Skip to content

Potential high latency when destroying an iterator #13673

Open
@sryanyuan

Description

@sryanyuan

PurgeObsoleteFiles will be called during compaction, flush, and similar operations, and it will be performed in the background threads (avoid-unnecessary-blocking-io is enabled).

Additionally, it may also be triggered when destroying an iterator in a user thread, in the case:

  • SST files will be deleted by background threads
  • while archived WAL log files will be unlinked directly in the user thread.

This design might cause high latency if there are many files to be deleted.

Question:

Are there any solutions to mitigate this latency issue if iterator operations are frequently performed?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions