From 97f2e7b760c90ecfd693d35980c4ab9e9be97ee8 Mon Sep 17 00:00:00 2001 From: Jason Lowe Date: Fri, 7 Aug 2020 17:49:01 -0500 Subject: [PATCH] Temporary workaround for RMM initial pool size bug (#530) Signed-off-by: Jason Lowe --- docs/configs.md | 2 +- .../src/main/scala/com/nvidia/spark/rapids/RapidsConf.scala | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/configs.md b/docs/configs.md index 208a10c09eb..f6779ed3f23 100644 --- a/docs/configs.md +++ b/docs/configs.md @@ -29,7 +29,7 @@ scala> spark.conf.set("spark.rapids.sql.incompatibleOps.enabled", true) Name | Description | Default Value -----|-------------|-------------- -spark.rapids.memory.gpu.allocFraction|The fraction of total GPU memory that should be initially allocated for pooled memory. Extra memory will be allocated as needed, but it may result in more fragmentation.|0.9 +spark.rapids.memory.gpu.allocFraction|The fraction of total GPU memory that should be initially allocated for pooled memory. Extra memory will be allocated as needed, but it may result in more fragmentation.|0.5 spark.rapids.memory.gpu.debug|Provides a log of GPU memory allocations and frees. If set to STDOUT or STDERR the logging will go there. Setting it to NONE disables logging. All other values are reserved for possible future expansion and in the mean time will disable logging.|NONE spark.rapids.memory.gpu.pooling.enabled|Should RMM act as a pooling allocator for GPU memory, or should it just pass through to CUDA memory allocation directly.|true spark.rapids.memory.host.spillStorageSize|Amount of off-heap host memory to use for buffering spilled GPU data before spilling to local disk|1073741824 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 23ac99394ca..13cecb05da5 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 @@ -258,7 +258,7 @@ object RapidsConf { "result in more fragmentation.") .doubleConf .checkValue(v => v >= 0 && v <= 1, "The fraction value must be in [0, 1].") - .createWithDefault(0.9) + .createWithDefault(0.5) val HOST_SPILL_STORAGE_SIZE = conf("spark.rapids.memory.host.spillStorageSize") .doc("Amount of off-heap host memory to use for buffering spilled GPU data " +