DS8870 R7.4 Performance Update 10-21-2014

© 2014 IBM Corporation

IBM Systems & Technology Group

IBM System Storage DS8870 Release R7.4 Performance Update

Enterprise Storage Performance


© 2014 IBM Corporation 2

Multi-thread Performance Accelerator(64 threads)

• There are two categories for the R7.4 performance enhancements; 32 thread and

64 thread.

• Common to both categories are the following code improvements: • Distribute the work to increase parallelism and limit the effect of synchronization to shared data

structures.

• Algorithms to cache updates to LRU lists in CPU caches without affecting LRU algorithm.

• Multi-threading background processes to keep with foreground I/O.

• Splitting hot locks into multiple locks to reduce lock contention.

• 64 thread further improves performance by better utilizing and distributing the

work on all available cores. • Must have 16 core machine with 512 GB memory minimum.

• No copy services are supported with 64 threads on R7.4.

• Recommended for use with High Performance Flash Enclosures

• Will not see performance improvement with ISS adapters.

• Concurrently loadable and supported on existing DS8870s.

• Enhancements allow for both overall increased system IOps performance as well

as reduced response times at higher IOps rates.



• All results are from a DS8870 Model 961 High Performance All Flash

Configuration with 16 P7+ cpu cores.

• All results are on pre-GA code and are subject to change.

R7.4 Performance



Performance Benchmarks

• OLTP Database Simulation Benchmarks • Simulates IO done by OLTP applications. Similar to SPC-1. Do a mix of random reads and writes

with cache hits and cache misses.

• DBO(Database Open): 70% read/30% write, 4KB IO’s, 50% read cache hit

• DB zOS(Database System Z): 75% read/25% write, 4KB IO’s, 72% read cache hit

• Cache Hostile: 72% read/28% write, 4KB IO’s, 40% read cache hit

• Sequential IO • Large block sequential reads or writes to the storage server’s drives. Similar to SPC-2.

• Corner benchmarks • Perform just one type of IO pattern. Most applications combine a mix of different IO patterns.

• Cache Hits: 4KB random reads or writes to the storage server’s cache.

• Cache Read Misses: 4KB random reads to the storage server’s drives.

• Writes Miss: 4KB random writes to the storage server’s drives.



Open Performance – Fullbox

8 HPFE RAID5

Sequential

0

5

10

15

20

25

Read WriteG

B/s

R7.3 R7.4 32 thread R7.4 64 thread

4KB Random

0

100

200

300

400

500

600

700

800

Read Write

KIO

/s

R7.3 R7.4 32 thread R7.4 64 thread



DBO(70/30/50) w/ 8 HPFE R7.3 vs R7.4 w/ 32 and 64 threads

0

0.2

0.4

0.6

0.8

1

1.2

1.4

1.6

1.8

2

0 100 200 300 400 500 600 700 800 900 1000

K IOps

Resp

on

se T

ime (

ms)

R7.3 R7.4 32 threads R7.4 64 threads

The DBO benchmark does 70% reads/30% writes with 50% read cache hits.



DBO(70/30/50) R7.3 vs R7.4 w/ 64 threads for 1 to 8 HPFE

0

0.2

0.4

0.6

0.8

1

1.2

1.4

1.6

1.8

2

0 100 200 300 400 500 600 700 800 900 1000

K IOps

Resp

on

se T

ime (

ms)

1 HPFE R7.3 2 HPFEs R7.3 4 HPFEs R7.3 8 HPFEs R7.3

1 HPFE R7.4 2 HPFE R7.4 4 HPFE R7.4 8 HPFE R7.4

The DBO benchmark does 70% reads/30% writes with 50% read cache hits.



CKD – DB z/OS (zHPF) w/ 8 HPFE R7.4 w/ 32 and 64 threads

0

0.2

0.4

0.6

0 100 200 300 400 500 600 700 800

K IOps

Re

sp

on

se

Tim

e (

ms

)

R7.4 32 threads R7.4 64 threads

The DB z/OS benchmark does 75% reads/25% writes with 72% read cache hits.



CKD – Cache Hostile (zHPF) w/ 8 HPFE R7.4 w/ 32 and 64 threads

0

0.2

0.4

0.6

0.8

1

1.2

1.4

1.6

0 100 200 300 400 500 600 700 800

K IOps

Re

sp

on

se

Tim

e (

ms

)

R7.4 32 threads R7.4 64 threads

The Cache Hostile benchmark does 72% reads/28% writes with 40% read cache hits.



CKD Performance w/zHPF – Fullbox

8 HPFE RAID5

4KB Random

0

100

200

300

400

500

600

700

Read

KIO

/s

R7.4 32 thread R7.4 64 thread



Multi-Target PPRC



Multi-Target PPRC

Configuration

1 PPRC primary, 2 PPRC secondary

DS8870, Primary 16-core, secondary: 8-core

8 host connections to 4 HAs on the primary

4 PPRC paths to each of the secondary, sharing 4 HAs

Primary: 8 DA pairs, mix of SSDs/10K

1st secondary: 4 DA pairs, 15K RPM drives

2nd secondary: 2 DA pairs, 1.2TB 10K RPM drives



Multi-Target PPRC: 4KB Write Hit (zHPF)



Multi-Target PPRC: 27KB Write Hit (zHPF)



Multi-Target PPRC: Sequential Write (zHPF)



Simulated Customer Workload

Online Batch

Read hit 92% 92%

Read/Write Ratio 3:1 2.4:1

% Sequential Read 0 23

Destage Rate 8.4% 16.5%

IOPS Curve 45KIOPs/80KIOPs

Avg. Xfer Size Read 27KB 50KB

Avg. Xfer Size Write 27KB 40KB

Volume 480 560



Multi-Target PPRC: Simulated Customer Workload - Online



Multi-Target PPRC: Simulated Customer Workload - Batch



New Drives



New Drives

600 GB 15K RPM 2.5” drives

1.6 TB 2.5” SSDs



The new 600GB 15K 2.5” HDDs deliver equivalent Random Read and Random

Write performance when comparing with 300GB 15K 2.5” HDDs.

Open – 600GB 15K 2.5” Drive Performance



The new 600GB 15K 2.5” HDDs deliver better sequential performance

comparing when with 300GB 15K 2.5” HDDs.




The new 600GB 15K 2.5” HDDs deliver better rebuild rate when comparing with

300GB 15K 2.5” HDDs.




The new 1.6 TB 2.5” SSDs deliver similar Random and Sequential Read/Write

performance when comparing with 800GB 2.5” SSDs.

Open – 1.6 TB 2.5” SSD Performance



Disk Magic Support



Disk Magic Support for R7.4

Support for 32 & 64 threads

Support for new 600 GB 15K RPM 2.5” HDDs & 1.6 TB 2.5” SSDs

Multi-target PPRC

Delivery

Initial Release to be delivered by Nov. 11th, including support for 32 & 64

threads & 600 GB 15K RPM 2.5” HDDs

Final Release to be delivered by Jan 9th, will add Multi-target PPRC and

1.6TB 2.5” SSDs



IBM Corporation 1994-2011 All rights reserved. References in this document to IBM products or services do not imply that IBM intends to make them available in every country. Trademarks of International Business Machines Corporation in the United States, other countries, or both can be found on the World Wide Web at http://www.ibm.com/legal/copytrade.shtml.

Intel, Intel logo, Intel Inside, Intel Inside logo, Intel Centrino, Intel Centrino logo, Celeron, Intel Xeon, Intel SpeedStep, Itanium, and Pentium are trademarks or registered trademarks of Intel Corporation or its subsidiaries in the United States and other countries. Linux is a registered trademark of Linus Torvalds in the United States, other countries, or both. Microsoft, Windows, Windows NT, and the Windows logo are trademarks of Microsoft Corporation in the United States, other countries, or both. UNIX is a registered trademark of The Open Group in the United States and other countries. Java and all Java-based trademarks are trademarks of Sun Microsystems, Inc. in the United States, other countries, or both. Other company, product, or service names may be trademarks or service marks of others. Information is provided "AS IS" without warranty of any kind. The customer examples described are presented as illustrations of how those customers have used IBM products and the results they may have achieved. Actual environmental costs and performance characteristics may vary by customer. Information concerning non-IBM products was obtained from a supplier of these products, published announcement material, or other publicly available sources and does not constitute an endorsement of such products by IBM. Sources for non-IBM list prices and performance numbers are taken from publicly available information, including vendor announcements and vendor worldwide homepages. IBM has not tested these products and cannot confirm the accuracy of performance, capability, or any other claims related to non-IBM products. Questions on the capability of non-IBM products should be addressed to the supplier of those products. All statements regarding IBM future direction and intent are subject to change or withdrawal without notice, and represent goals and objectives only. Some information addresses anticipated future capabilities. Such information is not intended as a definitive statement of a commitment to specific levels of performance, function or delivery schedules with respect to any future products. Such commitments are only made in IBM product announcements. The information is presented here to communicate IBM's current investment and development activities as a good faith effort to help with our customers' future planning. Performance is based on measurements and projections using standard IBM benchmarks in a controlled environment. The actual throughput or performance that any user will experience will vary depending upon considerations such as the amount of multiprogramming in the user's job stream, the I/O configuration, the storage configuration, and the workload processed. Therefore, no assurance can be given that an individual user will achieve throughput or performance improvements equivalent to the ratios stated here. Photographs shown may be engineering prototypes. Changes may be incorporated in production models.

Trademarks and Disclaimers

http://www.ibm.com/legal/copytrade.shtml



Thank You

DS8870 R7.4 Performance Update 10-21-2014

Documents

Transcript of DS8870 R7.4 Performance Update 10-21-2014