{"full_name":"facebook/zstd","owner":"facebook","name":"zstd","shard":"1","url":"https://github.com/facebook/zstd","description":"Zstandard - Fast real-time compression algorithm","homepage":"http://www.zstd.net","topics":[],"tag_pages":[],"language":"C","license":"NOASSERTION","avatar":"https://avatars.githubusercontent.com/u/69631?v=4","created_at":"2015-01-24T00:22:38Z","pushed_at":"2026-11-15T18:46:57Z","metrics":{"stars":28254,"forks":2690,"watchers":410,"issues":1614,"prs":3283,"releases":68,"issues_open":262,"issues_closed":1352,"prs_open":170,"prs_closed":482,"prs_merged":2631,"discussions":0},"growth":{"day":{"stars":4,"forks":1,"base_day":"2026-11-15"},"week":{"stars":101,"forks":19,"base_day":"2026-11-04"},"month":{"stars":245,"forks":61,"base_day":"2026-10-17"}},"history":{"dates":["2026-09-19","2026-09-20","2026-09-21","2026-09-22","2026-09-23","2026-09-24","2026-09-25","2026-09-26","2026-09-27","2026-09-28","2026-09-29","2026-09-30","2026-10-01","2026-10-02","2026-10-03","2026-10-04","2026-10-05","2026-10-06","2026-10-07","2026-10-08","2026-10-09","2026-10-10","2026-10-11","2026-10-12","2026-10-13","2026-10-14","2026-10-15","2026-10-16","2026-10-17","2026-10-18","2026-10-19","2026-10-20","2026-10-21","2026-10-22","2026-10-23","2026-10-24","2026-10-25","2026-10-26","2026-10-27","2026-10-28","2026-10-29","2026-10-30","2026-10-31","2026-11-01","2026-11-02","2026-11-03","2026-11-04","2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[27750,27804,27819,27833,27841,27855,27864,27873,27881,27894,27899,27915,27921,27923,27934,27937,27945,27950,27950,27959,27964,27971,27979,27987,27995,27997,27998,28003,28009,28019,28021,28029,28036,28045,28057,28064,28074,28079,28088,28091,28099,28105,28114,28117,28124,28153,28153,28216,28228,28243,28250,28246,28250,28254],"forks":[2589,2593,2594,2597,2598,2599,2601,2603,2604,2606,2607,2611,2613,2614,2615,2614,2614,2616,2619,2621,2620,2620,2621,2621,2623,2624,2624,2627,2629,2631,2630,2634,2636,2637,2639,2640,2643,2646,2646,2651,2654,2656,2658,2664,2665,2670,2671,2680,2683,2685,2685,2687,2689,2690],"watchers":[414,414,414,414,414,414,414,415,415,415,415,415,416,416,416,416,416,416,415,414,414,414,414,414,414,414,414,414,414,414,414,414,414,414,414,414,414,414,414,409,409,409,409,409,409,409,409,null,411,411,411,410,410,410],"issues_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,270,266,266,266,262,262],"prs_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,184,183,185,186,174,170]},"boards":{},"same_owner":[{"full_name":"facebook/react","name":"react","shard":"1","boards":{"daily_rate":197,"total":22}},{"full_name":"facebook/astryx","name":"astryx","shard":"1","boards":{"daily":20,"weekly":6,"monthly":30,"daily_rate":59,"weekly_rate":36,"monthly_rate":35,"daily_forks":44,"daily_watchers":81}},{"full_name":"facebook/fresco","name":"fresco","shard":"1","boards":{}}],"issues":[{"number":395,"title":"Is zstd splitabble in hadoop/spark/etc? ","comments":58,"created_at":"2016-09-28T13:20:29Z"},{"number":3271,"title":"Make CMake official? (Makefile build does not provide CMake config file)","comments":24,"created_at":"2022-09-21T21:34:10Z"},{"number":3882,"title":"zstd fails to process some filenames on Windows [we need a hero]","comments":19,"created_at":"2024-01-24T18:34:08Z"},{"number":2173,"title":"--patch-from extensions and speed optimizations","comments":19,"created_at":"2020-05-25T09:44:42Z"},{"number":2460,"title":"zstd_btultra corner case","comments":18,"created_at":"2021-01-07T20:26:38Z"},{"number":3508,"title":"issues found while fuzzing to compare behaviour of Zig decoder to this repo","comments":17,"created_at":"2023-02-14T09:06:50Z"},{"number":4446,"title":"small regression in compressed size of tiny chunk from commit 6004c11","comments":14,"created_at":"2025-07-23T16:28:54Z"},{"number":3627,"title":"Zstd should not ignore symbolic links when writing to stdout","comments":13,"created_at":"2023-04-21T08:41:28Z"}],"discussions":[],"latest_release":{"name":"Zstandard v1.5.7","tag":"v1.5.7","published_at":"2025-02-19T21:50:11Z","body":"Zstandard `v1.5.7` is a significant release, featuring over 500 commits accumulated over the past year. This update brings enhancements across various domains, including performance, stability, and functionality, and is particularly recommended for 32-bit users due to a bug fix detailed below.\r\n\r\n_edit_: man pages were not properly updated in this package, and are still pointing to `v1.5.6`. If you want the `v1.5.7` version, they are updated in `dev` branch, and can be cherry-picked using commit 6af3842118ea5325480b403213b2a9fbed3d3d74. Alternatively, they can also be built locally using `make manual` and `make -C programs man`.\r\n\r\n## Performance Enhancements\r\n\r\n### Enhanced Compression Speed for Small Data Blocks\r\n\r\nThe compression speed for small data blocks has been notably improved at fast compression levels, thanks to contributions from @TocarIP, further extended in #4165. Below are benchmark results illustrating the performance improvements for level 1 compression on the Silesia corpus, segmented into different block sizes:\r\n\r\n| Block Size | v1.5.6 | v1.5.7 | Improv. |\r\n| --- | --- | --- | --- |\r\n|   4 KB | 280 MB/s | 310 MB/s | +10% |\r\n|   8 KB | 328 MB/s | 364 MB/s | +11% |\r\n|  16 KB | 360 MB/s | 396 MB/s | +10% |\r\n|  32 KB | 383 MB/s | 458 MB/s | +20% |\r\n|  64 KB | 423 MB/s | 474 MB/s | +12% |\r\n| 128 KB | 460 MB/s | 485 MB/s | +5% |\r\n\r\nThese improvements are particularly beneficial in data centers and databases, where data is often divided into small segments to enhance seekability. A notable example is [RocksDB](https://github.com/facebook/rocksdb), which is frequently configured with block sizes around 16 KB. Such systems will experience an immediate performance boost by updating their compression library to `v1.5.7`.\r\n\r\nAdditionally, the speed improvements partially extend to dictionary compression, with observed gains ranging from none to +15%.\r\n\r\n### Substantial `--patch-from` improvements\r\n\r\nThe  `--patch-from`  functionality of the  `zstd`  CLI allows for differential compression of a file given an older version, similar to  `bsdiff`. While compression levels impact processing speed and compression ratio as expected, at high compression levels (18+), speed was previously reduced to uncomfortable levels.\r\n\r\n`v1.5.7`  largely mitigates the speed impact of high compression levels 18+, as illustrated in the following scenario, which compresses  `linux-6.13.tar`  as a difference from  `linux-6.12.tar`  using 6 threads:\r\n\r\n| level | v1.5.6 | v1.5.7 | Improv. |\r\n| --- | --- | --- | --- |\r\n| 18 | 210 s | 42.7 s | x4.9 |\r\n| 19 | 273 s | 61.8 s | x4.4 |\r\n| 20 | 310 s | 82.3 s | x3.8 |\r\n| 21 | 365 s | 120 s | x3.1 |\r\n\r\nAdditionally, compression ratio of `--patch-from`  is also substantially improved across the board, including higher compression levels:\r\n\r\n| level | v1.5.6 | v1.5.7 | Improv. |\r\n| --- | --- | --- | --- |\r\n| 15 | 6,383,341 | 6,003,514 | 6.3% |\r\n| 16 | 5,909,932 | 5,421,444 | 9.0% |\r\n| 17 | 5,613,879 | 5,214,734 | 7.7% |\r\n| 18 | 5,584,219 | 5,075,507 |10.0% |\r\n| 19 | 5,322,658 | 4,724,116 |12.6% |\r\n| 20 | 5,097,236 | 4,583,435 |11.2% |\r\n| 21 | 4,648,583 | 4,297,672 | 8.1% |\r\n| 22 | 4,560,051 | 4,225,283 | 7.9% |\r\n| `--max` |  N/A | 3,999,476 |\r\n    \r\n### Compression ratio improvements for large files\r\n\r\nThe compression ratio has been enhanced slightly for large data across all compression levels, thanks to a refined approach in selecting block boundaries. This improvement is more pronounced at lower compression levels (≤ 15), where the previous boundary selection method was relatively basic. In contrast, higher compression levels (16+) already employed some analysis, but still benefit from the introduction of the new heuristic, resulting in marginally better compression ratios.\r\n\r\nA comparison of the compression ratios between  `v1.5.6`  and  `v1.5.7`  is presented below:\r\n\r\n| level | `v1.5.6` | `v1.5.7` | Improv. |\r\n| --- | --- | --- | ---:|\r\n| 1 | 73,492,125 | 73,292,801 | -199,324\r\n| 3 | 66,555,241 | 66,2","is_prerelease":false},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}