd}:${docker_cwd} ${docker} /bin/bash ${script}
# EOF
# chmod 755 ${cwd}/execution/dockerScript
# cat > ${cwd}/execution/submitFile <<EOF
# Iwd=${cwd}/execution
# requirements=${nativeSpecs}
# leave_in_queue=true
# request_memory=${memory_mb}
# request_disk=${disk_kb}
# error=${cwd}/execution/stderr
# output=${cwd}/execution/stdout
# log_xml=true
# request_cpus=${cpu}
# executable=${cwd}/execution/dockerScript
# log=${cwd}/execution/execution.log
# queue
# EOF
# condor_submit ${cwd}/execution/submitFile
# """
#
# kill = "condor_rm ${job_id}"
# check-alive = "condor_q ${job_id}"
# job-id-regex = "(?sm).*cluster (\\d+)..*"
# }
#}
#Spark {
# actor-factory = "cromwell.backend.impl.spark.SparkBackendFactory"
# config {
# # Root directory where Cromwell writes job results. This directory must be
# # visible and writeable by the Cromwell process as well as the jobs that Cromwell
# # launches.
# root: "cromwell-executions"
#
# filesystems {
# local {
# localization: [
# "hard-link", "soft-link", "copy"
# ]
# }
# }
# # change (master, deployMode) to (yarn, client), (yarn, cluster)
# # or (spark://hostname:port, cluster) for spark standalone cluster mode
# master: "local"
# deployMode: "client"
# }
# }
#PAPI {
# actor-factory = "cromwell.backend.google.pipelines.v2alpha1.PipelinesApiLifecycleActorFactory"
# config {
# # Google project
# project = "my-cromwell-workflows"
#
# # Base bucket for workflow executions
# root = "gs://my-cromwell-workflows-bucket"
#
# # Set this to the lower of the two values "Queries per 100 seconds" and "Queries per 100 seconds per user" for
# # your project.
# #
# # Used to help determine maximum throughput to the Google Genomics API. Setting this value too low will
# # cause a drop in performance. Setting this value too high will cause QPS based locks from Google.
# # 1000 is the default "Queries per 100 seconds per user", 50000 is the default "Queries per 100 seconds"
# # See https://cloud.google.com/genomics/quotas for more information
# genomics-api-queries-per-100-seconds = 1000
#
# # Polling for completion backs-off gradually for slower-running jobs.
# # This is the maximum polling interval (in seconds):
# maximum-polling-interval = 600
#
# # Optional Dockerhub Credentials. Can be used to access private docker images.
# dockerhub {
# # account = ""
# # token = ""
# }
#
# # Number of workers to assaign to PAPI requests
# request-workers = 3
#
# genomics {
# # A reference to an auth defined in the `google` stanza at the top. This auth is used to create
# # Pipelines and manipulate auth JSONs.
# auth = "application-default"
#
#
# // alternative service account to use on the launched compute instance
# // NOTE: If combined with service account authorization, both that serivce account and this service account
# // must be able to read and write to the 'root' GCS path
# compute-service-account = "default"
#
# # Endpoint for APIs, no reason to change this unless directed by Google.
# endpoint-url = "https://genomics.googleapis.com/"
#
# # Restrict access to VM metadata. Useful in cases when untrusted containers are running under a service
# # account not owned by the submitting user
# restrict-metadata-access = false
# }
#
# filesystems {
# gcs {
# # A reference to a potentially different auth for manipulating files via engine functions.
# auth = "application-default"
# # Google project which will be billed for the requests
# project = "google-billing-project"
#
# caching {
# # When a cache hit is found, the following duplication strategy will be followed to use the cached outputs
# # Possible values: "copy", "reference". Defaults to "copy"
# # "copy": Copy the output files
# # "reference": DO NOT copy the output files but point to the original output files instead.
# # Will still make sure than all the original output files exist and are accessible before
# # going forward with the cache hit.
# duplication-strategy = "copy"
# }
# }
# }
#
# default-runtime-attributes {
# cpu: 1
# failOnStderr: false
# continueOnReturnCode: 0
# memory: "2048 MB"
# bootDiskSizeGb: 10
# # Allowed to be a String, or a list of Strings
# disks: "local-disk 10 SSD"
# noAddress: false
# preemptible: 0
# zones: ["us-central1-a", "us-central1-b"]
# }
# }
#}
#AWS {
# actor-factory = "cromwell.backend.impl.aws.AwsBackendActorFactory"
# config {
# ## These two settings are required to authenticate with the ECS service:
# accessKeyId = "..."
# secretKey = "..."
# }
#}
}
}
services {
MetadataService {
config {
# For the standard MetadataService implementation, cromwell.services.metadata.impl.MetadataServiceActor:
# Set this value to "Inf" to turn off metadata summary refresh. The default value is currently "2 seconds".
# metadata-summary-refresh-interval = "Inf"
# For higher scale environments, e.g. many workflows and/or jobs, DB write performance for metadata events
# can improved by writing to the database in batches. Increasing this value can dramatically improve overall
# performance but will both lead to a higher memory usage as well as increase the risk that metadata events
# might not have been persisted in the event of a Cromwell crash.
#
# For normal usage the default value of 200 should be fine but for larger/production environments we recommend a
# value of at least 500. There'll be no one size fits all number here so we recommend benchmarking performance and
# tuning the value to match your environment.
# db-batch-size = 200
#
# Periodically the stored metadata events will be forcibly written to the DB regardless of if the batch size
# has been reached. This is to prevent situations where events wind up never being written to an incomplete batch
# with no new events being generated. The default value is currently 5 seconds
# db-flush-rate = 5 seconds
# For the Google PubSub MetadataService implementation: cromwell.services.metadata.impl.pubsub.PubSubMetadataServiceActor:
# Google project
# project = "my-project"
# The auth *must* be a service-account auth with JSON auth.
# auth = "service-account"
# The PubSub topic to write to. Will be created if it doesn't already exist. Defaults to "cromwell-metadata"
# topic = "cromwell-metadata"
# An optional PubSub subscription name. If supplied and if it doesn't already exist, it will be created and
# subscribed to the topic
# subscription = "optional-subscription"
# An application name to set on your PubSub interaction.
# appName = "cromwell"
}
}
Instrumentation {
# StatsD - Send metrics to a StatsD server over UDP
# class = "cromwell.services.instrumentation.impl.statsd.StatsDInstrumentationServiceActor"
# config.statsd {
# hostname = "localhost"
# port = 8125
# prefix = "" # can be used to prefix all metrics with an api key for example
# flush-rate = 1 second # rate at which aggregated metrics will be sent to statsd
# }
}
HealthMonitor {
config {
# How long to wait between status check sweeps
# check-refresh-time = 5 minutes
# For any given status check, how long to wait before assuming failure
# check-timeout = 1 minute
# For any given status datum, the maximum time a value will be kept before reverting back to "Unknown"
# status-ttl = 15 minutes
# For any given status check, how many times to retry a failure before setting status to failed. Note this
# is the number of retries before declaring failure, not the total number of tries which is 1 more than
# the number of retries.
# check-failure-retry-count = 3
# For any given status check, how long to wait between failure retries.
# check-failure-retry-interval = 30 seconds
## When using the WorkbenchHealthMonitorServiceActor, the following are possibilities
# This *MUST* be set to the name of the PAPI (aka JES) backend one defined in the Backends stanza. Most likely
# it is "Jes" or "JES"
# papi-backend-name = JES
# The name of an authentication scheme to use for e.g. pinging PAPI and GCS. This should be either an application
# default or service account auth, otherwise things won't work as there'll not be a refresh token where you need
# them.
# google-auth-name = application-default
# A bucket in GCS to periodically stat to check for connectivity. This must be accessible by the auth mode
# specified by google-auth-name
# gcs-bucket-to-check = some-bucket-name
}
}
LoadController {
config {
# The load controller service will periodically look at the status of various metrics its collecting and make an
# assessment of the system's load. If necessary an alert will be sent to the rest of the system.
# This option sets how frequently this should happen
# To disable load control, set this to "Inf"
# control-frequency = 5 seconds
}
}
}
database {
# mysql example
#driver = "slick.driver.MySQLDriver$"
# see all possible parameters and default values here:
# http://slick.lightbend.com/doc/3.2.0/api/index.html#slick.jdbc.JdbcBackend$DatabaseFactoryDef@forConfig(String,Config,Driver):Database
#db {
# driver = "com.mysql.jdbc.Driver"
# url = "jdbc:mysql://host/cromwell?rewriteBatchedStatements=true"
# user = "user"
# password = "pass"
# connectionTimeout = 5000
#}
# For batch inserts the number of inserts to send to the DB at a time
# insert-batch-size = 2000
migration {
# For databases with a very large number of symbols, selecting all the rows at once can generate a variety of
# problems. In order to avoid any issue, the selection is paginated. This value sets how many rows should be
# retrieved and processed at a time, before asking for the next chunk.
#read-batch-size = 100000
# Because a symbol row can contain any arbitrary wdl value, the amount of metadata rows to insert from a single
# symbol row can vary from 1 to several thousands (or more). To keep the size of the insert batch from growing out
# of control we monitor its size and execute/commit when it reaches or exceeds writeBatchSize.
#write-batch-size = 100000
}
# To customize the metadata database connection, create a block under `database` with the metadata database settings.
#
# For example, the default database stores all data in memory. This commented out block would store `metadata` in an
# hsqldb file, without modifying the internal engine database connection.
#
# The value `${uniqueSchema}` is always replaced with a unqiue UUID on each cromwell startup.
#
# This feature should be considered experimental and likely to change in the future.
#metadata {
# profile = "slick.jdbc.HsqldbProfile$"
# db {
# driver = "org.hsqldb.jdbcDriver"
# url = "jdbc:hsqldb:file:metadata-${uniqueSchema};shutdown=false;hsqldb.tx=mvcc"
# connectionTimeout = 3000
# }
#}
}