[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <20211007170605.7062-1-xiang@kernel.org>
Date: Fri, 8 Oct 2021 01:06:02 +0800
From: Gao Xiang <xiang@...nel.org>
To: linux-erofs@...ts.ozlabs.org, Chao Yu <chao@...nel.org>
Cc: LKML <linux-kernel@...r.kernel.org>, Gao Xiang <xiang@...nel.org>
Subject: [PATCH 0/3] erofs: some decompression improvements
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/20210407043927.10623-1-xiang@kernel.org
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
Powered by blists - more mailing lists