DOCSLIB.ORG

Synnefo + Ganeti + Ceph

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Synnefo + Ganeti + Ceph 12/10/2013 Ceph Day London [email protected] SYNNEFO + GANETI + CEPH. VANGELIS KOUKIS, TECHNICAL LEAD, SYNNEFO 1 1 12/10/2013 Ceph Day London Running a public cloud: ~okeanos [email protected] History - Design started late 2010 - Production since July 2011 Numbers - Users: > 3500 - VMs: > 5500 currently active - More than 160k VMs spawned so far, more than 44k networks 2 2 12/10/2013 Ceph Day London Running a public cloud: ~okeanos [email protected] Our choices - Build own AWS-like service (Compute, Network, Storage) - Persistent VMs - Everything open source - Production-quality IaaS - Super-simple UI How? 3 3 12/10/2013 Ceph Day London Running a public cloud: ~okeanos [email protected] The tough stuff - Stability - Persistent VMs: VMs are not cattle, they are pets - Commodity hardware - Scalability - Manageability: Gradual rollout of upgrades and new features 4 4 12/10/2013 Ceph Day London Running a public cloud: ~okeanos [email protected] Our approach - Synnefo - Google Ganeti -DRBD -Ceph -OpenStackAPIs 5 5 ~okeanos VMs 3000 3500 4000 4500 1000 1500 2000 2500 500 0 6/8/2011 6/9/2011 6/10/2011 6/11/2011 6/12/2011 6/1/2012 6/2/2012 6/3/2012 6/4/2012 6/5/2012 6/6/2012 6/7/2012 6/8/2012 6/9/2012 6/10/2012 6/11/2012 6/12/2012 6/1/2013 6/2/2013 6/3/2013 6/4/2013 [email protected] Ceph DayLondon 6 VMs 12/10/2013 6 12/10/2013 Ceph Day London Cluster vs Cloud [email protected] OPENSTACK SYNNEFO UI OPENSTACK OPENSTACK API SYNNEFO CLOUD OPENSTACK CLUSTER GANETI LIBVIRT NODE KVM KVM HYPERVISOR 8 7 12/10/2013 Ceph Day London Google Ganeti [email protected] Mature, production-ready VM cluster management - used for Google’s corporate infrastructure Multiple storage backends out of the box -LVM, DRBD - Files on local or shared directory - RBD (Ceph/RADOS) External Storage Interface for SAN/NAS support Ganeti cluster = masterd on master, noded on nodes Easy to integrate into existing infrastructure - Remote API over HTTP, pre/post hooks for every action! 9 8 12/10/2013 Ceph Day London Architecture [email protected] 10 9 12/10/2013 Ceph Day London [email protected] Spawn my own Ubuntu Freeze 11 10 12/10/2013 Ceph Day London [email protected] Clone Ubuntu + user data Snapshot 12 11 12/10/2013 Ceph Day London [email protected] 13 12 12/10/2013 Ceph Day London [email protected] 14 13 12/10/2013 Ceph Day London [email protected] RADOS block I/O Monitor nodes Volume Composer Storage Mapper and object I/O Blocker Archipelago Object Storage nodes 15 14 12/10/2013 Ceph Day London Volumes: Archipelago [email protected] 16 15 12/10/2013 Ceph Day London Volumes: Archipelago [email protected] Unified storage for Files, Images Volumes Thin layer over the actual storage cluster Storage backend agnostic - NFS, RADOS, … Efficient syncing / sharing of Images as files on the storage service Zero-copy cloning of volumes from Images 17 16 12/10/2013 Ceph Day London Experience [email protected] Operations - Rolling hardware and software upgrades - kernel, Ganeti, RADOS, Synnefo - with no VM downtime - Node evacuations with live VM migrations - Cross-datacenter move, Intel AMD, no VM downtime - On-the-fly migration from NFS-backed storage to RADOS - IP renumbering of all VMs 18 17 12/10/2013 Ceph Day London Experience [email protected] Scalability - From few physical hosts to multiple racks - dynamic addition of Ganeti clusters Diverse workloads - Different network and storage backends - Choice exposed to the user 19 18 12/10/2013 Ceph Day London Try it out! [email protected] http://www.synnefo.org 20 19 12/10/2013 Ceph Day London Thank you! [email protected] 21 20.
Load more

Recommended publications
  • May 2013 M&A and Investment Summary
    May 2013 M&A and Investment Summary Expertise. Commitment. Results. Table of Contents 1 Overview of Monthly M&A and Investment Activity 3 2 Monthly M&A and Investment Activity by Industry Segment 8 3 Additional Monthly M&A and Investment Activity Data 40 4 About Petsky Prunier 55 Securities offered through Petsky Prunier Securities, LLC, member of FINRA. This M&A and Investment Summary has been prepared by and is being distributed in the United States by Petsky Prunier, a broker dealer register with the U.S. SEC and a member of FINRA. Petsky Prunier is not affi liate d with Altium Capital Ltd, but has partnered with Altium to expand its international presence. Altium has not prepared or verified the information in this Summary. Persons in the United States should contact Petsky Prunier for further information or services. This M&A and Investment Summary is not being distributed by Altium Capital Ltd in the United States and Altium Capital Ltd is not offering any services to persons in the United States. 2| M&A and Investment Summary May 2013 M&A and Investment Summary for All Segments Transaction Distribution . A total of 364 deals were announced in May 2013, of which 211 reported $20.2 billion in value . Marketing Technology and Digital Media/Commerce were the most active segments with a combined total of 159 transactions announced, of which 98 reported $2.7 billion in value . Software was the highest reported value segment, with 60 transactions announced, of which 38 reported $10.1 billion in value . Strategic buyers announced 162 deals (45 percent of total volume), of which 38 reported $7.
    [Show full text]
  • Easing Scientific Computing and Federated Management in The
    Easing Scientific Computing and Federated Management in the Cloud with OCCI Zdenekˇ Sustrˇ 1, Diego Scardaci2,3, Jirˇ´ı Sitera1, Boris Parak´ 1 and V´ıctor Mendez´ Munoz˜ 4 1Department of Distributed Computing, CESNET, Zikova 4, 160 00, Praha 6, Czech Republic 2European Grid Initiative, Science Park 140, 1098 XG Amsterdam, Netherlands 3INFN Sezione di Catania, Via S. Sofia 64, I-95123 Catania, Italy 4Computer Architecture & Operating Systems Department (CAOS), Universitat Autonoma` de Barcelona (UAB), Bellaterra, Spain Keywords: Federated Cloud, Cloud Standards, Cloud Interoperability, Cloud Solution Design Patterns, Cloud Application Architectures, Cloud Middleware Frameworks, Open Cloud Computing Interface. Abstract: One of the benefits of OCCI stems from simplifying the life of developers aiming to integrate multiple cloud managers. It provides them with a single protocol to abstract the differences between cloud service implemen- tations used on sites run by different providers. This comes particularly handy in federated clouds, such as the EGI Federated Cloud Platform, which bring together providers who run different cloud management plat- forms on their sites: most notably OpenNebula, OpenStack, or Synnefo. Thanks to the wealth of approaches and tools now available to developers of virtual resource management solutions, different paths may be cho- sen, ranging from a small-scale use of an existing command line client or single-user graphical interface, to libraries ready for integration with large workload management frameworks and job submission portals relied on by large science communities across Europe. From lone wolves in the long-tail of science to virtual or- ganizations counting thousands of users, OCCI simplifies their life through standardization, unification, and simplification.
    [Show full text]
  • A Survey of Mathematical Models, Simulation Approaches And
    Simulation Modelling Practice and Theory 39 (2013) 92–103 Contents lists available at SciVerse ScienceDirect Simulation Modelling Practice and Theory journal homepage: www.elsevier.com/locate/simpat A survey of mathematical models, simulation approaches and testbeds used for research in cloud computing ⇑ Georgia Sakellari a, , George Loukas b a School of Architecture, Computing and Engineering, University of East London, United Kingdom b School of Computing and Mathematical Sciences, University of Greenwich, United Kingdom article info abstract Article history: The first hurdle for carrying out research on cloud computing is the development of a suit- Received 11 January 2013 able research platform. While cloud computing is primarily commercially-driven and com- Received in revised form 16 April 2013 mercial clouds are naturally realistic as research platforms, they do not provide to the Accepted 17 April 2013 scientist enough control for dependable experiments. On the other hand, research carried Available online 15 May 2013 out using simulation, mathematical modelling or small prototypes may not necessarily be applicable in real clouds of larger scale. Previous surveys on cloud performance and Keywords: energy-efficiency have focused on the technical mechanisms proposed to address these Cloud computing issues. Researchers of various disciplines and expertise can use them to identify areas Energy efficiency Survey where they can contribute with innovative technical solutions. This paper is meant to be complementary to these surveys. By providing the landscape of research platforms for cloud systems, our aim is to help researchers identify a suitable approach for modelling, simulation or prototype implementation on which they can develop and evaluate their technical solutions.
    [Show full text]
  • Introducing the Synnefo Open Source Iaas Platform
    FOSDEM 2013 [email protected] INTRODUCING THE SYNNEFO OPEN SOURCE IAAS PLATFORM . VANGELIS KOUKIS TECHNICAL LEAD, ~OKEANOS 1 FOSDEM 2013 Motivation: ~okeanos [email protected] Goals -Everything open source - Production-quality IaaS - Persistent VMs - Commodity hardware – No SAN - Large-scale Installations - Super-simple UI How? 2 FOSDEM 2013 Cluster vs Cloud [email protected] OPENSTACK SYNNEFO UI OPENSTACK OPENSTACK API SYNNEFO CLOUD OPENSTACK CLUSTER GANETI LIBVIRT NODE KVM KVM HYPERVISOR 3 FOSDEM 2013 Google Ganeti [email protected] Mature, production-ready VM cluster management - used in Google’s corporate infrastructure Multiple storage backends out of the box - DRBD, LVM, Files on local or shared directory, RBD (Ceph/RADOS) External Storage Interface for SAN/NAS support Ganeti cluster = masterd on master, noded on nodes Easy to integrate into existing infrastructure - Remote API over HTTP, pre/post hooks for every action! 4 FOSDEM 2013 Compute – Network: Cyclades [email protected] Thin Compute layer over Ganeti - Python/Django - Supports multiple Ganeti clusters, for scaling - OpenStack Compute API Networking - No restrictions on deployment – it’s the Ganeti side - IPv4/IPv6 public networks, complete isolation among VMs - Thousands of private networks, private L2 segments over single VLAN 5 FOSDEM 2013 Cyclades [email protected] 6 FOSDEM 2013 Storage: Pithos [email protected] Every file is a collection of blocks Content-based addressing for blocks Partial file transfers, deduplication, efficient syncing Independent of storage
    [Show full text]
  • The Okeanos Iaas Cloud
    Η υπηρεσία Public IaaS Cloud @ ΕΔΕΤ ανάπτυξη και λειτουργία για χιλιάδες χρήστες Nectarios Koziris, GRNET Greek Research and Technology Network Cloud Computing Conference 2013 (Plaza, Maroussi) 1 What is Okeanos? ‘Okeanos’ is the Greek word for ‘ocean’ Oceans capture, store and deliver energy, oxygen and life around the planet. Greek Research and Technology Network Cloud Computing Conference 2013 (Plaza, Maroussi) 2 Late 2010: The challenge Goals Production-quality IaaS cloud similar to Amazon AWS Scalability to thousands users/nodes/VMs Persistent VMs Commodity components Everyone can use it No vendor lock-in Low admin costs, manageable by a small team Greek Research and Technology Network Cloud Computing Conference 2013 (Plaza, Maroussi) 3 Late 2010: The available offerings Reviewed open source ones •Eucalyptus •Cloudstack •Opennebula •Openstack ..etc.. Still evolving systems, silo ones (touching every layer) No turnkey solutions Greek Research and Technology Network Cloud Computing Conference 2013 (Plaza, Maroussi) 4 The ∼okeanos approach Features: Production-quality IaaS cloud Everything open source: Ganeti by by Persistent VMs Commodity Hardware – No SAN, No exotic network hw Add plain servers/disks/switches to scale up Three clicks to start 1 or 10s of VMs, in 15 secs Simple to operate Key decision: Decompose the problem into layers Greek Research and Technology Network Cloud Computing Conference 2013 (Plaza, Maroussi) 5 ‘Building a Cloud, cluster by cluster’ OPENSTACK SYNNEFO UI OPENSTACK OPENSTACK API SYNNEFO
    [Show full text]
  • D1.3 Production System
    REPORT FOR DELIVERABLE D1.3 1 1 INTRODUCTION This report provides an overview of the technical characteristics and functionality of deliverable D1.3 “Production System”. Its purpose is to provide a short introduction to the processes designed and implemented enabling the final production installation (g eodata.gov.gr) of the various software developed and reused by PublicaMundi . The reader is encouraged to visit the software’s repository (https://github.com/PublicaMundi) to receive: Up-to-date versions of the software, along with documentation targeted to developers Detailed information regarding all development effort (commits, activity, issues) Instructions regarding the installation of the software and its dependencies 2 2 DESCRIPTION OF TASK PublicaMundi aims to make open geospatial data easier to discover, reuse, and share by fully supporting their complete publishing lifecycle in open data catalogues. To achieve this, we are extending and integrating leading open source software for open data publishing and geos patial data management. The goal of Task 1.3 is to apply agile development principles with periodic integration in order to maintain relevant contributions. Integration is performed on labs.geodata.gov.gr, a beta-testing facility, where new functionalities are tested on real data and users. New versions are being deployed automatically and user feedback is collected with online tools bringing them in contact with developers. For the purposes of our production deployment, we built upon our first deployment of labs.geodata.gov.gr, extending our integration environment (D1.2) and through automation procedures we established the production environment. On this environment, a stable version of the software has been rolled out, after extensive testing of the components of PublicaMundi.
    [Show full text]
  • Synnefo: an Introduction and Update Constantinos Venetsanopoulos, Principal Cloud Engineer, Grnet
    GanetiCon 2014 [email protected] SYNNEFO: AN INTRODUCTION AND UPDATE CONSTANTINOS VENETSANOPOULOS, PRINCIPAL CLOUD ENGINEER, GRNET GanetiCon 2014 Synnefo cloud platform [email protected] An all-in-one cloud solution − Written from scratch in Python − Manages multiple Google Ganeti clusters of VMs − Uses Archipelago to unify all cloud storage resources − Exposes the OpenStack APIs to end users Live since 2011 − Came out of the ~okeanos public cloud service GanetiCon 2014 Synnefo cloud platform [email protected] A complete cloud platform − Identity Service (Keystone API) − Object Storage Service (Swift API) − Compute Service (Nova API) − Network Service (Neutron API) − Image Service (Glance API) − Volume Service (Cinder API) GanetiCon 2014 Unified view of storage resources [email protected] Files - User files, with Dropbox-like syncing Images - Templates for VM creation Volumes - Live disks, as seen from VMs Snapshots - Point-in-time snapshots of Volumes GanetiCon 2014 Services Overview [email protected] GanetiCon 2014 Layered design [email protected] Client OpenStack Synnefo UI vCloud OpenStack OpenStack API vCloud Synnefo CLOUD OpenStack vCenter CLUSTER Ganeti vSphere libvirt NODE ESXi KVM / XEN KVM / XEN HYPERVISOR GanetiCon 2014 Architecture [email protected] GanetiCon 2014 Interaction with Ganeti [email protected] Support for all Ganeti storage templates including ExtStorage OS Definition = snf-image Networking = gnt-network + snf-network (KVM ifup scripts) + nfdhcpd (custom NFQUEUE-based DHCP server) Asynchronous operation − Effect path: Receive API requests from
    [Show full text]
  • Guide to the Open Cloud Open Cloud Projects Profiled
    Guide to the Open Cloud Open cloud projects profiled A Linux Foundation publication January 2015 www.linuxfoundation.org Introduction The open source cloud computing landscape has changed significantly since we published our first cloud guide in October 2013. This revised version adds new projects See also the rise of Linux container and technology categories that have since technology with the advent of Docker gained importance, and in some cases and its emerging ecosystem. You will be radically change how companies approach hard pressed to find an enterprise Linux building and deploying an open source distribution that isn’t yet working on Docker cloud architecture. integration and touting its new container strategy. Even VMware vSphere, Google In 2013, many cloud projects were still Cloud Platform, and Microsoft Azure are working out their core enterprise features rushing to adapt their cloud platforms to the and furiously building in functionality. And open source Docker project. enterprises were still very much in the early stages of planning and testing their public, This rapid pace of innovation and resulting private or hybrid clouds–and largely at the disruption of existing platforms and vendors orchestration layer. can now serve as a solid case study for the role of open source software and Now, not only have cloud projects collaboration in advancing the cloud. consistently (and sometimes dramatically) grown their user and developer Other components of the cloud infrastructure communities, lines of code and commits have also followed suit, hoping to harness over the past year, their software is the power of collaboration. The Linux increasingly enterprise-ready.
    [Show full text]
  • Use Style: Paper Title
    Volume 8, No. 1, Jan-Feb 2017 ISSN No. 0976-5697 International Journal of Advanced Research in Computer Science RESEARCH PAPER Available Online at www.ijarcs.info Cloud Computing: A Perspective Approach Sharda Rani Assistant Professor Deptt of Computer Science R.K.S.D. College, Kaithal, India Abstract- Cloud service models are infrastructure as a Service (IaaS), Platform as a Service (PaaS), Software as a Service (SaaS), and Network as a Service (NaaS). Cloud deployment models are public cloud, private cloud, community cloud, and hybrid cloud. Cloud enables use of resources as per payment. It uses several technologies such as virtualization, multi-tenancy, and webServices. OpenStack is open source software to implement private and public cloud. It provides IaaS. This paper is a step towards alleviating efforts of setting up a private cloud. This OpenStack based implementation uses hardware assisted virtualization, logical volume management, and network interface card in promiscuous mode. Hardware assisted virtualization offers better performance. Logical volume management provides flexibility to file system expansion. Keystone, glance, cinder, quantum, and horizon services are grouped for one node, named controller node. Keyword: Cloud infrastructure, virtualization, openstack, Service Models of Cloud. These are four service models of cloud: Infrastructure as a I. INTRODUCTION Service, Platform as a Service, Software as a Service, and Cloud derives its name from the cloud shaped symbol Network as a Service. Figure 1 demonstrates the abstraction representing Internet, as it is used as an abstraction for its level of services. Software as a service is taken place at the complex infrastructure .Cloud computing is the use of the top.
    [Show full text]
  • Openstack Vs. Ganeti
    OpenStack vs. Ganeti · Lance Albertson · Director, OSU Open Source Lab · http://osuosl.org · @ramereth Attribution-ShareAlike CC BY-SA ©2015 Session Overview OpenStack quick overview Ganeti overview Ganeti walk-through Comparing both About me Lance Albertson Director, OSU Open Source Lab (OSUOSL) Provide infrastructure hosting for FOSS projects Linux Foundation, Python Software Foundation, Drupal, etc Ops guy Ganeti user since 2009 OpenStack user since 2013 http://osuosl.org Virtualized Computing Resources Each organization has different needs Some are small and simple Others are more complex and larger Cost is also a major factor (both in licenses and staff maintenence) Typical Solutions VMWare VirtualBox OpenStack [insert favorite solution] OpenStack is all the hype Designed to scale and be an AWS replacement (almost) Everyone is investing in it Still maturing as a project Includes a wide-array of features, many of which most people don't need OpenStack Overview OpenStack Pros Standard Cloud API Fast VM deployment and tear down Very elastic computing needs Large community support Fast growing and new features constantly OpenStack Cons Extremely difficult to deploy and maintain Lots of moving parts Project is still maturing and unstable Fits a very specific use-case (Cloud) Requires more than one machine to effectively use So what about Ganeti? First, what is Ganeti? Cluster management tool for virtual compute resources IaaS solution that uses either KVM or Xen hypervisors Provides fast and simple recovery from hardware failures Primarily
    [Show full text]
  • Sistem Za Nadzor Računarske Infrastrukture Kao Servisa
    UNIVERZITET U BANJOJ LUCI ELEKTROTEHNIČKI FAKULTET MIHAJLO SAVIĆ SISTEM ZA NADZOR RAČUNARSKE INFRASTRUKTURE KAO SERVISA DOKTORSKA DISERTACIJA BANJA LUKA, 2020. UNIVERSITY OF BANJA LUKA FACULTY OF ELECTRICAL ENGINEERING MIHAJLO SAVIĆ COMPUTER INFRASTRUCTURE AS A SERVICE MONITORING SYSTEM DOCTORAL DISSERTATION BANJA LUKA, 2020 INFORMACIJE O MENTORU I DISERTACIJI Mentor: prof. dr Zoran Jovanović, redovni profesor, Elektrotehnički fakultet Beograd Naslov doktorske disertacije: SISTEM ZA NADZOR RAČUNARSKE INFRASTRUKTURE KAO SERVISA Rezime: Disertacija predstavlja rezultat istraživanja u oblasti nadzora distribuirane i heterogene računarske infrastrukture sa posebnim osvrtom na računarsku infrastrukturu kao servis. Nakon opisa oblasti i pregleda dostupnih rješenja, izvršena je analiza zahtjeva koje mora da ispuni novi sistem za nadzor. Na osnovu podataka prikupljenih u toku VI-SEEM projekta koji je obuhvatao računarsku infrastrukturu u 16 država regiona, definisane su tri oblasti primjene sistema za nadzor: računarska infrastruktura kao servis, grid i računarstvo visokih performansi, te dijeljenje mrežne infrastrukture. Projektovan je i realizovan sistem za nadzor distribuirane heterogene računarske infrastrukture te je testiran za vrijeme trajanja projekta na regionalnoj infrastrukturi. Posebno značajan izlaz istraživanja je novi MIB (eng. Management Information Base) dokument koji podržava podatke iz svih analiziranih izvora. Nakon identifikovanja problema degradacije performansi u dijeljenim infrastrukturama projektovan je i sistem za korisnički
    [Show full text]
  • Deploying Helix Nebula Flagship Applications in a Hybrid Scenario
    EGI-InSPIRE Deploying Helix Nebula flagship applications in a hybrid scenario Salvatore Pinto Cloud Technologist EGI.eu 9/18/2013 1 EGI-InSPIRE RI-261323 www.egi.eu Agenda • Helix Nebula and the EGI Federated Cloud • The ESA flagship on Helix Nebula • ESA Proof of Concept on the EGI Federated Cloud • Next Steps 9/18/2013 2 EGI-InSPIRE RI-261323 www.egi.eu Helix Nebula and EGI FedCloud The EGI Federated Cloud is federation of institutional private Clouds, offering Cloud Infrastructure as a Service to scientists in Europe and worldwide. • Standards and validation: federation is based on common open-standards – OCCI, CDMI, OVF. • Heterogeneous implementation: no mandate on the cloud technology, the only condition is to expose the chosen interfaces and services. EGI-InSPIRE RI-261323 www.egi.eu Interoperability between Helix Nebula and EGI FedCloud Considering the Helix Nebula, Blue Box approach, the obvious interoperability solution for VM management is to add a OCCI connector to the Blue Box OCCI FedCloud BLUE BOX We concentrated our effort on one of the Blue Box solutions under test, SlipStream, which is an Open Source solution and has an EGI-InSPIRE mini-project to support OCCI cloud connectivity. NOTE: enStratius proposed Blue Box does not support OCCI at the time 9/18/2013 5 EGI-InSPIRE RI-261323 www.egi.eu The ESA flagship 9/18/2013 7 EGI-InSPIRE RI-261323 www.egi.eu The ESA flagship (SSEP) ESA flagship is integrated into the ESA’s SuperSite Exploitation Platform project, which exploit cloud resources to 1. Provision IaaS resources from different cloud providers as well as private cloud resources (hybrid multi-sourced cloud) 2.
    [Show full text]