sodonnel commented on PR #6613: URL: https://github.com/apache/ozone/pull/6613#issuecomment-3485814312
> I may have misunderstood "small read". What do you mean by small read? (1) or (2) below? > > 1. client opens a file, reads a small amount of data (say 4KB) and then the close the file; or > > 2. client opens a file with a small buffer (say 4KB), keep looping calling read(buffer) for many times and then the close the file. I have been primarily looking at 2, which I believe is the most common spark, Hive type workload, where blocks are largely read completely. 1 is more like an HBase use case, where it will scatter positional reads all over the file based on which part of the block its index tells it to read. -- 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. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
