maobaolong opened a new pull request #1212:
URL: https://github.com/apache/hadoop-ozone/pull/1212


   ## What changes were proposed in this pull request?
   
   Use chunkSize as bufferSize for stream copy, so that we can reduce the 
readChunk count from s3g to datanodes.
   
   For example, without this PR, the bufferSize is a hardcode 4096, it means 
each time readChunk request can only read 1M data, but a chunk is 4MB default, 
if we use the chunkSize as the bufferSize, so we can read 4M data for each 
readChunk request, reduce the request time of O3 communicate to datanode.
   
   BTW, clarify the ObjectEndpoint code of s3g, we can use seek to enforce skip 
performance.
   
   ## What is the link to the Apache JIRA
   
   HDDS-3979
   
   ## How was this patch tested?
   
   Using awscli or goofys


----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
[email protected]



---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to