[2020/03/03-10:58:27.427] [ActivityExecutor-28] [INFO] [dku] running compute_web_history_prepared_joined_NP - ---------------------------------------- [2020/03/03-10:58:27.427] [ActivityExecutor-28] [INFO] [dku] running compute_web_history_prepared_joined_NP - DSS startup: jek version:5.1.5 [2020/03/03-10:58:27.427] [ActivityExecutor-28] [INFO] [dku] running compute_web_history_prepared_joined_NP - DSS home: /appl/dataiku/dss_data [2020/03/03-10:58:27.427] [ActivityExecutor-28] [INFO] [dku] running compute_web_history_prepared_joined_NP - OS: Linux 3.10.0-1062.9.1.el7.x86_64 amd64 - Java: Oracle Corporation 1.8.0_242 [2020/03/03-10:58:27.426] [ActivityExecutor-28] [INFO] [dku.flow.jobrunner] running compute_web_history_prepared_joined_NP - Allocated a slot for this activity! [2020/03/03-10:58:27.428] [ActivityExecutor-28] [INFO] [dku.flow.jobrunner] running compute_web_history_prepared_joined_NP - Run activity [2020/03/03-10:58:27.438] [ActivityExecutor-28] [INFO] [dku.flow.activity] running compute_web_history_prepared_joined_NP - Executing default pre-activity lifecycle hook [2020/03/03-10:58:27.455] [ActivityExecutor-28] [INFO] [dku.flow.activity] running compute_web_history_prepared_joined_NP - Checking if sources are ready [2020/03/03-10:58:27.456] [ActivityExecutor-28] [DEBUG] [dku.db.internal] running compute_web_history_prepared_joined_NP - Borrowing a connection. Read-only: false [2020/03/03-10:58:27.473] [ActivityExecutor-28] [DEBUG] [dku.dataset.hash] running compute_web_history_prepared_joined_NP - Readiness cache miss for dataset__StamA3__DKU_TSHIRTS.web_history_prepared__NP [2020/03/03-10:58:27.481] [ActivityExecutor-28] [INFO] [dku.datasets.file] running compute_web_history_prepared_joined_NP - Building Filesystem handler config: {"connection":"filesystem_managed","path":"/DKU_TSHIRTS.web_history_prepared","notReadyIfEmpty":false,"filesSelectionRules":{"mode":"ALL","excludeRules":[],"includeRules":[],"explicitFiles":[]}} [2020/03/03-10:58:27.483] [ActivityExecutor-28] [INFO] [dku.datasets.ftplike] running compute_web_history_prepared_joined_NP - Enumerating Filesystem dataset prefix= [2020/03/03-10:58:27.500] [ActivityExecutor-28] [DEBUG] [dku.fs.local] running compute_web_history_prepared_joined_NP - Enumerating local filesystem prefix=/ [2020/03/03-10:58:27.501] [ActivityExecutor-28] [DEBUG] [dku.fs.local] running compute_web_history_prepared_joined_NP - Enumeration done nb_paths=1 size=492219 [2020/03/03-10:58:27.503] [ActivityExecutor-28] [INFO] [dku.dataset.hash] running compute_web_history_prepared_joined_NP - Caching readiness for dataset__StamA3__DKU_TSHIRTS.web_history_prepared__NP s=READY h=vrT9MPeLVLRYc5UDEPclDw [2020/03/03-10:58:27.504] [ActivityExecutor-28] [INFO] [dku.flow.activity] running compute_web_history_prepared_joined_NP - Checked source readiness DKU_TSHIRTS.web_history_prepared -> true [2020/03/03-10:58:27.508] [ActivityExecutor-28] [DEBUG] [dku.flow.activity] running compute_web_history_prepared_joined_NP - Computing hashes to propagate BEFORE activity [2020/03/03-10:58:27.509] [ActivityExecutor-28] [DEBUG] [dku.db.internal] running compute_web_history_prepared_joined_NP - Borrowing a connection. Read-only: false [2020/03/03-10:58:27.512] [ActivityExecutor-28] [DEBUG] [dku.dataset.hash] running compute_web_history_prepared_joined_NP - Readiness cache miss for dataset__StamA3__DKU_TSHIRTS.web_history_prepared__NP [2020/03/03-10:58:27.512] [ActivityExecutor-28] [INFO] [dku.datasets.file] running compute_web_history_prepared_joined_NP - Building Filesystem handler config: {"connection":"filesystem_managed","path":"/DKU_TSHIRTS.web_history_prepared","notReadyIfEmpty":false,"filesSelectionRules":{"mode":"ALL","excludeRules":[],"includeRules":[],"explicitFiles":[]}} [2020/03/03-10:58:27.513] [ActivityExecutor-28] [INFO] [dku.datasets.ftplike] running compute_web_history_prepared_joined_NP - Enumerating Filesystem dataset prefix= [2020/03/03-10:58:27.514] [ActivityExecutor-28] [DEBUG] [dku.fs.local] running compute_web_history_prepared_joined_NP - Enumerating local filesystem prefix=/ [2020/03/03-10:58:27.514] [ActivityExecutor-28] [DEBUG] [dku.fs.local] running compute_web_history_prepared_joined_NP - Enumeration done nb_paths=1 size=492219 [2020/03/03-10:58:27.515] [ActivityExecutor-28] [INFO] [dku.dataset.hash] running compute_web_history_prepared_joined_NP - Caching readiness for dataset__StamA3__DKU_TSHIRTS.web_history_prepared__NP s=READY h=vrT9MPeLVLRYc5UDEPclDw [2020/03/03-10:58:27.515] [ActivityExecutor-28] [DEBUG] [dku.flow.activity] running compute_web_history_prepared_joined_NP - Recorded 1 hashes before activity run [2020/03/03-10:58:27.516] [ActivityExecutor-28] [DEBUG] [dku.flow.activity] running compute_web_history_prepared_joined_NP - Building recipe runner of type [2020/03/03-10:58:27.528] [ActivityExecutor-28] [INFO] [dku.recipe.join] running compute_web_history_prepared_joined_NP - SET PAYLOAD: { "joins": [ { "table2": 1, "table1": 0, "conditionsMode": "AND", "rightLimit": { "decisionColumn": {} }, "type": "LEFT", "outerJoinOnTheLeft": true, "on": [ { "column1": { "name": "customer_id", "table": 0 }, "dateDiffUnit": "DAY", "column2": { "name": "customer_id", "table": 1 }, "maxMatches": 1, "caseInsensitive": false, "maxDistance": 0, "normalizeText": false, "type": "EQ", "strict": false } ] } ], "selectedColumns": [ { "name": "customer_id", "type": "string", "table": 0 }, { "name": "ip", "type": "string", "table": 0 }, { "name": "pages_visited", "type": "double", "table": 0 }, { "name": "campain", "type": "boolean", "table": 0 }, { "name": "revenue", "type": "bigint", "table": 0 }, { "name": "ip", "type": "string", "table": 1 }, { "name": "pages_visited", "type": "double", "table": 1 }, { "name": "campain", "type": "boolean", "table": 1 }, { "name": "revenue", "type": "bigint", "table": 1 } ], "engineParams": { "hive": { "skipPrerunValidate": false, "hiveconf": [], "inheritConf": "default", "addDkuUdf": false, "executionEngine": "HIVESERVER2" }, "impala": { "forceStreamMode": true }, "lowerCaseSchemaIfEngineRequiresIt": true, "sparkSQL": { "pipelineAllowMerge": true, "useGlobalMetastore": false, "pipelineAllowStart": true, "readParams": { "map": {} }, "overwriteOutputSchema": false, "executionEngine": "SPARK_SUBMIT", "sparkConfig": { "inheritConf": "default", "conf": [] } } }, "virtualInputs": [ { "preFilter": { "uiData": { "mode": "\u0026\u0026", "conditions": [ { "input": "pages_visited", "col": "ip", "num": 10, "operator": "\u003e [number]" } ] }, "$status": { "validated": true, "fullyTranslated": false, "ok": false, "message": "Filter expression is invalid" }, "distinct": false, "enabled": false }, "autoSelectColumns": false, "prefix": "first", "index": 0, "computedColumns": [] }, { "preFilter": { "uiData": { "mode": "\u0026\u0026", "conditions": [ { "input": "pages_visited", "col": "ip", "num": 10, "operator": "\u003e [number]" } ] }, "$status": { "validated": true, "fullyTranslated": false, "ok": false, "message": "Filter expression is invalid" }, "distinct": false, "enabled": true }, "autoSelectColumns": false, "prefix": "second", "index": 0, "computedColumns": [] } ], "computedColumns": [], "postFilter": { "$status": { "schema": { "columns": [ { "name": "first_customer_id", "type": "string" }, { "name": "first_ip", "type": "string" }, { "name": "first_pages_visited", "type": "double" }, { "name": "first_campain", "type": "boolean" }, { "name": "first_revenue", "type": "bigint" }, { "name": "second_ip", "type": "string" }, { "name": "second_pages_visited", "type": "double" }, { "name": "second_campain", "type": "boolean" }, { "name": "second_revenue", "type": "bigint" } ], "userModified": false } } }, "enableAutoCastInJoinConditions": false } [2020/03/03-10:58:27.561] [ActivityExecutor-28] [INFO] [com.dataiku.dip.hive.HiveConfigurator] running compute_web_history_prepared_joined_NP - Hive support is disabled (no hadoop) [2020/03/03-10:58:27.562] [ActivityExecutor-28] [INFO] [com.dataiku.dip.impala.ImpalaConfigurator] running compute_web_history_prepared_joined_NP - Impala support is disabled (no hadoop) [2020/03/03-10:58:27.593] [ActivityExecutor-28] [INFO] [dku.recipes.engines] running compute_web_history_prepared_joined_NP - Resolved preferences projectKey=DKU_TSHIRTS recipeType=join global={"forbiddenEngines":[],"enginesPreferenceOrder":[],"forbiddenByRecipeType":{},"preferenceByRecipeType":{}} project={"forbiddenEngines":[],"enginesPreferenceOrder":[],"forbiddenByRecipeType":{},"preferenceByRecipeType":{}} pplusg={"forbiddenEngines":[],"enginesPreferenceOrder":[],"forbiddenByRecipeType":{},"preferenceByRecipeType":{}} recipe=null resolved={"forbiddenEngines":[],"enginesPreferenceOrder":[],"forbiddenByRecipeType":{},"preferenceByRecipeType":{}} [2020/03/03-10:58:27.594] [ActivityExecutor-28] [INFO] [dku.recipes.visualsql] running compute_web_history_prepared_joined_NP - Auto-selected recipe engine: DSS [2020/03/03-10:58:27.602] [ActivityExecutor-28] [INFO] [dku.recipes.engines] running compute_web_history_prepared_joined_NP - Resolved preferences projectKey=DKU_TSHIRTS recipeType=join global={"forbiddenEngines":[],"enginesPreferenceOrder":[],"forbiddenByRecipeType":{},"preferenceByRecipeType":{}} project={"forbiddenEngines":[],"enginesPreferenceOrder":[],"forbiddenByRecipeType":{},"preferenceByRecipeType":{}} pplusg={"forbiddenEngines":[],"enginesPreferenceOrder":[],"forbiddenByRecipeType":{},"preferenceByRecipeType":{}} recipe=null resolved={"forbiddenEngines":[],"enginesPreferenceOrder":[],"forbiddenByRecipeType":{},"preferenceByRecipeType":{}} [2020/03/03-10:58:27.605] [ActivityExecutor-28] [INFO] [dku.recipes.visualsql] running compute_web_history_prepared_joined_NP - Auto-selected recipe engine: DSS [2020/03/03-10:58:27.606] [ActivityExecutor-28] [INFO] [dku.recipes.engines] running compute_web_history_prepared_joined_NP - Resolved preferences projectKey=DKU_TSHIRTS recipeType=join global={"forbiddenEngines":[],"enginesPreferenceOrder":[],"forbiddenByRecipeType":{},"preferenceByRecipeType":{}} project={"forbiddenEngines":[],"enginesPreferenceOrder":[],"forbiddenByRecipeType":{},"preferenceByRecipeType":{}} pplusg={"forbiddenEngines":[],"enginesPreferenceOrder":[],"forbiddenByRecipeType":{},"preferenceByRecipeType":{}} recipe=null resolved={"forbiddenEngines":[],"enginesPreferenceOrder":[],"forbiddenByRecipeType":{},"preferenceByRecipeType":{}} [2020/03/03-10:58:27.613] [ActivityExecutor-28] [INFO] [dku.recipes.visualsql] running compute_web_history_prepared_joined_NP - Auto-selected recipe engine: DSS [2020/03/03-10:58:27.631] [ActivityExecutor-28] [INFO] [dku.recipe.visual] running compute_web_history_prepared_joined_NP - Selected engine type: DSS [2020/03/03-10:58:27.632] [ActivityExecutor-28] [INFO] [dku.recipe.join] running compute_web_history_prepared_joined_NP - Using H2 implementation [2020/03/03-10:58:27.662] [ActivityExecutor-28] [INFO] [dku.connections.sql.provider] running compute_web_history_prepared_joined_NP - Connecting to jdbc:h2:/appl/dataiku/dss_data/jobs/DKU_TSHIRTS/Build_web_history_prepared_joined_2020-03-03T09-58-24.154/compute_web_history_prepared_joined_NP/dataset-to-h2/VleVPynaod5itz0tIZtT/dataset with props: {"USER":"h2_admin"} conn=h2connection-tMqHvTo [2020/03/03-10:58:27.662] [ActivityExecutor-28] [DEBUG] [dku.connections.sql.provider] running compute_web_history_prepared_joined_NP - Driver version 1.4 [2020/03/03-10:58:27.917] [ActivityExecutor-28] [INFO] [dku.connections.sql.provider] running compute_web_history_prepared_joined_NP - Driver: H2 JDBC Driver (JDBC 4.0) 1.4.195 (2017-04-23) (1.4) [2020/03/03-10:58:27.918] [ActivityExecutor-28] [INFO] [dku.connections.sql.provider] running compute_web_history_prepared_joined_NP - Database: H2 1.4.195 (2017-04-23) (1.4) rowSize=0 stmts=0 [2020/03/03-10:58:27.920] [ActivityExecutor-28] [INFO] [dku.dataset.sql] running compute_web_history_prepared_joined_NP - Executing statement: [2020/03/03-10:58:27.921] [ActivityExecutor-28] [INFO] [dku.dataset.sql] running compute_web_history_prepared_joined_NP - CREATE USER h2_user PASSWORD '' [2020/03/03-10:58:27.923] [ActivityExecutor-28] [INFO] [dku.dataset.sql] running compute_web_history_prepared_joined_NP - Statement done [2020/03/03-10:58:27.924] [ActivityExecutor-28] [INFO] [dku.dataset.sql] running compute_web_history_prepared_joined_NP - Executing statement: [2020/03/03-10:58:27.924] [ActivityExecutor-28] [INFO] [dku.dataset.sql] running compute_web_history_prepared_joined_NP - GRANT ALL ON SCHEMA public TO h2_user [2020/03/03-10:58:27.926] [ActivityExecutor-28] [INFO] [dku.dataset.sql] running compute_web_history_prepared_joined_NP - Statement done [2020/03/03-10:58:27.926] [ActivityExecutor-28] [DEBUG] [dku.connections.sql.provider] running compute_web_history_prepared_joined_NP - Close conn=h2connection-tMqHvTo [2020/03/03-10:58:27.932] [ActivityExecutor-28] [INFO] [dku.connections.sql.provider] running compute_web_history_prepared_joined_NP - Connecting to jdbc:h2:/appl/dataiku/dss_data/jobs/DKU_TSHIRTS/Build_web_history_prepared_joined_2020-03-03T09-58-24.154/compute_web_history_prepared_joined_NP/dataset-to-h2/VleVPynaod5itz0tIZtT/dataset with props: {"USER":"h2_user"} conn=h2connection-QQMfRHH [2020/03/03-10:58:27.932] [ActivityExecutor-28] [DEBUG] [dku.connections.sql.provider] running compute_web_history_prepared_joined_NP - Driver version 1.4 [2020/03/03-10:58:27.942] [ActivityExecutor-28] [INFO] [dku.connections.sql.provider] running compute_web_history_prepared_joined_NP - Driver: H2 JDBC Driver (JDBC 4.0) 1.4.195 (2017-04-23) (1.4) [2020/03/03-10:58:27.943] [ActivityExecutor-28] [INFO] [dku.connections.sql.provider] running compute_web_history_prepared_joined_NP - Database: H2 1.4.195 (2017-04-23) (1.4) rowSize=0 stmts=0 [2020/03/03-10:58:27.944] [ActivityExecutor-28] [INFO] [dku.h2] running compute_web_history_prepared_joined_NP - Init H2 recipe runner [2020/03/03-10:58:27.947] [ActivityExecutor-28] [INFO] [dku.datasets.file] running compute_web_history_prepared_joined_NP - Building Filesystem handler config: {"connection":"filesystem_managed","path":"DKU_TSHIRTS/web_history_prepared_joined","notReadyIfEmpty":false,"filesSelectionRules":{"mode":"ALL","excludeRules":[],"includeRules":[],"explicitFiles":[]}} [2020/03/03-10:58:27.948] [ActivityExecutor-28] [INFO] [dku.h2] running compute_web_history_prepared_joined_NP - Write mode : OVERWRITE [2020/03/03-10:58:27.948] [ActivityExecutor-28] [INFO] [dku.datasets.ftplike] running compute_web_history_prepared_joined_NP - Clear partitions [2020/03/03-10:58:27.950] [ActivityExecutor-28] [INFO] [dku.datasets.ftplike] running compute_web_history_prepared_joined_NP - Clearing partition as a folder : 'NP' [2020/03/03-10:58:27.952] [ActivityExecutor-28] [INFO] [dku.datasets.ftplike] running compute_web_history_prepared_joined_NP - Done clearing partition 'NP' [2020/03/03-10:58:27.952] [ActivityExecutor-28] [INFO] [dku.h2] running compute_web_history_prepared_joined_NP - Cleared FS dataset. Write mode : APPEND [2020/03/03-10:58:27.953] [ActivityExecutor-28] [DEBUG] [dku.flow.activity] running compute_web_history_prepared_joined_NP - Recipe runner built, will use 1 thread(s) [2020/03/03-10:58:27.953] [ActivityExecutor-28] [DEBUG] [dku.flow.activity] running compute_web_history_prepared_joined_NP - Starting execution thread: com.dataiku.dip.dataflow.exec.join.JoinRecipeRunner@504f14dc [2020/03/03-10:58:27.954] [ActivityExecutor-28] [DEBUG] [dku.flow.activity] running compute_web_history_prepared_joined_NP - Execution threads started, waiting for activity end [2020/03/03-10:58:27.955] [FRT-39-FlowRunnable] [INFO] [dku.flow.activity] act.compute_web_history_prepared_joined_NP - Run thread for activity compute_web_history_prepared_joined_NP starting [2020/03/03-10:58:27.955] [FRT-39-FlowRunnable] [INFO] [dku.recipe.visual] act.compute_web_history_prepared_joined_NP - Selected executor: com.dataiku.dip.dataflow.exec.join.JoinRecipeRunner$1 [2020/03/03-10:58:27.963] [FRT-39-FlowRunnable] [INFO] [dku.h2loader] act.compute_web_history_prepared_joined_NP - Dumping dataset to CSV for H2... [2020/03/03-10:58:27.964] [FRT-39-FlowRunnable] [INFO] [dku.datasets.file] act.compute_web_history_prepared_joined_NP - Building Filesystem handler config: {"connection":"filesystem_managed","path":"/DKU_TSHIRTS.web_history_prepared","notReadyIfEmpty":false,"filesSelectionRules":{"mode":"ALL","excludeRules":[],"includeRules":[],"explicitFiles":[]}} [2020/03/03-10:58:27.965] [FRT-39-FlowRunnable] [INFO] [dku.datasets.fsbased] act.compute_web_history_prepared_joined_NP - Get filter splits for com.dataiku.dip.input.filter.InputFilter@2b1b5862 [2020/03/03-10:58:27.966] [FRT-39-FlowRunnable] [INFO] [dku.datasets.fsbased] act.compute_web_history_prepared_joined_NP - Enumerate FS [2020/03/03-10:58:27.966] [FRT-39-FlowRunnable] [INFO] [dku.datasets.ftplike] act.compute_web_history_prepared_joined_NP - Enumerating Filesystem dataset prefix= [2020/03/03-10:58:27.967] [FRT-39-FlowRunnable] [DEBUG] [dku.fs.local] act.compute_web_history_prepared_joined_NP - Enumerating local filesystem prefix=/ [2020/03/03-10:58:27.968] [FRT-39-FlowRunnable] [DEBUG] [dku.fs.local] act.compute_web_history_prepared_joined_NP - Enumeration done nb_paths=1 size=492219 [2020/03/03-10:58:27.968] [FRT-39-FlowRunnable] [INFO] [dku.datasets.fsbased] act.compute_web_history_prepared_joined_NP - Enumerate done [2020/03/03-10:58:27.969] [FRT-39-FlowRunnable] [INFO] [dku.datasets.push] act.compute_web_history_prepared_joined_NP - Filter expression: val('pages_visited') > 10 [2020/03/03-10:58:27.969] [FRT-39-FlowRunnable] [INFO] [dku.datasets.push] act.compute_web_history_prepared_joined_NP - Create stream filter to apply filtering rules [2020/03/03-10:58:28.021] [FRT-39-FlowRunnable] [INFO] [dku.input.push] act.compute_web_history_prepared_joined_NP - USTP: push selection.method=FULL records=-1 ratio=0.02 col=null [2020/03/03-10:58:28.025] [FRT-39-FlowRunnable] [INFO] [dku.format] act.compute_web_history_prepared_joined_NP - Extractor run: limit={"maxBytes":-1,"maxRecords":-1,"ordering":{"enabled":false,"rules":[]}} totalRecords=0 [2020/03/03-10:58:28.029] [FRT-39-FlowRunnable] [INFO] [dku.format] act.compute_web_history_prepared_joined_NP - Start compressed [GZIP] stream: /appl/dataiku/dss_data/managed_datasets/DKU_TSHIRTS.web_history_prepared/out-s0.csv.gz / totalRecsBefore=0 [2020/03/03-10:58:28.408] [FRT-39-FlowRunnable] [INFO] [dku.format] act.compute_web_history_prepared_joined_NP - after stream totalComp=492219 totalUncomp=1163002 totalRec=29799 [2020/03/03-10:58:28.408] [FRT-39-FlowRunnable] [INFO] [dku.format] act.compute_web_history_prepared_joined_NP - Extractor run done, totalCompressed=492219 totalRecords=29799 [2020/03/03-10:58:28.408] [FRT-39-FlowRunnable] [INFO] [dku.h2loader] act.compute_web_history_prepared_joined_NP - Done: 452ms [2020/03/03-10:58:28.411] [FRT-39-FlowRunnable] [INFO] [dku.h2loader] act.compute_web_history_prepared_joined_NP - Creating H2 table from CSV. Statement: [2020/03/03-10:58:28.411] [FRT-39-FlowRunnable] [INFO] [dku.h2loader] act.compute_web_history_prepared_joined_NP - CREATE TABLE "DKU_TSHIRTS.web_history_prepared" ( "customer_id" varchar, "ip" varchar, "pages_visited" double, "campain" boolean, "revenue" bigint ) AS SELECT "customer_id","ip","pages_visited","campain","revenue" FROM CSVREAD('/appl/dataiku/dss_data/jobs/DKU_TSHIRTS/Build_web_history_prepared_joined_2020-03-03T09-58-24.154/compute_web_history_prepared_joined_NP/dataset-to-h2/VleVPynaod5itz0tIZtT/DKU_TSHIRTS.web_history_prepared.csv', 'customer_id,ip,pages_visited,campain,revenue', 'charset=UTF-8 escape=\\ fieldSeparator=, fieldDelimiter="') [2020/03/03-10:58:28.544] [FRT-39-FlowRunnable] [INFO] [dku.h2loader] act.compute_web_history_prepared_joined_NP - Done: 133ms [2020/03/03-10:58:28.553] [FRT-39-FlowRunnable] [INFO] [dku.datasets.file] act.compute_web_history_prepared_joined_NP - Building Filesystem handler config: {"connection":"filesystem_managed","path":"DKU_TSHIRTS/web_history_prepared_joined","notReadyIfEmpty":false,"filesSelectionRules":{"mode":"ALL","excludeRules":[],"includeRules":[],"explicitFiles":[]}} [2020/03/03-10:58:28.553] [FRT-39-FlowRunnable] [INFO] [dku.datasets.ftplike] act.compute_web_history_prepared_joined_NP - Clear partitions [2020/03/03-10:58:28.554] [FRT-39-FlowRunnable] [WARN] [dku.fs.local] act.compute_web_history_prepared_joined_NP - File does not exist: /appl/dataiku/dss_data/managed_datasets/DKU_TSHIRTS/web_history_prepared_joined [2020/03/03-10:58:28.555] [FRT-39-FlowRunnable] [INFO] [dku.datasets.ftplike] act.compute_web_history_prepared_joined_NP - Clearing partition as a folder : 'NP' [2020/03/03-10:58:28.556] [FRT-39-FlowRunnable] [WARN] [dku.fs.local] act.compute_web_history_prepared_joined_NP - File does not exist: /appl/dataiku/dss_data/managed_datasets/DKU_TSHIRTS/web_history_prepared_joined [2020/03/03-10:58:28.556] [FRT-39-FlowRunnable] [INFO] [dku.datasets.ftplike] act.compute_web_history_prepared_joined_NP - Done clearing partition 'NP' [2020/03/03-10:58:28.556] [FRT-39-FlowRunnable] [INFO] [dku.h2] act.compute_web_history_prepared_joined_NP - Opening writer [2020/03/03-10:58:28.557] [FRT-39-FlowRunnable] [INFO] [dku.datasets.file] act.compute_web_history_prepared_joined_NP - Building Filesystem handler config: {"connection":"filesystem_managed","path":"DKU_TSHIRTS/web_history_prepared_joined","notReadyIfEmpty":false,"filesSelectionRules":{"mode":"ALL","excludeRules":[],"includeRules":[],"explicitFiles":[]}} [2020/03/03-10:58:28.558] [FRT-39-FlowRunnable] [WARN] [dku.fs.local] act.compute_web_history_prepared_joined_NP - File does not exist: /appl/dataiku/dss_data/managed_datasets/DKU_TSHIRTS/web_history_prepared_joined [2020/03/03-10:58:28.561] [FRT-39-FlowRunnable] [WARN] [dku.fs.local] act.compute_web_history_prepared_joined_NP - File does not exist: /appl/dataiku/dss_data/managed_datasets/DKU_TSHIRTS/web_history_prepared_joined/out-s0.csv.gz [2020/03/03-10:58:28.561] [FRT-39-FlowRunnable] [INFO] [dku.output.file] act.compute_web_history_prepared_joined_NP - Writing base=/ split=0 chunk=0 -> target = out-s0.csv.gz [2020/03/03-10:58:28.562] [FRT-39-FlowRunnable] [INFO] [dku.h2] act.compute_web_history_prepared_joined_NP - Opening reader [2020/03/03-10:58:28.565] [FRT-39-FlowRunnable] [INFO] [dku.recipes.engines] act.compute_web_history_prepared_joined_NP - Resolved preferences projectKey=DKU_TSHIRTS recipeType=join global={"forbiddenEngines":[],"enginesPreferenceOrder":[],"forbiddenByRecipeType":{},"preferenceByRecipeType":{}} project={"forbiddenEngines":[],"enginesPreferenceOrder":[],"forbiddenByRecipeType":{},"preferenceByRecipeType":{}} pplusg={"forbiddenEngines":[],"enginesPreferenceOrder":[],"forbiddenByRecipeType":{},"preferenceByRecipeType":{}} recipe=null resolved={"forbiddenEngines":[],"enginesPreferenceOrder":[],"forbiddenByRecipeType":{},"preferenceByRecipeType":{}} [2020/03/03-10:58:28.570] [FRT-39-FlowRunnable] [INFO] [dku.recipes.visualsql] act.compute_web_history_prepared_joined_NP - Auto-selected recipe engine: DSS [2020/03/03-10:58:28.571] [FRT-39-FlowRunnable] [INFO] [dku.recipes.engines] act.compute_web_history_prepared_joined_NP - Resolved preferences projectKey=DKU_TSHIRTS recipeType=join global={"forbiddenEngines":[],"enginesPreferenceOrder":[],"forbiddenByRecipeType":{},"preferenceByRecipeType":{}} project={"forbiddenEngines":[],"enginesPreferenceOrder":[],"forbiddenByRecipeType":{},"preferenceByRecipeType":{}} pplusg={"forbiddenEngines":[],"enginesPreferenceOrder":[],"forbiddenByRecipeType":{},"preferenceByRecipeType":{}} recipe=null resolved={"forbiddenEngines":[],"enginesPreferenceOrder":[],"forbiddenByRecipeType":{},"preferenceByRecipeType":{}} [2020/03/03-10:58:28.572] [FRT-39-FlowRunnable] [INFO] [dku.recipes.visualsql] act.compute_web_history_prepared_joined_NP - Auto-selected recipe engine: DSS [2020/03/03-10:58:28.580] [FRT-39-FlowRunnable] [INFO] [dku.recipe.join] act.compute_web_history_prepared_joined_NP - Creating index on DKU_TSHIRTS.web_history_prepared / customer_id [2020/03/03-10:58:28.580] [FRT-39-FlowRunnable] [INFO] [dku.recipe.join] act.compute_web_history_prepared_joined_NP - Executing SQL: CREATE INDEX ON "DKU_TSHIRTS.web_history_prepared" ("customer_id") [2020/03/03-10:58:28.625] [FRT-39-FlowRunnable] [DEBUG] [dku.connections.sql.provider] act.compute_web_history_prepared_joined_NP - Commit conn=h2connection-QQMfRHH [2020/03/03-10:58:28.629] [FRT-39-FlowRunnable] [INFO] [dku.queries.executionplan] act.compute_web_history_prepared_joined_NP - Compute execution plan [2020/03/03-10:58:28.630] [FRT-39-FlowRunnable] [WARN] [dku.queries.executionplan] act.compute_web_history_prepared_joined_NP - Computing execution plan inside a transaction [2020/03/03-10:58:28.634] [FRT-39-FlowRunnable] [INFO] [dku.queries.executionplan] act.compute_web_history_prepared_joined_NP - Execution plan query: EXPLAIN SELECT "web_history_prepared"."customer_id" AS "first_customer_id", "web_history_prepared"."ip" AS "first_ip", "web_history_prepared"."pages_visited" AS "first_pages_visited", "web_history_prepared"."campain" AS "first_campain", "web_history_prepared"."revenue" AS "first_revenue", "web_history_prepared_2"."ip" AS "second_ip", "web_history_prepared_2"."pages_visited" AS "second_pages_visited", "web_history_prepared_2"."campain" AS "second_campain", "web_history_prepared_2"."revenue" AS "second_revenue" FROM "DKU_TSHIRTS.web_history_prepared" "web_history_prepared" LEFT JOIN ( SELECT "web_history_prepared_2".* FROM "DKU_TSHIRTS.web_history_prepared" "web_history_prepared_2" WHERE "pages_visited" > 10 ) "web_history_prepared_2" ON "web_history_prepared"."customer_id" = "web_history_prepared_2"."customer_id" [2020/03/03-10:58:28.643] [FRT-39-FlowRunnable] [INFO] [dku.h2] act.compute_web_history_prepared_joined_NP - Execution plan is SELECT "web_history_prepared"."customer_id" AS "first_customer_id", "web_history_prepared"."ip" AS "first_ip", "web_history_prepared"."pages_visited" AS "first_pages_visited", "web_history_prepared"."campain" AS "first_campain", "web_history_prepared"."revenue" AS "first_revenue", "web_history_prepared_2"."ip" AS "second_ip", "web_history_prepared_2"."pages_visited" AS "second_pages_visited", "web_history_prepared_2"."campain" AS "second_campain", "web_history_prepared_2"."revenue" AS "second_revenue" FROM PUBLIC."DKU_TSHIRTS.web_history_prepared" "web_history_prepared" /* PUBLIC."DKU_TSHIRTS.web_history_prepared".tableScan */ LEFT OUTER JOIN ( SELECT "web_history_prepared_2"."customer_id", "web_history_prepared_2"."ip", "web_history_prepared_2"."pages_visited", "web_history_prepared_2"."campain", "web_history_prepared_2"."revenue" FROM PUBLIC."DKU_TSHIRTS.web_history_prepared" "web_history_prepared_2" WHERE "pages_visited" > 10.0 ) "web_history_prepared_2" /* SELECT "web_history_prepared_2"."customer_id", "web_history_prepared_2"."ip", "web_history_prepared_2"."pages_visited", "web_history_prepared_2"."campain", "web_history_prepared_2"."revenue" FROM PUBLIC."DKU_TSHIRTS.web_history_prepared" "web_history_prepared_2" /++ PUBLIC.INDEX_7: "customer_id" IS ?1 ++/ WHERE ("pages_visited" > 10.0) AND ("web_history_prepared_2"."customer_id" IS ?1): "customer_id" = "web_history_prepared"."customer_id" */ ON "web_history_prepared"."customer_id" = "web_history_prepared_2"."customer_id" [2020/03/03-10:58:28.644] [FRT-39-FlowRunnable] [INFO] [dku.h2] act.compute_web_history_prepared_joined_NP - Execute statement: [2020/03/03-10:58:28.644] [FRT-39-FlowRunnable] [INFO] [dku.h2] act.compute_web_history_prepared_joined_NP - SELECT "web_history_prepared"."customer_id" AS "first_customer_id", "web_history_prepared"."ip" AS "first_ip", "web_history_prepared"."pages_visited" AS "first_pages_visited", "web_history_prepared"."campain" AS "first_campain", "web_history_prepared"."revenue" AS "first_revenue", "web_history_prepared_2"."ip" AS "second_ip", "web_history_prepared_2"."pages_visited" AS "second_pages_visited", "web_history_prepared_2"."campain" AS "second_campain", "web_history_prepared_2"."revenue" AS "second_revenue" FROM "DKU_TSHIRTS.web_history_prepared" "web_history_prepared" LEFT JOIN ( SELECT "web_history_prepared_2".* FROM "DKU_TSHIRTS.web_history_prepared" "web_history_prepared_2" WHERE "pages_visited" > 10 ) "web_history_prepared_2" ON "web_history_prepared"."customer_id" = "web_history_prepared_2"."customer_id" [2020/03/03-10:58:28.707] [FRT-39-FlowRunnable] [INFO] [dku.h2] act.compute_web_history_prepared_joined_NP - Starting to emit rows with 9 columns: [[SC:first_customer_id], [SC:first_ip], [SC:first_pages_visited], [SC:first_campain], [SC:first_revenue], [SC:second_ip], [SC:second_pages_visited], [SC:second_campain], [SC:second_revenue]] [2020/03/03-10:58:28.758] [FRT-39-FlowRunnable] [DEBUG] [dku.connections.sql.provider] act.compute_web_history_prepared_joined_NP - Close conn=h2connection-QQMfRHH [2020/03/03-10:58:28.785] [FRT-39-FlowRunnable] [INFO] [dku.flow.activity] act.compute_web_history_prepared_joined_NP - Run thread done for activity compute_web_history_prepared_joined_NP [2020/03/03-10:58:28.970] [ActivityExecutor-28] [INFO] [dku.flow.activity] running compute_web_history_prepared_joined_NP - activity is finished [2020/03/03-10:58:28.972] [ActivityExecutor-28] [INFO] [dku.flow.activity] running compute_web_history_prepared_joined_NP - Executing default post-activity lifecycle hook [2020/03/03-10:58:28.977] [ActivityExecutor-28] [INFO] [dku.flow.activity] running compute_web_history_prepared_joined_NP - Activity successful, computing metrics and running checks [2020/03/03-10:58:29.039] [ActivityExecutor-28] [INFO] [dku.flow.activity] running compute_web_history_prepared_joined_NP - Activity checks produced 0 values [2020/03/03-10:58:29.041] [ActivityExecutor-28] [DEBUG] [dku.db.internal] running compute_web_history_prepared_joined_NP - Borrowing a connection. Read-only: false [2020/03/03-10:58:29.042] [ActivityExecutor-28] [INFO] [dku.flow.activity] running compute_web_history_prepared_joined_NP - Activity is successful, computing timestamps to propagate [2020/03/03-10:58:29.053] [ActivityExecutor-28] [INFO] [dku.flow.activity] running compute_web_history_prepared_joined_NP - Activity is successful, propagating 3 timestamps [2020/03/03-10:58:29.055] [ActivityExecutor-28] [INFO] [dku.timestamps.sql] running compute_web_history_prepared_joined_NP - Starting to propagate 3 hashes [2020/03/03-10:58:29.063] [ActivityExecutor-28] [DEBUG] [dku.connections.sql.provider] running compute_web_history_prepared_joined_NP - Commit conn=dssdb-h2-flow_state-x3bDP9e [2020/03/03-10:58:29.064] [ActivityExecutor-28] [INFO] [dku.timestamps.sql] running compute_web_history_prepared_joined_NP - Hashes propagated in 9 ms [2020/03/03-10:58:29.065] [ActivityExecutor-28] [INFO] [dku.flow.activity] running compute_web_history_prepared_joined_NP - Removing samples for DKU_TSHIRTS.web_history_prepared_joined [2020/03/03-10:58:29.066] [ActivityExecutor-28] [INFO] [dku.flow.activity] running compute_web_history_prepared_joined_NP - Done post-activity tasks