From: "Austin S. Hemmelgarn" Subject: Re: [PATCH v5 2/5] lib: Add zstd modules Date: Thu, 10 Aug 2017 07:32:18 -0400 Message-ID: References: <20170810023553.3200875-1-terrelln@fb.com> <20170810023553.3200875-3-terrelln@fb.com> <20170810083017.GA10462@zzz.localdomain> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit Cc: Herbert Xu , kernel-team@fb.com, squashfs-devel@lists.sourceforge.net, linux-btrfs@vger.kernel.org, linux-kernel@vger.kernel.org, linux-crypto@vger.kernel.org To: Eric Biggers , Nick Terrell Return-path: In-Reply-To: <20170810083017.GA10462@zzz.localdomain> Content-Language: en-US Sender: linux-kernel-owner@vger.kernel.org List-Id: linux-crypto.vger.kernel.org On 2017-08-10 04:30, Eric Biggers wrote: > On Wed, Aug 09, 2017 at 07:35:53PM -0700, Nick Terrell wrote: >> >> It can compress at speeds approaching lz4, and quality approaching lzma. > > Well, for a very loose definition of "approaching", and certainly not at the > same time. I doubt there's a use case for using the highest compression levels > in kernel mode --- especially the ones using zstd_opt.h. Large data-sets with WORM access patterns and infrequent writes immediately come to mind as a use case for the highest compression level. As a more specific example, the company I work for has a very large amount of documentation, and we keep all old versions. This is all stored on a file server which is currently using BTRFS. Once a document is written, it's almost never rewritten, so write performance only matters for the first write. However, they're read back pretty frequently, so we need good read performance. As of right now, the system is set to use LZO compression by default, and then when a new document is added, the previous version of that document gets re-compressed using zlib compression, which actually results in pretty significant space savings most of the time. I would absolutely love to use zstd compression with this system with the highest compression level, because most people don't care how long it takes to write the file out, but they do care how long it takes to read a file (even if it's an older version). > >> >> The code was ported from the upstream zstd source repository. > > What version? > >> `linux/zstd.h` header was modified to match linux kernel style. >> The cross-platform and allocation code was stripped out. Instead zstd >> requires the caller to pass a preallocated workspace. The source files >> were clang-formatted [1] to match the Linux Kernel style as much as >> possible. > > It would be easier to compare to the upstream version if it was not all > reformatted. There is a chance that bugs were introduced by Linux-specific > changes, and it would be nice if they could be easily reviewed. (Also I don't > know what clang-format settings you used, but there are still a lot of > differences from the Linux coding style.) > >> >> I benchmarked zstd compression as a special character device. I ran zstd >> and zlib compression at several levels, as well as performing no >> compression, which measure the time spent copying the data to kernel space. >> Data is passed to the compresser 4096 B at a time. The benchmark file is >> located in the upstream zstd source repository under >> `contrib/linux-kernel/zstd_compress_test.c` [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. I benchmarked using `silesia.tar` [3], which is >> 211,988,480 B large. Run the following commands for the benchmark: >> >> sudo modprobe zstd_compress_test >> sudo mknod zstd_compress_test c 245 0 >> sudo cp silesia.tar zstd_compress_test >> >> The time is reported by the time of the userland `cp`. >> The MB/s is computed with >> >> 1,536,217,008 B / time(buffer size, hash) >> >> which includes the time to copy from userland. >> The Adjusted MB/s is computed with >> >> 1,536,217,088 B / (time(buffer size, hash) - time(buffer size, none)). >> >> The memory reported is the amount of memory the compressor requests. >> >> | Method | Size (B) | Time (s) | Ratio | MB/s | Adj MB/s | Mem (MB) | >> |----------|----------|----------|-------|---------|----------|----------| >> | none | 11988480 | 0.100 | 1 | 2119.88 | - | - | >> | zstd -1 | 73645762 | 1.044 | 2.878 | 203.05 | 224.56 | 1.23 | >> | zstd -3 | 66988878 | 1.761 | 3.165 | 120.38 | 127.63 | 2.47 | >> | zstd -5 | 65001259 | 2.563 | 3.261 | 82.71 | 86.07 | 2.86 | >> | zstd -10 | 60165346 | 13.242 | 3.523 | 16.01 | 16.13 | 13.22 | >> | zstd -15 | 58009756 | 47.601 | 3.654 | 4.45 | 4.46 | 21.61 | >> | zstd -19 | 54014593 | 102.835 | 3.925 | 2.06 | 2.06 | 60.15 | >> | zlib -1 | 77260026 | 2.895 | 2.744 | 73.23 | 75.85 | 0.27 | >> | zlib -3 | 72972206 | 4.116 | 2.905 | 51.50 | 52.79 | 0.27 | >> | zlib -6 | 68190360 | 9.633 | 3.109 | 22.01 | 22.24 | 0.27 | >> | zlib -9 | 67613382 | 22.554 | 3.135 | 9.40 | 9.44 | 0.27 | >> > > Theses benchmarks are misleading because they compress the whole file as a > single stream without resetting the dictionary, which isn't how data will > typically be compressed in kernel mode. With filesystem compression the data > has to be divided into small chunks that can each be decompressed independently. > That eliminates one of the primary advantages of Zstandard (support for large > dictionary sizes).