[PATCH 0/2] xfs: reduce ILOCK contention on O_DSYNC DIO

[Dave Chinner <david@fromorbit.com>]

Hi folks,

This is the changes I came up with in the course of the discussion
with Jan about the fallocate+DIO+O_DSYNC performance improvement
thread here:

https://lore.kernel.org/linux-xfs/CAM4Jq_71gxMcnOdgqWhKEa53sr9r57Qpi0hc5bs3NgtnNOGwtg@mail.gmail.com/T/#

The first patch is moves a little bit of code around to ensure
that xfs_inode_item_precommit() always calculates all the changes
before it starts manipulating the dirty and fsync flags on the inode
log item. Whilst technically it could be considered a bug fix, the
bug it fixes requires an inconsistency in the on disk format to
exist first, so it likely won't ever be an issue in normal
production systems. It also requires an application to run a
fdatasync and then have a system crash just after the
inconsistency is addressed to expose it. So the likelihood of it
ever being triggered as a data integrity issue is -extremely- tiny.

The second patch is the one that addresses the performance issue. It
removes the ILOCK from the sync/datasync path completely, and
instead relies on a new datasync commit sequence number being stored
in the inode log item to elide datasync journal flushes when they
are unnecessary. The mechanism is explained at length in the patch
description.

The changes have been perf tested by both Jan and Lukas, and it has
passed multiple fstests runs on a dozen different configs without
regressions here.

-Dave.