{"id":22359904,"url":"https://github.com/xiandong79/interference-aware-cluster-management","last_synced_at":"2026-02-09T22:31:33.624Z","repository":{"id":99039781,"uuid":"101944842","full_name":"xiandong79/Interference-Aware-Cluster-Management","owner":"xiandong79","description":null,"archived":false,"fork":false,"pushed_at":"2017-09-01T07:24:15.000Z","size":39644,"stargazers_count":3,"open_issues_count":0,"forks_count":2,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-08-20T14:49:37.201Z","etag":null,"topics":["interference-mitigation","management-server"],"latest_commit_sha":null,"homepage":null,"language":"HTML","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/xiandong79.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2017-08-31T01:21:06.000Z","updated_at":"2021-08-31T06:27:07.000Z","dependencies_parsed_at":null,"dependency_job_id":"68118e8b-4531-4354-ae79-b96ec829c308","html_url":"https://github.com/xiandong79/Interference-Aware-Cluster-Management","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/xiandong79/Interference-Aware-Cluster-Management","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xiandong79%2FInterference-Aware-Cluster-Management","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xiandong79%2FInterference-Aware-Cluster-Management/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xiandong79%2FInterference-Aware-Cluster-Management/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xiandong79%2FInterference-Aware-Cluster-Management/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/xiandong79","download_url":"https://codeload.github.com/xiandong79/Interference-Aware-Cluster-Management/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xiandong79%2FInterference-Aware-Cluster-Management/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29283578,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-09T21:57:15.303Z","status":"ssl_error","status_checked_at":"2026-02-09T21:57:11.537Z","response_time":56,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["interference-mitigation","management-server"],"created_at":"2024-12-04T15:28:09.987Z","updated_at":"2026-02-09T22:31:33.610Z","avatar_url":"https://github.com/xiandong79.png","language":"HTML","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Interference Aware Cluster Management\n\n\n## Background\n\n### [Relevant papers](https://github.com/xiandong79/Interference-Aware-Cluster-Management/tree/master/papers)\n1. Paragon: QoS-Aware Scheduling for Heterogeneous Datacenters - ASPLOS ’13\n2. Quasar: Resource-Efficient and QoS-Aware Cluster Management - ASPLOS ’14\n\n## [Testbed Installation](https://github.com/xiandong79/Interference-Aware-Cluster-Management/tree/master/installation-docs)\n\n1. SPEC CPU2006 单线程负载\n2. memcached 内存型数据库\n3. parsec 多线程负载\n4. websearch Latency critical 任务\n5. perf/lib-perf 任务性能检测\n\n## [Test \u0026 collect data](https://github.com/xiandong79/Interference-Aware-Cluster-Management/tree/master/shell-scripts)\n\n1. [bash_basic.sh](https://github.com/xiandong79/Interference-Aware-Cluster-Management/blob/master/shell-scripts/bash_basic.sh) - SPEC CPU 2006 任务间相互干扰\n2. [memcached+spec2006.sh](https://github.com/xiandong79/Interference-Aware-Cluster-Management/blob/master/shell-scripts/memcached%2Bspec2006.sh) - memcached+spec2006 任务间相互干扰\n3. [ibench.sh](https://github.com/xiandong79/Interference-Aware-Cluster-Management/blob/master/shell-scripts/ibench.sh) [autorun_ibench.sh](https://github.com/xiandong79/Interference-Aware-Cluster-Management/blob/master/shell-scripts/autorun_ibench.sh) - SPEC CPU 2006 任务在 ibench 七种不同压力干扰下的运行状况\n\n## Data Analysis\n\n1. [ALS_SGD_MF.py](https://github.com/xiandong79/Interference-Aware-Cluster-Management/blob/master/data-analysis-scripts/ALS_SGD_MF.py) \n\n```\n# Train rmse: 0.632234683903\n# Test rmse: 0.958863923627\n```\n2. [gridsearch_ALS_SGD_MF.py](https://github.com/xiandong79/Interference-Aware-Cluster-Management/blob/master/data-analysis-scripts/gridsearch_ALS_SGD_MF.py) - 可遍历地求出最优超参数\n\n3. [基于服务器 IPS参数 的推荐系统-20170823版本.html](https://github.com/xiandong79/Interference-Aware-Cluster-Management/blob/master/data-analysis-scripts/基于服务器%20IPS参数%20的推荐系统-20170823版本.html)\n\n```\n载入原始数据¶\nIn [2]:\n# Load data from disk\n\nnames = ['workload_id', 'pressure_id', 'rating']\ndf = pd.read_csv('/Users/dong/Desktop/体系-数据分析/IPS-rating-final.csv',delimiter=\",\", names=names)\n\nprint(df.shape)\n\nnum_workloads = df.workload_id.unique().shape[0]\nnum_pressures = df.pressure_id.unique().shape[0]\n\nprint(num_workloads, \"kinds of workloads\")\nprint(num_pressures, \"kinds of pressures\")\n(86, 3)\n12 kinds of workloads\n8 kinds of pressures\n```\n\n![](https://github.com/xiandong79/Interference-Aware-Cluster-Management/blob/master/pictures/plot-RMSE.png)\n\n## Results and Conclusion\n在未来的使用中，每次任务提交时，只需在IPS-rating-final.csv文件中，继续补充 此种workload_id 的在 pressure_id 测试值（2-3次），即可得出此种 workload在每一种压力下的 “百分制评分”。 Greedily选择最高评分即可。\n\n```\nPrediction Result...\n[[ 53  81  52  74 100  96  99 101]\n [ 49  79  49  72  98  94  97 100]\n [ 50  79  48  71  99  95  98 100]\n [ 51  78  47  70  97  93  97  99]\n [ 50  78  49  71  97  94  97  99]\n [ 50  78  50  71  96  93  95  98]\n [ 51  78  47  70  97  93  97  99]\n [ 86  81  58  76  88  87  92  95]\n [ 49  80  51  73 100  96  99 101]\n [ 50  79  50  72  98  94  97 100]\n [ 69  80  70  77  87  85  87  88]\n [ 79  80  78  79  82  81  82  83]]\n``` \n \n\n![](https://github.com/xiandong79/Interference-Aware-Cluster-Management/blob/master/pictures/libquantum_CPI.PNG)\n\n![](https://github.com/xiandong79/Interference-Aware-Cluster-Management/blob/master/pictures/libquantum_IPS.PNG)\n\n![](https://github.com/xiandong79/Interference-Aware-Cluster-Management/blob/master/pictures/sjeng_IPS.PNG)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxiandong79%2Finterference-aware-cluster-management","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fxiandong79%2Finterference-aware-cluster-management","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxiandong79%2Finterference-aware-cluster-management/lists"}