+ All Categories
Home > Documents > Alireza Angabini Advanced DB class Dr. M.Rahgozar Fall 88.

Alireza Angabini Advanced DB class Dr. M.Rahgozar Fall 88.

Date post: 31-Dec-2015
Category:
Upload: marshall-paul
View: 214 times
Download: 0 times
Share this document with a friend
Popular Tags:
25
Alireza Angabini Advanced DB class Dr. M.Rahgozar Fall 88
Transcript

Alireza Angabini

Advanced DB classDr. M.Rahgozar

Fall 88

Introduction

PNUTS Overview

Functionality

Architecture

Applications

Experimental Results

Conclusion

2A.Angabini - PNUTS

Main requirements of Web Apps

Scalability

Response Time and Geographic Scope

High Availability & Fault Tolerance

Relaxed Consistency Guarantees

3A.Angabini - PNUTS

PNUTS is

Massively parallel

Geographically distributed database system

Designed Yahoo!

Used by their web application

Shared between several applications

4A.Angabini - PNUTS

Data Model & Features

Fault Tolerance

Pub-Sub Message System

Hosting

5A.Angabini - PNUTS

Data & Query Model

Consistency Model

6A.Angabini - PNUTS

Simplified relational data model

Organizes data into tables of records with attributes

Allows arbitrary structure inside a record – “blob”

Schema are flexible

New attribute is added without halting query or update

activity

Allow to have empty attribute in the record

Query language

Supports selection and projection in single table

Updates & deletes with primary key only

7A.Angabini - PNUTS

Hide the complexity of replication

Considered between general serializability & eventual consistency

Per-record timeline consistency “All replica of given record apply all updates to the record

in the same order”

8A.Angabini - PNUTS

Support range of API calls with different

levels of consistency

Read-any

Read-critical(required_version)

Read-latest

Write

Test-and-set-write(required_version)

9A.Angabini - PNUTS

Data tables are horizontally partitioned into groups of records called tablets

10A.Angabini - PNUTS

Ordered table

Primary-key space of a table is divided into

intervals

Each interval corresponds to one tablet

The router stores interval mapping

For a given PMK, binary search is used to find

the tablet

11A.Angabini - PNUTS

Hash-organized tablen-bit hash function H(), 0 ≤ H() < 2n [0... 2n) is divided into intervals Each interval corresponds to single tabletTo map a key to a tablet,

1. Hash the key2. Search set of interval using binary search

12A.Angabini - PNUTS

The system uses asynchronous

replication

To ensure low-latency updates

Yahoo! Message Broker (YMB)

Used for replication & logging because:

1. Multiple steps are applied before committed

to DB

2. YMB is designed for wide-area replication

13A.Angabini - PNUTS

Recovery from failure (3 Steps)

1. the tablet controller requests a copy from the source tablet3. the source tablet is copied to the destination region2. “checkpoint message” is published to YMB

14A.Angabini - PNUTS

User Database

Social Applications

Content Meta-Data

Listings Management

Session Data

15A.Angabini - PNUTS

Three PNUTS regions 2 west coast, 1 east coast 5 storage units, 2 message brokers, 1 router West: Dual 2.8 GHz Xeon, 4GB RAM, 6 disk RAID 5 array East: Quad 2.13 GHz Xeon, 4GB RAM, 1 SATA disk

Workload 1200-3600 requests/second 0-50% writes 80% locality

Storage engine for hash table “Yahoo! propriety disk-based hashtable”

Storage engine for ordered tables MySQL using InnoDB

16A.Angabini - PNUTS

The coming experiments showThe impact of several factors on the

average latency for request

17A.Angabini - PNUTS

18A.Angabini - PNUTS

19A.Angabini - PNUTS

20A.Angabini - PNUTS

21A.Angabini - PNUTS

22A.Angabini - PNUTS

Rich database functionality and low

latency at massive scale.

Tradeoffs between functionality,

performance and scalability.

Choose asynchronous replication to

ensure low write latency.

Delivers the data management as

hosted service

23A.Angabini - PNUTS

B. Cooper, R. Ramakrishnan, U. Srivastava, A. Silberstein, P.

Bohannon, H. Jacobsen, N. Puz, D. Weaver, and R. Yerneni,

"PNUTS: Yahoo!'s hosted data serving platform," Proceedings of

the VLDB Endowment archive, vol. 1, 2008, p. 1277–1288.

Technical report, Raghu Ramakrishnan, Yahoo! Research and Platform Engineering Team

24A.Angabini - PNUTS

Thanks For Your AttentionThanks For Your Attention

??

25A.Angabini - PNUTS


Recommended