Effects of Storage Trends on Databases

Slides:



Advertisements
Similar presentations
55:035 Computer Architecture and Organization Lecture 7 155:035 Computer Architecture and Organization.
Advertisements

Virtual Memory. Hierarchy Cache Memory : Provide invisible speedup to main memory.
Denny Cherry Manager of Information Systems MVP, MCSA, MCDBA, MCTS, MCITP.
Data Storage Technology
Bits and Data Storage. Basic Hardware Units of a Computer.
Physical Storage and File Organization COMSATS INSTITUTE OF INFORMATION TECHNOLOGY, VEHARI.
Computers Central Processor Unit. Basic Computer System MAIN MEMORY ALUCNTL..... BUS CONTROLLER Processor I/O moduleInterconnections BUS Memory.
COEN/ELEN 180 Storage Systems Memory Hierarchy. We are therefore forced to recognize the possibility of constructing a hierarchy of memories, each of.
Overview of Physical Storage Media
1/14/2005Yan Huang - CSCI5330 Database Implementation – Storage and File Structure Storage and File Structure.
COEN 180 Memory Hierarchy. We are therefore forced to recognize the possibility of constructing a hierarchy of memories, each of which has greater capacity.
Data Storage and Querying in Various Storage Devices.
The very Essentials of Disk and Buffer Management.
Computer System Structures Storage
sponsored by HP Enterprise
TYPES OF MEMORY.
CMPE Database Systems Workshop June 16 Class Meeting
CS 704 Advanced Computer Architecture
Chapter 11: File System Implementation
Chapter 12: File System Implementation
Storage and Disks.
Lecture 16: Data Storage Wednesday, November 6, 2006.
Database Management Systems (CS 564)
Using non-volatile memory (NVDIMM-N) as block storage in Windows Server 2016 Tobias Klima Program Manager.
Secondary Storage Data Retrieval.
Secondary storage.
Introduction to Computer Architecture
CSE Algorithms Quicksort vs Heapsort: the “inside” story or
Local secondary storage (local disks)
Primary Storage and Secondary Storage Devices Chapter 3
Denny Cherry twitter.com/mrdenny
Disks and Files DBMS stores information on (“hard”) disks.
File Processing : Storage Media
Lecture 11: DMBS Internals
Introduction I/O devices can be characterized by I/O bus connections
PASTE: A Networking API for Non-Volatile Main Memory
Lecture 21: Memory Hierarchy
Lecture 21: Memory Hierarchy
What is the maximum capacity for DDR3 RAM?
Lecture 23: Cache, Memory, Virtual Memory
FIGURE 12-1 Memory Hierarchy
CS 140 Lecture Notes: Technology and Operating Systems
File Processing : Storage Media
CS 140 Lecture Notes: Technology and Operating Systems
Lecture 22: Cache Hierarchies, Memory
Introduction to Computer Architecture
CSE 451: Operating Systems Winter 2007 Module 13 Secondary Storage
Chap. 12 Memory Organization
CMSC 611: Advanced Computer Architecture
Lecture 20: OOO, Memory Hierarchy
Secondary Storage Management Brian Bershad
Lecture 20: OOO, Memory Hierarchy
CSE 451: Operating Systems Secondary Storage
Computer System Design Lecture 9
File-System Structure
Lecture 22: Cache Hierarchies, Memory
What is the maximum capacity for DDR3/DDR4 RAM?
Lecture 21: Memory Hierarchy
CHAPTER 16 Disk Storage, Basic File Structures, Hashing, and Modern Storage Architectures.
Secondary Storage Management Hank Levy
CSE 451: Operating Systems Autumn 2004 Secondary Storage
CSE 451: Operating Systems Winter 2004 Module 13 Secondary Storage
Updating Databases With Open SQL
CHAPTER 10 Memory and Storage
Lecture 18: DMBS Overview and Data Storage
Lecture 13: Cache Basics Topics: terminology, cache organization (Sections )
Memory Principles.
Updating Databases With Open SQL
Introduction to Operating Systems
Presentation transcript:

Effects of Storage Trends on Databases May 27, 2016

The Humble Disk Drive IBM introduced the disk drive in 1956.

The Humble Disk Drive A relatively simple landscape for 50+ years.

Media Landscape 1956-2006 DRAM Capacity DISK $$$ TAPE Performance FC SCSI SATA TAPE Performance Access Latency

Media Landscape Today FLASH Capacity

The Memory Hierarchy Application Oracle SAP HANA Updates (read/write/lseek) Kernel (POSIX) Buffer Cache VFS NFS blocks

The Memory Hierarchy We’re slaves to the Application Persistence layer Oracle SAP HANA Updates (read/write/lseek) Kernel (POSIX) Buffer Cache VFS NFS blocks

The Memory Hierarchy Application std::map (log2N, log2N) std:list (constant, N) boost::XXX bytes Control path (mmap, truncate) Kernel (POSIX) Buffer Cache VFS NFS

(Naïve) History of Databases Horizontal Decomposition (tables) Record oriented SEQUEL (SQL) Oracle MonetDB 1956 1974 1979 1999 2006

Asymptotic Opportunity End of the artificial dichotomy of OLAP/OLTP Many “in-memory” databases have missed the opportunity Performance improvement restricted to inherent medium speedup (DRAM) New data structures with random access possible! Tables (B+ tree derivative) or columns are artifacts of history O(N) is not always the best way. Frequently leads to O(N2)

Doug Santry dsantry@netapp.com