iSCSI Performance in Integrated LAN/SAN Environment

1
iSCSI Performance in Integrated LAN/SAN
Environment

• Li Yin
• U.C. Berkeley

2
Outline

• Motivations
• Network Congestion and Disk Congestion
  differentiation
• iSCSI ns-2 Simulator
• Conclusion
• Future work

3
Motivations

• Storage Area Network
• Hosts/Servers are connected to storage devices
  through network
• Advantages
• High availability
• Better resource sharing
• Easy to manage
• Transport SCSI over IP Networks
• Less cost
• Longer operating distance
• Leverage existing technology and management tools

4
Motivations (cont.)

• iSCSI is one of the most promising protocols to
  carry SCSI traffic over IP networks.
• SAN/LAN integration is one step towards SAN/WAN
  integration
• Utilize existing Ethernet to carry iSCSI traffic
• Problem
• iSCSI performance degrades dramatically with
  cross traffic
• Challenge
• How to sustain high I/O throughput even with
  competing traffic?

5
Why Performance Degrades?

• Resources are saturated
• Cross traffic will compete for network bandwidth,
  disk, CPU and etc.
• First step where is the congestion point?
• Our hypothesis Congestion caused by network and
  disk behave differently
• Second Step how to avoid it?

6
Test bed Setup

• Topology
• Cisco iSCSI initiator
• Target machine runs IBM iSCSI target software
  driver
• A SCSI disk is attached to the target machine as
  the target disk
• Nistnet running on the software router to control
  delay, packet drop rate and etc.

7
Experimental Setup

• iSCSI target disk is attached as raw device at
  the initiator
• To filter out file system effect
• 16384 64KB random requests (1G data in total)
• To reduce the cache effect
• Initiator response time seen by the initiator
• Tif Initiator request finish time Tir
  Initiator request receive time
• Target response time seen by the target iscsi
  driver
• Ttf Target request finish time Ttr Target
  request receive time

Read
Write
8
Case 1 Network congestion

• Use packet drops to reflect network congestion
• Nistnet introduces uniform random packet drops
• The target disk performs no other disk operations

9
Experimental Results
initiator
No drop
1 drop
5 drop
target
read
write
10
Case 2 Disk Competition

• Target machine continuously issue random I/O
  requests to the target disk
• No network interference is introduced

11
Experimental Results
initiator
No drop, No compete
4KB Competing Request
4MB Competing Requests
target
read
write
12
Result Analysis
initiator
No drop, No Compete
4KB Competing Request
1 Drop
target

• read

write
13
Congestion Caused by Network

• Target How to improve performance when the
  degradation is caused by network?
• Our methodology ns-2 based iSCSI simulator
• Simulation can help us alleviate the limitation
  of available testbed configuration
• Delay
• Bandwidth

14
Ns-2 iSCSI simulator

• iSCSI is implemented as a TCP application.
• all iSCSI messages are encapsulated as an
  application message transmitted using TCP
• Start from a simple disk models
• Parameters
• cache hit ratio
• mean, variance, minimum processing time and
  maximum processing time for various request size

15
Simulator Verification

• 16384 64KB random requests (1GB in total)

Throughput
Simulation
Testbed
Testbed
Delay
READ
WRITE
16
Impact of TCP Parameters

• Impact of minimum timeout value (minrto)
• Real RTT is roughly 1.5ms
• A more precise configuration of timeout value in
  LAN is useful, and is possible

Throughput
of Fast Retransmission
of Timeout
1s minrto
100ms minrto
10ms minrto
1ms minrto
17
Conclusions

• iSCSI performance in LAN/SAN integrated
  environment is very important
• Performance degradation caused by network and
  disk is possible to be distinguished
• Ns-2 based simulator can match the real curve
  closely
• TCP parameter configuration have big impact on
  the performance

18
Future Works

• Congestion point detection
• better monitoring point?
• more complicated cross traffic
• Simulation
• More verification on write operations
• Bursty Drop Model
• More realistic system and disk model
• More analysis on how TCP will affect the
  performance?

19
Future Work (Cont.)

• Design scheme to improve performance when
  congestion happens in network
• Can we avoid packet drop?
• Resource management?
• Shift to another target?
• Read Multiple replica may exist
• Write write to some target temporarily,
  re-organize data later
• QoS management
• Avoid iSCSI drop rate below some threshold
• If we have to, which packet to drop?
• Leverage application layer information
• Application importance
• iSCSI header packet vs. iSCSI data packet?
• Packets belong to same iSCSI data unit or
  multiple data units?