This is a fairly small update to the v7 set. It seems to pass all of my testing. Again, most of the changes are in the first two patches, but there are some differences in the patch that adds percpu counters as well. Since the report of a performance regression came just before the merge window, it looks like we're going to have to wait for yet another release, so consider this version v6.13 material. Signed-off-by: Jeff Layton <jlayton@xxxxxxxxxx> --- Changes in v8: - drop the cookie handling from the new timekeeper interfaces - add back the floor_swaps percpu counter - comment updates and minor cleanups - Link to v7: https://lore.kernel.org/r/20240913-mgtime-v7-0-92d4020e3b00@xxxxxxxxxx Changes in v7: - move the floor value handling into timekeeper for better performance - Link to v6: https://lore.kernel.org/r/20240715-mgtime-v6-0-48e5d34bd2ba@xxxxxxxxxx Changes in v6: - Normalize timespec64 in inode_set_ctime_to_ts - use DEFINE_PER_CPU counters for better vfs consistency - skip ctime cmpxchg if the result means nothing will change - add trace_ctime_xchg_skip to track skipped ctime updates - use __print_flags in ctime_ns_xchg tracepoint - Link to v5: https://lore.kernel.org/r/20240711-mgtime-v5-0-37bb5b465feb@xxxxxxxxxx Changes in v5: - refetch coarse time in coarse_ctime if not returning floor - timestamp_truncate before swapping new ctime value into place - track floor value as atomic64_t - cleanups to Documentation file - Link to v4: https://lore.kernel.org/r/20240708-mgtime-v4-0-a0f3c6fb57f3@xxxxxxxxxx Changes in v4: - reordered tracepoint fields for better packing - rework percpu counters again to also count fine grained timestamps - switch to try_cmpxchg for better efficiency - Link to v3: https://lore.kernel.org/r/20240705-mgtime-v3-0-85b2daa9b335@xxxxxxxxxx Changes in v3: - Drop the conversion of i_ctime fields to ktime_t, and use an unused bit of the i_ctime_nsec field as QUERIED flag. - Better tracepoints for tracking floor and ctime updates - Reworked percpu counters to be more useful - Track floor as monotonic value, which eliminates clock-jump problem Changes in v2: - Added Documentation file - Link to v1: https://lore.kernel.org/r/20240626-mgtime-v1-0-a189352d0f8f@xxxxxxxxxx --- Jeff Layton (11): timekeeping: move multigrain timestamp floor handling into timekeeper fs: add infrastructure for multigrain timestamps fs: have setattr_copy handle multigrain timestamps appropriately fs: handle delegated timestamps in setattr_copy_mgtime fs: tracepoints around multigrain timestamp events fs: add percpu counters for significant multigrain timestamp events Documentation: add a new file documenting multigrain timestamps xfs: switch to multigrain timestamps ext4: switch to multigrain timestamps btrfs: convert to multigrain timestamps tmpfs: add support for multigrain timestamps Documentation/filesystems/index.rst | 1 + Documentation/filesystems/multigrain-ts.rst | 121 ++++++++++++ fs/attr.c | 60 +++++- fs/btrfs/file.c | 25 +-- fs/btrfs/super.c | 3 +- fs/ext4/super.c | 2 +- fs/inode.c | 278 +++++++++++++++++++++++++--- fs/stat.c | 42 ++++- fs/xfs/libxfs/xfs_trans_inode.c | 6 +- fs/xfs/xfs_iops.c | 10 +- fs/xfs/xfs_super.c | 2 +- include/linux/fs.h | 36 +++- include/linux/timekeeping.h | 5 + include/trace/events/timestamp.h | 124 +++++++++++++ kernel/time/timekeeping.c | 83 +++++++++ kernel/time/timekeeping_debug.c | 12 ++ kernel/time/timekeeping_internal.h | 3 + mm/shmem.c | 2 +- 18 files changed, 742 insertions(+), 73 deletions(-) --- base-commit: da3ea35007d0af457a0afc87e84fddaebc4e0b63 change-id: 20240913-mgtime-20c98bcda88e Best regards, -- Jeff Layton <jlayton@xxxxxxxxxx>
