Details
-
Task
-
Status: Resolved
-
Major
-
Resolution: Fixed
-
2.3
-
None
-
None
Description
Currently, we write WAL files in work directory and then copy them to the archive after the segment is closed.
This was done to overcome XFS bug which leads to a double fsync cost immediately after file creation. This approach leads to excessive disk usage and can be optimized, especially for LOG_ONLY mode.
Attachments
Issue Links
- incorporates
-
IGNITE-7582 Document 'No Archiver' WAL mode
- Resolved
- is related to
-
IGNITE-7175 Throttling is not applied to page allocation
- Resolved
-
IGNITE-7584 Smooth decrease WAL write speed if low work segments left
- Resolved
- relates to
-
IGNITE-7507 Ignite node performance drop during checkpoint start: store metapage eviction causes long checkpoint lock hold time
- Resolved
-
IGNITE-7074 NPE when WAL path and WAL archive path are the same
- Resolved
- supercedes
-
IGNITE-6802 NullPointerException when WAL store and WAL archive paths are same
- Resolved
- links to