lyveng commented on issue #14461: URL: https://github.com/apache/pinot/issues/14461#issuecomment-2804462043
@Jackie-Jiang The requested usecase is a bit different. For eg., in GCP we use n2d instance types that allow us to attach 8 x 375GB nvme ssds(https://cloud.google.com/compute/docs/disks/local-ssd#local-ssd-perf-nvme). I want all these disks to be part of the dataDir although they are mounted at different directories. Even with the [tiered storage](https://docs.pinot.apache.org/operators/operating-pinot/separating-data-storage-by-age/using-multiple-directories), I would want all the 8 SSDs to be part of the same tier. The requirement is similar to how we specify multiple directories in HDFS datanode config([reference](https://learning.oreilly.com/library/view/hadoop-mapreduce-v2/9781783285471/ch03s10.html) - PFA screenshot). <img width="679" alt="Image" src="https://github.com/user-attachments/assets/84554543-21f2-41e9-9818-077b383eb267"; /> Another alternative is to add all the 8 disks in a Logical Volume, but that would require us to replace the entire node in case one of the disk goes bad unless we configure something like RAID1 or RAID5. -- 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: commits-unsubscr...@pinot.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@pinot.apache.org For additional commands, e-mail: commits-h...@pinot.apache.org
