[ https://issues.apache.org/jira/browse/HDFS-9259?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Ming Ma updated HDFS-9259: -------------------------- Description: We recently found that cross-DC hdfs write could be really slow. Further investigation identified that is due to SendBufferSize and ReceiveBufferSize used for hdfs write. The test ran "hadoop -fs -copyFromLocal" of a 256MB file across DC with different SendBufferSize and ReceiveBufferSize values. The results showed that c much faster than b; b is faster than a. a. SendBufferSize=128k, ReceiveBufferSize=128k (hdfs default setting). b. SendBufferSize=128K, ReceiveBufferSize=not set(TCP auto tuning). c. SendBufferSize=not set, ReceiveBufferSize=not set(TCP auto tuning for both) HDFS-8829 has enabled scenario b. We would like to enable scenario c by making SendBufferSize configurable at DFSClient side. Cc: [~cmccabe] [~He Tianyi] [~kanaka] [~vinayrpet]. was: We recently found that cross-DC hdfs write could be really slow. Further investigation identified that is due to SendBufferSize and ReceiveBufferSize used for hdfs write. The test is to do "hadoop -fs -copyFromLocal" of a 256MB file across DC with different SendBufferSize and ReceiveBufferSize values. The results showed that c much faster than b; b is faster than a. a. SendBufferSize=128k, ReceiveBufferSize=128k (hdfs default setting). b. SendBufferSize=128K, ReceiveBufferSize=not set(TCP auto tuning). c. SendBufferSize=not set, ReceiveBufferSize=not set(TCP auto tuning for both) HDFS-8829 has enabled scenario b. We would like to enable scenario c to make SendBufferSize configurable at DFSClient side. Cc: [~cmccabe] [~He Tianyi] [~kanaka] [~vinayrpet]. > Make SO_SNDBUF size configurable at DFSClient side for hdfs write scenario > -------------------------------------------------------------------------- > > Key: HDFS-9259 > URL: https://issues.apache.org/jira/browse/HDFS-9259 > Project: Hadoop HDFS > Issue Type: Improvement > Reporter: Ming Ma > > We recently found that cross-DC hdfs write could be really slow. Further > investigation identified that is due to SendBufferSize and ReceiveBufferSize > used for hdfs write. The test ran "hadoop -fs -copyFromLocal" of a 256MB file > across DC with different SendBufferSize and ReceiveBufferSize values. The > results showed that c much faster than b; b is faster than a. > a. SendBufferSize=128k, ReceiveBufferSize=128k (hdfs default setting). > b. SendBufferSize=128K, ReceiveBufferSize=not set(TCP auto tuning). > c. SendBufferSize=not set, ReceiveBufferSize=not set(TCP auto tuning for both) > HDFS-8829 has enabled scenario b. We would like to enable scenario c by > making SendBufferSize configurable at DFSClient side. Cc: [~cmccabe] [~He > Tianyi] [~kanaka] [~vinayrpet]. -- This message was sent by Atlassian JIRA (v6.3.4#6332)