mirror of
https://github.com/featurebasedb/featurebase.git
synced 2026-09-10 23:11:01 +00:00
b82375bca2
- terraform scripts to set up cluster - cloud-formation scripts to set up cluster - set up ingest node with kafka server and datagen - set up second ingest node with molecula-consumer-kafka-static - set up datadog in all nodes (ingest + featurebase) - set up script to execute different queries - only run delete test on schedule
65 lines
2 KiB
YAML
65 lines
2 KiB
YAML
fields:
|
|
- name: "uuid"
|
|
type: string
|
|
distribution: "shifting" # zipfian distruction and shifting the window over time.
|
|
step: 2 # step for "shifting" distribution means how often do we shift. Every time we generate a value, we'll add an amount to it, every <step> generations, we'll increase the amount by one.
|
|
cardinality: 4000000000
|
|
max_len: 32
|
|
s: 1.0001
|
|
v: 1
|
|
null_chance: 0
|
|
- name: "type"
|
|
type: "int" # (default IntField)
|
|
min: 0
|
|
max: 3
|
|
distribution: "zipfian"
|
|
s: 1.1
|
|
v: 5.1
|
|
- name: "ts"
|
|
type: "timestamp"
|
|
min_date: 2022-01-02T15:04:05.001Z # RFC3339Nano
|
|
max_date: 2022-02-02T15:04:05.001Z # RFC3339Nano
|
|
distribution: "increasing" # only "increasing" is supported right now
|
|
min_step_duration: "1ns"
|
|
max_step_duration: "2.50ms"
|
|
time_format: "unix"
|
|
time_unit: "ms"
|
|
- name: "lastupdated"
|
|
type: "timestamp"
|
|
min_date: 2022-01-02T15:04:05.001Z # RFC3339Nano
|
|
max_date: 2022-02-02T15:04:05.001Z # RFC3339Nano
|
|
distribution: "increasing" # only "increasing" is supported right now
|
|
min_step_duration: "1ns"
|
|
max_step_duration: "2.50ms"
|
|
time_format: "unix"
|
|
time_unit: "d"
|
|
- name: "slice"
|
|
type: "uint-set" # (default IDArrayField)
|
|
min: 0
|
|
max: 35000
|
|
distribution: "zipfian"
|
|
s: 1.1
|
|
v: 5.1
|
|
min_num: 1
|
|
max_num: 50
|
|
|
|
# idk_params describe how data from "fields" should be ingested by IDK
|
|
idk_params:
|
|
primary_key_config:
|
|
field: "uuid" # if this is a single field named "id" then we'll use uint IDs, if it's empty we'll autogen ids, and if it's anything else we'll do string keys... yes this is a bit hacky, needs to be cleaned up.
|
|
# fields is keyed by names of fields from top level "fields". It is
|
|
# not required that all fields appear here, those that don't will
|
|
# use the default ingestion.
|
|
fields:
|
|
lastupdated:
|
|
- type: "ID"
|
|
ts:
|
|
- type: "RecordTime"
|
|
unit: "ms"
|
|
name: "timestamp"
|
|
slice:
|
|
- type: "IDArray"
|
|
quantum: "D"
|
|
name: "segid"
|
|
type:
|
|
- type: "ID"
|