Hitachi VSP is a new paradigm in enterprise array performance. In this session we will discuss how the architecture of VSP enhances its box-wide performance. The results of performance testing with synthetic host I/O generators and the PAI/O driver will also be presented.

1. WHY HITACHI VIRTUAL
STORAGE PLATFORM DOES
SO WELL IN A MAINFRAME
ENVIRONMENT
HOW FAST CAN A VSP GO?
RON HAWKINS, MANAGER,
TECH OPS PERFORMANCE
NOV. 2, 2011

2. WEBTECH EDUCATIONAL SERIES
Why Hitachi Virtual Storage Platform (VSP) Does So Well in a Mainframe
Environment
Hitachi VSP is a new paradigm in enterprise array performance. In this session
we will discuss how the architecture of VSP enhances its box-wide performance.
The results of performance testing with synthetic host I/O generators and the
PAI/O driver will also be presented.
Attend this WebTech to learn how to:
 Improve performance in your environment with VSP
 Affect performance in mainframe environments with different RAID
architectures
 Optimize functionality with wide striping enabled by Hitachi Dynamic
Provisioning

3. UPCOMING WEBTECHS
 November and December
‒ Increase Your IT Agility and Cost-efficiency with HDS Cloud
Solutions, Nov. 9, 9 a.m. PT, 12 p.m. ET
‒ Best Practices for Upgrading to Hitachi Device Manager
v7, Nov. 16, 9 a.m. PT, 12 p.m. ET
‒ Hitachi Clinical Repository, Dec. 7, 9 a.m. PT, 12 p.m. ET
 Please check www.hds.com/webtech for
‒ Link to the recording, presentation and Q&A (available next
week)
‒ Schedule and registration for upcoming WebTech sessions

4. WE ARE TOP GUN
WHAT WE WILL COVER
 Unified microprocessor
 FICON front-end director
 The numbers
 Hitachi Dynamic
Provisioning for
Mainframe
Hitachi Virtual
Storage Platform

5. UNIFIED
MICROPROCESSOR
THE HEART OF THINGS

6. ANOTHER VIEW OF THE
HITACHI VIRTUAL STORAGE PLATFORM

7. MICROPROCESSORS HAVE MOVED OFF
THE FRONT-END AND BACK-END DIRECTORS

8. HITACHI UNIVERSAL STORAGE PLATFORM® V
ESTRANGED MICROPROCESSOR
Shared Memory

9. HITACHI UNIVERSAL STORAGE PLATFORM® V
ESTRANGED MICROPROCESSOR
Shared Memory

10. HITACHI UNIVERSAL STORAGE PLATFORM® V
ESTRANGED MICROPROCESSOR
Shared Memory

11. UNIFIED MICROPROCESSOR
4GB Local
XEON Quad RAM
Core CPU Cache
Package
Memory
Write Through Shared
Memory
Page In

12. FICON FRONT-END
DIRECTOR
AT THE EDGE

13. FICON FRONT-END DIRECTOR
FICON 16-PORT FEATURE
 Hitachi transport processor
‒ Initial FICON protocol
‒ Open exchanges
 MHUB + ASIC
‒ Data accelerator circuit
‒ A programmable
application-specific
integrated circuit
‒ Route command to virtual
storage director (VSD)
‒ Direct memory access
(DMA) engine

14. HITACHI VIRTUAL STORAGE PLATFORM
8-PORT FICON BOARD
HITACHI TRANSPORT PROCESSOR
 Accepts initial channel
command request from
host
 Multi-protocol
‒ FICON and high-
performance FICON
(zHPF)
 Establishes open This graphic is getting
hard to read in the red.
exchanges (480) Can the type be
reversed? -th
‒ Shared on demand by
Not Really as it is a
adjacent ports graphic lifted from
another source, we
don’ t have the original
graphic.

15. OPEN EXCHANGES
HITACHI TRANSPORT PROCESSOR
 64 for each host channel
‒ 2:1 fan-in is 128
‒ Adjacent ports 256 CMR
Time
‒ 4:1 fan-in is 256
‒ Adjacent ports 512
 Open Exchange (OE)
exhaustion increases
Command Response (CMR)
time
‒ Microprocessor busy (>80%)
‒ Low cache hits
‒ TCz synchronous

16. HITACHI VIRTUAL STORAGE PLATFORM
8-PORT FICON BOARD
MHUB + ASIC
 Two chips working
together
‒ Processor plus
programmable ASIC
‒ Commands to/from virtual
storage director
‒ Using LDEV mapping
tables
 DMA engine
‒ Read and write directly to
cache

17. THE NUMBERS
WE ARE TOP GUN

18. WE ARE TOP GUN
HITACHI UNIVERSAL STORAGE PLATFORM® V DUAL-CHASSIS CONFIGURATION
 All tests are a fully popped VSP (unless stated otherwise)
‒ 2 chassis
‒ 8 virtual storage directors
‒ 4 back-end directors
‒ 16 front-end directors (128 channels)
‒ 2048 HDD (10K 300GB)
‒ 512GB cache

19. WE ARE TOP GUN
HITACHI UNIVERSAL STORAGE PLATFORM® V AS AN I/O DRIVER
FNP Driver Results
1200000
1000000
800000
600000
400000 FNP Driver Results
200000
0
Zero Zero Front End Front End
Locality Locality Write Read
Write Read

20. PAI/O TESTING
THE LAB TO THE REAL WORLD
 Extended format VSAM
‒ 4KB and 26KB
 High overhead
‒ Two CCW per block
 Growing format for DB2
 Datasets >4GB
 What customers will really
get

21. WE ARE TOP GUN
CONSTRAINED BY CPU CAPACITY

22. WE ARE TOP GUN
BENEFIT OF ZHPF

23. WE ARE TOP GUN
CONSTRAINED BY VSD 80-85% BUSY

24. WE ARE TOP GUN
BENEFIT OF ZHPF

25. WE ARE TOP GUN
RANDOM WRITE MISS HIT 70% WP

26. WE ARE TOP GUN
CONSTRAINED BY VSD 80% BUSY

27. WE ARE TOP GUN
CONSTRAINED BY VSD 80% BUSY

28. WE ARE TOP GUN
HIGH-PERFORMANCE BED FEATURE
PAI/O H4
4K Read
100% Cache Miss
20
18
16
Response Time MS
14
12
10
8
6
4
2
0
0 20,000 40,000 60,000 80,000 100,000 120,000 140,000 160,000
IO Operations per Second
High Performance (2 BED) Standard Performance (1 BED)

29. WE ARE TOP GUN
HIGH-PERFORMANCE BED FEATURE
PAI/O G0 - Sequential Read
27K Chain Length 30 (1 Cyl)
100
90
80
Response Time MS
70
60
50
40
30
20
10
0
0 1,000 2,000 3,000 4,000 5,000 6,000 7,000 8,000
MB per second
High Performance (2 Bed) Standard Performance (1 BED)

30. HITACHI DYNAMIC
PROVISIONING
FOR MAINFRAME
SPREAD THE LOAD

31. HITACHI DYNAMIC PROVISIONING
FOR MAINFRAME (HDPM)
HDPM SPREADS THE LOAD
 Primary advantages of HDPM
‒ Wide striping eliminates skewed I/O to disk
‒ Greater throughput for cache miss I/O
‒ Configuration flexibility
‒ Custom volume sizes made easy
‒ Dynamic volume expansion
‒ IBM® FlashCopy® space-efficient pools
 Performance results focus on skewed I/O

32. PAI/O DRIVER – F1 (SYMMETRICAL)
PAI/O Driver - F1
4K Cache Hit Write Chain(1)
0.20
0.18
0.16
0.14
Response Time in MS
0.12
0.10
0.08
0.06
0.04
0.02
0.00
0 20,000 40,000 60,000 80,000 100,000 120,000 140,000 160,000 180,000
RD662NN RD662HF RD662HN Second
IO Per RD571NN RD571HF RD571HN
HDS Confidential

33. SKEW OR ASYMMETRICAL WORKLOAD
PAI/O DRIVER C* SERIES
Figure taken from PAI/O Driver User Guide
HDS Confidential

34. RAID 6 6D+2P PAI/O DRIVER – C6 (SKEWED OR ASYMMETRICAL)
LET HITACHI DYNAMIC PROVISIONING FOR MAINFRAME (HDPM)
SHARE THE LOAD
PAI/O Driver - C6
4K Skewed Series Chain(1)
70% Read / 30% Write
3.50
3.00
2.50
Response Time in MS
2.00
1.50
HDPM
Benefit Zone
1.00
0.50
0.00
0 2,000 4,000 6,000 8,000 10,000 12,000 14,000
I/O Per Second
RD662NN RD662HF RD662HN
HDS Confidential

35. FINAL THOUGHT
“I feel the need–the need for speed!”
―Top Gun

36. QUESTIONS AND
DISCUSSION

37. UPCOMING WEBTECHS
 November and December
‒ Increase Your IT Agility and Cost-efficiency with HDS Cloud
Solutions, Nov. 9, 9 a.m. PT, 12 p.m. ET
‒ Best Practices for Upgrading to Hitachi Device Manager
v7, Nov. 16, 9 a.m. PT, 12 p.m. ET
‒ Hitachi Clinical Repository, Dec. 7, 9 a.m. PT, 12 p.m. ET
 Please check www.hds.com/webtech for
‒ Link to the recording, presentation and Q&A (available next
week)
‒ Schedule and registration for upcoming WebTech sessions

38. THANK YOU