DOCSLIB.ORG

Ceph, Programmable Storage, and Data Fabrics Carlos Maltzahn, UC Santa Cruz Fermilab, 6/9/17 Carlos Maltzahn Background

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Ceph, Programmable Storage, and Data Fabrics Carlos Maltzahn, UC Santa Cruz Fermilab, 6/9/17 Carlos Maltzahn Background Ceph, Programmable Storage, and Data Fabrics Carlos Maltzahn, UC Santa Cruz Fermilab, 6/9/17 Carlos Maltzahn Background • Adjunct Professor, Computer Science, UC Santa Cruz • Current Research • Director, UCSC Systems Research • High-performance ultra-scale Laboratory (SRL) storage and data management • Director, Center for Research in Open • End-to-end Performance Source Software (CROSS) cross.ucsc.edu management and QoS • Director, UCSC/LANL Institute for • Reproducible Evaluation of Scalable Scientific Data Management Systems (ISSDM) • Network Intermediaries • 1999-2004: Performance Engineer, • Other Research Netapp • Data Management Games • Information Retrieval • Advising 6 Ph.D. students. • Cooperation Dynamics • Graduated 5 Ph.D. students • I do this 100% of my time! 2 Agenda • Overview of Ceph • Programmable Storage • CDNs/Data Fabrics Ceph, Programmable Storage, and Data Fabrics 3 Carlos Maltzahn Ceph History • 2005: Started as summer project • Funded by DOE/NNSA (LANL, LLNL, SNL) • Quickly turned into Sage Weil’s Ph.D. project • 2006: Publications at OSDI and SC • 2007: Sage graduated end of 2007, turned prototype into OSS project • 2010: Ceph Linux kernel client in 2.6.34 • 2011: Inktank startup • 2014: Red Hat acquires Inktank for $175m Ceph, Programmable Storage, and Data Fabrics 4 Carlos Maltzahn ARCHITECTURAL COMPONENTS APP HOST/VM CLIENT RGW RBD CEPHFS A web services A reliable, fully- A distributed <le gateway for object distributed block system with POSIX storage, compatible device with cloud semantics and scale- with S3 and Swift platform integration out metadata management LIBRADOS A library allowing apps to directly access RADOS (C, C++, Java, Python, Ruby, PHP) RADOS A software-based, reliable, autonomous, distributed object store comprised of self-healing, self-managing, intelligent storage nodes and lightweight monitors Ceph, Programmable Storage, and Data Fabrics 4 5 Carlos Maltzahn Ceph, Programmable Storage, and Data Fabrics 6 Carlos Maltzahn OBJECT STORAGE DAEMONS M OSD OSD OSD OSD M btrfs xfs ext4 FS FS FS FS DISK DISK DISK DISK M Ceph, Programmable Storage, and Data Fabrics 6 7 Carlos Maltzahn RADOS CLUSTER APPLICATION M M M M M RADOS CLUSTER Ceph, Programmable Storage, and Data Fabrics 7 8 Carlos Maltzahn RADOS COMPONENTS OSDs: . 10s to 10000s in a cluster . One per disk (or one per SSD, RAID group…) . Serve stored objects to clients . Intelligently peer for replication & recovery Monitors: . Maintain cluster membership and state . Provide consensus for distributed decision- M making . Small, odd number . These do not serve stored objects to clients Ceph, Programmable Storage, and Data Fabrics 8 9 Carlos Maltzahn WHERE DO OBJECTS LIVE? M ?? M APPLICATION OBJECT M Ceph, Programmable Storage, and Data Fabrics 9 10 Carlos Maltzahn A METADATA SERVER? M 1 M APPLICATION 2 M Ceph, Programmable Storage, and Data Fabrics 10 11 Carlos Maltzahn CALCULATED PLACEMENT A-G M H-N M APPLICATION F O-T M U-Z Ceph, Programmable Storage, and Data Fabrics 11 12 Carlos Maltzahn EVEN BETTER: CRUSH! 10 10 01 01 11 01 01 01 01 10 01 10 OBJECTS 10 01 11 10 10 01 11 10 10 01 01 01 PLACEMENT GROUPS CLUSTER (PGs) Ceph, Programmable Storage, and Data Fabrics 12 13 Carlos Maltzahn CRUSH IS A QUICK CALCULATION 10 01 01 11 01 01 10 01 OBJECT 01 11 10 10 10 10 01 01 RADOS CLUSTER Ceph, Programmable Storage, and Data Fabrics 13 14 Carlos Maltzahn CRUSH: DYNAMIC DATA PLACEMENT CRUSH: . Pseudo-random placement algorithm . Fast calculation, no lookup . Repeatable, deterministic . Statistically uniform distribution . Stable mapping . Limited data migration on change . Rule-based con<guration . Infrastructure topology aware . Adjustable replication . Weighting Ceph, Programmable Storage, and Data Fabrics 14 15 Carlos Maltzahn DATA IS ORGANIZED INTO POOLS 10 11 10 01 POO 10 01 01 11 OBJECTS L A 01 01 01 10 01 10 11 10 POO 01 01 10 01 OBJECTS L B 10 01 01 01 POO 10 01 11 OBJECTS L C 10 01 11 10 10 01 10 01 01 POO 11 10 OBJECTS L 01 10 10 10 01 01 D 01 01 10 01 CLUSTER POOLS (CONTAINING PGs) Ceph, Programmable Storage, and Data Fabrics 15 16 Carlos Maltzahn Ceph, Programmable Storage, and Data Fabrics 17 Carlos Maltzahn ACCESSING A RADOS CLUSTER APPLICATION LIBRADOS OBJECT socket M M M RADOS CLUSTER Ceph, Programmable Storage, and Data Fabrics 17 18 Carlos Maltzahn LIBRADOS: RADOS ACCESS FOR APPS LIBRADOS: . Direct access to RADOS for applications . C, C++, Python, PHP, Java, Erlang L . Direct access to storage nodes . No HTTP overhead Ceph, Programmable Storage, and Data Fabrics 18 19 Carlos Maltzahn Ceph, Programmable Storage, and Data Fabrics 20 Carlos Maltzahn THE RADOS GATEWAY APPLICATION APPLICATION REST RADOSGW RADOSGW LIBRADOS LIBRADOS socket M M M RADOS CLUSTER Ceph, Programmable Storage, and Data Fabrics 20 21 Carlos Maltzahn RADOSGW MAKES RADOS WEBBY RADOSGW: . REST-based object storage proxy . Uses RADOS to store objects . API supports buckets, accounts . Usage accounting for billing . Compatible with S3 and Swift applications Ceph, Programmable Storage, and Data Fabrics 21 22 Carlos Maltzahn Ceph, Programmable Storage, and Data Fabrics 23 Carlos Maltzahn STORING VIRTUAL DISKS VM HYPERVISOR LIBRBD M M RADOS CLUSTER Ceph, Programmable Storage, and Data Fabrics 23 24 Carlos Maltzahn KERNEL MODULE FOR MAX FLEXIBLE! LINUX HOST KRBD M M RADOS CLUSTER Ceph, Programmable Storage, and Data Fabrics 25 25 Carlos Maltzahn RBD STORES VIRTUAL DISKS RADOS BLOCK DEVICE: . Storage of disk images in RADOS . Decouples VMs from host . Images are striped across the cluster (pool) . Snapshots . Copy-on-write clones . Support in: . Mainline Linux Kernel (2.6.39+) . Qemu/KVM, native Xen coming soon . OpenStack, CloudStack, Nebula, Proxmox Ceph, Programmable Storage, and Data Fabrics 26 26 Carlos Maltzahn Ceph, Programmable Storage, and Data Fabrics 27 Carlos Maltzahn SEPARATE METADATA SERVER LINUX HOST KERNEL MODULE metadata 01 data 10 M M M RADOS CLUSTER Ceph, Programmable Storage, and Data Fabrics 28 28 Carlos Maltzahn SCALABLE METADATA SERVERS METADATA SERVER . Manages metadata for a POSIX-compliant shared <lesystem . Directory hierarchy . File metadata (owner, timestamps, mode, etc.) . Stores metadata in RADOS . Does not serve <le data to clients . Only required for shared <lesystem Ceph, Programmable Storage, and Data Fabrics 29 29 Carlos Maltzahn Programmable Storage Students: Michael Sevilla, Noah Watkins, Ivo Jimenez, Collaborators: Jeff LeFevre, Peter Alvaro, Shel Finkelstein, Carlos Maltzahn M. Sevilla et al. “Malacology: A Programmable Storage System,” EuroSys 2017, Belgrade, Serbia, April 23-26, 2017. Ceph, Programmable Storage, and Data Fabrics 30 Carlos Maltzahn Narrow waist of storage • Traditional • Blocks: fixed sized, small data chunks (512B, 4KB), flat name space • Objects: flexibly sized, large data chunks (100KBs to MBs), flat name space • Files: flexibly sized byte streams, hierarchical name space • Narrow waist creates a semantic gap • Storage systems have no idea what the data means • Applications have no idea how to best store the data: lots of magic numbers! • Advent of open-source software storage systems • No more fear of vendor lock-in • New opportunity to construct better storage interfaces Ceph, Programmable Storage, and Data Fabrics 31 Carlos Maltzahn scrubbing [50]. Ceph already provides some degree of pro- programmers wanting to exploit application-specific seman- grammability; the object storage daemons support domain- tics, and/or programmers knowing how to manage resources specific code that can manipulate objects on the server that to improve performance. A solution based on application- has the data local. These “interfaces” are implemented by specific object interfaces is a way to work around the tradi- composing existing low-level storage abstractions that exe- tionally rigid storage APIs because custom object interfaces cute atomically. They are written in C++ and are statically give programmers the ability to tell the storage system about loaded into the system. their application: if the application is CPU or I/O bound, if it The Ceph community provides empirical evidence that has locality, if its size has the potential to overload a single developers are already beginning to embrace programmable node, etc. Programmers often know what the problem is and storage. Figure 2 shows a dramatic growth in the produc- how to solve it, but until the ability to modify object inter- tion use of domain-specific interfaces in the Ceph commu- faces, they had no way to express to the storage system how nity since 2010. In that figure, classes are functional group- to handle their data. ings of methods on storage objects (e.g. remotely computing Our approach is to expose more of the commonly used, and caching the checksum of an object extent). What is most code-hardened subsystems of the underlying storage system remarkable is that this trend contradicts the notion that API as interfaces. The intent is that these interfaces, which can changes are a burden for users. Rather it appears that gaps be as simple as a redirection to the persistent data store or in existing interfaces are being addressed through ad-hoc ap- as complicated as a strongly consistent directory service, proaches to programmability. In fact, Table 1 categorizes ex- should be used and re-used in many contexts to implement isting interfaces and we clearly see a trend towards reusable a wide range of services. By making programmability a scrubbing [50]. Ceph already provides some degree of pro- programmers wanting to exploit application-specific seman- services. ‘feature’, rather than a ‘hack’ or ‘workaround’, we help grammability; the object storage daemons support domain- tics, and/or programmers knowing how to manage resources specific code that can manipulate objects on the server that to improve performance. A solution based on application- standardize a development process that now is largely ad- has the data local. These “interfaces” are implemented by specific object interfaces is a way to work around the tradi- hoc. composing existing low-level storage abstractions that exe- tionally rigid storage APIs because custom object interfaces cute atomically.
Load more

Recommended publications
  • Ceph: Distributed Storage for Cloud Infrastructure
    ceph: distributed storage for cloud infrastructure sage weil msst – april 16, 2012 outline ● motivation ● practical guide, demo ● overview ● hardware ● ● how it works installation ● failure and recovery ● architecture ● rbd ● data distribution ● libvirt ● rados ● ● rbd project status ● distributed file system storage requirements ● scale ● terabytes, petabytes, exabytes ● heterogeneous hardware ● reliability and fault tolerance ● diverse storage needs ● object storage ● block devices ● shared file system (POSIX, coherent caches) ● structured data time ● ease of administration ● no manual data migration, load balancing ● painless scaling ● expansion and contraction ● seamless migration money ● low cost per gigabyte ● no vendor lock-in ● software solution ● commodity hardware ● open source ceph: unified storage system ● objects ● small or large ● multi-protocol Netflix VM Hadoop ● block devices radosgw RBD Ceph DFS ● snapshots, cloning RADOS ● files ● cache coherent ● snapshots ● usage accounting open source ● LGPLv2 ● copyleft ● free to link to proprietary code ● no copyright assignment ● no dual licensing ● no “enterprise-only” feature set distributed storage system ● data center (not geo) scale ● 10s to 10,000s of machines ● terabytes to exabytes ● fault tolerant ● no SPoF ● commodity hardware – ethernet, SATA/SAS, HDD/SSD – RAID, SAN probably a waste of time, power, and money architecture ● monitors (ceph-mon) ● 1s-10s, paxos ● lightweight process ● authentication, cluster membership, critical cluster state ● object storage daemons (ceph-osd)
    [Show full text]
  • Open Source Software
    OPEN SOURCE SOFTWARE Product AVD9x0x0-0010 Firmware and version 3.4.57 Notes on Open Source software The TCS device uses Open Source software that has been released under specific licensing requirements such as the ”General Public License“ (GPL) Version 2 or 3, the ”Lesser General Public License“ (LGPL), the ”Apache License“ or similar licenses. Any accompanying material such as instruction manuals, handbooks etc. contain copyright notes, conditions of use or licensing requirements that contradict any applicable Open Source license, these conditions are inapplicable. The use and distribution of any Open Source software used in the product is exclusively governed by the respective Open Source license. The programmers provided their software without ANY WARRANTY, whether implied or expressed, of any fitness for a particular purpose. Further, the programmers DECLINE ALL LIABILITY for damages, direct or indirect, that result from the using this software. This disclaimer does not affect the responsibility of TCS. AVAILABILITY OF SOURCE CODE: Where the applicable license entitles you to the source code of such software and/or other additional data, you may obtain it for a period of three years after purchasing this product, and, if required by the license conditions, for as long as we offer customer support for the device. If this document is available at the website of TCS and TCS offers a download of the firmware, the offer to receive the source code is valid for a period of three years and, if required by the license conditions, for as long as TCS offers customer support for the device. TCS provides an option for obtaining the source code: You may obtain any version of the source code that has been distributed by TCS for the cost of reproduction of the physical copy.
    [Show full text]
  • Digitalocean
    UPDATE SAGE WEIL – RED HAT SC16 CEPH BOF – 2016.11.16 2 JEWEL APPAPP APPAPP HOST/VMHOST/VM CLIENTCLIENT RADOSGWRADOSGW RBDRBD CEPHCEPH FSFS LIBRADOSLIBRADOS AA bucket-based bucket-based AA reliable reliable and and fully- fully- AA POSIX-compliant POSIX-compliant AA library library allowing allowing RESTREST gateway, gateway, distributeddistributed block block distributeddistributed file file appsapps to to directly directly compatiblecompatible with with S3 S3 device,device, with with a a Linux Linux system,system, with with a a accessaccess RADOS, RADOS, andand Swift Swift kernelkernel client client and and a a LinuxLinux kernel kernel client client withwith support support for for QEMU/KVMQEMU/KVM driver driver andand support support for for C,C, C++, C++, Java, Java, FUSEFUSE Python,Python, Ruby, Ruby, andand PHP PHP AWESOME AWESOME NEARLY AWESOME AWESOME RADOSRADOS AWESOME AA reliable, reliable, autonomous, autonomous, distributed distributed object object store store comprised comprised of of self-healing, self-healing, self-managing, self-managing, intelligentintelligent storage storage nodes nodes 3 2016 = FULLY AWESOME OBJECT BLOCK FILE RGW RBD CEPHFS S3 and Swift compatible A virtual block device with A distributed POSIX file object storage with object snapshots, copy-on-write system with coherent versioning, multi-site clones, and multi-site caches and snapshots on federation, and replication replication any directory LIBRADOS A library allowing apps to direct access RADOS (C, C++, Java, Python, Ruby, PHP) RADOS A software-based,
    [Show full text]
  • SLA-Aware Adaptive Mapping Scheme in Bigdata Distributed Storage Systems
    SMA 2020, September 17-19, Jeju, Republic of Korea, S. Chum et al. SLA-Aware Adaptive Mapping Scheme in Bigdata Distributed Storage Systems Sopanhapich Chum Jerry Li Department of Computer Science Memory Solutions Lab. Dankook University Samsung Semiconductor Inc. Yongin, Korea San Jose, CA, USA [email protected] [email protected] Heekwon Park Jongmoo Choi Memory Solutions Lab. Department of Computer Science Samsung Semiconductor Inc. Dankook University San Jose, CA, USA Yongin, Korea [email protected] [email protected] ABSTRACT by 2025, with a compounded annual growth rate of 61% [23]. In As data are processed by diverse clients ranging from urgent time- addition, these data are processed instantly to extract information critical to best-effort, supporting different QoS (Quality of Service) for decision making, recommendation and autonomous control becomes a vital component in a distributed storage system. In this using various analytic models and frameworks [1, 8, 11, 20, 27, 30]. paper, we propose a novel SLA (Service Level Agreement)-aware We indeed live in Bigdata era [24]. adaptive mapping scheme that can differentiate between urgent Distributed storage (also called as Cloud storage) plays a key and normal clients based on their I/O requirements. The scheme ba- role in Bigdata era. There are various distributed storage systems sically divides storage into two regions, normal and urgent, which including GFS [14], HDFS [26], Ceph [2, 33], Azure Storage [16], makes it feasible to isolate urgent clients from normal ones. In Amazon S3 [22], Openstack Swift [18], Haystack [6], Lustre [35], addition, it changes the size of the isolated region in an adaptive GlusterFS [17] and so on.
    [Show full text]
  • File Systems Unfit As Distributed Storage Back Ends
    File Systems Unfit as Distributed Storage Back Ends LessonsSYSTEMS from 10 Years of Ceph Evolution ABUTALIB AGHAYEV, SAGE WEIL, MICHAEL KUCHNIK, MARK NELSON, GREG GANGER, AND GEORGE AMVROSIADIS Abutalib Aghayev is a PhD stu- or a decade, the Ceph distributed file system followed the conventional dent in the Computer Science wisdom of building its storage back end on top of local file systems. Department at Carnegie Mellon The experience with different file systems showed that this approach University. He has broad research F interests in computer systems, always leaves significant performance on the table while incurring signifi- including storage and file systems, distributed cant accidental complexity [2]. Therefore, the Ceph team embarked on an systems, and operating systems. ambitious project to build BlueStore, a new back end designed to run directly [email protected] on raw storage devices. Somewhat surprisingly, BlueStore matured in less Sage Weil is the Lead Architect than two years. It outperformed back ends built atop file systems and got and co-creator of the Ceph open adopted by 70% of users in production. source distributed storage sys- Figure 1 shows the high-level architecture of Ceph. At the core of Ceph is the Reliable Auto- tem. Ceph was created to pro- nomic Distributed Object Store (RADOS) service. RADOS scales to thousands of Object vide a stable, next generation Storage Devices (OSDs), providing self-healing, self-managing, replicated object storage with distributed storage system for Linux. Inktank strong consistency. Ceph’s librados library provides a transactional interface for manipu- was co-founded by Sage in 2012 to support lating objects and object collections in RADOS.
    [Show full text]
  • Ceph Parallel File System Evaluation Report
    ORNL/TM-2013/151 National Center for Computatational Sciences Ceph Parallel File System Evaluation Report Feiyi Wang Mark Nelson ORNL/NCCS Inktank Inc. Other contributors: Sarp Oral Doug Fuller Scott Atchley Blake Caldwell James Simmons Brad Settlemyer Jason Hill Sage Weil (Inktank Inc.) Prepared by OAK RIDGE NATIONAL LABORATORY Oak Ridge, Tennessee 37831-6283 managed by UT-BATTELLE, LLC for the U.S. DEPARTMENT OF ENERGY This research was supported by, and used the resources of, the Oak Ridge Leadership Computing Facility, located in the National Center for Computational Sciences at ORNL, which is managed by UT Battelle, LLC for the U.S. DOE (under the contract No. DE-AC05-00OR22725). Contents 1 Introduction 1 2 Testbed Environment Description 2 3 Baseline Performance 3 3.1 Block I/O over Native IB ..................................... 3 3.2 IP over IB ............................................. 3 4 System Tuning 3 5 XFS Performance As Backend File System 4 6 Ceph RADOS Scaling: Initial Test 5 6.1 Scaling on number of OSDs per server ............................ 6 6.2 Scaling on number of OSD servers ............................... 6 7 Ceph File System Performance: Initial Test 7 8 Improving RADOS Performance 8 8.1 Disable Cache Mirroring on Controllers ............................ 9 8.2 Disable TCP autotuning ..................................... 10 8.3 Repeating RADOS Scaling Test ................................. 10 9 Improving Ceph File System Performance 12 9.1 Disabling Client CRC32 ..................................... 12 9.2 Improving IOR Read Performance ............................... 13 9.3 Repeating the IOR Scaling Test ................................. 14 10 Metadata Performance 15 11 Observations and Conclusions 17 Appendix A - CephFS Final Mount 18 Appendix B - OSD File System Options 18 Appendix C - CRUSH map 19 Appendix D - Final ceph.conf 23 Appendix E - Tuning Parameters 24 3 List of Figures 1 DDN SFA10K hardware and host connection diagram ...................
    [Show full text]
  • A Tool for Modeling, Viewing, and Checking Distributed System
    ;login FALL 2016 VOL. 41, NO. 3 : & POSIX: The Old, the New, and the Missing Vaggelis Atlidakis, Jeremy Andrus, Roxana Geambasu, Dimitris Mitropoulos, and Jason Nieh & Runway: A Tool for Modeling, Viewing, and Checking Distributed Systems Diego Ongaro & Create a Threat Model for Your Organization Bruce Potter & Eliminating Toil Betsy Beyer, Brendan Gleason, Dave O’Connor, and Vivek Rau Columns Separating Protocol Implementations from Transport in Python David Beazley Shutting Down Go Servers with Manners Kelsey Hightower Using Consul for Distributed Key-Value Stores David N. Blank-Edelman Monitoring Paging Trauma Dave Josephsen Making Security into a Science Dan Geer Distributed Systems Robert G. Ferrell UPCOMING EVENTS OSDI ’16: 12th USENIX Symposium on Operating Enigma 2017 Systems Design and Implementation January 30–February 1, 2017, Oakland, CA, USA Sponsored by USENIX in cooperation with ACM SIGOPS enigma.usenix.org November 2–4, 2016, Savannah, GA, USA www.usenix.org/osdi16 FAST ’17: 15th USENIX Conference on File and Co-located with OSDI ’16 Storage Technologies INFLOW ’16: 4th Workshop on Interactions of NVM/Flash Sponsored by USENIX in cooperation with ACM SIGOPS with Operating Systems and Workloads February 27–March 2, 2017, Santa Clara, CA, USA November 1, 2016 Submissions due September 27, 2016 www.usenix.org/inflow16 www.usenix.org/fast17 LISA16 SREcon17 December 4–9, 2016, Boston, MA, USA March 13–14, 2017, San Francisco, CA, USA www.usenix.org/lisa16 Co-located with LISA16 NSDI ’17: 14th USENIX Symposium on Networked SESA
    [Show full text]
  • Open Source Software License Information
    Open Source Software license information This document contains an open source software license information for the product VACUU·SELECT. The product VACUU·SELECT contains open source components which are licensed under the applicable open source licenses. The applicable open source licenses are listed below. The open source software licenses are granted by the respective right holders directly. The open source licenses prevail all other license information with regard to the respective open source software components contained in the product. Modifications of our programs which are linked to LGPL libraries are permitted for the customer's own use and reverse engineering for debugging such modifications. However, forwarding the information acquired during reverse engineering or debugging to third parties is prohibited. Furthermore, it is prohibited to distribute modified versions of our programs. In any case, the warranty for the product VACUU·SELECT will expire, as long as the customer cannot prove that the defect would also occur without these modification. WARRANTY DISCLAIMER THE OPEN SOURCE SOFTWARE IN THIS PRODUCT IS DISTRIBUTED IN THE HOPE THAT IT WILL BE USEFUL, BUT WITHOUT ANY WARRANTY, WITHOUT EVEN THE IMPLIED WARRANTY OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. See the applicable licenses for more details. Written offer This product VACUU·SELECT contains software components that are licensed by the holder of the rights as free software, or Open Source software, under GNU General Public License, Versions 2 and 3, or GNU Lesser General Public License, Versions 2.1, or GNU Library General Public License, Version 2, respectively. The source code for these software components can be obtained from us on a data carrier (e.g.
    [Show full text]
  • Summer 2020 Vol
    ;login SUMMER 2020 VOL. 45, NO. 2 : & Finding Anomalies in Linux Performance Richard L. Sites & Misaligned Incentives and Bad Software Design Marianne Bellotti & Failures in Enterprise SSDs Stathis Maneas, Kaveh Mahdaviani, Tim Emami, and Bianca Schroeder & Using ML in Support of SRE Steven Ross and Todd Underwood & Interview with Natalie Silvanovich Rik Farrow Columns Culture of Complacency and Crisis Laura Nolan Using eBPF, Part 2 Dave Josephsen Supporting OSS Dan Geer and George P. Sieniawski Thanks to our USENIX Supporters! USENIX appreciates the financial assistance our Supporters provide to subsidize our day-to-day operations and to continue our non-profit mission. Our supporters help ensure: • Free and open access to technical information • Student Grants and Diversity Grants to participate in USENIX conferences • The nexus between academic research and industry practice • Diversity and representation in the technical workplace We need you now more than ever! Contact us at [email protected]. USENIX PATRONS USENIX BENEFACTORS USENIX PARTNERS We offer our heartfelt appreciation to the following sponsors and champions of conference diversity, open access, and our SREcon communities via their sponsorship of multiple conferences: Ethyca Dropbox Microsoft Azure Packet Datadog Goldman Sachs LinkedIn Salesforce More information at www.usenix.org/supporters SUMMER 2020 VOL. 45, NO. 2 EDITOR Rik Farrow EDITORIAL MANAGING EDITOR Michele Nelson 2 Musings Rik Farrow COPY EDITORS FILE SYSTEMS AND STORAGE Steve Gilmartin Amber Ankerholz 6
    [Show full text]
  • Licence Agreement Supplement
    Licence Agreement Supplement 2 Index The ISC License ............................................ 300 Unicode License ........................................... 301 Contents X11 License.................................................. 302 Overview .......................................................... 3 Zlib License .................................................. 302 Note ................................................................. 3 Academic Free License 2.1 .............................. 4 Apache License, Version 2.0 ............................ 7 Beerware License ........................................... 10 Boost Software License 1.0 ........................... 10 BSD 2-clause .................................................. 11 BSD 3-clause .................................................. 17 BSD 4-Clause ................................................. 25 BSD variants................................................... 26 Bzip2 License ................................................. 26 Coffee-ware License ...................................... 27 Copyleft-next License .................................... 27 Curl License ................................................... 31 dhcp License .................................................. 32 Dropbear License ........................................... 33 expat License ................................................. 35 GNU GPL v 1.0 ............................................... 36 GNU GPL v 2.0 ............................................... 40 GNU GPL 3.0 ...............................................
    [Show full text]
  • Delivering Openstack and Ceph in Containers
    DELIVERING OPENSTACK AND CEPH IN CONTAINERS OpenStack Summit Sydney — November 7, 2017 The Three Amigos Andrew Federico Sébastien Hatfield Lucifredi Han Practice Lead Product Management Director Principal Software Engineer Cloud Storage Red Hat Ceph Storage Storage Architect Brisbane, Australia Boston, USA Paris, France 2 OpenStack Summit Sydney - October 2017 Where we are today Drivers Why are we moving toward containers? Packaging Scalability format Speed Upgrade Immutable downgrade infrastructure flexibility Deployment Resource flexibility constraints 4 OpenStack Summit Sydney - October 2017 Entering Kubernetes with OpenStack Kubernetes is an open-source orchestrator automating the deployment, scaling, and management of containerized applications. Container management platform: ● Self-healing ● Load balancing ● Automated rollouts and rollbacks ● Pluggable architecture: ○ Storage ○ Network ○ Containers runtime ○ Scheduling 5 OpenStack Summit Sydney - October 2017 Persistent Storage Pool of Persistent Volumes Ceph Ceph Ceph register PV iSCSI CephFS NFS RBD RBD RBD PV PV PV PV PV PV Admin Pod Pod Pod Pod create claim Claim Claim Claim Claim User Project 6 OpenStack Summit Sydney - October 2017 Dynamic Voluming Provisioning Slow Azure Azure-Disk Provisioner Define Storage Class Fast AWS AWS-SSD Provisioner Admin Fastest Provision Ceph PV Ceph-RBD Provisioner Pod Create claim: Fastest OpenShift PV Controller User Claim 7 OpenStack Summit Sydney - October 2017 OpenStack in Containers Why OpenStack on Kubernetes? Day 1: ease deployment ● OpenStack itself turned into microservice oriented architecture with its services ● Kubernetes manages applications ● Kubernetes load, driven by application needs, can vary dramatically over wide time scales (hours, days, weeks) ● Leverage the ease, scale and power of the Containers Day 2: ● Share scheduling functions between Nova and Kubernetes 9 OpenStack Summit Sydney - October 2017 Kolla Some background.
    [Show full text]
  • VPP: the Ultimate NFV Vswitch (And More!)?
    VPP: The ultimate NFV vSwitch (and more!)? Franck Baudin, Principal Product Manager - OpenStack NFV - Red Hat Uri Elzur, DNSG CTO - Intel OpenStack Summit | Barcelona 2016 Agenda ● FD.io project and community overview ● FD.io Vector Packet Processing framework ● FD.io in a broader context ○ OPNFV and FDS ○ OpenStack and ML2 ○ ODL and SFC ○ Containers ● Summary Key message: FD.io is getting ready for production readiness and offers some interesting innovations 2 OpenStack summit 2016, Barcelona FD.io overview Some slides adapted from multiple presentations at wiki.fd.io The authors wish to also thank: Frank Brockners, Keith Burns, Joel Halpern, Ray Kinsella, Hongjun Ni, Ed Warnicke, Yi Yang, Jerome Tollet, Danny Zhou, … ● FD.io FD.io in context ○ Offers a new high speed dynamic and programmable data plane adapted and optimized to the Server architecture Cloud ● VPP provides Management ○ IO, Processing and Management, for System Bare Metal, VM or Container ○ IO: HW / vHW cores/threads ○ Packet Processing: Classify, Transform, SDN Prioritize, Forward, Terminate Controller ○ Management Agents: control/manage IO/Processing ○ Local and remote Server 4 OpenStack summit 2016, Barcelona Introduction Fast Data: Scope Good Governance -> Fast Innovation Continuous Performance Lab Modular Governance supports concept of independent sub-projects enabling: ● faster evolution ● independant work stream ● Greater flexibility 5 OpenStack summit 2016, Barcelona projects 6 OpenStack summit 2016, Barcelona FD.io governance Subprojects: Anyone May Participate – Not just members Composed of the committers to that subproject – those Anyone can contribute code who can merge code Anyone can rise to being a committer via meritocracy Responsible for sub project oversight and autonomous releases Anyone can propose a subproject Make technical decisions for that subproject by consensus, Technical Steering Committee or failing that, majority vote.
    [Show full text]