From 4a377aff2d36b64a65b54192a987aba44b8f78e0 Mon Sep 17 00:00:00 2001 From: Davies Liu Date: Tue, 18 Nov 2014 16:17:51 -0800 Subject: [SPARK-3721] [PySpark] broadcast objects larger than 2G This patch will bring support for broadcasting objects larger than 2G. pickle, zlib, FrameSerializer and Array[Byte] all can not support objects larger than 2G, so this patch introduce LargeObjectSerializer to serialize broadcast objects, the object will be serialized and compressed into small chunks, it also change the type of Broadcast[Array[Byte]]] into Broadcast[Array[Array[Byte]]]]. Testing for support broadcast objects larger than 2G is slow and memory hungry, so this is tested manually, could be added into SparkPerf. Author: Davies Liu Author: Davies Liu Closes #2659 from davies/huge and squashes the following commits: 7b57a14 [Davies Liu] add more tests for broadcast 28acff9 [Davies Liu] Merge branch 'master' of github.com:apache/spark into huge a2f6a02 [Davies Liu] bug fix 4820613 [Davies Liu] Merge branch 'master' of github.com:apache/spark into huge 5875c73 [Davies Liu] address comments 10a349b [Davies Liu] address comments 0c33016 [Davies Liu] Merge branch 'master' of github.com:apache/spark into huge 6182c8f [Davies Liu] Merge branch 'master' into huge d94b68f [Davies Liu] Merge branch 'master' of github.com:apache/spark into huge 2514848 [Davies Liu] address comments fda395b [Davies Liu] Merge branch 'master' of github.com:apache/spark into huge 1c2d928 [Davies Liu] fix scala style 091b107 [Davies Liu] broadcast objects larger than 2G --- python/pyspark/worker.py | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'python/pyspark/worker.py') diff --git a/python/pyspark/worker.py b/python/pyspark/worker.py index 2bdccb5e93..e1552a0b0b 100644 --- a/python/pyspark/worker.py +++ b/python/pyspark/worker.py @@ -31,7 +31,7 @@ from pyspark.broadcast import Broadcast, _broadcastRegistry from pyspark.files import SparkFiles from pyspark.serializers import write_with_length, write_int, read_long, \ write_long, read_int, SpecialLengths, UTF8Deserializer, PickleSerializer, \ - CompressedSerializer + SizeLimitedStream, LargeObjectSerializer from pyspark import shuffle pickleSer = PickleSerializer() @@ -78,11 +78,13 @@ def main(infile, outfile): # fetch names and values of broadcast variables num_broadcast_variables = read_int(infile) - ser = CompressedSerializer(pickleSer) + bser = LargeObjectSerializer() for _ in range(num_broadcast_variables): bid = read_long(infile) if bid >= 0: - value = ser._read_with_length(infile) + size = read_long(infile) + s = SizeLimitedStream(infile, size) + value = list((bser.load_stream(s)))[0] # read out all the bytes _broadcastRegistry[bid] = Broadcast(bid, value) else: bid = - bid - 1 -- cgit v1.2.3