siddharthteotia commented on a change in pull request #6625:
URL: https://github.com/apache/incubator-pinot/pull/6625#discussion_r589662746
##########
File path:
pinot-controller/src/test/resources/recommenderInput/RealtimeProvisioningInput.json
##########
@@ -0,0 +1,170 @@
+{
+ "schema":{
+ "schemaName": "tableSchema",
+ "dimensionFieldSpecs": [
+ {
+ "name": "a",
+ "dataType": "INT",
+ "cardinality":20,
+ "numValuesPerEntry":1
+ },
+ {
+ "name": "b",
+ "dataType": "DOUBLE",
+ "cardinality":6,
+ "numValuesPerEntry":1.5,
+ "singleValueField": false
+ },
+ {
+ "name": "c",
+ "dataType": "FLOAT",
+ "cardinality":7,
+ "numValuesPerEntry":1
+ },
+ {
+ "name": "d",
+ "dataType": "STRING",
+ "cardinality":41,
+ "numValuesPerEntry":2,
+ "averageLength" : 27,
+ "singleValueField": false
+ },
+ {
+ "name": "e",
+ "dataType": "LONG",
+ "cardinality":18,
+ "numValuesPerEntry":4,
+ "singleValueField": false
+ },
+ {
+ "name": "f",
+ "dataType": "DOUBLE",
+ "cardinality":13,
+ "numValuesPerEntry":3,
+ "singleValueField": false
+ },
+ {
+ "name": "g",
+ "dataType": "STRING",
+ "cardinality":6,
+ "numValuesPerEntry":2,
+ "averageLength" : 100,
+ "singleValueField": false
+ },
+ {
+ "name": "h",
+ "dataType": "BYTES",
+ "cardinality":12,
+ "numValuesPerEntry":1,
+ "averageLength" : 10
+ },
+ {
+ "name": "i",
+ "dataType": "STRING",
+ "cardinality":7,
+ "numValuesPerEntry":1,
+ "averageLength" : 25,
+ "singleValueField": false
+ },
+ {
+ "name": "j",
+ "dataType": "DOUBLE",
+ "cardinality":4,
+ "numValuesPerEntry":1.00000001,
+ "singleValueField": false
+ }
+ ],
+ "metricFieldSpecs": [
+ {
+ "name": "k",
+ "dataType": "DOUBLE",
+ "cardinality":1000,
+ "numValuesPerEntry":1,
+ "averageLength" : 100
+ },
+ {
+ "name": "l",
+ "dataType": "STRING",
+ "cardinality":1000,
+ "numValuesPerEntry":1,
+ "averageLength" : 10
+ },
+ {
+ "name": "m",
+ "dataType": "BYTES",
+ "cardinality":1000,
+ "numValuesPerEntry":1,
+ "averageLength" : 25
+ },
+ {
+ "name": "n",
+ "dataType": "DOUBLE",
+ "cardinality":1000,
+ "numValuesPerEntry":1
+ },
+ {
+ "name": "o",
+ "dataType": "DOUBLE",
+ "cardinality":1000,
+ "numValuesPerEntry":1,
+ "averageLength" : 25
+ },
+ {
+ "name": "p",
+ "dataType": "DOUBLE",
+ "cardinality":1000,
+ "numValuesPerEntry":1
+ }
+ ],
+ "timeFieldSpec": {
+ "incomingGranularitySpec": {
+ "dataType": "INT",
+ "name": "t",
+ "timeType": "DAYS",
+ "cardinality":1000,
+ "numValuesPerEntry":1
+ }
+ }
+ },
+ "queriesWithWeights":{
+ "select i from tableName where b in (2,4) and ((a in (1,2,3) and e = 4) or
c = 7) and d in ('#VALUES', 23) and t > 500": 1,
+ "select j from tableName where (a=3 and (h = 5 or f >34) and
REGEXP_LIKE(i, 'as*')) or ((f = 3 or j in ('#VALUES', 4)) and REGEXP_LIKE(d,
'fl*'))": 2,
+ "select f from tableName where (a=0 or (b=1 and (e in ('#VALUES',2) or
c=7))) and TEXT_MATCH(d, 'dasd') and MAX(MAX(h,i),j)=4 and t<3": 4,
+ "select f from tableName where (a=0 and b=1) or c=7 or (d = 7 and e =1)":
2,
+ "select f from tableName where t between 1 and 1000": 2
+ },
+ "qps": 150,
+ "numMessagesPerSecInKafkaTopic":1000,
+ "numRecordsPerPush":10000,
Review comment:
I know for unit/integration tests, we may not want to use a higher
number of records. But locally, have you tested with higher number of records.
IIRC, as part of previous PR, you mentioned going to > = million records ? Just
confirming
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
