Download job-talk0

An Integrated Approach to
Improving Web Performance
Lili Qiu
Cornell University
1
Outline


Motivation & Open Issues
Solutions




Study the workload of a busy Web server
Optimize TCP performance for Web transfers
Provision the content distribution networks
Summary & Other Work
2
Motivation

Web is the most dominant traffic in the
Internet today


Accounts for over 70% wide-area traffic
Web performance is often unsatisfactory


WWW – World Wide Wait
Consequence: losing potential customers!
Network
congestion
Overloaded
Web server
3
Challenges in Providing Highly
Efficient Web Services

Protocol
Inefficiency
Workload characterization


Workload
Characterization
Protocol inefficiency


Infrastructure
Provisioning
The workload of busy Web
sites is not well understood
Mismatch between Web
transfers and TCP protocol
Infrastructure provisioning


Current trend: Content
Distribution Networks
Problem: Where to place
replicas?
4
Our Solutions

Web Workload Characterization


Improve protocol efficiency


Study the workload of a busy Web server
Optimize TCP startup performance for Web
transfers
Provision Web replication infrastructure

Develop placement algorithms for content
distribution networks (CDNs)
5
Part I Web Workload Characterization

The Content and Access Dynamics of a Busy Web
Site: Findings and Implications. Proceedings of
ACM SIGCOMM 2000, Stockholm, Sweden,
August 2000. (Joint work with V. N. Padmanabhan)
6
Motivation


Solid understanding of Web workload is critical
for designing robust and scalable systems
Missing piece in previous work: workload of busy
Web servers
replica
proxy
Internet
proxy
Clients
replica
proxy
Servers
7
Overview

MSNBC server site






Server logs




a large news site
consistently ranked among the busiest sites in the Web
server cluster with 40 nodes
25 million accesses a day (HTML content alone)
Period studied: Aug. – Oct. 99 & Dec. 17, 98 flash crowd
HTTP access logs
Content Replication System (CRS) logs
HTML content logs
Data analysis


Content dynamics
Access dynamics
8
Temporal Stability of
File Popularity

Methodology

17DEC98 - 18OCT99
01AUG99 - 18OCT99
17OCT99 - 18OCT99
Extent of overlap
1

0.8

0.6

0.4
Results

0.2
0

1
10
100
1000
# popular documents picked
10000
Consider the traces from a
pair of days
Pick the top n popular
documents from each day
Compute the overlap
100000

One day apart:significant
overlap (80%)
Two months apart: smaller
overlap (20-80%)
Ten months apart: very
small overlap (mostly below
20%)
The set of popular documents remains stable for days
9
Spatial Locality in
Client Accesses
Dec. 17, 1998
1.2
1
Fraction of requests shared
Fraction of requests shared
Normal Day
0.8
0.6
0.4
0.2
0
1
0.8
Trace
0.6
Random
0.4
0.2
0
0
10000
20000
30000
Domain ID
40000
50000
0
5000
10000 15000 20000 25000 30000 35000
Domain ID
Domain membership is significant
except when there is a “hot” event of global interest
10
Spatial Distribution of
Client Accesses

Cluster clients using
network aware clustering
[KW00]


IP addresses with the
same address prefix
belongs to a cluster
Top 10, 100, 1000, 3000
clusters account for
about 24%, 45%, 78%,
and 94% of the requests
respectively
A small number of client clusters
contribute most of the requests.
11
The Applicability of Zipf-law
to Web requests
MSNBC
Proxies
Less popular servers
2
1.5

1
0.5
0

The Web requests follow Zipf-like distribution


Request frequency  1/i, where i is a document’s ranking
The value of  is much larger in MSNBC traces




1.4 – 1.8 in MSNBC traces
smaller or close to 1 in the proxy traces
close to 1 in the small departmental server logs [ABC+96]
Highest when there is a hot event
12
Impact of larger 
Percentage of Requests

1.2
1
0.8
0.6
0.4
0.2
0
0
0.5
1
1.5
Percentage of Documents (sorted by popularity)
12/17/98 Server Traces
10/06/99 Proxy Traces
08/01/99 Server Traces
Accesses in MSNBC traces
are much more concentrated
90% of the accesses are
accounted by

Top 2-4% files in MSNBC
traces

Top 36% files in proxy
traces (Microsoft proxies
and the proxies studied in
[BCF+99])

Top 10% files in small
departmental server logs
reported in [AW96]
Popular news sites like MSNBC see much more concentrated
accesses  Reverse caching and replication can be very effective!
13
Part II Transport Layer
Optimization for the Web

Speeding Up Short Data Transfers: Theory,
Architectural Support, and Simulation Results.
Proceedings of NOSSDAV 2000 (Joint work with
Yin Zhang and Srinivasan Keshav)
14
Motivation

Characteristics of Web data transfers



Short & bursty [Mah97]
Use TCP
Problem: Short data transfers interact
poorly with TCP !
15
TCP/Reno Basics

Slow Start



Congestion Avoidance


Exponential growth in
congestion window,
Slow: log(n) round trips
for n segments
Linear probing of BW
Fast Retransmission

Triggered by 3
Duplicated ACK’s
16
Related Work

P-HTTP [PM94]


T/TCP [Bra94]




Cache connection count, RTT
TCP Control Block Interdependence [Tou97]:


Reuses a single TCP connection for multiple Web
transfers, but still pays slow start penalty
Cache cwnd, but large bursts cause losses
Rate Based Pacing [VH97]
4K Initial Window [AFP98]
Fast Start [PK98, Pad98]

Need router support to ensure TCP friendliness
17
Our Approach


Directly enter Congestion Avoidance
Choose optimal initial congestion window

A Geometry Problem: Fitting a block to the
service rate curve to minimize completion time
18
Optimal Initial cwnd

Minimize completion time by having the
transfer end at an epoch boundary.
19
Shift Optimization

Minimize initial cwnd while keeping the
same integer number of RTTs
Before optimization:
cwnd = 9
After optimization:
cwnd = 5
20
Effect of Shift
Optimization
21
TCP/SPAND

Estimate network state by sharing performance
information

SPAND: Shared PAssive Network Discovery
[SSK97]
Internet
Web Servers


Performance
gateway
Directly enter Congestion Avoidance, starting with
the optimal initial cwnd
Avoid large bursts by pacing
22
Implementation Issues

Scope for sharing and aggregation



Collecting performance information


Sliding window average
Retrieving estimation of network state


Performance reports, New TCP option, Windmill’s
approach, …
Information aggregation


24-bit heuristic
network-aware clustering [KW00]
Explicit query, active push, …
Pacing

Leaky-bucket based pacing
23
Opportunity for Sharing

MSNBC: 90% requests arrive within 5 minutes
since the most recent request from the same
client network (using 24-bit heuristic)
24
Cost for Sharing

MSNBC: 15,000-25,000 different client networks
in a 5-minute interval during peak hours (using 24bit heuristic)
25
Simulation Results

Methodology


Performance Metric


Download files in rounds
Average completion time
TCP flavors considered




reno-ssr: Reno with slow start restart
reno-nssr: Reno w/o slow start restart
newreno-ssr: NewReno with slow start restart
newreno-nssr: NewReno w/o slow start restart
26
Simulation Topologies
27
T1 Terrestrial WAN Link with
Single Bottleneck
28
T1 Terrestrial WAN Link with
Multiple Bottlenecks
29
TCP Friendliness
30
Summary

TCP/SPAND significantly reduces latency
for short data transfers





35-65% compared to reno-ssr / newreno-ssr
20-50% compared to reno-nssr / newreno-nssr
Even higher for fatter pipes
TCP/SPAND is TCP-friendly
TCP/SPAND is incrementally deployable


Server-side modification only
No modification at client-side
31
Part III Provision Content
Distribution Networks (CDNs)

On the Placement of Web Server Replicas. To
appear in INFOCOM'2001. (Joint work with V. N.
Padmanabhan and G. M. Voelker)
32
Introduction to CDNs

server
server
CDN server

server
server
Content providers want to
offer better service to their
clients at lower cost
Increasing deployment of
content distribution networks
(CDNs)

Clients
Content
Providers


Akamai, Digital Island, Exodus …
Idea: a network of servers
Features:
 Outsourcing infrastructure
 Improve performance by
moving content closer to end
users
 Flash crowd protection
33
Placement of CDN servers

server
Goal

server
CDN server

server
server
minimize users’ latency or
bandwidth usage
Minimum K-median problem

Select K centers to minimize
the sum of assignment costs

Clients
Content
Providers

Cost can be latency or
bandwidth or other metric we
want to optimize
NP-hard problem
34
Placement Algorithms

Tree based algorithm [LGG+99]



Random


Assume the underlying topologies are trees, and
model it as a dynamic programming problem
O(N3M2) for choosing M replicas among N potential
places
Pick the best among several random assignments
Hot spot

Place replicas near the clients that generate the
largest load
35
Placement Algorithms (Cont.)

Greedy algorithm
Greedy(N,M) {
for I = 1 .. M {
for each remaining replica R {
cost[R] = cost after placing an
additional replica at R
}
select the replica with the lowest cost
}
}

Super Optimal algorithm

Lagrangian relaxation + subgradient method
36
Simulation Methodology

Network topology

Randomly generated topologies


Real Internet network topology


AS level topology obtained using BGP routing data
from a set of seven geographically dispersed BGP
peers
Web Workload

Real server traces


Using GT-ITM Internet topology generator
MSNBC, ClarkNet, NASA Kennedy Space Center
Performance Metric

Relative performance: costpractical/costsuper-optimal
37
Simulation Results in
Random Graph Topologies
38
Simulation Results in
Real Internet Topologies
39
Effects of Imperfect Knowledge
about Input Data

Predict load using moving window average
(a) Perfect knowledge
about topology
(b) Knowledge about Topology
with a factor of 2 accurate
40
Summary



First experimental study on placement of CDNs
Knowledge about client workload and topology is
crucial for provisioning CDNs
The greedy algorithm performs the best


The greedy algorithm is insensitive to noise


Stay within a factor of 2 of the super-optimal when the
salted error is a factor of 4
The hot spot algorithm performs nearly as well


Within a factor of 1.1 – 1.5 of super-optimal
Within a factor of 1.6 – 2 of super-optimal
How to obtain inputs


Moving window average for load prediction
Using BGP router data to obtain topology information
41
Contributions

Protocol
Efficiency
Workload characterization


Protocol efficiency

Workload
Characterization
Infrastructure
Provisioning

Study the workload of
MSNBC web site
Optimize TCP startup
performance for Web
transfers
Infrastructure provisioning

Develop placement
algorithms for Content
Distribution Networks
42
Other Work




Available at
http://www.cs.cornell.edu/lqiu/papers/papers.html
Fast Firewall Implementations for Software and
Hardware-based Routers. Submitted to ACM
SIGMETRICS’2001.
Integrating Packet FEC into Adaptive Voice
Playout Buffer Algorithms on the Internet.
Proceedings of IEEE INFOCOM'2000, Tel-Aviv,
Israel, March 2000.
On Individual and Aggregate TCP Performance.
7th International Conference on Network
Protocols (ICNP'99), Toronto, Canada, October
1999.
43