You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@hbase.apache.org by GitBox <gi...@apache.org> on 2020/08/20 16:09:47 UTC

[GitHub] [hbase] 1996fanrui edited a comment on pull request #2288: HBASE-24915 Improve BlockCache read performance by specifying BlockType

1996fanrui edited a comment on pull request #2288:
URL: https://github.com/apache/hbase/pull/2288#issuecomment-677748719


   > Nice patch, do you know of any other callers who can pass `BlockType` argument?
   
   @virajjasani Thanks for your comment.
   
   The main flow of get() will initialize Scanner and call StoreFileScanner.seek().Subsequent method call stack:
   
   StoreFileScanner.seek -> StoreFileScanner.seekAtOrAfter -> HFileReaderImpl.HFileScannerImpl#seekTo -> HFileBlockIndex$CellBasedKeyBlockIndexReader.loadDataBlockWithScanInfo
   
   In the loadDataBlockWithScanInfo method, the BlockType can be known according to the Tree Level. Here is the main process of reading data, the frequency of call is high, so from my understanding: the current patch should have some benefits.
   
   code link: https://github.com/apache/hbase/blob/1164531d5ab519ab58af82ba3849f8fcded3453f/hbase-server/src/main/java/org/apache/hadoop/hbase/io/hfile/HFileBlockIndex.java#L322


----------------------------------------------------------------
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:
users@infra.apache.org