Hi folks,

This patchset is mainly intended for the upcoming LZMA preparation,
but they still have some benefits to the exist LZ4 decompression.

The first patch looks up compression algorithms on mapping instead
of in the decompression frontend, which is used for the rest patches.

The second patch introduces another compression HEAD (HEAD2) so that
each file can be compressed with two different algorithms at most,
which can be used for the upcoming LZMA compression and LZ4 range
dictionary compression for various data patterns.

The third patch introduces a new readmore decompression strategy to
avoid partial decompression for large big pcluster. It resolves the
randread issue mentioned in the original big pcluster patchset [1]:

randread
Kernel: 5.15.0-rc2+
pclustersize            Vanilla         Patched
 4096                    54.6 MiB/s      54.0 MiB/s
16384                   117.4 MiB/s     143.8 MiB/s
32768                   113.6 MiB/s     199.6 MiB/s
65536                    72.8 MiB/s     236.4 MiB/s

The latest version can also be fetched from
git://git.kernel.org/pub/scm/linux/kernel/git/xiang/linux.git -b erofs/readmore

[1] https://lore.kernel.org/r/[email protected]

Thanks,
Gao Xiang

Gao Xiang (3):
  erofs: get compression algorithms directly on mapping
  erofs: introduce the secondary compression head
  erofs: introduce readmore decompression strategy

 fs/erofs/compress.h          |   5 --
 fs/erofs/erofs_fs.h          |   8 ++-
 fs/erofs/internal.h          |  28 ++++++++-
 fs/erofs/zdata.c             | 106 ++++++++++++++++++++++++++---------
 fs/erofs/zmap.c              |  57 ++++++++++++-------
 include/trace/events/erofs.h |   2 +-
 6 files changed, 150 insertions(+), 56 deletions(-)

-- 
2.20.1

Reply via email to