Re: [PATCH v4 4/5] squashfs: Add zstd support

[Sean Purcell]

Signed-off-by: Sean Purcell <me@xxxxxxxxx>

On Fri, Aug 4, 2017 at 4:19 PM, Nick Terrell <terrelln@xxxxxx> wrote:
> Add zstd compression and decompression support to SquashFS. zstd is a
> great fit for SquashFS because it can compress at ratios approaching xz,
> while decompressing twice as fast as zlib. For SquashFS in particular,
> it can decompress as fast as lzo and lz4. It also has the flexibility
> to turn down the compression ratio for faster compression times.
>
> The compression benchmark is run on the file tree from the SquashFS archive
> found in ubuntu-16.10-desktop-amd64.iso [1]. It uses `mksquashfs` with the
> default block size (128 KB) and and various compression algorithms/levels.
> xz and zstd are also benchmarked with 256 KB blocks. The decompression
> benchmark times how long it takes to `tar` the file tree into `/dev/null`.
> See the benchmark file in the upstream zstd source repository located under
> `contrib/linux-kernel/squashfs-benchmark.sh` [2] for details.
>
> I ran the benchmarks on a Ubuntu 14.04 VM with 2 cores and 4 GiB of RAM.
> The VM is running on a MacBook Pro with a 3.1 GHz Intel Core i7 processor,
> 16 GB of RAM, and a SSD.
>
> | Method         | Ratio | Compression MB/s | Decompression MB/s |
> |----------------|-------|------------------|--------------------|
> | gzip           |  2.92 |               15 |                128 |
> | lzo            |  2.64 |              9.5 |                217 |
> | lz4            |  2.12 |               94 |                218 |
> | xz             |  3.43 |              5.5 |                 35 |
> | xz 256 KB      |  3.53 |              5.4 |                 40 |
> | zstd 1         |  2.71 |               96 |                210 |
> | zstd 5         |  2.93 |               69 |                198 |
> | zstd 10        |  3.01 |               41 |                225 |
> | zstd 15        |  3.13 |             11.4 |                224 |
> | zstd 16 256 KB |  3.24 |              8.1 |                210 |
>
> This patch was written by Sean Purcell <me@xxxxxxxxx>, but I will be
> taking over the submission process.
>
> [1] http://releases.ubuntu.com/16.10/
> [2] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/squashfs-benchmark.sh
>
> zstd source repository: https://github.com/facebook/zstd
>
> Cc: Sean Purcell <me@xxxxxxxxx>
> Signed-off-by: Nick Terrell <terrelln@xxxxxx>
> ---
> v3 -> v4:
> - Fix minor linter warnings
>
>  fs/squashfs/Kconfig        |  14 +++++
>  fs/squashfs/Makefile       |   1 +
>  fs/squashfs/decompressor.c |   7 +++
>  fs/squashfs/decompressor.h |   4 ++
>  fs/squashfs/squashfs_fs.h  |   1 +
>  fs/squashfs/zstd_wrapper.c | 149 +++++++++++++++++++++++++++++++++++++++++++++
>  6 files changed, 176 insertions(+)
>  create mode 100644 fs/squashfs/zstd_wrapper.c
>
> diff --git a/fs/squashfs/Kconfig b/fs/squashfs/Kconfig
> index ffb093e..1adb334 100644
> --- a/fs/squashfs/Kconfig
> +++ b/fs/squashfs/Kconfig
> @@ -165,6 +165,20 @@ config SQUASHFS_XZ
>
>           If unsure, say N.
>
> +config SQUASHFS_ZSTD
> +       bool "Include support for ZSTD compressed file systems"
> +       depends on SQUASHFS
> +       select ZSTD_DECOMPRESS
> +       help
> +         Saying Y here includes support for reading Squashfs file systems
> +         compressed with ZSTD compression.  ZSTD gives better compression than
> +         the default ZLIB compression, while using less CPU.
> +
> +         ZSTD is not the standard compression used in Squashfs and so most
> +         file systems will be readable without selecting this option.
> +
> +         If unsure, say N.
> +
>  config SQUASHFS_4K_DEVBLK_SIZE
>         bool "Use 4K device block size?"
>         depends on SQUASHFS
> diff --git a/fs/squashfs/Makefile b/fs/squashfs/Makefile
> index 246a6f3..6655631 100644
> --- a/fs/squashfs/Makefile
> +++ b/fs/squashfs/Makefile
> @@ -15,3 +15,4 @@ squashfs-$(CONFIG_SQUASHFS_LZ4) += lz4_wrapper.o
>  squashfs-$(CONFIG_SQUASHFS_LZO) += lzo_wrapper.o
>  squashfs-$(CONFIG_SQUASHFS_XZ) += xz_wrapper.o
>  squashfs-$(CONFIG_SQUASHFS_ZLIB) += zlib_wrapper.o
> +squashfs-$(CONFIG_SQUASHFS_ZSTD) += zstd_wrapper.o
> diff --git a/fs/squashfs/decompressor.c b/fs/squashfs/decompressor.c
> index d2bc136..8366398 100644
> --- a/fs/squashfs/decompressor.c
> +++ b/fs/squashfs/decompressor.c
> @@ -65,6 +65,12 @@ static const struct squashfs_decompressor squashfs_zlib_comp_ops = {
>  };
>  #endif
>
> +#ifndef CONFIG_SQUASHFS_ZSTD
> +static const struct squashfs_decompressor squashfs_zstd_comp_ops = {
> +       NULL, NULL, NULL, NULL, ZSTD_COMPRESSION, "zstd", 0
> +};
> +#endif
> +
>  static const struct squashfs_decompressor squashfs_unknown_comp_ops = {
>         NULL, NULL, NULL, NULL, 0, "unknown", 0
>  };
> @@ -75,6 +81,7 @@ static const struct squashfs_decompressor *decompressor[] = {
>         &squashfs_lzo_comp_ops,
>         &squashfs_xz_comp_ops,
>         &squashfs_lzma_unsupported_comp_ops,
> +       &squashfs_zstd_comp_ops,
>         &squashfs_unknown_comp_ops
>  };
>
> diff --git a/fs/squashfs/decompressor.h b/fs/squashfs/decompressor.h
> index a25713c..0f5a8e4 100644
> --- a/fs/squashfs/decompressor.h
> +++ b/fs/squashfs/decompressor.h
> @@ -58,4 +58,8 @@ extern const struct squashfs_decompressor squashfs_lzo_comp_ops;
>  extern const struct squashfs_decompressor squashfs_zlib_comp_ops;
>  #endif
>
> +#ifdef CONFIG_SQUASHFS_ZSTD
> +extern const struct squashfs_decompressor squashfs_zstd_comp_ops;
> +#endif
> +
>  #endif
> diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h
> index 506f4ba..24d12fd 100644
> --- a/fs/squashfs/squashfs_fs.h
> +++ b/fs/squashfs/squashfs_fs.h
> @@ -241,6 +241,7 @@ struct meta_index {
>  #define LZO_COMPRESSION                3
>  #define XZ_COMPRESSION         4
>  #define LZ4_COMPRESSION                5
> +#define ZSTD_COMPRESSION       6
>
>  struct squashfs_super_block {
>         __le32                  s_magic;
> diff --git a/fs/squashfs/zstd_wrapper.c b/fs/squashfs/zstd_wrapper.c
> new file mode 100644
> index 0000000..d70efa8
> --- /dev/null
> +++ b/fs/squashfs/zstd_wrapper.c
> @@ -0,0 +1,149 @@
> +/*
> + * Squashfs - a compressed read only filesystem for Linux
> + *
> + * Copyright (c) 2016-present, Facebook, Inc.
> + * All rights reserved.
> + *
> + * This program is free software; you can redistribute it and/or
> + * modify it under the terms of the GNU General Public License
> + * as published by the Free Software Foundation; either version 2,
> + * or (at your option) any later version.
> + *
> + * This program is distributed in the hope that it will be useful,
> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
> + * GNU General Public License for more details.
> + *
> + * zstd_wrapper.c
> + */
> +
> +#include <linux/mutex.h>
> +#include <linux/buffer_head.h>
> +#include <linux/slab.h>
> +#include <linux/zstd.h>
> +#include <linux/vmalloc.h>
> +
> +#include "squashfs_fs.h"
> +#include "squashfs_fs_sb.h"
> +#include "squashfs.h"
> +#include "decompressor.h"
> +#include "page_actor.h"
> +
> +struct workspace {
> +       void *mem;
> +       size_t mem_size;
> +};
> +
> +static void *zstd_init(struct squashfs_sb_info *msblk, void *buff)
> +{
> +       struct workspace *wksp = kmalloc(sizeof(*wksp), GFP_KERNEL);
> +
> +       if (wksp == NULL)
> +               goto failed;
> +       wksp->mem_size = ZSTD_DStreamWorkspaceBound(max_t(size_t,
> +                               msblk->block_size, SQUASHFS_METADATA_SIZE));
> +       wksp->mem = vmalloc(wksp->mem_size);
> +       if (wksp->mem == NULL)
> +               goto failed;
> +
> +       return wksp;
> +
> +failed:
> +       ERROR("Failed to allocate zstd workspace\n");
> +       kfree(wksp);
> +       return ERR_PTR(-ENOMEM);
> +}
> +
> +
> +static void zstd_free(void *strm)
> +{
> +       struct workspace *wksp = strm;
> +
> +       if (wksp)
> +               vfree(wksp->mem);
> +       kfree(wksp);
> +}
> +
> +
> +static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm,
> +       struct buffer_head **bh, int b, int offset, int length,
> +       struct squashfs_page_actor *output)
> +{
> +       struct workspace *wksp = strm;
> +       ZSTD_DStream *stream;
> +       size_t total_out = 0;
> +       size_t zstd_err;
> +       int k = 0;
> +       ZSTD_inBuffer in_buf = { NULL, 0, 0 };
> +       ZSTD_outBuffer out_buf = { NULL, 0, 0 };
> +
> +       stream = ZSTD_initDStream(wksp->mem_size, wksp->mem, wksp->mem_size);
> +
> +       if (!stream) {
> +               ERROR("Failed to initialize zstd decompressor\n");
> +               goto out;
> +       }
> +
> +       out_buf.size = PAGE_SIZE;
> +       out_buf.dst = squashfs_first_page(output);
> +
> +       do {
> +               if (in_buf.pos == in_buf.size && k < b) {
> +                       int avail = min(length, msblk->devblksize - offset);
> +
> +                       length -= avail;
> +                       in_buf.src = bh[k]->b_data + offset;
> +                       in_buf.size = avail;
> +                       in_buf.pos = 0;
> +                       offset = 0;
> +               }
> +
> +               if (out_buf.pos == out_buf.size) {
> +                       out_buf.dst = squashfs_next_page(output);
> +                       if (out_buf.dst == NULL) {
> +                               /* Shouldn't run out of pages
> +                                * before stream is done.
> +                                */
> +                               squashfs_finish_page(output);
> +                               goto out;
> +                       }
> +                       out_buf.pos = 0;
> +                       out_buf.size = PAGE_SIZE;
> +               }
> +
> +               total_out -= out_buf.pos;
> +               zstd_err = ZSTD_decompressStream(stream, &out_buf, &in_buf);
> +               total_out += out_buf.pos; /* add the additional data produced */
> +
> +               if (in_buf.pos == in_buf.size && k < b)
> +                       put_bh(bh[k++]);
> +       } while (zstd_err != 0 && !ZSTD_isError(zstd_err));
> +
> +       squashfs_finish_page(output);
> +
> +       if (ZSTD_isError(zstd_err)) {
> +               ERROR("zstd decompression error: %d\n",
> +                               (int)ZSTD_getErrorCode(zstd_err));
> +               goto out;
> +       }
> +
> +       if (k < b)
> +               goto out;
> +
> +       return (int)total_out;
> +
> +out:
> +       for (; k < b; k++)
> +               put_bh(bh[k]);
> +
> +       return -EIO;
> +}
> +
> +const struct squashfs_decompressor squashfs_zstd_comp_ops = {
> +       .init = zstd_init,
> +       .free = zstd_free,
> +       .decompress = zstd_uncompress,
> +       .id = ZSTD_COMPRESSION,
> +       .name = "zstd",
> +       .supported = 1
> +};
> --
> 2.9.3
>