{"id":13584259,"url":"https://github.com/dolohow/uksm","last_synced_at":"2025-04-07T01:31:52.352Z","repository":{"id":37451132,"uuid":"60715085","full_name":"dolohow/uksm","owner":"dolohow","description":"Ultra Kernel Samepage Merging","archived":true,"fork":false,"pushed_at":"2022-05-23T13:18:16.000Z","size":443,"stargazers_count":241,"open_issues_count":18,"forks_count":35,"subscribers_count":34,"default_branch":"master","last_synced_at":"2024-11-06T01:39:48.278Z","etag":null,"topics":["kernel","ksm","linux","patch"],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dolohow.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2016-06-08T17:03:36.000Z","updated_at":"2024-08-05T14:15:03.000Z","dependencies_parsed_at":"2022-08-01T00:08:27.251Z","dependency_job_id":null,"html_url":"https://github.com/dolohow/uksm","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dolohow%2Fuksm","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dolohow%2Fuksm/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dolohow%2Fuksm/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dolohow%2Fuksm/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dolohow","download_url":"https://codeload.github.com/dolohow/uksm/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247577998,"owners_count":20961214,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["kernel","ksm","linux","patch"],"created_at":"2024-08-01T15:04:07.531Z","updated_at":"2025-04-07T01:31:47.343Z","avatar_url":"https://github.com/dolohow.png","language":null,"funding_links":[],"categories":["Others"],"sub_categories":[],"readme":"# UKSM\n----------------------------------------------------\nThe patches in this repo are the latest UKSM patches\n\nThe current release number: 0.1.2.6\n\nThis release includes two bug fixes from Huawei, many thanks to their engineers and esepcially to @colo-ft who submitted the patches.\n\nChangelog for all versions is in Documentation/vm/uksm.txt.\n\n# What is it?\n\nThe Ultra Kernel Samepage Merging feature\n----------------------------------------------\n\nUltra KSM. Copyright (C) 2011-2016 Nai Xia\n\nThis is an improvement upon KSM. Some basic data structures and routines\nare borrowed from ksm.c .\n\nIts new features:\n\n1. Full system scan:\n     It automatically scans all user processes' anonymous VMAs. Kernel-user\n     interaction to submit a memory area to KSM is no longer needed.\n\n2. Rich area detection:\n     It automatically detects rich areas containing abundant duplicated\n     pages based. Rich areas are given a full scan speed. Poor areas are\n     sampled at a reasonable speed with very low CPU consumption.\n\n3. Ultra Per-page scan speed improvement:\n     A new hash algorithm is proposed. As a result, on a machine with\n     Core(TM)2 Quad Q9300 CPU in 32-bit mode and 800MHZ DDR2 main memory, it\n     can scan memory areas that does not contain duplicated pages at speed of\n     627MB/sec ~ 2445MB/sec and can merge duplicated areas at speed of\n     477MB/sec ~ 923MB/sec.\n\n4. Thrashing area avoidance:\n     Thrashing area(an VMA that has frequent Ksm page break-out) can be\n     filtered out. My benchmark shows it's more efficient than KSM's per-page\n     hash value based volatile page detection.\n\n\n5. Misc changes upon KSM:\n     * It has a fully x86-opitmized memcmp dedicated for 4-byte-aligned page\n       comparison. It's much faster than default C version on x86.\n     * rmap_item now has an struct *page member to loosely cache a\n       address--\u003epage mapping, which reduces too much time-costly\n       follow_page().\n     * The VMA creation/exit procedures are hooked to let the Ultra KSM know.\n     * try_to_merge_two_pages() now can revert a pte if it fails. No break_\n       ksm is needed for this case.\n\n6. Full Zero Page consideration(contributed by Figo Zhang)\n   Now uksmd consider full zero pages as special pages and merge them to an\n   special unswappable uksm zero page.\n\n# Credits\n\nUltra KSM. Copyright (C) 2011-2016 Nai Xia\n\n\n# Reference\n\n[FAST '18] UKSM: Swift Memory Deduplication via Hierarchical and Adaptive Memory Region Distilling [[PDF](https://www.usenix.org/system/files/conference/fast18/fast18-xia.pdf)] [[Slides](https://www.usenix.org/sites/default/files/conference/protected-files/fast18_slides_xia.pdf)]\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdolohow%2Fuksm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdolohow%2Fuksm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdolohow%2Fuksm/lists"}