Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

Infrastructure Stratergy > Lecture Six - Data Centre > Flashcards

Lecture Six - Data Centre Flashcards

1
Q

Data Centre - Definition

A

A facility housing computer systems and components, including servers, storage systems, and networking equipment.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Data Centre - Purpose

A

Provides centralized data storage, processing, and dissemination services for organizations.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Data Centre - Importance

A

Essential for supporting web services, cloud computing, and large-scale computational tasks.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Data Centre - Historical Context

A

Data centres have evolved from simple server rooms to complex facilities.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Data Centre - Key drivers

A

Demand for large-scale computing services.
Applications in web search, online social networks, and scientific computations.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Data Centre - Challenges

A

Increasing resource requirements.
Bottlenecks in inter-node communication bandwidth.
Majority of traffic is internal within the Data Centre Network (DCN).

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Data Centre Networking Basics - Components

A

Servers: Transition from high-end enterprise servers to low-cost, large-scale server deployments.
Networking Infrastructure: Needs to support extensive inter-server communication.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Data Centre Networking Basics - Trends

A

Shift towards commoditization using large numbers of affordable servers.
Aggregate reliability mitigates individual server vulnerability.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Data Centre Networking Basics - Networking Challenges

A

Traditional enterprise solutions are insufficient for large-scale needs.
Movement towards scalable, commodity-based networking components.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Desirable Features for Data Centre Networks

A

Support for a large number of servers (100k+ hosts).
High capacity and bandwidth between servers.
Full access to resource pools with flexible network allocation.
High utilization and reliability.
Backward compatibility and energy efficiency.
Scalability and cost-effectiveness.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

High Performance Computing (HPC)

A

Designed for applications requiring significant computational power.
Examples: Financial systems and scientific computing utilizing technologies like InfiniBand and Myrinet.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

High Performance Computing (HPC) - Advantages

A

High bandwidth and low latency.
Simple setup and low maintenance complexity.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

High Performance Computing (HPC) - Disadvantages

A

High costs due to non-commodity equipment.
Incompatibility with TCP/IP applications.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Networking Approach

A

Utilizes off-the-shelf networking equipment such as Ethernet networks.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Networking Approach - Advancements

A

Switches with more ports and higher bandwidth capabilities.
Leverages ongoing technology improvements for cost-effective solutions.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Networking Approach - Pros

A

Cost-effective and backward-compatible.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

Networking Approach - Cons

A

Challenges in building scalable and efficient Data Centre Networks (DCNs).

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

Conventional Data Centre Networks Architecture - Structure

A

Commodity servers and networking elements arranged in racks.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

Conventional Data Centre Networks Architecture - Topologies

A

Top-of-Rack (ToR): Network switches located on top of server racks.
End-of-Row (EoR): Centralized switching for entire rows of racks.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

Conventional Data Centre Networks Architecture - Architecture Levels

A

Core: High-level routing and backbone connectivity.
Aggregation: Intermediate layer connecting core and access levels.
Access/Edge: Connects directly to servers and devices.

21
Q

Data Centre Networks Issues - Challenge in Conventional Architectures

A

Resource Fragmentation: Inefficient resource allocation across the network.
Server-to-Server Bandwidth: Limited by high oversubscription ratios (few:1 to hundreds:1).
Service Isolation: Difficulties in segregating services within shared environments.
TCP Incast Problem: Network congestion due to simultaneous data requests from multiple servers.

22
Q

Fat Tree Concept - Core Idea

A

Balances uplink and downlink bandwidths, creating a non-blocking and non-interfering network

23
Q

Fat Tree Concept - Architecture

A

Hierarchical network design resembling a tree structure, expanding bandwidth as it ascends.

24
Q

Fat Tree Concept - Features

A

Equal uplink and downlink bandwidth.
Scalable and flexible design, suitable for large-scale data centers.

25
Q

Fat Tree Topology Examples

A

Structure:
Pods: Groups of interconnected switches (e.g., Pod 0, Pod 1, etc.).
Layers: Composed of edge, aggregation, and core layers.
Illustration: A fat tree with 𝑘 = 4 k=4 demonstrating scalability using k-port switches.
Advantages: Offers numerous equal-cost paths, enhancing redundancy and load balancing.

26
Q

Fat Tree Properties - Configurations

A

Utilizes k-port switches in a 3-layer structure (edge, aggregation, core).

27
Q

Fat Tree Properties - Maximum Hosts

A

Max Hosts = (k^3)/4 where k is the number of ports

28
Q

Fat Tree Properties - Example Set Up

A

48-port switches in 48 pods.
Each pod has 24 edge and 24 aggregation switches.
24 servers per edge switch, forming 1,152 subnets.

29
Q

Fat Tree Properties - Path Redundancy

A

Multiple equal-cost paths between nodes in different pods.

30
Q

Fat Tree Properties - Routing Challenges

A

OSPF (Open Shortest Path First) uses one shortest path; ECMP (Equal Cost Multi-Path) enhances scalability but poses availability issues.

31
Q

Fat Tree Addressing - Addressing Scheme

A

Hierarchical IP addressing based on the network topology.

32
Q

Fat Tree Addressing - Example

A

Format: 10.pod.switch.host
Subnet and Host Routing: Determines forwarding paths based on destination IP.

33
Q

Fat Tree Addressing - Routing Strategy

A

Two-stage lookup using prefix and suffix for efficient packet delivery.

34
Q

Fat Tree Addressing - Illustration

A

Shows routing process for packets with different destination IPs.

35
Q

Fat Tree Routing - Routing Process

A

Stage 1: Prefix Lookup for downward direction (toward hosts).
Stage 2: Suffix Lookup for upward direction (toward core network).

36
Q

Fat Tree Routing - Example Routing

A

Packet with destination 10.2.0.2 forwarded to port 0.
Packet with destination 10.3.0.3 forwarded to port 3.

37
Q

Fat Tree Routing - Benefits

A

Efficient routing using hierarchical addressing and lookup tables.

38
Q

Fat Tree - Advantages

A

Utilizes commodity network equipment.
Reduces oversubscription and resource fragmentation.
Provides load balancing capabilities across the network.

39
Q

Fat Tree - Disadvantages

A

Requires custom addressing and routing solutions.
Complexity in cabling and network setup.
Challenges with load balancing in heterogeneous environments.

40
Q

Virtual Layer-2 Network - Concept

A

Simulates a flat Layer-2 network for simplified inter-server communication.

41
Q

Virtual Layer-2 Network - Design Features

A

Server and Location Separation: Distinguishes between application addresses (AAs) and location addresses (LAs).
Traffic Spreading: Uses ECMP and Valiant load balancing to distribute traffic evenly.

42
Q

Virtual Layer-2 Network - Benefits

A

Addresses scalability and load balancing challenges in traditional Layer-2 networks.

43
Q

Portland Concept - Dual MAC Addressing

A

AMAC: Actual MAC address for device identification.
PMAC: Pseudo MAC address encoding network topology.

44
Q

Portland Concept - Fabric Manager

A

Manages address mappings and network agility.

45
Q

Portland Concept - Routing Efficiency

A

PMAC routing reduces complexity in forwarding decisions.
Topology encoding aids in quick routing resolutions.

46
Q

Portland Concept - Scalability

A

Supports large Layer-2 networks with simplified management.

47
Q

Beyond Fat Trees - Alternative Approaches

A

Server-Centric DCNs: Use servers as relay nodes to enhance network expandability and reduce network diameter (e.g., BCube, DCell).
Optical/Electronic DCNs: Leverage optical communication for energy efficiency and reduced complexity (e.g., Helios, C-Through).

48
Q

Beyond Fat Trees - Pros and Cons

A

Server-Centric: Expandability vs. increased wiring complexity.
Optical: Energy efficiency vs. high equipment costs.

Infrastructure Stratergy (9 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions