From e6323e107e76acec2830d9249c2f497ea6159432 Mon Sep 17 00:00:00 2001 From: dding3 Date: Wed, 8 Apr 2020 20:03:18 -0700 Subject: [PATCH] update error message in AllReduceParameter (#2997) * update error message in AllReduceParameter --- .../bigdl/dllib/optim/parameters/AllReduceParameter.scala | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/scala/dllib/src/main/scala/com/intel/analytics/bigdl/dllib/optim/parameters/AllReduceParameter.scala b/scala/dllib/src/main/scala/com/intel/analytics/bigdl/dllib/optim/parameters/AllReduceParameter.scala index 06eb0692e08..2a71233188f 100644 --- a/scala/dllib/src/main/scala/com/intel/analytics/bigdl/dllib/optim/parameters/AllReduceParameter.scala +++ b/scala/dllib/src/main/scala/com/intel/analytics/bigdl/dllib/optim/parameters/AllReduceParameter.scala @@ -207,7 +207,8 @@ class AllReduceParameter[T: ClassTag]( val blockId = getWeightBlockId(pid) val localBuffer = BlockManagerWrapper.getLocalOrRemoteBytes(blockId).getOrElse { throw new RuntimeException(s"Didn't find weight block $blockId in the block " + - s"manager. Did you initialize this AllReduceParameter on every executor?") + s"manager. This is usually because executor crashed. Please check your" + + s"executors' log see the error (usually an OutOfMemory error)") } val start = pid * taskSize + math.min(pid, extraSize) val length = taskSize + (if (pid < extraSize) 1 else 0)