HP ProLiant DL585 server Lotus NotesBench audit report

Camille Davis

Informations

• Publié par: Urke
• Nombre de lectures: 34
• Langue: Slovak

Extrait

 

 

 

HP ProLiant DL585 server Lotus NotesBench audit report

  Abstract The HP ProLiant DL585 server is designed for enterprise customers with growing data centers who require a rack optimized 4-processor server that delivers maximum performance and high availability for highly complex, business-critical applications such as Lotus Domino. Built around the AMD Opteron 800 series processors and the AMD Opteron 8000 chipset, the ProLiant DL585 is 4-way x86 rack server that delivers 32-bit performance as well as enabling 64-bit capabilities so that customers are able to deploy a common 4-way platform for their 32-bit and future 64-bit computing requirements. The R6Mail workload was run to simulate26,000 R6Mail usersagainst a Lotus Domino 6.5.1 Server. The test ran 7.5 hours during which time the system under test achieved 38,623 NotesMark(transactions per minute or tpm) with anaverage response time of 0.097 seconds. Based on these results, the price/performance ratio is$3.24/User(or $2.18/NotesMark).

Table of Contents

Abstract..............................................................................................................................................1  Table of Contents................................................................................................................................. 2   Section 1  Executive summary.............................................................................................................. 3   Test sponsor .................................................................................................................................... 3   Test methodologies........................................................................................................................... 3   Conclusions.....................................................................................................................................3   Section 2  Benchmark Objectives ......................................................................................................... 4   Section 3  Test Methodologies ............................................................................................................. 5   Test configuration............................................................................................................................. 5   Test procedure.................................................................................................................................5   Section 4  R6Mail Data ...................................................................................................................... 7   Lotus NotesMark values for benchmarked configurations ...................................................................... 7   R6Mail users per server .................................................................................................................... 9   CPU performance as recorded by Windows Performance Monitor ....................................................... 10   Section 5  Analysis........................................................................................................................... 11   Price/performance ratios: ............................................................................................................... 11   NotesNum output:.......................................................................................................................... 11   Section 6  Conclusions ..................................................................................................................... 12   Section 7 Statement by Auditor .......................................................................................................... 13   Appendix A  Overall test setup and software versions .......................................................................... 14     Test setup ...................................................................................................................................... 14   Appendix B  System configuration...................................................................................................... 16   SUT (system under test) ................................................................................................................... 16   Clients .......................................................................................................................................... 16   Network equipment ........................................................................................................................ 16   HP ProCurve 5300xl Series Switch................................................................................................... 16   Software versions ........................................................................................................................... 16   Appendix C  Operating system parameter values ................................................................................ 17   Appendix D  Lotus Notes parameters.................................................................................................. 18   R6Mail workload test...................................................................................................................... 18   System under test Notes.ini .......................................................................................................... 18   The sample client Notes.ini .......................................................................................................... 23   Appendix E  Network configuration files ............................................................................................. 27   Network configuration .................................................................................................................... 28   Appendix F  Guidelines for information usage ..................................................................................... 29   Appendix G  System pricing.............................................................................................................. 30   Appendix H  Vendor statement .......................................................................................................... 31 Appendix I - Show Stat Output from Audit Run    as separate file) (attached        

 

NotesBench test results

Section 1  Executive summary

Test sponsor This Lotus NotesBench testing was sponsored by Hewlett-Packard Company (HP). The NotesBench benchmark was developed and engineered by Lotus Development Corporation. Testing took place at the HP Microsoft Solutions  Lotus Engineering laboratories in Nashua, New Hampshire in June, 2004 and was audited by KMDS Technical Associates, Inc., in June, 2004.

Test methodologies An HP ProLiant DL585 server was configured to run a single test, NotesBench R6Mail. The NotesBench R6Mail workload is designed to replicate an average group of users performing everyday mail tasks. The test measured the performance of 26,000 users participating in Notes R6Mail related activities simultaneously connected to four instances of Lotus Domino R6.5.1 Server, on a single HP ProLiant DL585 server. The test was set up using two groups of hardware: the driving systems, and the system under test (SUT). The SUT was configured with four AMD 2.2 GHz Opteron CPUs, 8 gigabytes of RAM, and four 36.4GB SCSI hard disks. The new HP ProLiant DL585 platform delivers 32- bit performance as well as 64-bit capabilities, enabling customers to deploy a common 4- way platform for their 32-bit and future 64-bit computing requirements. Using three HP Smart Array 6402 disk controllers, the ProLiant DL585 server was connected to six HP StorageWorks storage enclosures subsystems. Each storage enclosure was configured with thirteen 36.4GB Pluggable Ultra320 SCSI hard drives. The detailed hardware configuration and test procedure are provided in Section 3 of this report.

Conclusions The R6Mail workload was run to simulate26,000 R6Mail usersagainst a Lotus Domino 6.5.1 Server. The test ran seven and a half hours during which time the system under test achieved38,623 NotesMark(transactions per minute or tpm) with anaverage response time of 0.097 seconds. Based on these results, the price/performance ratio is$3.24/User (or $2.18/NotesMark).

3 

Section 2  Benchmark Objectives

A question that most HP customers ask about Lotus Notes is: What is the maximum number of active Domino user sessions for our environment? The answer is determined by three criteria: •   The application profiling (what type of workload) •   The hardware configuration (for example, the number of system CPUs or the amount of memory) •   The operating system (OS)

The information provided in this report should help customers in their planning processes. With the publication of this and future full disclosure reports, HP and Lotus are working together to provide information that will help Notes users in their activities associated with performance tuning, enterprise network design, and many other areas. This report includes one workload: R6Mail on Domino 6.5.1 All tests were performed on the Microsoft® Windows® Server 2003 platform; similar performance information for other hardware configurations is forthcoming.

4 

Section 3  Test Methodologies

Test configuration The HP Performance Test Lab for Lotus Domino uses HP ProLiant BL10e systems, configured with Lotus Notes R6 client with NotesBench. Each ProLiant BL10e server has an 800 MHz processor, 40GB hard disk, and 1024 MBs of RAM. For the testing of R6Mail, twenty ProLiant BL10e systems were used to create load. Additionally, an HP ProLiant DL360 system was deployed to act as the Parent system. All systems were connected over an isolated TCP/IP LAN using100BaseT or 1000BaseT medium. All drivers were loaded with Microsoft Windows 2000 Server with Service Pack 3; the system under test was loaded with Microsoft Windows Server 2003. All Windows Server 2003 parameters were constant for the remaining benchmark sequences. Any Lotus Domino Server specific parameter changes are displayed in bold type in Appendix Ds NOTES.INI files.

Test procedure For this workload, HP Engineers first performed several trial runs to determine the best test duration and confirmation of steady state. Both test duration and steady state were determined using real time monitor utilities from Microsoft. During the trial runs, HP engineers observed the Windows Performance Monitor to determine the maximum number of users supported by the configuration. For this audit report, the decision was made to test only a single workload. Storage was provided using three HP Smart Array 6402 disk controllers connected to six HP StorageWorks storage enclosures systems, or two storage enclosures per Smart Array controller. Each storage enclosure was configured with thirteen 36.4GB Pluggable Ultra320 SCSI hard drives. All three Smart Array controllers were configured identically, providing three (3) logical disk units to the operating system. The first logical unit was comprised of eighteen 36.4GB disks in a RAID0+1 configuration. The second logical unit was comprised of six 36.4GB disks in a RAID0+1 configuration, and the final logical unit was comprised of the two 36.4GB disks in a RAID0+1 set. The Windows disk manager was used to create a three disk stripe set of the second logical units of all three controllers, resulting in four logical disks with a 327GB capacity each for the data directories of the Domino servers, and three 36.4GB logical disks for usage by the Windows pagefile. Having set up the storage system, four Domino partitions were then created and registered in the same Domino domain. Each of the partitions was then assigned to listen on a unique TCP/IP address on one of the two embedded NC7782 PCI-X Gigabit Network Interface controllers. Each of the four partitions had an identical Domino directory that contained more then 52,000 registered users, and each Domino Server was configured to have four mail.box files. Testing began with the clients being added incrementally to the Domino environment using a Childstagger value setting at 15 minutes for the first 15 drivers, 30 minutes for the remaining 5 drivers, as specified in the parent Notes.ini. The Client systems used a Threadstagger of .6 seconds for the first 15 drivers, and .9 seconds for the remaining 5 drivers, as specified in each client Notes.ini. All drivers created 1300 R6Mail users each. Each Domino server had its own copy of that directory, and mail was routed between all four partitions for delivery.

5 

The test ran for seven and a half hours after all client threads were connected to the system under test; over 90% of the mail generated during the run was delivered during the run. Steady state was determined to be achieved during each test run by monitoring server output, as well as mail routing, calendar and scheduling activities. The test data collected includes the following files for each partition:

•   The SUT Notes.INI file and Log.nsf file

•   All clients Notes.INI file

•   The NotesNum utility results file

•   Stat Tables for each partition after run completion

6 

Section 4  R6Mail Data Lotus NotesMark values for benchmarked configurations

  Figure 1.NotesMark for R6Mail Workload

 

45,000 40,000 35,000 30,000 25,000 20,000 15,000 10,000 5,000 0

R 6Mail Work load

38,623

P roL ian t DL 585 - 4 x 2.2 GHz

  •   NotesMark  transactions per minute or tpm

7 

  Figure 2.Response Time for R6Mail Workload

 

 

 

 

1 0.9 0.8 0.7 0.6 0.5 0.4 0.3 0.2 0.1 0

R 6Mail Work lo ad

0.097

P ro L ian t DL 585 - 4 X 2.2 GHz

8 

R6Mail users per server

  Figure 3.R6Mail Users

 

 

30,000

25,000

20,000

15,000

10,000

5,000

0

R 6Mail Work load

26,000

P roL ian t DL 585 - 4 X 2.2 GHz

9 

CPU performance as recorded by Windows Performance Monitor

  Figure 4.CPU performance Windows Performance Monitor

 

 

10 

Section 5  Analysis By conducting this performance benchmark, HP has demonstrated its leadership in Windows-based messaging solutions using Lotus Domino. Price/performance ratios:  

R6Mail 26,000 Users Price/Performance for System Workload Capacity:  38,623 Price/Performance for System NotesMark Throughput: (tpm)

$3.24/User $2.18/NotesMark 

  NotesNum output:   •   The 26,000 R6Mail Users Test Report  Reading results file - c:\results\results1\res1 ... Reading results file - c:\results\results1\res2 ... Reading results file - c:\results\results1\res3 ... Reading results file - c:\results\results1\res4 ... Reading results file - c:\results\results1\res5 ...  Reading results file - c:\results\results1\res6 ... Reading results file - c:\results\results1\res7 ... Reading results file - c:\results\results1\res8 ... Reading results file - c:\results\results1\res9 ... Reading results file - c:\results\results1\res10 ... Reading results file - c:\results\results1\res11 ... Reading results file - c:\results\results1\res12 ... Reading results file - c:\results\results1\res13 ... Reading results file - c:\results\results1\res14 ... Reading results file - c:\results\results1\res15 ... Reading results file - c:\results\results1\res16 ... Reading results file - c:\results\results1\res17 ... Reading results file - c:\results\results1\res18 ... Reading results file - c:\results\results1\res19 ... Reading results file - c:\results\results1\res20 ...  Min Start Time = 06/02/2004 01:33:41 PM Max Stop Time = 06/03/2004 03:54:16 AM Total Test Errors = 0 Total Test Time = 51660 sec  Test Run: Users = 26000 NotesMark = 38623 Response Time = 97 msec (06/02/2004 07:49:00 PM to 06/03/2004 03:28:00 AM)  Note: Poller Data not collected. Either the Poller was not run, or the  Poller Data file 'c:\results\results1\pout' was deleted  

11