Resource containers: A new facility for resource management in server systems

1
Resource containers A new facility for resource
management in server systems

• G. Banga, P. Druschel and J. Mogul
• Rice University
• Presented by
• Bhuvan Urgaonkar

2
Motivation

• Web servers should be able to
• Provide resource guarantees
• Counter DoS attacks
• Do accurate billing
• Shortcomings in OS abstractions
  
• Process is unit of resource management
• Apps have no control over resources kernel
  consumes for them
• gt achieving above goals difficult

3
Outline

• Motivation
• Shortcomings of OS Abstractions
• Resource Containers
• Performance Evaluation
• Conclusions/Comments

4
Resource Principals and Protection Domains

• Resource Principals
• Entities for which separate resource allocation
  and accounting done
• Protection Domain
• Entities that need to be isolated from each other
• Popular Operating Systems
• Process resource principal
• Process protection domain

5
A classical application

• Process appropriate resource principal

6
A network-intensive application

• Resources consumed by kernel unaccounted
• gt process inappropriate as resource principal

7
A multi-process application

• The resource principal should be the set of all
  processes

8
Single-process MT application

• Correct resource principal smaller than a process

9
OS shortcomings summary

• OS unit of resource mgt. (process) often
  different from desired unit
• Apps cannot control resource allocation to their
  activities
• Inaccurate accounting and charging of resources
• Incorrect scheduling decisions

10
Resource container

• Contains all system resources used for an
  independent activity
• E.g. For a HTTP connection served by a web
  server
• CPU time spent on the connection
• sockets, PCBs, network buffers etc
• Mechanisms for accurate accounting
• Lazy Receiver Processing (LRP)

11
Containers and CPU scheduling

• Applications associate containers with
  independent activities
• Dynamic binding between threads and containers
• Threads consumption charged to right container

12
Containers and CPU scheduling

• Threads scheduled based on combined allocation
  and usage of all associated containers
• Apps can associate scheduling info with
  activities
• Threads within a container may be scheduled as
  the app pleases
• Resource container hierarchy

13
Other resources

• Similar accounting mechanism possible for other
  resources
• Support required to account for resources
  consumed by the kernel on behalf of applications

14
Containers in a MT server

• New container created for new connection
• Serving thread bound to this container

15
Containers in event-driven server

• New container created for new connection
• Threads binding changed as it serves different
  connections

16
More examples

• Different priorities to requests from different
  sources
• Restrict resource consumption of certain requests
• Defend against DoS attacks
• Generating accurate bills

17
Prototype implementation

• Modifications to Digital UNIX 4.0D
• CPU scheduler
• TCP/IP subsystem LRP
• Server software single-process, event-driven
• Clients used the S-Client software

18
Costs of new primitives

• Throughput of server unchanged on modified kernel

19
Prioritized handling of clients

• Number of concurrent low-priority clients

20
Controlling resource usage of CGI processing

• Number of concurrent CGI requests

21
Immunity against SYN-flooding

• SYN-Flood Rate (1000s of SYNs/sec)

22
Conclusions

• Resource container, an OS abstraction to
  explicitly identify a resource principal
• Prototype implementation in Digital UNIX
• Combined with accurate resource accounting (e.g.,
  LRP) can help web servers provide differentiated
  QoS