Suspend-aware Segment Cleaning in Log-Structured File System
|
|
|
- Gwendoline Deborah Ferguson
- 6 years ago
- Views:
Transcription
1 USENI HotStorage 15 Santa Clara, CA, USA, July 6~7, 2015 Suspend-aware Segment Cleaning in Log-Structured File System Dongil Park, Seungyong Cheon, Youjip Won Hanyang University
2 Outline Introduction Log-structured File System and Segment Cleaning Suspend Mode on Smartphone Problem assessment Suspend-aware Segment Cleaning Design Virtual Segment Cleaning Utilization-based Segment Cleaning Experiment Conclusion Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 2
3 Introduction Flash memory based storage is widely used nowadays. Log-structured file system has been around for 20+ years. It has not been deployed on commercial devices. F2FS (Flash Friendly File System) is a log-structured file system optimized for mobile device. F2FS is adopted in commercial mobile devices as their stock file system. Motorola Droid family Motorola Moto, Moto G, Moto E Google Nexus 9 Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 3
4 Flash Friendly File System F2FS shows great random write performance on flash memory. more than 3ⅹ sequential write sequential read random write random read source: C. Lee et al., FAST 15 Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 4
5 Log-structured File System inode data In-place update file system update(file A) A A C B A A B C Disk Log-structured file system update(file A) A A B B C C A A Log Disk Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 5
6 Log-structured File System Segment: unit of disk write Disk Block: unit of write operation Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 6
7 Block and Segment Free block Free segment No data Only free blocks Valid block Valid segment Valid data Valid & free blocks Invalid block Invalid segment Invalid data No free block Including invalid block Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 7
8 Writing in Log-structured File System Writing data in append-only manner segment 0 (invalid) segment 1 (valid) segment 2 (valid) A A A A Y Y Y Y A A B B C C Y Y Z Z A A Y Y Modify A Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 8
9 Segment Cleaning Segment cleaning segment 0 (invalid) segment 1 (valid) segment 2 (valid) A A A A B B C C Y Y Y Y Y Y Z Z data data A A A A C C data data data data Y Y data data data data victim segment 1. Select victim segment. 2. Migrate valid blocks. 3. Mark victim segment as free. Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 9
10 Segment Cleaning Two types of segment cleaning Foreground segment cleaning: on-demand Write request I/O latency complete Segment cleaning time Background segment cleaning: periodically Write request complete request idle Segment cleaning period time Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 10
11 Suspend Mode of Smartphone Android adopts Suspend Mode to save battery buffer disk task Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 11
12 Suspend Mode of Smartphone Android adopts Suspend Mode to save battery buffer disk task Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 12
13 Problem Log-structured File System vs. Android Log-structured file system needs segment cleaning to generate free space Android smartphone is suspended when screen is turned off Does segment cleaning works well when smartphone is suspended? Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 13
14 Segment Cleaning and Suspend Mode Power management Active Suspend File system time Background segment cleaning S 0 S 1 S 2 S 3 S 4 S 5 S 6 S 7 Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 14
15 Segment Cleaning and Suspend Mode Power management Active Suspend File system time Background segment cleaning S 0 S 1 S 2 S 3 S 4 S 5 S 6 S 7 Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 15
16 Segment Cleaning and Suspend Mode Power management Active Suspend File system Background segment cleaning CONFLICT!! S 0 S 1 S 2 S 3 S 4 S 5 S 6 S 7 time Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 16
17 Observation Active period in real setting 100% 80% 60% 40% 20% 0% About 75% user 1 user 2 Suspend Active Average 5.6 sec. Device may be in suspend state when Background Segment Cleaning is activated. Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 17
18 Observation There is a large time slack Average 1.8 sec. Active Suspend Waiting for the wakeup events to be cleared time Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 18
19 Design Use the time between LCD off and entering suspend! CPU and I/O devices are still awaken Does not interfere with user and foreground apps Perform segment cleaning when suspending device Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 19
20 Virtual Segment Cleaning Do not migrate valid block directly A A A A B B C C Y Y Y Y Y Y Z Z A A A A C C Y Y victim segment page cache Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 20
21 Virtual Segment Cleaning Do not migrate valid block directly Suspend routine start A A A A C C Y Y Y Y Y Y Z Z A A A A C C victim segment page cache B B Y Y Mark page cache entry as dirty Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 21
22 Virtual Segment Cleaning Do not migrate valid block directly Call sys_sync() Y Y Y Y Y Y Z Z A A A A C C B B Y Y victim segment page cache Mark page cache entry as dirty Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 22
23 Virtual Segment Cleaning LCD off sys_sync() suspended t idle t idle VSC 1 VSC 2 VSC 3 time : Time for processing other suspend routine VSC i : i th Virtual Segment Cleaning t idle : Idle period to throttle the amount of reclaimed segments Too frequent segment cleaning may leads to the reduction of the NAND flash lifetime Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 23
24 Utilization-based Segment Cleaning Threshold of file system utilization to activate SC pinv (Invalid block ratio, %) Activate SC u (File system utilization, %) u: File system utilization Idea threshold p inv : Invalid block ratio Approximated threshold Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 24
25 Utilization-based Segment Cleaning Idle period between segment cleaning Reclaim 2 ~ 6 free segments at once Adaptive with file system utilization and invalid block ratio Using time slack between LCD off and entering suspend 300 ms < t idle < 900 ms Segment cleaning is activated with threshold and idle period is t idle Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 25
26 Experiment Motorola Moto G (KK 4.4.2, Linux 3.4) Component Specification AP Qualcomm Snapdragon 400 CPU RAM Internal storage File system Cortex-A7 1.2GHz Quad-core 1GB 8GB emmc F2FS (data), ET4 (others) Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 26
27 # of reclaimed segments Experiment Number of reclaimed segments Original Segment cleaning, suspend on Original Segment cleaning, suspend off Suspend-aware Segment Cleaning, suspend on reclaimed 6 more segments time (min.) Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 27
28 Avg. # of reclaimed segments Idle Period Model Verification Number of reclaimed segments vs. File system utilization Vary the file system utilization and the fraction of invalid blocks Enter suspend mode 50 times p inv = 25% p inv = 50% p inv = 75% increased by invalid block ratio Ideal value increased by file system utilization Utilization (%) Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 28
29 Conclusion Background segment cleaning of log-structured file system and suspend feature of Android system directly conflict with each other. Suspend-aware Segment Cleaning seamlessly reclaims free segments with suspend module of the smartphone Suspend-aware Segment Cleaning claims 6 as many segments as the stock background segment cleaning does. Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 29
30 Dongil Park et al. USENI HotStorage 15, Santa Clara, CA, July 6~7 30
Suspend-aware Segment Cleaning in Log-structured File System
Suspend-aware Segment Cleaning in Log-structured File System Dongil Park, Seungyong Cheon, and Youjip Won Hanyang University, Seoul, Korea {idoitl pg chunccc y jwon}@hanyang.ac.kr Abstract The suspend
I/O Stack Optimization for Smartphones
I/O Stack Optimization for Smartphones Sooman Jeong 1, Kisung Lee 2, Seongjin Lee 1, Seoungbum Son 2, and Youjip Won 1 1 Dept. of Electronics and Computer Engineering, Hanyang University 2 Samsung Electronics
CFDC A Flash-aware Replacement Policy for Database Buffer Management
CFDC A Flash-aware Replacement Policy for Database Buffer Management Yi Ou University of Kaiserslautern Germany Theo Härder University of Kaiserslautern Germany Peiquan Jin University of Science and Technology
A Self Learning Algorithm for NAND Flash Controllers
A Self Learning Algorithm for NAND Flash Controllers Hao Zhi, Lee Firmware Manager Core Storage Electronics Corp./Phison Electronics Corp. haozhi_lee@phison.com Santa Clara, CA 1 Outline Basic FW Architecture
Virtual Storage Tier and Beyond
Virtual Storage Tier and Beyond Manish Agarwal Sr. Product Manager, NetApp Santa Clara, CA 1 Agenda Trends Other Storage Trends and Flash 5 Min Rule Issues for Flash Dedupe and Flash Caching Architectural
Purity: building fast, highly-available enterprise flash storage from commodity components
Purity: building fast, highly-available enterprise flash storage from commodity components J. Colgrove, J. Davis, J. Hayes, E. Miller, C. Sandvig, R. Sears, A. Tamches, N. Vachharajani, and F. Wang 0 Gala
Solid State Drives (SSDs) Jin-Soo Kim Computer Systems Laboratory Sungkyunkwan University
Solid State Drives (SSDs) Jin-Soo Kim (jinsookim@skku.edu) Computer Systems Laboratory Sungkyunkwan University http://csl.skku.edu Memory Types FLASH High-density Low-cost High-speed Low-power High reliability
Re-Architecting Cloud Storage with Intel 3D XPoint Technology and Intel 3D NAND SSDs
Re-Architecting Cloud Storage with Intel 3D XPoint Technology and Intel 3D NAND SSDs Jack Zhang yuan.zhang@intel.com, Cloud & Enterprise Storage Architect Santa Clara, CA 1 Agenda Memory Storage Hierarchy
Raising QLC Reliability in All-Flash Arrays
Raising QLC Reliability in All-Flash Arrays Jeff Yang Principal Engineer Storage Research Dept. Silicon Motion, Inc. Santa Clara, CA 1 QLC Characteristics (Estimation) QLC Endurance: 1~3K P/E.(limited
Using Non-volatile Memories for Browser Performance Improvement. Seongmin KIM and Taeseok KIM *
2017 2nd International Conference on Computer, Network Security and Communication Engineering (CNSCE 2017) ISBN: 978-1-60595-439-4 Using Non-volatile Memories for Browser Performance Improvement Seongmin
Optimizing Server Flash with Intelligent Caching (Enterprise Storage Track)
Optimizing Server Flash with Intelligent Caching (Enterprise Storage Track) Mohit Bhatnagar Sr. Director Flash Products and Solutions Santa Clara, CA 1 Definition of Intelligent Source: Dictionary.com
FlashTier: A Lightweight, Consistent and Durable Storage Cache
FlashTier: A Lightweight, Consistent and Durable Storage Cache Mohit Saxena PhD Candidate University of Wisconsin-Madison msaxena@cs.wisc.edu Flash Memory Summit 2012 Santa Clara, CA Flash is a Good Cache
SFS: Random Write Considered Harmful in Solid State Drives
SFS: Random Write Considered Harmful in Solid State Drives Changwoo Min 1, 2, Kangnyeon Kim 1, Hyunjin Cho 2, Sang-Won Lee 1, Young Ik Eom 1 1 Sungkyunkwan University, Korea 2 Samsung Electronics, Korea
Exploring System Challenges of Ultra-Low Latency Solid State Drives
Exploring System Challenges of Ultra-Low Latency Solid State Drives Sungjoon Koh Changrim Lee, Miryeong Kwon, and Myoungsoo Jung Computer Architecture and Memory systems Lab Executive Summary Motivation.
A Memory Management Scheme for Hybrid Memory Architecture in Mission Critical Computers
A Memory Management Scheme for Hybrid Memory Architecture in Mission Critical Computers Soohyun Yang and Yeonseung Ryu Department of Computer Engineering, Myongji University Yongin, Gyeonggi-do, Korea
Benchmark: In-Memory Database System (IMDS) Deployed on NVDIMM
Benchmark: In-Memory Database System (IMDS) Deployed on NVDIMM Presented by Steve Graves, McObject and Jeff Chang, AgigA Tech Santa Clara, CA 1 The Problem: Memory Latency NON-VOLATILE MEMORY HIERARCHY
Flash Memory Based Storage System
Flash Memory Based Storage System References SmartSaver: Turning Flash Drive into a Disk Energy Saver for Mobile Computers, ISLPED 06 Energy-Aware Flash Memory Management in Virtual Memory System, islped
Cooperating Write Buffer Cache and Virtual Memory Management for Flash Memory Based Systems
Cooperating Write Buffer Cache and Virtual Memory Management for Flash Memory Based Systems Liang Shi, Chun Jason Xue and Xuehai Zhou Joint Research Lab of Excellence, CityU-USTC Advanced Research Institute,
A File-System-Aware FTL Design for Flash Memory Storage Systems
1 A File-System-Aware FTL Design for Flash Memory Storage Systems Po-Liang Wu, Yuan-Hao Chang, Po-Chun Huang, and Tei-Wei Kuo National Taiwan University 2 Outline Introduction File Systems Observations
About the Need to Power Instrument the Linux Kernel
Embedded Linux Conference February 21st, 2017 Portland, OR, USA About the Need to Power Instrument the Linux Kernel Patrick Titiano, System Power Management Expert, BayLibre co-founder. www.baylibre.com
Power Management for Embedded Systems
Power Management for Embedded Systems Minsoo Ryu Hanyang University Why Power Management? Battery-operated devices Smartphones, digital cameras, and laptops use batteries Power savings and battery run
Using Transparent Compression to Improve SSD-based I/O Caches
Using Transparent Compression to Improve SSD-based I/O Caches Thanos Makatos, Yannis Klonatos, Manolis Marazakis, Michail D. Flouris, and Angelos Bilas {mcatos,klonatos,maraz,flouris,bilas}@ics.forth.gr
Understanding Storage I/O Behaviors of Mobile Applications. Louisiana State University Department of Computer Science and Engineering
Understanding Storage I/O Behaviors of Mobile Applications Jace Courville jcourv@csc.lsu.edu Feng Chen fchen@csc.lsu.edu Louisiana State University Department of Computer Science and Engineering The Rise
EECS750: Advanced Operating Systems. 2/24/2014 Heechul Yun
EECS750: Advanced Operating Systems 2/24/2014 Heechul Yun 1 Administrative Project Feedback of your proposal will be sent by Wednesday Midterm report due on Apr. 2 3 pages: include intro, related work,
Under The Hood: Performance Tuning With Tizen. Ravi Sankar Guntur
Under The Hood: Performance Tuning With Tizen Ravi Sankar Guntur How to write a Tizen App Tools already available in IDE v2.3 Dynamic Analyzer Valgrind 2 What s NEXT? Want to optimize my application App
I/O Systems (4): Power Management. CSE 2431: Introduction to Operating Systems
I/O Systems (4): Power Management CSE 2431: Introduction to Operating Systems 1 Outline Overview Hardware Issues OS Issues Application Issues 2 Why Power Management? Desktop PCs Battery-powered Computers
File System Implementations
CSE 451: Operating Systems Winter 2005 FFS and LFS Steve Gribble File System Implementations We ve looked at disks and file systems generically now it s time to bridge the gap by talking about specific
Command Register Settings Description Notes
Technical Note e.mmc Automotive 5.0 Cache Features TN-FC-50: e.mmc Automotive 5.0 Cache Features Introduction Introduction This technical note introduces an optional cache feature defined in the e.mmc
Power Measurements using performance counters
Power Measurements using performance counters CSL862: Low-Power Computing By Suman A M (2015SIY7524) Android Power Consumption in Android Power Consumption in Smartphones are powered from batteries which
Flash File Systems Overview
Table of contents 1.0 Overview 3 1.1 Flash architecture 3 1.1.1 Partitions 3 1.1.2 Blocks 3 1.2 Programming data 3 1.3 Data integrity 4 2.0 Flash file system functions 4 2.1 Wear leveling 4 2.2 Reclaim
Memory Management Outline. Operating Systems. Motivation. Paging Implementation. Accessing Invalid Pages. Performance of Demand Paging
Memory Management Outline Operating Systems Processes (done) Memory Management Basic (done) Paging (done) Virtual memory Virtual Memory (Chapter.) Motivation Logical address space larger than physical
Designing Enterprise Controllers with QLC 3D NAND
Designing Enterprise Controllers with QLC 3D NAND Roman Pletka, Radu Stoica, Nikolas Ioannou, Sasa Tomic, Nikolaos Papandreou, Haralampos Pozidis IBM Research Zurich Research Laboratory Santa Clara, CA
Cascade Mapping: Optimizing Memory Efficiency for Flash-based Key-value Caching
Cascade Mapping: Optimizing Memory Efficiency for Flash-based Key-value Caching Kefei Wang and Feng Chen Louisiana State University SoCC '18 Carlsbad, CA Key-value Systems in Internet Services Key-value
2. PICTURE: Cut and paste from paper
File System Layout 1. QUESTION: What were technology trends enabling this? a. CPU speeds getting faster relative to disk i. QUESTION: What is implication? Can do more work per disk block to make good decisions
Page Mapping Scheme to Support Secure File Deletion for NANDbased Block Devices
Page Mapping Scheme to Support Secure File Deletion for NANDbased Block Devices Ilhoon Shin Seoul National University of Science & Technology ilhoon.shin@snut.ac.kr Abstract As the amount of digitized
The Unwritten Contract of Solid State Drives
The Unwritten Contract of Solid State Drives Jun He, Sudarsun Kannan, Andrea C. Arpaci-Dusseau, Remzi H. Arpaci-Dusseau Department of Computer Sciences, University of Wisconsin - Madison Enterprise SSD
ParaFS: A Log-Structured File System to Exploit the Internal Parallelism of Flash Devices
ParaFS: A Log-Structured File System to Exploit the Internal Parallelism of Devices Jiacheng Zhang, Jiwu Shu, Youyou Lu Tsinghua University 1 Outline Background and Motivation ParaFS Design Evaluation
STORAGE LATENCY x. RAMAC 350 (600 ms) NAND SSD (60 us)
1 STORAGE LATENCY 2 RAMAC 350 (600 ms) 1956 10 5 x NAND SSD (60 us) 2016 COMPUTE LATENCY 3 RAMAC 305 (100 Hz) 1956 10 8 x 1000x CORE I7 (1 GHZ) 2016 NON-VOLATILE MEMORY 1000x faster than NAND 3D XPOINT
COMPUTER ORGANIZATION AND DESIGN The Hardware/Software Interface. 5 th. Edition. Chapter 5. Large and Fast: Exploiting Memory Hierarchy
COMPUTER ORGANIZATION AND DESIGN The Hardware/Software Interface 5 th Edition Chapter 5 Large and Fast: Exploiting Memory Hierarchy Principle of Locality Programs access a small proportion of their address
POWER MANAGEMENT AND ENERGY EFFICIENCY
POWER MANAGEMENT AND ENERGY EFFICIENCY * Adopted Power Management for Embedded Systems, Minsoo Ryu 2017 Operating Systems Design Euiseong Seo (euiseong@skku.edu) Need for Power Management Power consumption
Architecture Exploration of High-Performance PCs with a Solid-State Disk
Architecture Exploration of High-Performance PCs with a Solid-State Disk D. Kim, K. Bang, E.-Y. Chung School of EE, Yonsei University S. Yoon School of EE, Korea University April 21, 2010 1/53 Outline
Could We Make SSDs Self-Healing?
Could We Make SSDs Self-Healing? Tong Zhang Electrical, Computer and Systems Engineering Department Rensselaer Polytechnic Institute Google/Bing: tong rpi Santa Clara, CA 1 Introduction and Motivation
Copyright 2014 Fusion-io, Inc. All rights reserved.
Snapshots in a Flash with iosnap TM Sriram Subramanian, Swami Sundararaman, Nisha Talagala, Andrea Arpaci-Dusseau, Remzi Arpaci-Dusseau Presented By: Samer Al-Kiswany Snapshots Overview Point-in-time representation
OASIS: Self-tuning Storage for Applications
OASIS: Self-tuning Storage for Applications Kostas Magoutis, Prasenjit Sarkar, Gauri Shah 14 th NASA Goddard- 23 rd IEEE Mass Storage Systems Technologies, College Park, MD, May 17, 2006 Outline Motivation
ECOS: Practical Mobile Application Offloading for Enterprises. Aaron Gember, Chris Dragga, Aditya Akella University of Wisconsin-Madison
ECOS: Practical Mobile Application Offloading for Enterprises Aaron Gember, Chris Dragga, Aditya Akella University of Wisconsin-Madison 1 Mobile Device Trends More mobile device usage in enterprises Need
PCIe Storage Beyond SSDs
PCIe Storage Beyond SSDs Fabian Trumper NVM Solutions Group PMC-Sierra Santa Clara, CA 1 Classic Memory / Storage Hierarchy FAST, VOLATILE CPU Cache DRAM Performance Gap Performance Tier (SSDs) SLOW, NON-VOLATILE
Energy Discounted Computing On Multicore Smartphones Meng Zhu & Kai Shen. Atul Bhargav
Energy Discounted Computing On Multicore Smartphones Meng Zhu & Kai Shen Atul Bhargav Overview Energy constraints in a smartphone Li-Ion Battery Arm big.little Hardware Sharing What is Energy Discounted
ijournaling: Fine-Grained Journaling for Improving the Latency of Fsync System Call
ijournaling: Fine-Grained Journaling for Improving the Latency of Fsync System Call Daejun Park and Dongkun Shin, Sungkyunkwan University, Korea https://www.usenix.org/conference/atc17/technical-sessions/presentation/park
A Caching-Oriented FTL Design for Multi-Chipped Solid-State Disks. Yuan-Hao Chang, Wei-Lun Lu, Po-Chun Huang, Lue-Jane Lee, and Tei-Wei Kuo
A Caching-Oriented FTL Design for Multi-Chipped Solid-State Disks Yuan-Hao Chang, Wei-Lun Lu, Po-Chun Huang, Lue-Jane Lee, and Tei-Wei Kuo 1 June 4, 2011 2 Outline Introduction System Architecture A Multi-Chipped
Towards SDN-Defined Programmable BYOD (Bring Your Own Device) Security
Towards SDN-Defined Programmable BYOD (Bring Your Own Device) Security Sungmin Hong, Robert Baykov, Lei Xu, Srinath Nadimpalli, Guofei Gu SUCCESS Lab Texas A&M University Outline Introduction & Motivation
CFLRU:A A Replacement Algorithm for Flash Memory
CFLRU:A A Replacement Algorithm for Flash Memory CASES'06, October 23 25, 2006, Seoul, Korea. Copyright 2006 ACM 1-59593-543-6/06/0010 Yen-Ting Liu Outline Introduction CFLRU Algorithm Simulation Implementation
Chapter 6 Objectives
Chapter 6 Memory Chapter 6 Objectives Master the concepts of hierarchical memory organization. Understand how each level of memory contributes to system performance, and how the performance is measured.
Toward Seamless Integration of RAID and Flash SSD
Toward Seamless Integration of RAID and Flash SSD Sang-Won Lee Sungkyunkwan Univ., Korea (Joint-Work with Sungup Moon, Bongki Moon, Narinet, and Indilinx) Santa Clara, CA 1 Table of Contents Introduction
Adapted from instructor s supplementary material from Computer. Patterson & Hennessy, 2008, MK]
![Adapted from instructor s supplementary material from Computer. Patterson & Hennessy, 2008, MK]](/thumbs/80/82108809.jpg "Adapted from instructor s supplementary material from Computer. Patterson & Hennessy, 2008, MK]")
Lecture 17 Adapted from instructor s supplementary material from Computer Organization and Design, 4th Edition, Patterson & Hennessy, 2008, MK] SRAM / / Flash / RRAM / HDD SRAM / / Flash / RRAM/ HDD SRAM
Aerospike Scales with Google Cloud Platform
Aerospike Scales with Google Cloud Platform PERFORMANCE TEST SHOW AEROSPIKE SCALES ON GOOGLE CLOUD Aerospike is an In-Memory NoSQL database and a fast Key Value Store commonly used for caching and by real-time
Clustered Page-Level Mapping for Flash Memory-Based Storage Devices
H. Kim and D. Shin: ed Page-Level Mapping for Flash Memory-Based Storage Devices 7 ed Page-Level Mapping for Flash Memory-Based Storage Devices Hyukjoong Kim and Dongkun Shin, Member, IEEE Abstract Recent
Experimental Results of Implementing NV Me-based Open Channel SSDs
Experimental Results of Implementing NV Me-based Open Channel SSDs Sangjin Lee, Yong Ho Song Hanyang University, Seoul, Korea Santa Clara, CA 1 OpenSSD Project Open source SSD for search and education
Lecture 17 Introduction to Memory Hierarchies" Why it s important " Fundamental lesson(s)" Suggested reading:" (HP Chapter
Processor components" Multicore processors and programming" Processor comparison" vs." Lecture 17 Introduction to Memory Hierarchies" CSE 30321" Suggested reading:" (HP Chapter 5.1-5.2)" Writing more "
Smartwatches (April 12, 2017) Samsung Gear Live, 2014 Samsung S 3G, 2014 Samsung S3 LTE, November 2016
Smartwatches (April 12, 2017) Samsung Gear Live, 2014 Samsung S 3G, 2014 Samsung S3 LTE, November 2016 1 Samsung Gear Live 2 Samsung Gear Live 1.63 Super AMOLED display with a resolution of 320 x 320 pixels
Designing Next Generation FS for NVMe and NVMe-oF
Designing Next Generation FS for NVMe and NVMe-oF Liran Zvibel CTO, Co-founder Weka.IO @liranzvibel Santa Clara, CA 1 Designing Next Generation FS for NVMe and NVMe-oF Liran Zvibel CTO, Co-founder Weka.IO
Deukyeon Hwang UNIST. Wook-Hee Kim UNIST. Beomseok Nam UNIST. Hanyang Univ.
Deukyeon Hwang UNIST Wook-Hee Kim UNIST Youjip Won Hanyang Univ. Beomseok Nam UNIST Fast but Asymmetric Access Latency Non-Volatility Byte-Addressability Large Capacity CPU Caches (Volatile) Persistent
Performance Trade-Offs in Using NVRAM Write Buffer for Flash Memory-Based Storage Devices
Performance Trade-Offs in Using NVRAM Write Buffer for Flash Memory-Based Storage Devices Sooyong Kang, Sungmin Park, Hoyoung Jung, Hyoki Shim, and Jaehyuk Cha IEEE TRANSACTIONS ON COMPUTERS, VOL. 8, NO.,
Optimizing Software-Defined Storage for Flash Memory
Optimizing Software-Defined Storage for Flash Memory Avraham Meir Chief Scientist, Elastifile Santa Clara, CA 1 Agenda What is SDS? SDS Media Selection Flash-Native SDS Non-Flash SDS File system benefits
Solving the I/O bottleneck with Flash
Solving the I/O bottleneck with Flash Ori Balaban Director of Sales for Global Accounts SanDisk Corporation August 2007 1 Agenda Performance bottlenecks in HDD Alternative solutions SSD value proposition
The Dangers and Complexities of SQLite Benchmarking. Dhathri Purohith, Jayashree Mohan and Vijay Chidambaram
The Dangers and Complexities of SQLite Benchmarking Dhathri Purohith, Jayashree Mohan and Vijay Chidambaram 2 3 Benchmarking SQLite is Non-trivial! Benchmarking complex systems in a repeatable fashion
SHRD: Improving Spatial Locality in Flash Storage Accesses by Sequentializing in Host and Randomizing in Device
SHRD: Improving Spatial Locality in Flash Storage Accesses by Sequentializing in Host and Randomizing in Device Hyukjoong Kim 1, Dongkun Shin 1, Yun Ho Jeong 2 and Kyung Ho Kim 2 1 Samsung Electronics
Computer Architecture. Fall Dongkun Shin, SKKU
Computer Architecture Fall 2018 1 Syllabus Instructors: Dongkun Shin Office : Room 85470 E-mail : dongkun@skku.edu Office Hours: Wed. 15:00-17:30 or by appointment Lecture notes nyx.skku.ac.kr Courses
Tips and Tricks: Designing low power Native and WebApps. Harita Chilukuri and Abhishek Dhanotia
Tips and Tricks: Designing low power Native and WebApps Harita Chilukuri and Abhishek Dhanotia Acknowledgements William Baughman for his help with the browser analysis Ross Burton & Thomas Wood for information
What s Wrong with the Operating System Interface? Collin Lee and John Ousterhout
What s Wrong with the Operating System Interface? Collin Lee and John Ousterhout Goals for the OS Interface More convenient abstractions than hardware interface Manage shared resources Provide near-hardware
Dongjun Shin Samsung Electronics
2014.10.31. Dongjun Shin Samsung Electronics Contents 2 Background Understanding CPU behavior Experiments Improvement idea Revisiting Linux I/O stack Conclusion Background Definition 3 CPU bound A computer
SmartSaver: Turning Flash Drive into a Disk Energy Saver for Mobile Computers
SmartSaver: Turning Flash Drive into a Disk Energy Saver for Mobile Computers Feng Chen 1 Song Jiang 2 Xiaodong Zhang 1 The Ohio State University, USA Wayne State University, USA Disks Cost High Energy
Storage Architecture and Software Support for SLC/MLC Combined Flash Memory
Storage Architecture and Software Support for SLC/MLC Combined Flash Memory Soojun Im and Dongkun Shin Sungkyunkwan University Suwon, Korea {lang33, dongkun}@skku.edu ABSTRACT We propose a novel flash
CFS-v: I/O Demand-driven VM Scheduler in KVM
CFS-v: Demand-driven VM Scheduler in KVM Hyotaek Shim and Sung-Min Lee (hyotaek.shim, sung.min.lee@samsung.com) Software R&D Center, Samsung Electronics 2014. 10. 16 Problem in Server Consolidation 2/16
How to Build a Successful Business with Flash Green. powered by America s Largest and Most Reliable Network
How to Build a Successful Business with Flash Green powered by America s Largest and Most Reliable Network Table of Contents This playbook contains everything you need build a successful business with
CSE 2021: Computer Organization
CSE 2021: Computer Organization Lecture-12 Caches-1 The basics of caches Shakil M. Khan Memory Technology Static RAM (SRAM) 0.5ns 2.5ns, $2000 $5000 per GB Dynamic RAM (DRAM) 50ns 70ns, $20 $75 per GB
File Systems. Kartik Gopalan. Chapter 4 From Tanenbaum s Modern Operating System
File Systems Kartik Gopalan Chapter 4 From Tanenbaum s Modern Operating System 1 What is a File System? File system is the OS component that organizes data on the raw storage device. Data, by itself, is
Scaling Indexer Clustering
Scaling Indexer Clustering 5 Million Unique Buckets and Beyond Cher-Hung Chang Principal Software Engineer Tameem Anwar Software Engineer 09/26/2017 Washington, DC Forward-Looking Statements During the
The Google File System
October 13, 2010 Based on: S. Ghemawat, H. Gobioff, and S.-T. Leung: The Google file system, in Proceedings ACM SOSP 2003, Lake George, NY, USA, October 2003. 1 Assumptions Interface Architecture Single
CSE 153 Design of Operating Systems
CSE 153 Design of Operating Systems Winter 2018 Lecture 22: File system optimizations and advanced topics There s more to filesystems J Standard Performance improvement techniques Alternative important
ECE 7650 Scalable and Secure Internet Services and Architecture ---- A Systems Perspective. Part I: Operating system overview: Memory Management
ECE 7650 Scalable and Secure Internet Services and Architecture ---- A Systems Perspective Part I: Operating system overview: Memory Management 1 Hardware background The role of primary memory Program
BIBIM: A Prototype Multi-Partition Aware Heterogeneous New Memory
HotStorage 18 BIBIM: A Prototype Multi-Partition Aware Heterogeneous New Memory Gyuyoung Park 1, Miryeong Kwon 1, Pratyush Mahapatra 2, Michael Swift 2, and Myoungsoo Jung 1 Yonsei University Computer
I/O Devices & SSD. Dongkun Shin, SKKU
I/O Devices & SSD 1 System Architecture Hierarchical approach Memory bus CPU and memory Fastest I/O bus e.g., PCI Graphics and higherperformance I/O devices Peripheral bus SCSI, SATA, or USB Connect many
MySQL Performance Optimization and Troubleshooting with PMM. Peter Zaitsev, CEO, Percona
MySQL Performance Optimization and Troubleshooting with PMM Peter Zaitsev, CEO, Percona In the Presentation Practical approach to deal with some of the common MySQL Issues 2 Assumptions You re looking
An SMR-aware Append-only File System Chi-Young Ku Stephen P. Morgan Futurewei Technologies, Inc. Huawei R&D USA
An SMR-aware Append-only File System Chi-Young Ku Stephen P. Morgan Futurewei Technologies, Inc. Huawei R&D USA SMR Technology (1) Future disk drives will be based on shingled magnetic recording. Conventional
CSE502: Computer Architecture CSE 502: Computer Architecture
CSE 502: Computer Architecture Memory Hierarchy & Caches Motivation 10000 Performance 1000 100 10 Processor Memory 1 1985 1990 1995 2000 2005 2010 Want memory to appear: As fast as CPU As large as required
Real-World Performance Training Core Database Performance
Real-World Performance Training Core Database Performance Real-World Performance Team Agenda 1 2 3 4 5 6 Computer Science Basics Schema Types and Database Design Database Interface DB Deployment and Access
2009. October. Semiconductor Business SAMSUNG Electronics
2009. October Semiconductor Business SAMSUNG Electronics Why SSD performance is faster than HDD? HDD has long latency & late seek time due to mechanical operation SSD does not have both latency and seek
Motorola Phone Manual Razr Maxx 4g Android Phone Black 32gb
Motorola Phone Manual Razr Maxx 4g Android Phone Black 32gb Motorola DROID Maxx Android smartphone. Announced 2013, July. Features 3G, 5.0 Super AMOLED capacitive touchscreen, 10 MP camera, Wi-Fi, GPS.
Optimizing Performance and Reliability of Mobile Storage Memory
Optimizing Performance and Reliability of Mobile Storage Memory 8/5/14 You Sung Kim SK hynix America, Inc. August 2014 1 Memory Trend PC Era (1980~) CPU centric (GHz spec.) Smart & Mobile Era (2007~) Mobile
Introduction to Energy-Efficient Software 2 nd life talk
Introduction to Energy-Efficient Software 2 nd life talk Intel Software and Solutions Group Bob Steigerwald Nov 8, 2007 Taylor Kidd Nov 15, 2007 Agenda Demand for Mobile Computing Devices What is Energy-Efficient
Memory Technology. Chapter 5. Principle of Locality. Chapter 5 Large and Fast: Exploiting Memory Hierarchy 1
COMPUTER ORGANIZATION AND DESIGN The Hardware/Software Interface Chapter 5 Large and Fast: Exploiting Memory Hierarchy 5 th Edition Memory Technology Static RAM (SRAM) 0.5ns 2.5ns, $2000 $5000 per GB Dynamic
19: I/O Devices: Clocks, Power Management
19: I/O Devices: Clocks, Power Management Mark Handley Clock Hardware: A Programmable Clock Pulses Counter, decremented on each pulse Crystal Oscillator On zero, generate interrupt and reload from holding
SRM-Buffer: An OS Buffer Management SRM-Buffer: An OS Buffer Management Technique toprevent Last Level Cache from Thrashing in Multicores
SRM-Buffer: An OS Buffer Management SRM-Buffer: An OS Buffer Management Technique toprevent Last Level Cache from Thrashing in Multicores Xiaoning Ding The Ohio State University dingxn@cse.ohiostate.edu
Memory Technology. Caches 1. Static RAM (SRAM) Dynamic RAM (DRAM) Magnetic disk. Ideal memory. 0.5ns 2.5ns, $2000 $5000 per GB
Memory Technology Caches 1 Static RAM (SRAM) 0.5ns 2.5ns, $2000 $5000 per GB Dynamic RAM (DRAM) 50ns 70ns, $20 $75 per GB Magnetic disk 5ms 20ms, $0.20 $2 per GB Ideal memory Average access time similar
Page Replacement Algorithms
Page Replacement Algorithms MIN, OPT (optimal) RANDOM evict random page FIFO (first-in, first-out) give every page equal residency LRU (least-recently used) MRU (most-recently used) 1 9.1 Silberschatz,
LocAdoc Test Report. Version 1.0. Prepared by: Abhi Jay Krishnan Kim Hyeoncheol Rivaldo Erawan Durrah Afshan
LocAdoc Test Report Version 1.0 Prepared by: Abhi Jay Krishnan Kim Hyeoncheol Rivaldo Erawan Durrah Afshan Table of Contents 1. Introduction 1 2. Test Plan Overview 1 2.1 Objective 1 2.2 Approach 1 2.3
A Page-Based Storage Framework for Phase Change Memory
A Page-Based Storage Framework for Phase Change Memory Peiquan Jin, Zhangling Wu, Xiaoliang Wang, Xingjun Hao, Lihua Yue University of Science and Technology of China 2017.5.19 Outline Background Related
Webinar Series: Triangulate your Storage Architecture with SvSAN Caching. Luke Pruen Technical Services Director
Webinar Series: Triangulate your Storage Architecture with SvSAN Caching Luke Pruen Technical Services Director What can you expect from this webinar? To answer a simple question How can I create the perfect
Performance Consistency
White Paper Performance Consistency SanDIsk Corporation Corporate Headquarters 951 SanDisk Drive, Milpitas, CA 95035, U.S.A. Phone +1.408.801.1000 Fax +1.408.801.8657 www.sandisk.com Performance Consistency
Unblinding the OS to Optimize User-Perceived Flash SSD Latency
Unblinding the OS to Optimize User-Perceived Flash SSD Latency Woong Shin *, Jaehyun Park **, Heon Y. Yeom * * Seoul National University ** Arizona State University USENIX HotStorage 2016 Jun. 21, 2016