pr\u00e9sentent<\/p>\n\n\n\n
Autoris\u00e9 \u00e0 pr\u00e9senter ses travaux en vue de l\u2019obtention du Doctorat de l’Institut Polytechnique de Paris, pr\u00e9par\u00e9 \u00e0 T\u00e9l\u00e9com SudParis en :<\/p>\n\n\n\n
le JEUDI 14 D\u00c9CEMBRE 2023 \u00e0 10h30<\/p>\n\n\n\n
\u00e0<\/p>\n\n\n\n
Amphith\u00e9\u00e2tre 4
19 Place Marguerite Perey, 91120 Palaiseau<\/p>\n\n\n\n
Membres du jury :<\/strong><\/p>\n\n\n\n M. Ga\u00ebl THOMAS<\/strong>, Professeur, T\u00e9l\u00e9com SudParis, FRANCE – Directeur de these R\u00e9sum\u00e9 :<\/strong><\/p>\n\n\n\n Les centres de donn\u00e9es reposent largement sur les machines virtuelles comme unit\u00e9 de d\u00e9ploiement afin de garantir une isolation forte entre deux d\u00e9ploiements. L’introduction de la virtualisation a permis une am\u00e9lioration significative de l’utilisation des ressources d’un datacenter par rapport \u00e0 la location d’une machine physique pour chaque utilisateur. Malgr\u00e9 ce gain, les machines virtuelles offrent toujours un gain d’utilisation de ressources plus faible que l’isolation fournie par le syst\u00e8me d’exploitation \u00e0 travers des processus. Deux ph\u00e9nom\u00e8nes expliquent le gain relatif des machines virtuelles : au moment de l’allocation d’une VM, un orchestrateur traduit l’allocation en une requ\u00eate d’allocation de plusieurs ressources sur plusieurs serveurs. Le probl\u00e8me que doit r\u00e9soudre l’orchestrateur afin de trouver un placement optimal des VMs est NP-difficile, imposant \u00e0 l’orchestrateur l’utilisation d’heuristiques de placement qui laissent une part de ressource inutilis\u00e9es sur chaque serveur. De plus, durant l’ex\u00e9cution de la VM, la consommation m\u00e9moire augmente \u00e0 mesure que les acc\u00e8s sont effectu\u00e9s et la diff\u00e9rence entre allocation m\u00e9moire et utilisation m\u00e9moire r\u00e9sulte en un ensemble de ressource m\u00e9moire qui ne peuvent \u00eatre utilis\u00e9 sans risque de crash de VMs. Dans un premier temps, nous proposons un prototype permettant d’acc\u00e9der aux ressources m\u00e9moires inutilis\u00e9es sur d’autres serveurs. Notre solution est transparente pour les applications s’ex\u00e9cutant dans une VM et offre une r\u00e9servation \u00e0 grain fin des ressources m\u00e9moires distantes. Dans un second temps, nous pr\u00e9sentons les r\u00e9sultats de notre \u00e9tude des techniques existantes permettant d’ajuster la capacit\u00e9 m\u00e9moire d’une VM sur la m\u00e9moire qu’elle utilise. Notre travail montre que les solutions actuelles impl\u00e9ment\u00e9es au niveau de l’hyperviseur introduisent une d\u00e9gradation des performances des VMs ainsi que des temps de r\u00e9ponse \u00e9lev\u00e9s emp\u00eachant le partage des ressources m\u00e9moires par plusieurs VMs. Nous proposons une solution utilisant les informations disponibles dans la VM pour adapter rapidement leurs capacit\u00e9s m\u00e9moires.<\/p>\n\n\n\n Abstract :<\/strong><\/p>\n\n\n\n Data-centers rely on virtual machines (VMs) to offer isolation between deployments. While, the use of VMs enables better resource usage compared to running a service per bare-metal machine, it achieves poorer resource usage than multiprocessus solutions. This is caused by two phenomena: At VM allocation time, VMs are scheduled as resource requests on a VM scheduler which perform virtual machine allocations across a set of servers. Optimal solution to this scheduling problem is NP-hard leading to the adoption of heuristic based allocation that let a good percentage of unallocated memory on each server known as `stranded memory`. At VM runtime, VM memory is consumed on-demand and the difference between memory allocation and usage results in a decent portion of `allocated unused memory` currently impractically usable. First, we propose a transparent solution for applications running inside VMs to remotely access stranded memory in remote machines with fine-grained reservation of remote resources. Second, we review current techniques trying to fit allocated memory to used memory. We show that all these techniques are managed by the hypervisor and introduce performance degradation in VMs and more importantly high response time which makes resource sharing unpractical. Instead, we propose an abstraction to perform VM-initiated memory provisioning, and we present early results of fast adaptation of VM memory.<\/p>\n","protected":false},"excerpt":{"rendered":" L’Ecole doctorale : Ecole Doctorale de l’Institut Polytechnique de Paris et le Laboratoire de recherche SAMOVAR – Services r\u00e9partis, Architectures, Mod\u00e9lisation, Validation, Administration des R\u00e9seaux pr\u00e9sentent l\u2019AVIS DE SOUTENANCE de Monsieur Yohan PIPEREAU Autoris\u00e9 \u00e0 pr\u00e9senter ses travaux en vue de l\u2019obtention du Doctorat de l’Institut Polytechnique de Paris, pr\u00e9par\u00e9 \u00e0 T\u00e9l\u00e9com SudParis en : […]<\/p>\n","protected":false},"author":4,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"ocean_post_layout":"","ocean_both_sidebars_style":"","ocean_both_sidebars_content_width":0,"ocean_both_sidebars_sidebars_width":0,"ocean_sidebar":"0","ocean_second_sidebar":"0","ocean_disable_margins":"enable","ocean_add_body_class":"","ocean_shortcode_before_top_bar":"","ocean_shortcode_after_top_bar":"","ocean_shortcode_before_header":"","ocean_shortcode_after_header":"","ocean_has_shortcode":"","ocean_shortcode_after_title":"","ocean_shortcode_before_footer_widgets":"","ocean_shortcode_after_footer_widgets":"","ocean_shortcode_before_footer_bottom":"","ocean_shortcode_after_footer_bottom":"","ocean_display_top_bar":"default","ocean_display_header":"default","ocean_header_style":"","ocean_center_header_left_menu":"0","ocean_custom_header_template":"0","ocean_custom_logo":0,"ocean_custom_retina_logo":0,"ocean_custom_logo_max_width":0,"ocean_custom_logo_tablet_max_width":0,"ocean_custom_logo_mobile_max_width":0,"ocean_custom_logo_max_height":0,"ocean_custom_logo_tablet_max_height":0,"ocean_custom_logo_mobile_max_height":0,"ocean_header_custom_menu":"0","ocean_menu_typo_font_family":"0","ocean_menu_typo_font_subset":"","ocean_menu_typo_font_size":0,"ocean_menu_typo_font_size_tablet":0,"ocean_menu_typo_font_size_mobile":0,"ocean_menu_typo_font_size_unit":"px","ocean_menu_typo_font_weight":"","ocean_menu_typo_font_weight_tablet":"","ocean_menu_typo_font_weight_mobile":"","ocean_menu_typo_transform":"","ocean_menu_typo_transform_tablet":"","ocean_menu_typo_transform_mobile":"","ocean_menu_typo_line_height":0,"ocean_menu_typo_line_height_tablet":0,"ocean_menu_typo_line_height_mobile":0,"ocean_menu_typo_line_height_unit":"","ocean_menu_typo_spacing":0,"ocean_menu_typo_spacing_tablet":0,"ocean_menu_typo_spacing_mobile":0,"ocean_menu_typo_spacing_unit":"","ocean_menu_link_color":"","ocean_menu_link_color_hover":"","ocean_menu_link_color_active":"","ocean_menu_link_background":"","ocean_menu_link_hover_background":"","ocean_menu_link_active_background":"","ocean_menu_social_links_bg":"","ocean_menu_social_hover_links_bg":"","ocean_menu_social_links_color":"","ocean_menu_social_hover_links_color":"","ocean_disable_title":"default","ocean_disable_heading":"default","ocean_post_title":"","ocean_post_subheading":"","ocean_post_title_style":"","ocean_post_title_background_color":"","ocean_post_title_background":0,"ocean_post_title_bg_image_position":"","ocean_post_title_bg_image_attachment":"","ocean_post_title_bg_image_repeat":"","ocean_post_title_bg_image_size":"","ocean_post_title_height":0,"ocean_post_title_bg_overlay":0.5,"ocean_post_title_bg_overlay_color":"","ocean_disable_breadcrumbs":"default","ocean_breadcrumbs_color":"","ocean_breadcrumbs_separator_color":"","ocean_breadcrumbs_links_color":"","ocean_breadcrumbs_links_hover_color":"","ocean_display_footer_widgets":"default","ocean_display_footer_bottom":"default","ocean_custom_footer_template":"0","ocean_post_oembed":"","ocean_post_self_hosted_media":"","ocean_post_video_embed":"","ocean_link_format":"","ocean_link_format_target":"self","ocean_quote_format":"","ocean_quote_format_link":"post","ocean_gallery_link_images":"off","ocean_gallery_id":[],"footnotes":""},"categories":[286,623],"tags":[],"class_list":["post-6418","post","type-post","status-publish","format-standard","hentry","category-fractualites-ennews-fr","category-seminaires-benagil-fr","entry"],"_links":{"self":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/6418","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/comments?post=6418"}],"version-history":[{"count":1,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/6418\/revisions"}],"predecessor-version":[{"id":6419,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/6418\/revisions\/6419"}],"wp:attachment":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/media?parent=6418"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/categories?post=6418"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/tags?post=6418"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
M. Pierre SENS<\/strong>, Professeur, Sorbonne Universit\u00e9, FRANCE – Rapporteur
M. Romain ROUVOY<\/strong>, Professeur, l\u2019Universit\u00e9 de Lille 1, Sciences et Technologies, FRANCE – Rapporteur
M. Brice GOGLIN<\/strong>, Directeur de recherche, Universit\u00e9 de Bordeaux, FRANCE – Examinateur
M. Mathieu BACOU<\/strong>, Ma\u00eetre de conf\u00e9rences, T\u00e9l\u00e9com SudParis, FRANCE – Co-encadrant de these
Mme Stella BITCHEBE<\/strong>, Postdoctoral Researcher, McGill University, CANADA – Examinateur<\/p>\n\n\n\n\u00ab Am\u00e9lioration de l’utilisation de ressources m\u00e9moires pour les machines virtuelles \u00bb<\/h2>\n\n\n\n
pr\u00e9sent\u00e9 par Monsieur Yohan PIPEREAU<\/h2>\n\n\n\n