scalability - number of users per presentation server

12
NUMBER OF USERS PER PRESENTATION SERVER Planning how many users can exist on a Presentation Server can be a complicated task. The number of users that a server can support depends on several factors including:  The Presentation Server’s hardware specifications  The applications in use (applications’ memory and CPU requirements)  How busy the applications are with processing user input This section discusses how to achieve realistic sizing for Presentation Server by using Citrix Resource Manager and presents benchmark results taken from the Citrix eLabs. Using Citrix Resource Manager to Determine User Capacity Citrix Resource Manager’s Summary Database feature makes it possible to realistically determine the capacity of a Presentati on Server. The Summary Database store s information concerning CPU and memory usage for various processes running on Presentation Server. To determine user capacity: 1. Add the Presentation Server to the relevant applications in an existing farm, or create a new farm and limit user access to approximately 20 users per processor. 2. Enable the Citrix Resource Manager’s Summary Database. 3. Allow the users to launch and use appli cations running on that server. This period can last as long as is necessary (days or weeks). 4. Create a report that queries the information required to assess single server scalability. The report should contain at least the following:  Average CPU and memory usage for the specific processes being assessed per user  Average CPU and memory usage for other processes associated with a user, such as explorer.exe, ctfmon.exe, osa.exe, wfshell.exe, csrss.exe, svchost.exe, and winlogon.exe  A defined threshold, such as no more than 90% CPU usage and/or no more than 3 GB of RAM used  A calculation to extrapolate the number of users that can be divided into the threshold given the resource usage above The longer users are able to use the server, the better the data averages that can be collected from the Summary Database. Citrix ICAMark Citrix ICAMark is an internal tool which is based on the Citrix Server Test Kit (CSTK) and used by Citrix Engineering for benchmarking purposes to quantify the optimal number of simulated client sessions that can be connected to a Presentation Server with acceptable performance. The test simulates users constantly typing and performing actions in Microsoft PowerPoint 2003, Microsoft Access 2003, and Micr osoft Excel 2003. Different applicat ions can utilize more or less memory and CPU than Microsoft Office 2003 and therefore could produce different results for the

Upload: evivv

Post on 06-Apr-2018

226 views

Category:

Documents


0 download

TRANSCRIPT

8/3/2019 Scalability - Number of Users Per Presentation Server

http://slidepdf.com/reader/full/scalability-number-of-users-per-presentation-server 1/12

NUMBER OF USERS PER PRESENTATION SERVER

Planning how many users can exist on a Presentation Server can be a complicated task. The

number of users that a server can support depends on several factors including:

•  The Presentation Server’s hardware specifications

•  The applications in use (applications’ memory and CPU requirements)

•  How busy the applications are with processing user input

This section discusses how to achieve realistic sizing for Presentation Server by using Citrix

Resource Manager and presents benchmark results taken from the Citrix eLabs.

Using Citrix Resource Manager to Determine User Capacity

Citrix Resource Manager’s Summary Database feature makes it possible to realistically determine

the capacity of a Presentation Server. The Summary Database stores information concerning CPU

and memory usage for various processes running on Presentation Server.

To determine user capacity:

1.  Add the Presentation Server to the relevant applications in an existing farm, or create a

new farm and limit user access to approximately 20 users per processor.

2.  Enable the Citrix Resource Manager’s Summary Database.

3.  Allow the users to launch and use applications running on that server. This period can

last as long as is necessary (days or weeks).

4.  Create a report that queries the information required to assess single server scalability.

The report should contain at least the following:

•  Average CPU and memory usage for the specific processes being assessed per

user

•  Average CPU and memory usage for other processes associated with a user,

such as explorer.exe, ctfmon.exe, osa.exe, wfshell.exe, csrss.exe, svchost.exe,

and winlogon.exe

•  A defined threshold, such as no more than 90% CPU usage and/or no more than

3 GB of RAM used

•  A calculation to extrapolate the number of users that can be divided into the

threshold given the resource usage above

The longer users are able to use the server, the better the data averages that can be collected from

the Summary Database.

Citrix ICAMarkCitrix ICAMark is an internal tool which is based on the Citrix Server Test Kit (CSTK) and used

by Citrix Engineering for benchmarking purposes to quantify the optimal number of simulated

client sessions that can be connected to a Presentation Server with acceptable performance.

The test simulates users constantly typing and performing actions in Microsoft PowerPoint 2003,

Microsoft Access 2003, and Microsoft Excel 2003. Different applications can utilize more or less

memory and CPU than Microsoft Office 2003 and therefore could produce different results for the

8/3/2019 Scalability - Number of Users Per Presentation Server

http://slidepdf.com/reader/full/scalability-number-of-users-per-presentation-server 2/12

test. Note, that the simulated users in this test are constantly typing into these applications at

around 40 words per minute and may be considered more “rigorous” than normal users.

In this test, a step size of “number of users” is defined as 10. During the course of the test, after

the first 10 users are logged in, ICAMark launches simulated user scripts on all 10 sessions. Each

script opens a Microsoft PowerPoint presentation, creates 6 slides and modifies them including

spell checking, font changes, slide copies and deletions. Once the PowerPoint phase is complete,

PowerPoint is closed and Microsoft Access is opened. The script then simulates the creation of an

Access database, including a table, query, and form, with data manipulation. Once the Access

phase is complete Microsoft Excel is launched and simulates the creation of a spreadsheet,

including calculations and graphs. When a script is finished with all applications it remains idle

until the scripts on all sessions are complete. The next iteration is then launched, adding 10 more

sessions to the test and the process begins again.

Based on how long the scripts take to complete, an ICAMark score is calculated. For this test, a

score of 80 has been determined as the optimal load for a server. The ICAMark score is calculated

by comparing a calibration value of the script time with the time gathered during the iteration.

The calibration value was determined by running the scripts on a calibration machine. This

machine is considered to perform at the level we expect from a stand alone workstation. Each

script on the calibration machine was run locally, and the data recorded.

An ICAMark score of 80 means that the server has enough additional CPU and memory resources

to handle spikes in performance, while maintaining a consistent user experience. When the test

iteration score drops below 80, additional users added to the server consume more resources,

producing lower test scores and slower performance.

Single Server Scalability Benchmarks

Citrix Presentation Server 4.5The Single Server Scalability test is designed to quantify for benchmarking purposes the optimal

number of simulated client sessions that can be connected to a Presentation Server with acceptable

performance. Extending the number of concurrent simulated users beyond the acceptable

performance recommendation will result in decreased performance and impacts end user

experience.

The following results were collected for this test:

Server Hardware Configuration:64-bit ICAMark EnvironmentHP ProLiant DL585

Dual AMD Opteron Processor 848:

2.2 GHz CPU Speed

36GB U320 SCSI 15K RPM HDD

16GB RAM

16GB Page File

32-bit ICAMark EnvironmentDell PowerEdge 1600SC

Dual Intel XEON Processor:

2.0 GHz CPU Speed

36GB U320 SCSI 10K RPM HDD

4GB RAM

4GB Page File

8/3/2019 Scalability - Number of Users Per Presentation Server

http://slidepdf.com/reader/full/scalability-number-of-users-per-presentation-server 3/12

8/3/2019 Scalability - Number of Users Per Presentation Server

http://slidepdf.com/reader/full/scalability-number-of-users-per-presentation-server 4/12

# of Users Time BytesSent

KBps ICAMark Score

Iteration Step 1 16:30 87871.9 0.271821 102.2045

Iteration Step 2 16:32 69396.3 0.213825 102.0795

Iteration Step 3 16:32 62701.18 0.192954 102.0835

Iteration Step 4 16:48 59661.38 0.180928 100.8834

Iteration Step 5 16:59 57724.7 0.173181 100.0349

Iteration Step 6 16:52 55874.84 0.169896 101.0841

Iteration Step 7 17:22 54800.8 0.16151 98.31556

Iteration Step 8 17:51 54247.02 0.155467 96.01294

Iteration Step 9 18:09 53030.61 0.151507 95.39122

Iteration Step 10 18:40 52898.31 0.14871 94.35711

Iteration Step 11 19:10 53053.48 0.146699 92.72538

Iteration Step 12 19:48 53046.96 0.143225 91.02248

Iteration Step 13 20:32 53176.64 0.140288 89.3034

Iteration Step 14 21:08 52188.88 0.133458 86.17348

Iteration Step 15 22:35 52936 0.128879 82.55042

Iteration Step 16 23:24 52361.91 0.125801 81.38084Iteration Step 17 24:43 52470.66 0.121081 78.18494

Test Configuration:Step Size: 10 users 

Iterations: 10 Iterations

Total simulated users in this test: 100

Script Version: 3.0

On the Dell PowerEdge 1600SC running script version 3.0, the results show 95 simulated users

concurrently running Microsoft Office applications without significant performance degradation.

By looking at the chart below the easiest way to determine the server’s degradation point is to look 

at the ICAMark score column. Note that when the score of 80 is reached the server is considered

8/3/2019 Scalability - Number of Users Per Presentation Server

http://slidepdf.com/reader/full/scalability-number-of-users-per-presentation-server 5/12

fully loaded. This means that the server has enough additional CPU and memory resources to

handle spikes in performance, while maintaining a consistent user experience.

# of Users Time BytesSent

KBps ICAMark Score

Iteration Step 1 16:30 88376.83 0.273492 102.0759

Iteration Step 2 16:30 70761.23 0.218359 102.2522Iteration Step 3 16:44 63121.73 0.193023 101.5336

Iteration Step 4 17:11 59896.68 0.179046 99.63337

Iteration Step 5 18:56 59622.71 0.170708 96.44272

Iteration Step 6 19:21 57934.55 0.159233 92.97345

Iteration Step 7 20:29 57790.56 0.151365 89.48422

Iteration Step 8 23:26 58627.77 0.146637 86.27086

Iteration Step 9 24:37 59780.27 0.140293 82.15797

Iteration Step 10 26:55 58678.96 0.129638 77.38841

8/3/2019 Scalability - Number of Users Per Presentation Server

http://slidepdf.com/reader/full/scalability-number-of-users-per-presentation-server 6/12

The Effect of disabling Session Reliability on Single Server Scalability

This section discusses the difference in performance or user capacity with Presentation Server 4.5

when client Session Reliability is enabled and disabled.

Results

Configuration # of Simulated Users % ChangeSession Reliability Enabled 95 ± 1.5 NA

Session Reliability Disabled 99 ± 1.5 + 4.2%

The results of the Single Server Salability test conclude that disabling Session Reliability on the

client provides a gain of 4 simulated users or a 4.2% increase in performance on Presentation

Server 4.5.

This test shows that the impact of the Session Reliability is minimal and falls within the tests

standard deviation of ±1.5 users.

Server Hardware Configurations

Dell PowerEdge 1600SC

Dual Intel XEON Processor:

2.0 GHz CPU Speed

36GB U320 SCSI 10K RPM HDD

4GB RAM

4GB Page File

Client Hardware Configuration

Dell PowerEdge 1750

Single Intel XEON Processor:

2.8 GHz CPU Speed

8/3/2019 Scalability - Number of Users Per Presentation Server

http://slidepdf.com/reader/full/scalability-number-of-users-per-presentation-server 7/12

36GB U320 SCSI 10K RPM HDD

1GB RAM

1.5GB Page File

Server Software ConfigurationWindows Server 2003 SP1

Citrix Presentation Server 4.5 Enterprise Edition

Microsoft Office 2003 – Excel 2003, PowerPoint 2003, and Access 2003

Client Software Configuration

Windows Server 2003 SP1

Citrix ICA Windows 32-bit Program Neighborhood 

The Effect of CDF Tracing on Single Server Scalability 

Common Diagnostic Facility tracing is designed to aid in the collection of diagnostic information

for Presentation Server 4.5 with minimum impact to the host system that might be a production

server handling a heavy load. Its main benefit is the ease of collecting needed diagnostic

information from the field.

This section discusses the differences in performance or user capacity with Presentation Server 4.5

when CDF tracing is enabled. The standard Single Server Scalability test was used to establish a

performance baseline. On the subsequent runs CDF Tracing was enabled on the server using the

following command “tracelog -start t1 -guid “ctl_file” -cir 50 -f “output_file” -flag 0xffffff -level

16 -min 64 -max 128”. All tracing information was logged to a file located on the server; the

traceview application used for displaying real time trace information was not used during this test.

Results

Server Configuration # of Simulated Users % Change

Baseline 95 ± 1.5 NA 

  All Tracing Enabled 92 ± 1.5 - 3.2%

The results of the Single Server Salability test conclude that enabling CDF Tracing has a small

impact up to 3.2% on Presentation Server 4.5 server scalability.

8/3/2019 Scalability - Number of Users Per Presentation Server

http://slidepdf.com/reader/full/scalability-number-of-users-per-presentation-server 8/12

Server Hardware Configurations

Dell PowerEdge 1600SC

Dual Intel XEON Processor:

2.0 GHz CPU Speed

36GB U320 SCSI 10K RPM HDD

4GB RAM

4GB Page File

Client Hardware Configuration

Dell PowerEdge 1750

Single Intel XEON Processor:

2.8 GHz CPU Speed

36GB U320 SCSI 10K RPM HDD

1GB RAM

1.5GB Page File

Server Software ConfigurationWindows Server 2003 SP1

Citrix Presentation Server 4.5 Enterprise Edition

Microsoft Office 2003 – Excel 2003, PowerPoint 2003, and Access 2003

Client Software ConfigurationWindows Server 2003 SP1

Citrix ICA Windows 32-bit Program Neighborhood 

The following (control) files were used in this test ALL.ctl

7460B365-C1D2-495E-843E-5C88865CA6F1 MF_Driver_Wdica

40ED53F1-907F-4A83-9646-DCE4CED0748E MF_Driver_Cdm

B751ED6E-60A3-4056-B7C2-BF4597D038AF MF_Driver_Thinwire

D9F0D8C5-E4AA-4556-9003-95AD7AD7A022 MF_Driver_Reducer

70F2785E-FCF2-4007-9D67-7585ECF32249 MF_Driver_SMC474958F4-8121-4425-A33A-7FE098530599 MF_Driver_PDCommon

67F3FD1B-6DF3-45D8-95E8-17C72A3AB105 MF_Driver_PDCompress

CA2EFD38-2806-4E4A-8E75-0D57489F1196 MF_Driver_PDCrypt

11A62BCA-2191-49E0-8C9B-F4D671C69182 MF_Driver_PDFrame

D42BBDD0-B5D6-4054-A062-4CC59287AD60 MF_Driver_PDRFrame

78A9AAF8-6495-40A4-B9E2-9F060FEB7D0A MF_Driver_PDReliable

BCFD511F-59E2-4290-B0D7-A3E97D054AC0 MF_Driver_Cdf 

5DF7C852-3BB0-49A2-A2DD-3D63D0B143DB MF_DLL_Wsxica

5863B83B-7DB6-4691-89EA-D0C97A1CE37A MF_DLL_CtxRdpWsx

C24D513B-9186-4586-9023-07EF048E3D51 MF_DLL_Wsxlic

84B7BA7D-469B-4D7D-AF19-B22827D55BF4 MF_DLL_Ctxnotif 

5FB513F8-5E39-4695-A54F-AD1D039E274E MF_DLL_Cdmprov

E3CC5036-7030-4B91-9559-A50386F2F7ED MF_DLL_Cpmmon

  AEAF61D0-483B-4CD9-B30E-5B7EDB0CB0FD MF_DLL_Cutildll

3755472F-8DA0-4BFD-BA4A-0008D74E995F MF_DLL_Vclipbd

C85C6EE9-F215-43DA-B471-1FF2F50B73DD MF_DLL_Ccticket

82A3EC58-C123-4E7F-AC74-78B534BF43BC MF_DLL_MfObjectPermissions

5BC1109B-A75A-4AC4-BCC2-5908CC709660 MF_DLL_MMVD

66936DE6-9247-4A7A-B3BF-89F2E49D4A1C MF_DLL_SpMkMci

8/3/2019 Scalability - Number of Users Per Presentation Server

http://slidepdf.com/reader/full/scalability-number-of-users-per-presentation-server 9/12

9E703A05-D8BA-42DE-A64A-C5FED3388E34 MF_DLL_Ctxgina

56A0D1EE-F894-433D-B938-5C27DFED3B18 MF_Service_CdmSvc

7EB18582-343E-4239-95DD-F34F6C1D60BC MF_Services_ServerFTA 

04979F4A-470E-4569-97A9-A0D6FB785872 MF_Service_CtxXmlSS

E85B6971-974E-4A02-9071-EBBC4279D675 MF_Service_CtxCdfSvc

91BFA822-B20E-45CF-825A-1AF5AA8939EC MF_Session_CtxRdpShell

B78FCCAF-01C8-47AF-8F91-F26A44983E20 MF_Session_Wfshell

C45B30F2-1C03-4B8E-91E6-474EB7335EDE MF_Session_ICASTExe

F3DF3BE6-1D5D-4CBE-B240-BCFBC4191964 MF_Session_CtxRdpStExe

  AF1BFA8E-2DC0-4D9D-B893-0BC74E507C7A MF_Session_TWI

1939608A-B4AE-4735-A9B1-1B3034ECEB78 MF_Session_TWI_HOOK 

DBC8D781-361C-4F4C-B3B9-A328CAF4877F MF_Session_ICACTLS

8AAF4FE4-8BA7-4189-90E3-EAEA0DDCEF58 MF_Session_CTXRDPCTLS

B991403C-6AAC-429F-B7CE-C33C7A6DC81E MF_Session_SpMkSrv

595405BF-97FF-47E4-9F54-19A1D13B8C93 MF_Session_tzUser

1661FF10-2D91-457C-B614-35908302634F MF_Session_EUKS

51B921DE-8B61-484F-AE1B-7B0749A61C1B MF_Session_twcds

CE6D343A-E297-4AF8-B742-4287BBA2AEAB MF_CtxRdpCcExeD00F3CAE-0C0A-41E7-8300-A4B29A40FF3D MF_Utility_CMSTART

BAF75945-93DD-4D3D-836A-8A0BC3396154 MF_Utility_ChgcdmExe

1736EC8E-492C-4FC0-8D80-D19F428CDC9C MF_Utility_PrintcfgExe

C10C18A5-20A9-4F67-B91B-445AFC503F4C MF_Utility_SpeedBrowseFilter

28FB3FE7-B3E9-4E46-B462-D8AAB4AC3E0E MF_SDK_MfcomExe

  AC600763-4A5F-451B-A790-69944E202D9A MF_Zlc_ApiDll

  A8A09A30-A9E2-48A8-8D22-55316F5EC899 MF_Zlc_SupDll

9E3441C6-BE6F-46E7-AA86-603795FEC65C MF_Zlc_FontDll

E4FCC965-362C-4C2A-8026-38131B53865E MF_Hook_MfApHook 

683E8D55-B7EF-4BB8-990C-BA13C65B2673 MF_Hook_TzHook 

CBD02229-5273-4F63-9007-5D1DC43392D9 MF_Hook_InjIME

1966E2C3-1023-4FA4-99A7-55F04A3C40DD MF_XMLRelay_Wpnbr

4A3030F8-88E4-44DE-AC66-27FA9584CA83 MF_XMLRelay_Clm

3641629E-E701-4CF2-BAFE-C63DB21F60CC MF_XMLRelay_Admin

0FB20993-72EC-425B-8743-43316089AB5B IMA_Sals_Browser

C655D97C-6831-46AA-9F28-FC060646E509 IMA_Sals_Content

D9AB3732-E6C2-4345-B4B7-33CBC77B3E5C IMA_Sals_MfApp

EE31F1B5-1C65-4C97-B9C2-0275951B3316 IMA_Sals_MfPrint

5AC034C2-4069-4DAC-878D-32323A1EB630 IMA_Sals_PN

0432987E-F918-4598-8AA0-50657FDFE334 IMA_Sals_MfServer

9A0617E6-8576-4D7F-B14E-BFCEADAFD0A1 IMA_Subsystems_MfPrint

08265143-ADBE-4578-8EDB-987FD15F3104 IMA_Subsystems_Browser

5BD888D6-6540-462C-A011-9B0D2C205B3B IMA_Subsystems_MfServer87AD7FB3-7D29-4775-A78B-AEBB23407586 IMA_Subsystems_Content

2C1661A8-5B48-4533-9BED-63945F8CF5D2 IMA_Subsystems_MfApp

  A6B12B89-7156-4EA1-9AB2-B912DF7CED96 IMA_Subsystems_MfRpc

5ECEE192-DB61-4746-92E7-5FE42A4AE823 IMA_Subsystems_PN

3A2C6159-6DA1-4586-AAA5-037B84F16833 IMA_Subsystems_UserWin

DF157FC9-70FE-41A8-8A8A-57090C5BF21B IMA_Subsystems_UserNds

5B545211-E888-4B3E-A9A9-5206321CA86B IMA_Subsystems_LMS

8/3/2019 Scalability - Number of Users Per Presentation Server

http://slidepdf.com/reader/full/scalability-number-of-users-per-presentation-server 10/12

58E3240C-0583-4871-8594-9D62300F5DF3 MF_Library_System

39BAD8B6-4C73-4EF0-966A-582F2A046F59 MF_Install

63D00EC3-1CB2-490E-AD95-224754128462 MF_Session_SpeedFlash

4E9A6239-70D9-4D24-AF5E-92FE8AB70CED IMA_Library_ImaRpc

  A6E313FE-983B-4803-B66F-86F5517B9A5C IMA_Library_ObjectPermissions

DFE2A7A5-8EB7-42ED-AF88-D0770C5DDE72 IMA_RemoteAccess

50381E5B-C32A-455B-B3C2-9735570677F2 IMA_Runtime_DynamicStore

5D452398-2CE7-4A5B-955E-F907A86BC5F7 IMA_Runtime_HostResolver

3A02EF43-BC8F-4D76-BE63-2CE5EAFE7126 IMA_Runtime_PersistentStore

F2F8EC10-BDDF-4D92-9015-A07D3D2B97B8 IMA_Runtime_Runtime

45FE0318-F476-404F-A906-3F0594B29E17 IMA_Runtime_ServiceLocator

61CABB44-ADDE-40EF-9EFF-1DE676EAA687 IMA_Runtime_SubscriptionManager

4AEAF09B-6997-4CF3-96F4-F823A46510DC IMA_Runtime_ZoneManager

22D700CB-DB81-45B9-BF46-2AB356D94A62 IMA_System_DataStoreDriver

56BE8567-F9FF-4703-AAF5-0EA61069EEC4 IMA_System_Loader

925C5B50-A0B2-45BA-B87A-D2B94CDD1157 IMA_System_Message

E71A692F-7B0E-4F96-B086-E203216214A2 IMA_System_Registrar

EC19883C-E86B-4B6A-B552-EA8F6BD7C00F IMA_System_Support5AD82332-790A-4B1C-941C-AADF4AC4BB25 IMA_System_System

4EC76A67-3659-4255-A225-D911D5C9E232 IMA_System_Transport

  A9E5F912-F901-4BE0-AA3A-4C823F4F71CE IMA_Sals_AdminTool

B573D34F-33E7-4522-A50E-E3404CBD8565 IMA_Sals_Comapp

E2960059-75AF-4019-B0E6-D8D6FEE96962 IMA_Sals_Comsrv

72B80D93-C6B1-4B3B-9F11-0327E82B0E1A IMA_Sals_Distribution

5AE8BF20-77E2-4C21-A870-D4CC94F1A2B6 IMA_Sals_ImaRpcClient

374B7D61-B7A5-426F-A783-CC69539695FF IMA_Sals_IMS

  AB24CC65-6704-43D2-967F-61EEB086DCF6 IMA_Sals_LMS

16F1AE5E-D790-48BF-AAF2-E4D90212999A IMA_Sals_Group

  A027A206-091A-47B5-863A-A23B9CE19D43 IMA_Sals_Relationship

7978C702-F187-4E69-BDDF-DECDD1030298 IMA_Sals_UserMgmt

76FE0864-7E9C-4E6A-BE26-B61B7D83AEDC IMA_Subsystems_AdminTool

CB194955-7D95-4219-832C-F5FB78050FB4 IMA_Subsystems_ComApp

1017700C-EC97-4637-A3FE-4776EE3661F8 IMA_Subsystems_ComSrv

E9A3E538-007E-4FC3-89F1-4F51FAD134DB IMA_Subsystems_Distribution

308D42B8-296F-4319-8B05-025C88075031 IMA_Subsystems_ImaRpc

092F0714-7498-4FDF-953F-3C8CE210771F IMA_Subsystems_Policy

6CF78BED-C1C2-4673-8CAF-3953ACF37883 IMA_Subsystems_PolicyApi

27F60934-5C69-428E-A9BA-B6A35E4BEDF0 IMA_Subsystems_User

E6D65C42-B19A-4B75-8352-A96A79BE14E4 IMA_Subsystems_Group

C1B12497-6872-4A4D-BD76-1713343AC70F IMA_Subsystems_Relationship

217DA661-2E34-4119-BD21-4CDEEC31C210 IMA_Subsystems_FileF2028166-86F2-47F4-9ACC-D6CB00FF3B31 IMA_Subsystems_RMAlert

CD8EFA97-8C85-40EB-9D89-3BC76CF9E62B IMA_Subsystems_RMAnalysis

8679C60D-43F9-4644-852A-38157F2B8F8C IMA_Subsystems_RMApplication

  A2043308-FE75-4B25-9A8A-671D347A8CDF IMA_Subsystems_RMSummaryDB

D0F5892D-F868-4069-BBB5-0732B7DE0FF2 IMA_Subsystems_RMCrmsDB

2B6889F4-8F0A-47B5-9E5A-B6C3E2326835 IMA_Subsystems_RMMetrics

C668662F-1540-4CC1-ACFD-5890FC72FC14 IMA_Subsystems_RMMonitor

8/3/2019 Scalability - Number of Users Per Presentation Server

http://slidepdf.com/reader/full/scalability-number-of-users-per-presentation-server 11/12

3FFC941A-E901-4768-97DC-5B5022A551C7 IMA_Subsystems_RMBilling

3C320956-CF70-44CE-9C51-060424EC5E2F IMA_Subsystems_RMReport

B289C918-6336-4D80-810C-E6557D9A3A50 IMA_Subsystems_RMServer

896537B9-C582-47E9-8DC5-0E90E050BCB4 IMA_Subsystems_RMLogFile

F3F83808-1880-452D-9DF5-6F0B66BF0CC7 IMA_Subsystems_IMS

8728360C-8220-4565-8477-BC5F776970CC IMA_Tools_Dscheck 

6E4B9EED-1DC3-412F-9D04-C75E304653EA IMA_Tools_Dsmaint

BE01EE0D-F1EA-4DA7-941A-E820044AB744 IMA_Tools_ImaPerf 

4A1C5BE4-1D6D-474B-91CB-8C82448E76C3 IMA_Tools_MfxpPerf 

28809B3A-A696-42E1-A5D6-1BD66F78AB85 IMA_Tools_MfxpPerfData

F8BC0945-3E78-466D-82D1-75BB7493F0AA IMA_Tools_RMDBReconnect

BDF61BD1-A374-4CB2-B08F-3FB914726F4C IMA_Tools_RMDebug

35E47238-F974-448D-9DED-63FD039747B6 IMA_Tools_RMUtils

738A2048-E88D-4448-990E-D1045D157D52 PRODLIC_Library_Common

03D58FC0-18F3-4253-8398-303A2798AF87 PRODLIC_LicPolEng

27C16A5F-4A19-42D8-BDBA-7314794CE6BE XTE_mod_cgp

  A9DF9314-2C5A-4717-B66E-F22B583E8E03 XTE_mod_multiplexer

0824D858-4332-4C6B-ACE9-F1B50DED528E XTE_mod_podBC8970E1-748E-4D4A-B227-A9511880716D XTE_mod_schannel

053A6B1B-D7DB-4093-A3EE-CABB8776A71D XTE_mod_socks

12A29DBB-7FC6-4FED-A6D8-C1A3FFDF7E8F XTE_mod_vhost_throttle

60725A77-179C-4EAB-B152-8807EE95E959 XTE_mod_winevent_log

Measurements and Calculations

There are many calculations performed by ICAMark. Here is a summary of the more complex

equations involved and measurements used in ICAMark.

Time

The time is taken using Ctime objects provided by MFC. A start and stop time are taken, and the

difference is calculated using a CTimeSpan object.

Bytes

The byte count is measured by taking the output bytes from a WFAPI call and saving them as the

start bytes. Then the script is run, and the stop bytes are taken. The difference is recorded.

KBps

This is taken by dividing the delta bytes by the time. The time is converted to seconds using the

CtimeSpan.GetTotalSeconds() function.

AppScore

This is the score a script receives after it runs. The ICAMark client calculates it after a run of the

script. Calibration time is the time recorded in the registry for each script. It was generated on the

calibration machine. Delta time is the time recorded for the script just ran.

100* DeltaTime

nTimeCalibratio AppScore =

 

8/3/2019 Scalability - Number of Users Per Presentation Server

http://slidepdf.com/reader/full/scalability-number-of-users-per-presentation-server 12/12

 

FailScoreThis is the recovery score that is recorded when a script fails. It is calculated by dividing the

calibration fail score for the script by the fail score.

100*TimeScriptFail

nFailTimeCalibratioFailScore =

 

IterationScoreThis is the summary of the ICAMark score per iteration. It is the sum off all the app scores divided

by the number of users. This score will be calculated at the end of the test. Data is recorded along

the way to allow for this calculation.

nUsers

 AppScore AppScore AppScore

core IterationS

Users

u

n

*

)...(1

10

0

∑=

+++

n = the number of apps being tested.

U = current user.

Users = the number of users involved in an iteration.

AppScore includes both FailScore and AppScore values listed above.

Standard Performance Data Log CountersThe following is a list of the standard Performance Monitor counters that are gathered for each

ICAMark test.

Cache\Copy Read Hits %

Memory\% Commited Bytes In Use

Memory\Available MBytes

Memory\Free System Page Table Entries

Memory\Page Faults/Sec

Memory\Pages Input/secMemory\Pages Output/sec

Memory\Pages/Sec

Memory\Pool Nonpaged Bytes

Memory\Pool Paged Bytes

Network\Bytes Received/sec

Network\Bytes Sent/sec

Network\Bytes Total/sec

Paging File(\??\C:\pagefile.sys)\% Usage

Paging File(\??\C:\pagefile.sys)\% Usage Peak 

PhysicalDisk(_Total)\% Disk Time

PhysicalDisk(_Total)\Current Disk Queue Length

Process(_Total)\Page File Bytes

Process(_Total)\Virtual BytesProcess(_Total)\Working Set

Processor(_Total)\% Processor Time

System\Context Switches/sec

System\Processor Queue Length

Terminal Services\Active Sessions

Terminal Services\Total Sessions