forked from apache/pulsar
-
Notifications
You must be signed in to change notification settings - Fork 0
/
functions_worker.yml
319 lines (281 loc) · 13 KB
/
functions_worker.yml
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
#
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
#
####################
# Worker Settings
####################
workerId: standalone
workerHostname: localhost
workerPort: 6750
workerPortTls: 6751
# Configuration Store connection string
configurationStoreServers: localhost:2181
# ZooKeeper session timeout in milliseconds
zooKeeperSessionTimeoutMillis: 30000
# ZooKeeper operation timeout in seconds
zooKeeperOperationTimeoutSeconds: 30
################################
# Function package management
################################
numFunctionPackageReplicas: 1
downloadDirectory: download/pulsar_functions
# Classname of Pluggable JVM GC metrics logger that can log GC specific metrics
# jvmGCMetricsLoggerClassName:
#################################################################
# Function metadata managment (assignment, scheduling, and etc)
#################################################################
# Configure the pulsar client used by function metadata management
#
# points
# Whether to enable TLS when clients connect to broker
useTls: false
# For TLS:
# brokerServiceUrl=pulsar+ssl://localhost:6651/
pulsarServiceUrl: pulsar://localhost:6650
# For TLS:
# webServiceUrl=https://localhost:8443/
pulsarWebServiceUrl: http://localhost:8080
############################################
# security settings for pulsar broker client
############################################
# The path to trusted certificates used by the Pulsar client to authenticate with Pulsar brokers
# brokerClientTrustCertsFilePath:
# Whether to enable the broker client authentication used by function workers to talk to brokers
# brokerClientAuthenticationEnabled: false
# the authentication plugin to be used by the pulsar client used in worker service
# brokerClientAuthenticationPlugin:
# the authentication parameter to be used by the pulsar client used in worker service
# brokerClientAuthenticationParameters:
# Bookie Authentication
#
# Authentication plugin to use when connecting to bookies
# bookkeeperClientAuthenticationPlugin:
# BookKeeper auth plugin implementatation specifics parameters name and values
# bookkeeperClientAuthenticationParametersName:
# Parameters for bookkeeper auth plugin
# bookkeeperClientAuthenticationParameters:
# pulsar topics used for function metadata management
pulsarFunctionsNamespace: public/functions
pulsarFunctionsCluster: standalone
functionMetadataTopicName: metadata
clusterCoordinationTopicName: coordinate
# Should the metadata topic be compacted? Defaulting it to false for backwards compatibility
useCompactedMetadataTopic: false
# Number of threads to use for HTTP requests processing. Default is set to 8
numHttpServerThreads: 8
# function assignment and scheduler
schedulerClassName: "org.apache.pulsar.functions.worker.scheduler.RoundRobinScheduler"
functionAssignmentTopicName: "assignments"
failureCheckFreqMs: 30000
rescheduleTimeoutMs: 60000
# frequency at which to check if cluster needs rebalancing (set to -1 to disable)
rebalanceCheckFreqSec: -1
initialBrokerReconnectMaxRetries: 60
assignmentWriteMaxRetries: 60
instanceLivenessCheckFreqMs: 30000
# Frequency how often worker performs compaction on function-topics
topicCompactionFrequencySec: 1800
# should the function context have pulsar admin client exposed? Default is disabled.
exposeAdminClientEnabled: false
###############################
# Function Runtime Management
###############################
#### Process Runtime ####
# Pulsar function instances are launched as processes
functionRuntimeFactoryClassName: org.apache.pulsar.functions.runtime.process.ProcessRuntimeFactory
functionRuntimeFactoryConfigs:
# location of log files for functions
logDirectory: logs/
# change the jar location only when you put the java instance jar in a different location
javaInstanceJarLocation:
# change the python instance location only when you put the python instance jar in a different location
pythonInstanceLocation:
# change the extra dependencies location:
extraFunctionDependenciesDir:
#### Thread Runtime ####
# Pulsar function instances are run as threads
#functionRuntimeFactoryClassName: org.apache.pulsar.functions.runtime.thread.ThreadRuntimeFactory
#functionRuntimeFactoryConfigs:
# # thread group name
# threadGroupName: "Thread Function Container Group"
## Set the pulsar client memory limit
#pulsarClientMemoryLimit
# # the max memory in bytes the pulsar client can use
# absoluteValue:
# # the max memory the pulsar client can use as a percentage of max direct memory set for JVM
# percentOfMaxDirectMemory:
#### Kubernetes Runtime ####
# Pulsar function are deployed to Kubernetes
#functionRuntimeFactoryClassName: org.apache.pulsar.functions.runtime.kubernetes.KubernetesRuntimeFactory
#functionRuntimeFactoryConfigs:
# # uri to kubernetes cluster, leave it to empty and it will use the kubernetes settings in function worker
# k8Uri:
# # the kubernetes namespace to run the function instances. it is `default`, if this setting is left to be empty
# jobNamespace:
# # The Kubernetes pod name to run the function instances. It is set to
# # `pf-<tenant>-<namespace>-<function_name>-<random_uuid(8)>` if this setting is left to be empty
# jobName:
# # the docker image to run function instance. by default it is `apachepulsar/pulsar`
# pulsarDockerImageName:
# # the docker image to run function instance according to different configurations provided by users.
# # By default it is `apachepulsar/pulsar`.
# # e.g:
# # functionDockerImages:
# # JAVA: JAVA_IMAGE_NAME
# # PYTHON: PYTHON_IMAGE_NAME
# # GO: GO_IMAGE_NAME
# functionDockerImages:
# # "The image pull policy for image used to run function instance. By default it is `IfNotPresent`
# imagePullPolicy: IfNotPresent
# # the root directory of pulsar home directory in `pulsarDockerImageName`. by default it is `/pulsar`.
# # if you are using your own built image in `pulsarDockerImageName`, you need to set this setting accordingly
# pulsarRootDir:
# # The config admin CLI allows users to customize the configuration of the admin cli tool, such as:
# # `/bin/pulsar-admin and /bin/pulsarctl`. By default it is `/bin/pulsar-admin`. If you want to use `pulsarctl`
# # you need to set this setting accordingly
# configAdminCLI:
# # this setting only takes effects if `k8Uri` is set to null. if your function worker is running as a k8 pod,
# # setting this to true is let function worker to submit functions to the same k8s cluster as function worker
# # is running. setting this to false if your function worker is not running as a k8 pod.
# submittingInsidePod: false
# # setting the pulsar service url that pulsar function should use to connect to pulsar
# # if it is not set, it will use the pulsar service url configured in worker service
# pulsarServiceUrl:
# # setting the pulsar admin url that pulsar function should use to connect to pulsar
# # if it is not set, it will use the pulsar admin url configured in worker service
# pulsarAdminUrl:
# # The flag indicates to install user code dependencies. (applied to python package)
# installUserCodeDependencies:
# # The repository that pulsar functions use to download python dependencies
# pythonDependencyRepository:
# # The repository that pulsar functions use to download extra python dependencies
# pythonExtraDependencyRepository:
# # the custom labels that function worker uses to select the nodes for pods
# customLabels:
# # The expected metrics collection interval, in seconds
# expectedMetricsCollectionInterval: 30
# # Kubernetes Runtime will periodically checkback on
# # this configMap if defined and if there are any changes
# # to the kubernetes specific stuff, we apply those changes
# changeConfigMap:
# # The namespace for storing change config map
# changeConfigMapNamespace:
# # The ratio cpu request and cpu limit to be set for a function/source/sink.
# # The formula for cpu request is cpuRequest = userRequestCpu / cpuOverCommitRatio
# cpuOverCommitRatio: 1.0
# # The ratio memory request and memory limit to be set for a function/source/sink.
# # The formula for memory request is memoryRequest = userRequestMemory / memoryOverCommitRatio
# memoryOverCommitRatio: 1.0
# # The port inside the function pod which is used by the worker to communicate with the pod
# grpcPort: 9093
# # The port inside the function pod on which prometheus metrics are exposed
# metricsPort: 9094
# # The directory inside the function pod where nar packages will be extracted
# narExtractionDirectory:
# # The classpath where function instance files stored
# functionInstanceClassPath:
# # the directory for dropping extra function dependencies
# # if it is not an absolute path, it is relative to `pulsarRootDir`
# extraFunctionDependenciesDir:
# # Additional memory padding added on top of the memory requested by the function per on a per instance basis
# percentMemoryPadding: 10
## A set of the minimum amount of resources functions must request.
## Support for this depends on function runtime.
## Only kubernetes runtime currently supports this.
# functionInstanceMinResources:
# cpu: 1
# ram: 1073741824
# disk: 10737418240
## A set of the maximum amount of resources functions may request.
## Support for this depends on function runtime.
## Only kubernetes runtime currently supports this.
# functionInstanceMaxResources:
# cpu: 16
# ram: 17179869184
# disk: 107374182400
## Granularities of requested resources.
## If the granularity of any type of resource is set,
## the requested resource of the type must be a multiple of the granularity.
#functionInstanceResourceGranularities:
# cpu: 1.0
# ram: 1073741824
# disk: 10737418240
## If this configuration is set to be true, the amount of requested resources of all type of resources
## that have the granularity set must be the same multiples of their granularities.
#functionInstanceResourceChangeInLockStep: true
## The full class-name of an instance of RuntimeCustomizer.
## This class receives the customRuntimeOptions string and can customize details of how the runtime operates.
#runtimeCustomizerClassName: "org.apache.pulsar.functions.runtime.kubernetes.KubernetesManifestCustomizer"
## This config will pass to RuntimeCustomizer's initialize function to do initializing.
#runtimeCustomizerConfig:
# extractLabels:
# extraLabel: value
# extraAnnotations:
# extraAnnotation: value
# nodeSelectorLabels:
# customLabel: value
# jobNamespace: namespace
# tolerations:
# - key: custom-key
# value: value
# effect: NoSchedule
## Config admin CLI
#configAdminCLI:
############################################
# security settings for worker service
############################################
# Enforce authentication
authenticationEnabled: false
# Enforce authorization on accessing functions api
authorizationEnabled: false
# Set of authentication provider name list, which is a list of class names
authenticationProviders:
# Authorization provider fully qualified class-name
authorizationProvider: org.apache.pulsar.broker.authorization.PulsarAuthorizationProvider
# Set of role names that are treated as "super-user", meaning they will be able to access any admin-api
superUserRoles:
#### tls configuration for worker service
# Enable TLS
tlsEnabled: false
# Path for the TLS certificate file
tlsCertificateFilePath:
# Path for the TLS private key file
tlsKeyFilePath:
# Path for the trusted TLS certificate file
tlsTrustCertsFilePath:
# Accept untrusted TLS certificate from client
tlsAllowInsecureConnection: false
# Whether server hostname must match the common name of the certificate
tlsEnableHostnameVerification: false
# Tls cert refresh duration in seconds (set 0 to check on every new connection)
tlsCertRefreshCheckDurationSec: 300
########################
# State Management
########################
# the service url points to bookkeeper table service
# stateStorageServiceUrl: bk://localhost:4181
########################
# Connectors
########################
connectorsDirectory: ./connectors
functionsDirectory: ./functions
# Should connector config be validated during during submission
validateConnectorConfig: false
# Whether to initialize distributed log metadata by runtime.
# If it is set to true, you must ensure that it has been initialized by "bin/pulsarinitialize-cluster-metadata" command.
initializedDlogMetadata: false