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. Software Router TargetInitiators

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 T if : Initiator request finish time; T ir : Initiator request receive time Target: response time seen by the target iscsi driver T tf : Target request finish time; T tr : Target request receive time Read Write RiRi RiRi RtRt RtRt

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 target readwrite No drop 1% drop 5% drop

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 target readwrite No drop, No compete 4KB Competing Request 4MB Competing Requests

12. Result Analysis readwrite initiator target No drop, No Compete 4KB Competing Request 1% Drop

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) READWRITE Throughput Delay Simulation Testbed

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 1s minrto100ms minrto10ms minrto1ms minrto Throughput# of Fast Retransmission# of Timeout

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?