From e685197900f765b3201027f95e18be98f6a9eb35 Mon Sep 17 00:00:00 2001 From: Raza Jafri Date: Wed, 6 Jul 2022 22:06:30 -0700 Subject: [PATCH] set default value to true for reading doubles when reading json and csv files (#5935) Signed-off-by: Raza Jafri Co-authored-by: Raza Jafri --- docs/configs.md | 4 ++-- .../src/main/scala/com/nvidia/spark/rapids/RapidsConf.scala | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/docs/configs.md b/docs/configs.md index d67a6c9f22c..9fee7fa2770 100644 --- a/docs/configs.md +++ b/docs/configs.md @@ -68,7 +68,7 @@ Name | Description | Default Value spark.rapids.sql.castStringToTimestamp.enabled|When set to true, casting from string to timestamp is supported on the GPU. The GPU only supports a subset of formats when casting strings to timestamps. Refer to the CAST documentation for more details.|false spark.rapids.sql.concurrentGpuTasks|Set the number of tasks that can execute concurrently per GPU. Tasks may temporarily block when the number of concurrent tasks in the executor exceeds this amount. Allowing too many concurrent tasks on the same GPU may lead to GPU out of memory errors.|1 spark.rapids.sql.csv.read.decimal.enabled|CSV reading is not 100% compatible when reading decimals.|false -spark.rapids.sql.csv.read.double.enabled|CSV reading is not 100% compatible when reading doubles.|false +spark.rapids.sql.csv.read.double.enabled|CSV reading is not 100% compatible when reading doubles.|true spark.rapids.sql.csv.read.float.enabled|CSV reading is not 100% compatible when reading floats.|true spark.rapids.sql.decimalOverflowGuarantees|FOR TESTING ONLY. DO NOT USE IN PRODUCTION. Please see the decimal section of the compatibility documents for more information on this config.|true spark.rapids.sql.enabled|Enable (true) or disable (false) sql operations on the GPU|true @@ -113,7 +113,7 @@ Name | Description | Default Value spark.rapids.sql.join.leftSemi.enabled|When set to true left semi joins are enabled on the GPU|true spark.rapids.sql.join.rightOuter.enabled|When set to true right outer joins are enabled on the GPU|true spark.rapids.sql.json.read.decimal.enabled|JSON reading is not 100% compatible when reading decimals.|false -spark.rapids.sql.json.read.double.enabled|JSON reading is not 100% compatible when reading doubles.|false +spark.rapids.sql.json.read.double.enabled|JSON reading is not 100% compatible when reading doubles.|true spark.rapids.sql.json.read.float.enabled|JSON reading is not 100% compatible when reading floats.|true spark.rapids.sql.metrics.level|GPU plans can produce a lot more metrics than CPU plans do. In very large queries this can sometimes result in going over the max result size limit for the driver. Supported values include DEBUG which will enable all metrics supported and typically only needs to be enabled when debugging the plugin. MODERATE which should output enough metrics to understand how long each part of the query is taking and how much data is going to each part of the query. ESSENTIAL which disables most metrics except those Apache Spark CPU plans will also report or their equivalents.|MODERATE spark.rapids.sql.mode|Set the mode for the Rapids Accelerator. The supported modes are explainOnly and executeOnGPU. This config can not be changed at runtime, you must restart the application for it to take affect. The default mode is executeOnGPU, which means the RAPIDS Accelerator plugin convert the Spark operations and execute them on the GPU when possible. The explainOnly mode allows running queries on the CPU and the RAPIDS Accelerator will evaluate the queries as if it was going to run on the GPU. The explanations of what would have run on the GPU and why are output in log messages. When using explainOnly mode, the default explain output is ALL, this can be changed by setting spark.rapids.sql.explain. See that config for more details.|executeongpu diff --git a/sql-plugin/src/main/scala/com/nvidia/spark/rapids/RapidsConf.scala b/sql-plugin/src/main/scala/com/nvidia/spark/rapids/RapidsConf.scala index 65714baf775..714eda201e5 100644 --- a/sql-plugin/src/main/scala/com/nvidia/spark/rapids/RapidsConf.scala +++ b/sql-plugin/src/main/scala/com/nvidia/spark/rapids/RapidsConf.scala @@ -922,7 +922,7 @@ object RapidsConf { val ENABLE_READ_CSV_DOUBLES = conf("spark.rapids.sql.csv.read.double.enabled") .doc("CSV reading is not 100% compatible when reading doubles.") .booleanConf - .createWithDefault(false) + .createWithDefault(true) val ENABLE_READ_CSV_DECIMALS = conf("spark.rapids.sql.csv.read.decimal.enabled") .doc("CSV reading is not 100% compatible when reading decimals.") @@ -948,7 +948,7 @@ object RapidsConf { val ENABLE_READ_JSON_DOUBLES = conf("spark.rapids.sql.json.read.double.enabled") .doc("JSON reading is not 100% compatible when reading doubles.") .booleanConf - .createWithDefault(false) + .createWithDefault(true) val ENABLE_READ_JSON_DECIMALS = conf("spark.rapids.sql.json.read.decimal.enabled") .doc("JSON reading is not 100% compatible when reading decimals.")