mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
5c1aab1dd5
Add zstd compression and decompression support to BtrFS. zstd at its fastest level compresses almost as well as zlib, while offering much faster compression and decompression, approaching lzo speeds. I benchmarked btrfs with zstd compression against no compression, lzo compression, and zlib compression. I benchmarked two scenarios. Copying a set of files to btrfs, and then reading the files. Copying a tarball to btrfs, extracting it to btrfs, and then reading the extracted files. After every operation, I call `sync` and include the sync time. Between every pair of operations I unmount and remount the filesystem to avoid caching. The benchmark files can be found in the upstream zstd source repository under `contrib/linux-kernel/{btrfs-benchmark.sh,btrfs-extract-benchmark.sh}` [1] [2]. 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. The first compression benchmark is copying 10 copies of the unzipped Silesia corpus [3] into a BtrFS filesystem mounted with `-o compress-force=Method`. The decompression benchmark times how long it takes to `tar` all 10 copies into `/dev/null`. The compression ratio is measured by comparing the output of `df` and `du`. See the benchmark file [1] for details. I benchmarked multiple zstd compression levels, although the patch uses zstd level 1. | Method | Ratio | Compression MB/s | Decompression speed | |---------|-------|------------------|---------------------| | None | 0.99 | 504 | 686 | | lzo | 1.66 | 398 | 442 | | zlib | 2.58 | 65 | 241 | | zstd 1 | 2.57 | 260 | 383 | | zstd 3 | 2.71 | 174 | 408 | | zstd 6 | 2.87 | 70 | 398 | | zstd 9 | 2.92 | 43 | 406 | | zstd 12 | 2.93 | 21 | 408 | | zstd 15 | 3.01 | 11 | 354 | The next benchmark first copies `linux-4.11.6.tar` [4] to btrfs. Then it measures the compression ratio, extracts the tar, and deletes the tar. Then it measures the compression ratio again, and `tar`s the extracted files into `/dev/null`. See the benchmark file [2] for details. | Method | Tar Ratio | Extract Ratio | Copy (s) | Extract (s)| Read (s) | |--------|-----------|---------------|----------|------------|----------| | None | 0.97 | 0.78 | 0.981 | 5.501 | 8.807 | | lzo | 2.06 | 1.38 | 1.631 | 8.458 | 8.585 | | zlib | 3.40 | 1.86 | 7.750 | 21.544 | 11.744 | | zstd 1 | 3.57 | 1.85 | 2.579 | 11.479 | 9.389 | [1] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/btrfs-benchmark.sh [2] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/btrfs-extract-benchmark.sh [3] http://sun.aei.polsl.pl/~sdeor/index.php?page=silesia [4] https://cdn.kernel.org/pub/linux/kernel/v4.x/linux-4.11.6.tar.xz zstd source repository: https://github.com/facebook/zstd Signed-off-by: Nick Terrell <terrelln@fb.com> Signed-off-by: Chris Mason <clm@fb.com>
433 lines
10 KiB
C
433 lines
10 KiB
C
/*
|
|
* 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 v2 as published by the Free Software Foundation.
|
|
*
|
|
* 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.
|
|
*/
|
|
#include <linux/bio.h>
|
|
#include <linux/err.h>
|
|
#include <linux/init.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/refcount.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/zstd.h>
|
|
#include "compression.h"
|
|
|
|
#define ZSTD_BTRFS_MAX_WINDOWLOG 17
|
|
#define ZSTD_BTRFS_MAX_INPUT (1 << ZSTD_BTRFS_MAX_WINDOWLOG)
|
|
#define ZSTD_BTRFS_DEFAULT_LEVEL 3
|
|
|
|
static ZSTD_parameters zstd_get_btrfs_parameters(size_t src_len)
|
|
{
|
|
ZSTD_parameters params = ZSTD_getParams(ZSTD_BTRFS_DEFAULT_LEVEL,
|
|
src_len, 0);
|
|
|
|
if (params.cParams.windowLog > ZSTD_BTRFS_MAX_WINDOWLOG)
|
|
params.cParams.windowLog = ZSTD_BTRFS_MAX_WINDOWLOG;
|
|
WARN_ON(src_len > ZSTD_BTRFS_MAX_INPUT);
|
|
return params;
|
|
}
|
|
|
|
struct workspace {
|
|
void *mem;
|
|
size_t size;
|
|
char *buf;
|
|
struct list_head list;
|
|
};
|
|
|
|
static void zstd_free_workspace(struct list_head *ws)
|
|
{
|
|
struct workspace *workspace = list_entry(ws, struct workspace, list);
|
|
|
|
kvfree(workspace->mem);
|
|
kfree(workspace->buf);
|
|
kfree(workspace);
|
|
}
|
|
|
|
static struct list_head *zstd_alloc_workspace(void)
|
|
{
|
|
ZSTD_parameters params =
|
|
zstd_get_btrfs_parameters(ZSTD_BTRFS_MAX_INPUT);
|
|
struct workspace *workspace;
|
|
|
|
workspace = kzalloc(sizeof(*workspace), GFP_KERNEL);
|
|
if (!workspace)
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
workspace->size = max_t(size_t,
|
|
ZSTD_CStreamWorkspaceBound(params.cParams),
|
|
ZSTD_DStreamWorkspaceBound(ZSTD_BTRFS_MAX_INPUT));
|
|
workspace->mem = kvmalloc(workspace->size, GFP_KERNEL);
|
|
workspace->buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
|
|
if (!workspace->mem || !workspace->buf)
|
|
goto fail;
|
|
|
|
INIT_LIST_HEAD(&workspace->list);
|
|
|
|
return &workspace->list;
|
|
fail:
|
|
zstd_free_workspace(&workspace->list);
|
|
return ERR_PTR(-ENOMEM);
|
|
}
|
|
|
|
static int zstd_compress_pages(struct list_head *ws,
|
|
struct address_space *mapping,
|
|
u64 start,
|
|
struct page **pages,
|
|
unsigned long *out_pages,
|
|
unsigned long *total_in,
|
|
unsigned long *total_out)
|
|
{
|
|
struct workspace *workspace = list_entry(ws, struct workspace, list);
|
|
ZSTD_CStream *stream;
|
|
int ret = 0;
|
|
int nr_pages = 0;
|
|
struct page *in_page = NULL; /* The current page to read */
|
|
struct page *out_page = NULL; /* The current page to write to */
|
|
ZSTD_inBuffer in_buf = { NULL, 0, 0 };
|
|
ZSTD_outBuffer out_buf = { NULL, 0, 0 };
|
|
unsigned long tot_in = 0;
|
|
unsigned long tot_out = 0;
|
|
unsigned long len = *total_out;
|
|
const unsigned long nr_dest_pages = *out_pages;
|
|
unsigned long max_out = nr_dest_pages * PAGE_SIZE;
|
|
ZSTD_parameters params = zstd_get_btrfs_parameters(len);
|
|
|
|
*out_pages = 0;
|
|
*total_out = 0;
|
|
*total_in = 0;
|
|
|
|
/* Initialize the stream */
|
|
stream = ZSTD_initCStream(params, len, workspace->mem,
|
|
workspace->size);
|
|
if (!stream) {
|
|
pr_warn("BTRFS: ZSTD_initCStream failed\n");
|
|
ret = -EIO;
|
|
goto out;
|
|
}
|
|
|
|
/* map in the first page of input data */
|
|
in_page = find_get_page(mapping, start >> PAGE_SHIFT);
|
|
in_buf.src = kmap(in_page);
|
|
in_buf.pos = 0;
|
|
in_buf.size = min_t(size_t, len, PAGE_SIZE);
|
|
|
|
|
|
/* Allocate and map in the output buffer */
|
|
out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
|
|
if (out_page == NULL) {
|
|
ret = -ENOMEM;
|
|
goto out;
|
|
}
|
|
pages[nr_pages++] = out_page;
|
|
out_buf.dst = kmap(out_page);
|
|
out_buf.pos = 0;
|
|
out_buf.size = min_t(size_t, max_out, PAGE_SIZE);
|
|
|
|
while (1) {
|
|
size_t ret2;
|
|
|
|
ret2 = ZSTD_compressStream(stream, &out_buf, &in_buf);
|
|
if (ZSTD_isError(ret2)) {
|
|
pr_debug("BTRFS: ZSTD_compressStream returned %d\n",
|
|
ZSTD_getErrorCode(ret2));
|
|
ret = -EIO;
|
|
goto out;
|
|
}
|
|
|
|
/* Check to see if we are making it bigger */
|
|
if (tot_in + in_buf.pos > 8192 &&
|
|
tot_in + in_buf.pos <
|
|
tot_out + out_buf.pos) {
|
|
ret = -E2BIG;
|
|
goto out;
|
|
}
|
|
|
|
/* We've reached the end of our output range */
|
|
if (out_buf.pos >= max_out) {
|
|
tot_out += out_buf.pos;
|
|
ret = -E2BIG;
|
|
goto out;
|
|
}
|
|
|
|
/* Check if we need more output space */
|
|
if (out_buf.pos == out_buf.size) {
|
|
tot_out += PAGE_SIZE;
|
|
max_out -= PAGE_SIZE;
|
|
kunmap(out_page);
|
|
if (nr_pages == nr_dest_pages) {
|
|
out_page = NULL;
|
|
ret = -E2BIG;
|
|
goto out;
|
|
}
|
|
out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
|
|
if (out_page == NULL) {
|
|
ret = -ENOMEM;
|
|
goto out;
|
|
}
|
|
pages[nr_pages++] = out_page;
|
|
out_buf.dst = kmap(out_page);
|
|
out_buf.pos = 0;
|
|
out_buf.size = min_t(size_t, max_out, PAGE_SIZE);
|
|
}
|
|
|
|
/* We've reached the end of the input */
|
|
if (in_buf.pos >= len) {
|
|
tot_in += in_buf.pos;
|
|
break;
|
|
}
|
|
|
|
/* Check if we need more input */
|
|
if (in_buf.pos == in_buf.size) {
|
|
tot_in += PAGE_SIZE;
|
|
kunmap(in_page);
|
|
put_page(in_page);
|
|
|
|
start += PAGE_SIZE;
|
|
len -= PAGE_SIZE;
|
|
in_page = find_get_page(mapping, start >> PAGE_SHIFT);
|
|
in_buf.src = kmap(in_page);
|
|
in_buf.pos = 0;
|
|
in_buf.size = min_t(size_t, len, PAGE_SIZE);
|
|
}
|
|
}
|
|
while (1) {
|
|
size_t ret2;
|
|
|
|
ret2 = ZSTD_endStream(stream, &out_buf);
|
|
if (ZSTD_isError(ret2)) {
|
|
pr_debug("BTRFS: ZSTD_endStream returned %d\n",
|
|
ZSTD_getErrorCode(ret2));
|
|
ret = -EIO;
|
|
goto out;
|
|
}
|
|
if (ret2 == 0) {
|
|
tot_out += out_buf.pos;
|
|
break;
|
|
}
|
|
if (out_buf.pos >= max_out) {
|
|
tot_out += out_buf.pos;
|
|
ret = -E2BIG;
|
|
goto out;
|
|
}
|
|
|
|
tot_out += PAGE_SIZE;
|
|
max_out -= PAGE_SIZE;
|
|
kunmap(out_page);
|
|
if (nr_pages == nr_dest_pages) {
|
|
out_page = NULL;
|
|
ret = -E2BIG;
|
|
goto out;
|
|
}
|
|
out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
|
|
if (out_page == NULL) {
|
|
ret = -ENOMEM;
|
|
goto out;
|
|
}
|
|
pages[nr_pages++] = out_page;
|
|
out_buf.dst = kmap(out_page);
|
|
out_buf.pos = 0;
|
|
out_buf.size = min_t(size_t, max_out, PAGE_SIZE);
|
|
}
|
|
|
|
if (tot_out >= tot_in) {
|
|
ret = -E2BIG;
|
|
goto out;
|
|
}
|
|
|
|
ret = 0;
|
|
*total_in = tot_in;
|
|
*total_out = tot_out;
|
|
out:
|
|
*out_pages = nr_pages;
|
|
/* Cleanup */
|
|
if (in_page) {
|
|
kunmap(in_page);
|
|
put_page(in_page);
|
|
}
|
|
if (out_page)
|
|
kunmap(out_page);
|
|
return ret;
|
|
}
|
|
|
|
static int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
|
|
{
|
|
struct workspace *workspace = list_entry(ws, struct workspace, list);
|
|
struct page **pages_in = cb->compressed_pages;
|
|
u64 disk_start = cb->start;
|
|
struct bio *orig_bio = cb->orig_bio;
|
|
size_t srclen = cb->compressed_len;
|
|
ZSTD_DStream *stream;
|
|
int ret = 0;
|
|
unsigned long page_in_index = 0;
|
|
unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_SIZE);
|
|
unsigned long buf_start;
|
|
unsigned long total_out = 0;
|
|
ZSTD_inBuffer in_buf = { NULL, 0, 0 };
|
|
ZSTD_outBuffer out_buf = { NULL, 0, 0 };
|
|
|
|
stream = ZSTD_initDStream(
|
|
ZSTD_BTRFS_MAX_INPUT, workspace->mem, workspace->size);
|
|
if (!stream) {
|
|
pr_debug("BTRFS: ZSTD_initDStream failed\n");
|
|
ret = -EIO;
|
|
goto done;
|
|
}
|
|
|
|
in_buf.src = kmap(pages_in[page_in_index]);
|
|
in_buf.pos = 0;
|
|
in_buf.size = min_t(size_t, srclen, PAGE_SIZE);
|
|
|
|
out_buf.dst = workspace->buf;
|
|
out_buf.pos = 0;
|
|
out_buf.size = PAGE_SIZE;
|
|
|
|
while (1) {
|
|
size_t ret2;
|
|
|
|
ret2 = ZSTD_decompressStream(stream, &out_buf, &in_buf);
|
|
if (ZSTD_isError(ret2)) {
|
|
pr_debug("BTRFS: ZSTD_decompressStream returned %d\n",
|
|
ZSTD_getErrorCode(ret2));
|
|
ret = -EIO;
|
|
goto done;
|
|
}
|
|
buf_start = total_out;
|
|
total_out += out_buf.pos;
|
|
out_buf.pos = 0;
|
|
|
|
ret = btrfs_decompress_buf2page(out_buf.dst, buf_start,
|
|
total_out, disk_start, orig_bio);
|
|
if (ret == 0)
|
|
break;
|
|
|
|
if (in_buf.pos >= srclen)
|
|
break;
|
|
|
|
/* Check if we've hit the end of a frame */
|
|
if (ret2 == 0)
|
|
break;
|
|
|
|
if (in_buf.pos == in_buf.size) {
|
|
kunmap(pages_in[page_in_index++]);
|
|
if (page_in_index >= total_pages_in) {
|
|
in_buf.src = NULL;
|
|
ret = -EIO;
|
|
goto done;
|
|
}
|
|
srclen -= PAGE_SIZE;
|
|
in_buf.src = kmap(pages_in[page_in_index]);
|
|
in_buf.pos = 0;
|
|
in_buf.size = min_t(size_t, srclen, PAGE_SIZE);
|
|
}
|
|
}
|
|
ret = 0;
|
|
zero_fill_bio(orig_bio);
|
|
done:
|
|
if (in_buf.src)
|
|
kunmap(pages_in[page_in_index]);
|
|
return ret;
|
|
}
|
|
|
|
static int zstd_decompress(struct list_head *ws, unsigned char *data_in,
|
|
struct page *dest_page,
|
|
unsigned long start_byte,
|
|
size_t srclen, size_t destlen)
|
|
{
|
|
struct workspace *workspace = list_entry(ws, struct workspace, list);
|
|
ZSTD_DStream *stream;
|
|
int ret = 0;
|
|
size_t ret2;
|
|
ZSTD_inBuffer in_buf = { NULL, 0, 0 };
|
|
ZSTD_outBuffer out_buf = { NULL, 0, 0 };
|
|
unsigned long total_out = 0;
|
|
unsigned long pg_offset = 0;
|
|
char *kaddr;
|
|
|
|
stream = ZSTD_initDStream(
|
|
ZSTD_BTRFS_MAX_INPUT, workspace->mem, workspace->size);
|
|
if (!stream) {
|
|
pr_warn("BTRFS: ZSTD_initDStream failed\n");
|
|
ret = -EIO;
|
|
goto finish;
|
|
}
|
|
|
|
destlen = min_t(size_t, destlen, PAGE_SIZE);
|
|
|
|
in_buf.src = data_in;
|
|
in_buf.pos = 0;
|
|
in_buf.size = srclen;
|
|
|
|
out_buf.dst = workspace->buf;
|
|
out_buf.pos = 0;
|
|
out_buf.size = PAGE_SIZE;
|
|
|
|
ret2 = 1;
|
|
while (pg_offset < destlen && in_buf.pos < in_buf.size) {
|
|
unsigned long buf_start;
|
|
unsigned long buf_offset;
|
|
unsigned long bytes;
|
|
|
|
/* Check if the frame is over and we still need more input */
|
|
if (ret2 == 0) {
|
|
pr_debug("BTRFS: ZSTD_decompressStream ended early\n");
|
|
ret = -EIO;
|
|
goto finish;
|
|
}
|
|
ret2 = ZSTD_decompressStream(stream, &out_buf, &in_buf);
|
|
if (ZSTD_isError(ret2)) {
|
|
pr_debug("BTRFS: ZSTD_decompressStream returned %d\n",
|
|
ZSTD_getErrorCode(ret2));
|
|
ret = -EIO;
|
|
goto finish;
|
|
}
|
|
|
|
buf_start = total_out;
|
|
total_out += out_buf.pos;
|
|
out_buf.pos = 0;
|
|
|
|
if (total_out <= start_byte)
|
|
continue;
|
|
|
|
if (total_out > start_byte && buf_start < start_byte)
|
|
buf_offset = start_byte - buf_start;
|
|
else
|
|
buf_offset = 0;
|
|
|
|
bytes = min_t(unsigned long, destlen - pg_offset,
|
|
out_buf.size - buf_offset);
|
|
|
|
kaddr = kmap_atomic(dest_page);
|
|
memcpy(kaddr + pg_offset, out_buf.dst + buf_offset, bytes);
|
|
kunmap_atomic(kaddr);
|
|
|
|
pg_offset += bytes;
|
|
}
|
|
ret = 0;
|
|
finish:
|
|
if (pg_offset < destlen) {
|
|
kaddr = kmap_atomic(dest_page);
|
|
memset(kaddr + pg_offset, 0, destlen - pg_offset);
|
|
kunmap_atomic(kaddr);
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
const struct btrfs_compress_op btrfs_zstd_compress = {
|
|
.alloc_workspace = zstd_alloc_workspace,
|
|
.free_workspace = zstd_free_workspace,
|
|
.compress_pages = zstd_compress_pages,
|
|
.decompress_bio = zstd_decompress_bio,
|
|
.decompress = zstd_decompress,
|
|
};
|