You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Consider using single spill file for multiple partitions #3859
When spilling occurs in native shuffle, Comet writes one spill file per partition. These files are then merged into the final file when shuffle completed.
Gluten combines spill data from multiple partitions into a single spill file. The data is ordered by partition. This results in fewer file handles and fewer metadata ops, which could be a benefit when using EBS for shuffle data.
Activity
Shekharrajak commentedon Apr 5, 2026
Looking into this.
peterxcli commentedon Sep 9, 2026
take
peterxcli commentedon Sep 9, 2026
ref: https://www.anyscale.com/blog/ray-data-shuffle-v2#disk-shuffle
perf: spill every shuffle partition of a task into one file (apache#5916