CS 295: Modern Systems Storage Technologies Introduction Sang-Woo

CS 295: Modern Systems Storage Technologies Introduction Sang-Woo

CS 295: Modern Systems Storage Technologies Introduction Sang-Woo Jun Spring, 2019 Storage Used To be a Secondary Concern Typically, storage was not a first order citizen of a computer system o o o o As allured by its name secondary storage Its job was to load programs and data to memory, and disappear

Most applications only worked with CPU and system memory (DRAM) Extreme applications like DBMSs were the exception Because conventional secondary storage was very slow o Things are changing! Some (Pre)History Magnetic core memory 1950~1970s (1024 bits in photo) Photos from Wikipedia Rope memory (ROM) 1960s 72 KiB per cubic foot!

Hand-woven to program the Apollo guidance computer Drum memory 100s of KiB 1950s Some (More Recent) History Floppy disk drives 1970s~2000s 100 KiBs to 1.44 MiB Photos from Wikipedia

Hard disk drives 1950s to present MBs to TBs Some (Current) History Solid State Drives 2000s to present GB to TBs Non-Volatile Memory 2010s to present GBs Hard Disk Drives

Dominant storage medium for the longest time o Still the largest capacity share Data organized into multiple magnetic platters o Mechanical head needs to move to where data is, to read it o Good sequential access, terrible random access 100s of MB/s sequential, maybe 1 MB/s 4 KB random o Time for the head to move to the right location (seek time) may be ms long 1000,000s of cycles! Typically ATA (Including IDE and EIDE), and later SATA interfaces o Connected via South bridge chipset Ding Yuan, Operating Systems ECE344 Lecture 11: File System

Solid State Drives Solid state, meaning no mechanical parts, addressed much like DRAM o Relatively low latency compared to HDDs (10s of us, compared to ms) o Easily parallelizable using more chips Multi-GB/s Simple explanation: flash cells store state in a floating gate by charging it at a high voltage o High voltage acquired via internal charge pump (no need for high V input) Solid State Drives Serial ATA (SATA) interface, over Advanced Host Controller Interface (AHCI) standard o Used to be connected to south bridge, o Up to 600 MB/s, quickly became too slow for SSDs

Non-Volatile Memory Express (NVMe) o PCIe-attached storage devices multi-GB/s o Redesigns many storage support components in the OS for performance Non-Volatile Memory Naming convention is a bit vague o Flash storage is also often called NVM Storage-Class Memory (SCM)? o Anything that is non-volatile and fast? Too fast for even PCIe/NVMe software o Plugged into memory slots, accessed like memory

But not quite as fast as DRAM o Latency/Bandwidth/Access granularity o Usage under active research! Souce: NetApp blog, Storage Class Memory: Whats Next in Enterprise Storage, 2018 System Architecture Snapshot (2019) SATA Up to 600 MB/s GPU South Bridge SSD

NVMe CPU DDR4 2666 MHz 128 GB/s 100s of GB I/O Hub (IOH) Network Interface Host Memory

(DDR4,) Storage-Class Memory QPI/UPI 12.8 GB/s (QPI) 20.8 GB/s (UPI) PCIe 16-lane PCIe Gen3: 16 GB/s Lots of moving parts!

Storage for Analytics (2019) Fine-grained, Irregular access Terabytes in size TB DRAM of DRAM $$$ $8000/TB, 200W The goal:

$ $400/TB, 10W $ $150/TB, 2W Performance Challenges in Flash Storage 1 Flash Bandwidth: 0.6-10 GB/s DRAM ~50 GB/s Not bad! Considering local DRAM and RAID

Performance Challenges in Flash Storage 2 Flash Bandwidth: Latency: 0.6-10 GB/s ~100 s DRAM ~50 GB/s ? ~15 ns

Most latency from device itself Xu et. al., Performance Analysis of NVMe SSDs and their Implication on Real World Databases SYSTOR 2015 Performance Challenges in Flash Storage 2 Flash Bandwidth: Latency: DRAM 0.6-10 GB/s ~50 GB/s

! ~100 s ~15 ns Becomes the norm after a while Xu et. al., Performance Analysis of NVMe SSDs and their Implication on Real World Databases SYSTOR 2015 Flash Fabric Characteristic Read/Write Imbalance Limited Cell Lifetime

block (~2 MB) Blocks can die after ~3000 erases page (~8 KB) In-place writes are bad! Only erased pages can be written Erasures done in block granularity In-place writes are bad! Flash Translation Layer Bus, Chip, Block, Page

DRAM Flash Translation Layer Logical Block Address Host Logical-to-Physical mapping Wear leveling Write-ahead logging Error correction Garbage collection Deduplication Quad-core ARM chip, GBs of DRAM Performance Challenges in Flash Storage 3

Flash Bandwidth: Latency: DRAM 0.6-10 GB/s ~50 GB/s ~100 s ~15 ns 8192 Bytes

128 Bytes Access Granularity: * Wastes performance by not using most of fetched page Things to Come

Recently Viewed Presentations

  • INTRODUCTION TO PERSEPOLIS East versus West  The East

    INTRODUCTION TO PERSEPOLIS East versus West The East

    The West The terms "East" and "West"… have been common for centuries are a convenient way to group cultures are often used as stereotypes Iran Tehran IRAQ IRAN SAUDI ARABIA ancient city of Persepolis Iran The country that is now...
  • Safe Harbor Statement The following is intended to

    Safe Harbor Statement The following is intended to

    This presentation contains information proprietary to Oracle Corporation ... Cloud Foundation Application is a set of best-of-breed products provided by Oracle that provide what we believe is the key foundation infrastructure for building cloud environments for running private clouds or...
  • Verb Identification

    Verb Identification

    Verbs give the action or state of being in a sentence. There are six primary verb tenses. Some types of verbs are stronger than others. Linking Verbs. Linking verbs express a subject's state of being. I am your teacher. It...
  • BARE BONES SENTENCES - WordPress.com

    BARE BONES SENTENCES - WordPress.com

    BARE BONES SENTENCES. If you have the simplest subject and simplest predicate possible, then you have a bare bones sentence. ... When you look at a skeleton, you can see the basic type of animal or person it is. But...
  • Eisenhower and the Cold War - Weebly

    Eisenhower and the Cold War - Weebly

    Third World Unrest. Indochina (Vietnam/Cambodia/Laos) France tries to retake. Ho Chi Minh and Communists fight for independence. U.S. gives aid to French. USSR to Ho Chi Minh. U.S. refuses to send in troops, French lose. ... Eisenhower and the Cold...
  • スライド 1 - 東京工業大学

    スライド 1 - 東京工業大学

    Summary. A new method to determine the . accurate. inlet/outlet BC for vascular CFD analysis using 4D-Flow is proposed. Its practically sufficient accuracy is validated through the experiments with straight and curved pipe phantoms.
  • The 2010 Patient Protection and Affordable Care Act

    The 2010 Patient Protection and Affordable Care Act

    Employer incentives in 2014. Penalties: 1-50 employees exempt from any penalty. 50-199 employees must pay penalties of up to $3,000 per employee. 200+ employees must enroll employees in a health insurance plan
  • Chapter 12

    Chapter 12

    Faith, Fortune, and Fame * The Big Picture 1500 1700 1600 Tudor Dynasty in England African Slave Trade Stuart Dynasty in England Spanish and Portuguese Exploration English, French, and Dutch Exploration Golden Age of Piracy The World Imagined The Lure...