-
Notifications
You must be signed in to change notification settings - Fork 5
/
config.pubsub.reference.hocon
77 lines (71 loc) · 2.33 KB
/
config.pubsub.reference.hocon
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
{
"input": {
# Enable the Pubsub source
"type": "PubSub"
# Your GCP project id
"projectId": "my-project"
# Your GCP PubSub subscription id
"subscriptionId": "my-subscription"
# Optional, configure the checkpointer.
"checkpointSettings": {
# The max number of concurrent effects for checkpointer.
# Default is 100.
"maxConcurrent": 100
}
}
"output" : {
# Events that pass validation are written to Postgres.
"good": {
"type": "Postgres"
# PostgreSQL host ('localhost' for enabled SSH Tunnel)
"host": "localhost"
# PostgreSQL database port
"port": 5432
# PostgreSQL database name
"database": "snowplow"
# PostgreSQL user to load data
"username": "postgres"
# PostgreSQL password, either plain text or from an environment variable
"password": "mysecretpassword"
"password": ${?POSTGRES_PASSWORD}
# PostgreSQL database schema
"schema": "atomic"
# JDBC ssl mode
"sslMode": "REQUIRE"
# Maximum number of connections database pool is allowed to reach
# Default is 10
"maxConnections": 10
# Size of the thread pool for blocking database operations
# Default is value of "maxConnections"
"threadPoolSize": 10
}
# Events that fail validation are written to specified stream.
# If this section is removed from config, bad row output will be disabled.
"bad": {
# Enable the Pubsub sink as bad row sink
"type": "PubSub"
# Your GCP project id
"projectId": "my-project"
# Your GCP PubSub topic id
"topicId": "my-topic"
# The delay threshold to use for batching
# Default is 200 milliseconds
"delayThreshold": 200 milliseconds
# Max number of items in the batch to collect before emitting
# Default is 500
"maxBatchSize": 500
# Max size of the batch in bytes before emitting
# Default is 5MB
"maxBatchBytes": 5000000
# Only used when "type" is "Noop" or missing. How often to log number of bad rows discarded.
"reportPeriod": 10 seconds
}
}
# Kind of data stored in this instance. Either ENRICHED_EVENTS or JSON
"purpose": "ENRICHED_EVENTS"
# Minimum and maximum backoff periods
"backoffPolicy": {
"minBackoff": 100 milliseconds
"maxBackoff": 10 seconds
}
}