avoid taking the iolock in fsync unless actually needed

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Subject: avoid taking the iolock in fsync unless actually needed
From: Christoph Hellwig <hch@xxxxxx>
Date: Mon, 11 Jan 2021 17:15:42 +0100

Hi all,

this series avoids taking the iolock in fsync if there is no dirty
metadata.

Follow-Ups:
- [PATCH 2/2] xfs: reduce ilock acquisitions in xfs_file_fsync
  - From: Christoph Hellwig
- [PATCH 1/2] xfs: refactor xfs_file_fsync
  - From: Christoph Hellwig

Prev by Date: [PATCH 3/3] xfs: try to avoid the iolock exclusive for non-aligned direct writes
Next by Date: [PATCH 1/2] xfs: refactor xfs_file_fsync
Previous by thread: improve sub-block size direct I/O concurrency
Next by thread: [PATCH 1/2] xfs: refactor xfs_file_fsync
Index(es):
- Date
- Thread

[Index of Archives] [XFS Filesystem Development (older mail)] [Linux Filesystem Development] [Linux Audio Users] [Yosemite Trails] [Linux Kernel] [Linux RAID] [Linux SCSI]

Powered by Linux