This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
This document contains information about the EMC® CLARiiON® CX3-20 Storage Solution for Microsoft Exchange Server.
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Overview
OverviewThis document provides information on the EMC CLARiiON® CX3-20 storage solution based on the Microsoft Exchange Solution Reviewed Program (ESRP) - Storage program1. For any questions or comments regarding the contents of this document, see the “Contact Information” section.
DisclaimerThis document has been produced independently of Microsoft Corporation. Microsoft Corporation expressly disclaims responsibility for, and makes no warranty—express or implied—with respect to the accuracy of the contents of this document.
The information contained in this document represents the current view of EMC on the issues discussed as of the date of publication. Due to changing market conditions, it should not be interpreted as a commitment on the part of EMC. In addition, EMC cannot guarantee the accuracy of any information presented after the date of publication.
FeaturesThis document describes an approach that can be used to configure Exchange solutions around EMC's CLARiiON CX3-20 storage systems.
Built on the innovative EMC CLARiiON CX3 UltraScale architecture, the EMC CX3-20 offers exceptional performance, ease-of-use, and unmatched reliability. It meets the storage needs of a wide range of applications—including:
• Mail/messaging
• Databases
• File/print and Web services
• Distributed applications
1. The ESRP - Storage program was developed by Microsoft Corporation to provide a common storage testing framework for vendors to provide information on its storage solutions for Microsoft Exchange Server software. For more details on the Microsoft ESRP - Storage program, please go to http://www.microsoftstoragepartners.com/.
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 3
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Solution description
• Remote replication
In addition, the CX3-20 supports a wide range of server operating environments—Microsoft Windows, Linux, Solaris, AIX, HP-UX, and VMware ESX Server.
With the EMC CX3-20 you can choose the drive options that meet your specific needs, thereby providing the flexibility to offer multiple levels of performance in one system. The CX3-20 supports both high-performance and high-capacity disk drives in the same system, can scale from 365 GB to 59 TB, and supports 128 high-availability hosts. It supports 4 Gb/s (15k RPM) Fibre Channel drives for demanding applications requiring maximum performance. Choose 2 Gb/s Fibre Channel (10k RPM) for applications that require balancing performance and cost. Or, choose low-cost 2 Gb/s Fibre Channel drives (7.2k RPM) for Tier 2 applications requiring high capacities and low cost—such as disk-based backup.
The CX3-20 delivers tiered storage that enables you to provide the right level of performance to the right applications. The system also delivers exceptional 4 Gb/s performance throughout the entire system—without compromises or bottlenecks. Performance-boosting features include four front-end and two back-end 4 Gb/s ports—plus state-of-the-art low-latency, high-bandwidth I/O inter-connect technologies.
The performance results and best practices discussed in this document provide tested guidelines for configuring the EMC CX3-20 for a high-performance Exchange environment. For this solution, a CX3-20 storage system was used and configured for 8,000 Exchange 2003 users. Each of the 8,000 users is profiled using a value of 1 IOPS per user and a 200-MB mailbox requirement.
Solution descriptionSizing and configuring storage for use with Microsoft Exchange Server is a complicated process, driven by many variables and factors, which vary from organization to organization.
One method often used to simplify the sizing and configuration of large amounts of EMC CLARiiON storage for use with Microsoft Exchange Server 2003 is to define a unit of measure. Such a unit of measure—in this case one server with 38 storage spindles (32 for databases and 6 for logs)—meets all of the Microsoft Exchange Server recommended metrics for excellent reliability, scalability, and performance.
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Solution description
This unit of measure—or building block—needs to be scalable. In that way, an organization can simply take this block of work and multiply it by some factor until the desired number of Microsoft Exchange Server users (i.e., Microsoft MAPI Outlook users) has been properly met or configured to satisfy the Microsoft Exchange Server recommended performance metrics.
If each unit is properly configured, it will match the Microsoft Exchange Server recommendations for a healthy-performing system—from both a disk and an end-user perspective.
Table 1 describes the characteristics of each building block.
Using the performance characteristics of the CLARiiON CX3-20 architecture and the I/O capability of the 146-GB disk drives, 38 spindles are required to provide the necessary performance to match the I/O requirements of 4,000, 1.0 IOPS users. The Exchange databases reside on 32 spindles in four 4+4 1/0 RAID Groups. The logs will be placed on one 3 +3 1/0 RAID I/O Group. This design is then duplicated one more time, resulting in two building-blocks of 4000 users, for a total of 8,000 total users.
See Figure 1 for a view of the CLARiiON CX3-20 ESRP test environment.
Table 1 Building block characteristics
Number of users 4,000
Number of Exchange Servers 1
IOPS per user 1.0
Mailbox size 200 MB
Number of disks required for Logs and Database
38
Disk type 146 GB 15 K
RAID type 1/0
Number of storage groups per server 4
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 5
6
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Solution description
Figure 1 CLARiiON CX3-20 ESRP test environment
The ESRP Storage program focuses on storage solution testing to address performance and reliability issues with storage design. However, storage is not the only factor to consider when designing a scalable Exchange solution. Other factors that affect the server scalability are:
• Server processor utilization
• Server physical and virtual memory limitations
• Resource requirements for other applications
• Directory and network service latencies
• Network infrastructure limitations
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Targeted customer profile
• Replication and recovery requirements
• Client usage profiles
Due to such variables, the number of mailboxes hosted per server, as part of the tested configuration, may not necessarily be viable for some customer deployments.
For more information on identifying and addressing performance bottlenecks in an Exchange system, please refer to Microsoft's Troubleshooting Microsoft Exchange Server Performance, available at: http://go.microsoft.com/fwlink/?LinkId=23454.
Targeted customer profileThis solution is intended for medium-to-large Enterprise Exchange customers. This configuration is designed to support 8,000 Exchange users, with the following assumptions:
• 2 Exchange Server
• 4,000 users per Exchange Server
• 1 IOPS per user
• 200-MB mailbox
• Four Exchange storage groups per Exchange Server
• Five databases per storage group
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 7
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Best practices
Best practicesMicrosoft Exchange Server is a disk-intensive application. It is characterized as a very bursty (mostly 4-KB random access) read/write operation to the database files, with a sequential (mostly 512 byte) write operation to the transaction logs. It is this random, bursty workload—with periods of high peaks—that makes designing a well-performing storage solution with Microsoft Exchange Server a challenge. Different corporate environments have different user and storage requirements, so storage design cannot be based simply on generalizations.
Based on the testing run using ESRP framework, EMC recommends following these best practices to improve storage performance with Exchange solutions. For Exchange best practices on storage design, please visit:
Core storage 1. Use diskpart (in Windows 2003 SP1) to align all Microsoft-Exchange-related disks, using a value of 64 for CLARiiON. This aligns all of the Exchange-related NTFS partitions on a 64-KB boundary.
2. Isolate the Microsoft Exchange Database workload from other I/O-intensive applications or workloads. This ensures the highest levels of performance for Microsoft Exchange and makes troubleshooting easier in the event of a disk-related Microsoft Exchange performance problem.
3. The logs and databases should be separated onto different disks and CLARiiON RAID Groups.
4. Size and configure the environment for spindle performance as a primary consideration, with spindle or storage capacity a secondary issue. In other words, size for performance first and make the capacity requirements work.
5. Striped metaLUNS should be used for all Microsoft Exchange Server implementations. Concatenated metaLUNs would limit the I/O capacity to that of a single metaLUN component or FLARE LUN. metaLUNs can also provide:
• Expandability• Load balancing
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 13
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Best practices
6. Tuning the CX3-20 storage system parameters is important in obtaining best performance. The following list details the optimal parameters for Exchange:
• Cache page size of 4KB• Maximized write cache size• Read and write cache enabled for all LUNs• Read cache minimum of 50-100 MB for prefetch
Note: In the event a performance problem cannot be resolved using common performance analysis, EMC Corporation strongly recommends that a case be opened with EMC Customer Service, so that the appropriate Customer Support resources may be engaged.
Backup strategy A well designed and implemented disaster recovery strategy should be a top priority for Exchange implementations. Proper planning must be done prior to configuration in order to meet required service-level agreements (SLAs) for server downtime. Various backup and restore strategies can be implemented, depending on the requirements of the environment. EMC offers multiple backup-to disk solutions that deliver all of the flexibility needed to accommodate a full spectrum of SLA’s.
EMC offers NetWorker™, which can perform traditional Exchange backups to tape and disk, and Replication Manager, which can manage snapshots or replicas of your Exchange environment, utilizing the ground breaking technology of TimeFinder®. Both Replication Manager and NetWorker can be used in conjunction with Exchange 2003 Volume Shadow Copy services (VSS). These solutions are proven, tested and blueprinted with leading backup software applications and can be deployed in existing SAN or LAN storage infrastructures.
For example, EMC offers the Symmetrix® with Low Cost Fibre Channel (LCFC) and the CLARiiON CX series with either ATA or LCFC drives. EMC provides operationally simple disk libraries that easily integrate with existing backup environments through tape emulation. Leading backup software, such as EMC NetWorker, is supported on EMC’s Disk Library, CLARiiON CX series, Symmetrix DMX, and Celerra® NS offerings. In this solution, the tested method for backup was a one stage disk-to-disk backup. With this configuration, several best practice considerations must be understood in order to achieve optimal performance.
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Testing and performance results
Best practices 1. Disk-to-disk backup LUNs should be configured in a separate disk group.
Workload isolation will optimize performance of the streaming backups and minimize the impact on the production workload.
2. Higher capacity Fibre Channel or FATA drives should be utilized if the environment requires additional backup copies of the data on the primary disks.
FATA drives should not be utilized to host production Exchange traffic without careful consideration of the performance impact. FATA drives operate at a lower rotational speed and will provide much lower throughput than Fibre Channel drives. FATA drives are also designed for an 8*5 duty cycle and not meant to operate 24*7. This results in a shorter mean time between failure (MTBF) than Fibre Channel drives (which are rated for 24*7) if over utilized.
3. Maximize the number of Exchange databases and storage groups on the Exchange server in order to minimize the time required for disaster recovery operations.
Exchange storage groups can be backed up in parallel, so having the maximum of four storage groups enables four parallel backup operations. Up to twenty databases can be created for Exchange 2003. By utilizing the maximum number of databases, this keeps the size of each database smaller and reduces the restore window. Best practices are to keep the database sizes in the 30-45GB range.
Testing and performance resultsThis section provides a high-level summary of the test data from ESRP, as well as links to the detailed reports located in “Appendix A: Test Reports”, which are generated by the ESRP testing framework.
Reliability A number of the tests in the framework are designed to test reliability over a 24-hour period. The goal of these tests is to verify that the storage can handle high I/O load for a long period of time. Following the stress test, both log and database files are analyzed for integrity to ensure there is no database/log corruption.
• No errors were reported in the event log file for the storage reliability testing.
• No errors were reported for the database and log checksum.
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 15
16
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Testing and performance results
• Backup-to disk test is N/A.• Database checksum on the remote storage database is N/A
Performance Performance results - 2-hour Performance Test
To see the Jetstress performance results (2-hour performance test), see the section “Performance tests” on page 38.
Performance testing exercises the storage with maximum sustainable Exchange-type I/O for two hours. The test is used to show how long it takes for the storage to respond to an I/O under load. The data included in the following tables is a sample taken from each of the attached hosts. It is the average of all the logical disks in the two-hour test duration.
EXCH320-1
Average of the database disks read latency (ms)
10.5 ms
Average of the database disks write latency (ms)
3.5 ms
Average of the log disks write latency (ms) 1 ms
Average database disk read I/O per sec per storage group
740 IOPS
Average database disk write I/O per sec per storage group
335 IOPS
Average log disk write I/O per sec per storage group
72 IOPS
Average database disk read I/O per second per host
2,960 IOPs per sec. (740 IOPS * 4 SGs)
Average database disk write I/O per second per host
1,340 IOPs per sec. (335 IOPs * 4 SGs)
Average log disk write I/O per second per host
288 IOPs (80 IOPs * 4 SGs)
Max database page fault stalls per sec 0
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Testing and performance results
EXCH320-2
Streaming backup performance
This test runs through four phases:
1. Performance log generating:
This phase runs similarly to the performance test run; however, circular logging is disabled. The test stops after 100 log files are created in each storage group.
2. Soft recovery:
After phase one, the checkpoint files are deleted, and the application will mount the databases. This will force Jet to go through each log file. Disk performance is measured while each log file is replayed.
3. Database checksum:
This phase is performed to simulate the integrity check (i.e., eseutil /k) against all the databases. Disk performance is measured.
4. Log checksum:
Average of the database disks read latency (ms)
10.5 ms
Average of the database disks write latency (ms)
3 ms
Average of the log disks write latency (ms) 1 ms
Average database disk read I/O per sec per storage group
773 IOPS
Average database disk write I/O per sec per storage group
350 IOPS
Average log disk write I/O per sec per storage group
76 IOPS
Average database disk read I/O per second per host
3,092 IOPs per sec. (773 IOPS * 4 SGs)
Average database disk write I/O per second per host
1,400 IOPs per sec. (350 IOPs * 4 SGs)
Average log disk write I/O per second per host
304 IOPs (76 IOPs * 4 SGs)
Max database page fault stalls per sec 0
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 17
18
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Testing and performance results
This phase is to simulate the integrity check (i.e., eseutil /k) against all log files to ensure no corruption.
Database read-only performance
To see the complete backup-to-disk database read-only complete performance results, see the section: “Backup” on page 53.
This test is used to measure the maximum rate at which databases could be recovered. The following tables show the average rate for a single database file:
EXCH320-1
EXCH320-2
Log read-only performance
This test is used to measure the maximum rate at which the log files can be played against the databases. The following tables show the average rate for 100 log files played in a single storage group. Each log file is 5 MB in size.
Log read-only performance
This test is used to measure the maximum rate at which the log files can be played against the databases. The following tables show the average rate for 100 log files played in a single storage group. Each log file is 5 MB in size.
MB read/sec per storage group 82.2 MB/s
MB read/sec per host 329.1 MB/s
File size seconds taken 675372 MB/2052 seconds
MB read/sec per storage group 81.9 MB/s
MB read/sec per host 327.9 MB/s
File size seconds taken 677156 MB/2052 seconds
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Testing and performance results
EXCH320-1
EXCH320-2
* Log recovery performance for EXCH32-1 and EXCH320-2 was calculated based upon the average performance of only three of the storage groups. The performance of the fourth storage group is skewed based on the impact of the database checksum process commencing on the second server in the environment (see “Appendix A: Test Reports” on page 23 for html output files). Eseutil is a very I/O intensive operation and should only be conducted outside of normal business hours to minimize the impact on the production environment.
Backup-to-Disk Performance
The backup-to-disk performance test runs a steaming backup for all the database files and stores them on disks. The following tables show an average rate at which each storage group can be backed up.
EXCH320-1
Average time to play one log file (sec) 2.01
Average log disks read bytes/sec 5642547
Average time to play one log file (sec) 1.93
Average log disks read bytes/sec 5737933
Total database size per storage group (GB) 164.94 GB
Time taken to backup each storage group* 150 minutes
Avarage MB backup/sec per storage group 18.49 MB/sec
Avarage MB backup/sec per server 73.96 MB/sec
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 19
20
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Conclusion
EXCH320-2
* The four Storage groups are backed up in parallel during the ESRP test. All backups finish before the four-hour Service Level Agreement window.
ConclusionAs this document illustrates, EMC’s CLARiiON CX3-20 is more than capable of supporting deployments of up to 8,000 users at 1 IOPs per user. A careful analysis of each environment must be performed in order to understand the specific requirements of the architecture and to adapt a solution that best fits those needs. The information included in this document verifies that the CX3-20 can support a high-performance Exchange configuration.
From the backup and restore perspective, this configuration meets a four-hour Service Level Agreement (SLA) for backing up all four storage groups on two Exchange servers to a backup disk group. The test results indicate that a single database can be read at approximately 82 MB/s. However, the overall rate for each server is four times that rate, since one database from each storage group is being processed concurrently. Thus, the overall streaming rate from each server is approximately 328 MB/s. The test results in “Backup-to-Disk Performance” indicate a backup rate of approximately 18.35 MB/sec per storage group. With two servers, this is an average across four storage groups per server, for a cumulative backup rate of 146.8 MB/sec. This results in a backup rate of 534 GB/hour or a little over 8.9 GB/min for this configuration.
Please note that while this configuration worked excellently, neither local clone nor remote SAN Copy replication were part of the solution. If these are a part of your solution, the number of users supported will be affected.
This document is developed by EMC and reviewed by the Microsoft Exchange Product team. The test results/data presented in this document are based on the tests introduced in the ESRP test framework. The customer should not quote the data directly for his/her pre-deployment verification. It
Total database size per storage group (GB) 164.68 GB
Time taken to backup each storgae group* 150 mintes
Avarage MB backup/sec per storage group 18.21 MB/sec
Avarage MB backup/sec per server 72.84 MB/sec
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Conclusion
is still necessary to go through the exercises to validate the storage design for a specific customer environment.
The ESRP program is not designed to be a benchmark program; tests are not designed to get the maximum throughput for a given situation. Rather, it is focused on producing recommendations from vendors for the Exchange application. Therefore, the data presented in this document should not be used for direct comparisons among the solutions.
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 21
22
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Contact Information
Contact InformationEMC recommends that you consult with EMC Professional Services to assist with the design and deployment of a similar solution. For information regarding this or any other EMC solution, please use the following numbers:
For additional information on EMC products and services available to customers and partners, please refer to:
http//EMC.com
or to
http://powerlink.EMC.com
United States: (800) 782-4362 (SVC-4EMC)
Canada: (800) 543-4782 (543-4SVC)
Worldwide: (508) 497-7901
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Appendix A: Test Reports
Appendix A: Test Reports
Stress testing
EXCH320-1 Database checksum statistics
The following table provides a quick overview of checksum statistics for EXCH320-1.
Detected JetstressUI version: 6.5.7830.0Detected operating system: Microsoft Windows Server 2003 R2 (5.2.3790.0) Service Pack 1Detected ESE.dll version: 6.5.7638.2Detected ESEPERF.dll version: 6.5.7638.1
8/31/2006 10:37:52 PM -- Validating input parameters, it may take a few
Storage Volume
Avg. Disk sec/Read
Avg. Disk sec/Write Disk Reads/sec Disk Writes/sec Total Seconds
K: 0.256 0.000 999.42 0.000 2702.21
L: 0.257 0.000 996.20 0.000 2694.46
M: 0.256 0.000 999.31 0.001 2708.60
N: 0.256 0.000 997.29 0.000 2702.11
Counter Average Minimum Maximum
% Processor Time 6.979 0.000 10.77
Available MBytes 14742.41 14740.00 14790.00
Free System Page Table Entries 14860.00 14860.00 14860.00
Pages/Sec 0.000 0.000 0.000
Pool Nonpaged Bytes 30911960.00 30904320.00 30945280.00
Pool Paged Bytes 33855950.00 32407550.00 33873920.00
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 25
26
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Stress testing
minutes...8/31/2006 10:37:53 PM -- Attaching databases ... (it may take a few minutes if the databases are in dirty shutdown state)8/31/2006 10:37:58 PM -- Loading performance counters...8/31/2006 10:37:58 PM -- Instance1372.1: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 10:37:58 PM -- Instance1372.2: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 10:37:58 PM -- Instance1372.3: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 10:37:58 PM -- Instance1372.4: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 10:37:58 PM -- Start Jetstress test...8/31/2006 10:38:00 PM -- Starting Stress test run...8/31/2006 10:38:01 PM -- Performance logging started.8/31/2006 10:38:01 PM -- Performance data will be saved to C:\Program Files\Jetstress\Stress_2006_8_31_22-37-58.blg.9/1/2006 10:37:09 PM -- Adding new data to the performance log file...9/1/2006 10:38:01 PM -- Performance logging stopped.9/1/2006 10:38:01 PM -- Stopping Jetstress...9/1/2006 10:38:35 PM -- Creating test report ...9/1/2006 10:38:45 PM -- Volume L: has 0.0115 for Avg. Disk sec/Read.9/1/2006 10:38:45 PM -- Volume K: has 0.0105 for Avg. Disk sec/Read.9/1/2006 10:38:45 PM -- Volume N: has 0.0109 for Avg. Disk sec/Read.9/1/2006 10:38:45 PM -- Volume M: has 0.0102 for Avg. Disk sec/Read.9/1/2006 10:38:45 PM -- Volume G: has 0.0010 for Avg. Disk sec/Write.9/1/2006 10:38:45 PM -- Volume G: has 0.0000 for Avg. Disk sec/Read.9/1/2006 10:38:45 PM -- Volume H: has 0.0010 for Avg. Disk sec/Write.9/1/2006 10:38:45 PM -- Volume H: has 0.0000 for Avg. Disk sec/Read.9/1/2006 10:38:45 PM -- Volume I: has 0.0010 for Avg. Disk sec/Write.9/1/2006 10:38:45 PM -- Volume I: has 0.0000 for Avg. Disk sec/Read.9/1/2006 10:38:45 PM -- Volume J: has 0.0010 for Avg. Disk sec/Write.9/1/2006 10:38:45 PM -- Volume J: has 0.0000 for Avg. Disk sec/Read.9/1/2006 10:38:45 PM -- Test has 0 Max Database Page Fault Stalls/sec.9/1/2006 10:38:45 PM -- Test has 0 Database Page Fault Stalls/sec samples higher than 0.9/1/2006 10:38:46 PM -- Performance logging started.9/1/2006 10:38:46 PM -- Performance data will be saved to C:\Program Files\Jetstress\DatabaseChecksum_2006_9_1_22-38-45.blg.9/1/2006 10:38:46 PM -- Checksum validation may take a while depending on the file sizes.9/1/2006 11:23:55 PM -- Database checksum in progress: Storage Group #1 (100%), Storage Group #2 (100%), Storage Group #3
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Stress testing
(100%), and Storage Group #4 (100%).9/1/2006 11:23:55 PM -- Performance logging stopped.9/1/2006 11:23:55 PM -- Checksum is completed, please open C:\Program Files\Jetstress\DatabaseChecksum_2006_9_1_22-38-45.html for checksum result.
EXCH320-1 Stress statistics
The purpose of this test is to verify the storage configuration which the customer is planning to deploy. The test run has been successful, meaning the database read latency and log write latency are below 20ms; Database page fault stalls/sec is 0. However, Microsoft strongly recommends that you perform further validation of this storage solution (additional tasks listed below):
1. You should refer to the table below to determine if the actual disk IO (achieved IO) has exceeded the targeted IO (expected IO). If not, you may want to increase the thread count to increase the load, provided that the disk latency will not exceed the threshold.
2. You need to confirm whether the storage solution has synchronous replication as part of the implementation. If the solution does not utilize synchronous replication, then you should check for the database write latency, the desired value should be under 20 ms. (Please refer to http://support.microsoft.com/?kbid=895847 for synchronous replication definitions.)
3. Please check the status pane in the Jetstress window, to make sure that no errors were logged during the database checksum validation.
Planned disk subsystem profile:
Total test database sizeProduction
data sizeTotal number of
databases Expected I/OAchieved
I/O
622.43 GB (based on the attached database)
(n/a) 24 (4 storage(s) * 6 database(s))
4000.00 (4000 mailboxes of 1.00 IOPS)
4307.67
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 27
Detected JetstressUI version: 6.5.7830.0Detected operating system: Microsoft Windows Server 2003 R2 (5.2.3790.0) Service Pack 1Detected ESE.dll version: 6.5.7638.2Detected ESEPERF.dll version: 6.5.7638.1
8/31/2006 10:37:52 PM -- Validating input parameters, it may take a few minutes...8/31/2006 10:37:53 PM -- Attaching databases ... (it may take a few minutes if the databases are in dirty shutdown state)8/31/2006 10:37:58 PM -- Loading performance counters...8/31/2006 10:37:58 PM -- Instance1372.1: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 10:37:58 PM -- Instance1372.2: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 10:37:58 PM -- Instance1372.3: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 10:37:58 PM -- Instance1372.4: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 10:37:58 PM -- Start Jetstress test...8/31/2006 10:38:00 PM -- Starting Stress test run...
Counter Average Minimum Maximum
% Processor Time 5.609 3.776 7.042
Available MBytes 13871.31 13858.00 14019.00
Free System Page Table Entries 14860.00 14860.00 14860.00
Pages/Sec 0.017 0.000 22.32
Pool Nonpaged Bytes 31135102.13 31092736.00 31207424.00
Pool Paged Bytes 33333600.96 31698944.00 35483648.00
Database Page Fault Stalls/sec 0.000 0.000 0.000
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 29
30
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Stress testing
8/31/2006 10:38:01 PM -- Performance logging started.8/31/2006 10:38:01 PM -- Performance data will be saved to C:\Program Files\Jetstress\Stress_2006_8_31_22-37-58.blg.9/1/2006 10:37:09 PM -- Adding new data to the performance log file...9/1/2006 10:38:01 PM -- Performance logging stopped.9/1/2006 10:38:01 PM -- Stopping Jetstress...9/1/2006 10:38:35 PM -- Creating test report ...9/1/2006 10:38:45 PM -- Volume L: has 0.0115 for Avg. Disk sec/Read.9/1/2006 10:38:45 PM -- Volume K: has 0.0105 for Avg. Disk sec/Read.9/1/2006 10:38:45 PM -- Volume N: has 0.0109 for Avg. Disk sec/Read.9/1/2006 10:38:45 PM -- Volume M: has 0.0102 for Avg. Disk sec/Read.9/1/2006 10:38:45 PM -- Volume G: has 0.0010 for Avg. Disk sec/Write.9/1/2006 10:38:45 PM -- Volume G: has 0.0000 for Avg. Disk sec/Read.9/1/2006 10:38:45 PM -- Volume H: has 0.0010 for Avg. Disk sec/Write.9/1/2006 10:38:45 PM -- Volume H: has 0.0000 for Avg. Disk sec/Read.9/1/2006 10:38:45 PM -- Volume I: has 0.0010 for Avg. Disk sec/Write.9/1/2006 10:38:45 PM -- Volume I: has 0.0000 for Avg. Disk sec/Read.9/1/2006 10:38:45 PM -- Volume J: has 0.0010 for Avg. Disk sec/Write.9/1/2006 10:38:45 PM -- Volume J: has 0.0000 for Avg. Disk sec/Read.9/1/2006 10:38:45 PM -- Test has 0 Max Database Page Fault Stalls/sec.9/1/2006 10:38:45 PM -- Test has 0 Database Page Fault Stalls/sec samples higher than 0.
EXCH320-2 Database checksum statistics
The following table shows a quick overview of checksum statistics for EXCH320-2:
Avg. Disk sec/Write Disk Reads/sec Disk Writes/sec Total Seconds
K: 0.256 0.000 999.02 0.000 2700.54
L: 0.256 0.000 1000.81 0.000 2707.95
M: 0.256 0.000 997.38 0.000 2704.52
N: 0.255 0.000 1002.10 0.000 2704.24
Counter Average Minimum Maximum
% Processor Time 7.079 0.000 11.92
Available MBytes 14785.89 14764.00 14834.00
Free System Page Table Entries 14799.58 14799.00 14799.00
Pages/Sec 0.001 0.000 0.986
Pool Nonpaged Bytes 30803190.00 30785540.00 30842880.00
Pool Paged Bytes 22127640.00 20668420.00 22155260.00
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Stress testing
Detected operating system: Microsoft Windows Server 2003 R2 (5.2.3790.0) Service Pack 1Detected ESE.dll version: 6.5.7638.2Detected ESEPERF.dll version: 6.5.7638.1
8/31/2006 10:37:39 PM -- Validating input parameters, it may take a few minutes...8/31/2006 10:37:39 PM -- Attaching databases ... (it may take a few minutes if the databases are in dirty shutdown state)8/31/2006 10:37:43 PM -- Loading performance counters...8/31/2006 10:37:43 PM -- Instance2760.1: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 10:37:43 PM -- Instance2760.2: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 10:37:43 PM -- Instance2760.3: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 10:37:43 PM -- Instance2760.4: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 10:37:43 PM -- Start Jetstress test...8/31/2006 10:37:45 PM -- Starting Stress test run...8/31/2006 10:37:45 PM -- Performance logging started.8/31/2006 10:37:45 PM -- Performance data will be saved to C:\Program Files\Jetstress\Stress_2006_8_31_22-37-43.blg.9/1/2006 10:36:46 PM -- Adding new data to the performance log file...9/1/2006 10:37:44 PM -- Performance logging stopped.9/1/2006 10:37:44 PM -- Stopping Jetstress...9/1/2006 10:38:16 PM -- Creating test report ...9/1/2006 10:38:46 PM -- Volume L: has 0.0099 for Avg. Disk sec/Read.9/1/2006 10:38:46 PM -- Volume K: has 0.0107 for Avg. Disk sec/Read.9/1/2006 10:38:46 PM -- Volume N: has 0.0099 for Avg. Disk sec/Read.9/1/2006 10:38:46 PM -- Volume M: has 0.0107 for Avg. Disk sec/Read.9/1/2006 10:38:46 PM -- Volume G: has 0.0010 for Avg. Disk sec/Write.9/1/2006 10:38:46 PM -- Volume G: has 0.0000 for Avg. Disk sec/Read.9/1/2006 10:38:46 PM -- Volume H: has 0.0010 for Avg. Disk sec/Write.9/1/2006 10:38:46 PM -- Volume H: has 0.0000 for Avg. Disk sec/Read.9/1/2006 10:38:46 PM -- Volume I: has 0.0010 for Avg. Disk sec/Write.9/1/2006 10:38:46 PM -- Volume I: has 0.0000 for Avg. Disk sec/Read.9/1/2006 10:38:46 PM -- Volume J: has 0.0010 for Avg. Disk sec/Write.9/1/2006 10:38:46 PM -- Volume J: has 0.0000 for Avg. Disk sec/Read.9/1/2006 10:38:46 PM -- Test has 0 Max Database Page Fault Stalls/sec.9/1/2006 10:38:46 PM -- Test has 0 Database Page Fault Stalls/sec samples higher than 0.9/1/2006 10:38:47 PM -- Performance logging started.
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 33
34
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Stress testing
9/1/2006 10:38:47 PM -- Performance data will be saved to C:\Program Files\Jetstress\DatabaseChecksum_2006_9_1_22-38-46.blg.9/1/2006 10:38:47 PM -- Checksum validation may take a while depending on the file sizes.9/1/2006 11:23:55 PM -- Database checksum in progress: Storage Group #1 (100%), Storage Group #2 (100%), Storage Group #3 (100%), and Storage Group #4 (100%).9/1/2006 11:23:55 PM -- Performance logging stopped.9/1/2006 11:23:55 PM -- Checksum is completed, please open C:\Program Files\Jetstress\DatabaseChecksum_2006_9_1_22-38-46.html for checksum result.
EXCH320-2 Stress statistics
The purpose of this test is to verify the storage configuration which the customer is planning to deploy. The test run has been successful, meaning the database read latency and log write latency are below 20ms; Database page fault stalls/sec is 0. However, Microsoft strongly recommends that you perform further validation of this storage solution (additional tasks listed below):
1. You should refer to the table below to determine if the actual disk IO (achieved IO) has exceeded the targeted IO (expected IO). If not, you may want to increase the thread count to increase the load, provided that the disk latency will not exceed the threshold.
2. You need to confirm whether the storage solution has synchronous replication as part of the implementation. If the solution does not utilize synchronous replication, then you should check for the database write latency, the desired value should be under 20 ms. (Please refer to http://support.microsoft.com/?kbid=895847 for synchronous replication definitions.)
3. Please check the status pane in the Jetstress window, to make sure that no errors were logged during the database checksum validation.
Planned disk subsystem profile:
Total test database sizeProduction
data sizeTotal number of
databases Expected I/OAchieved
I/O
622.31 GB (based on the attached database)
(n/a) 24 (4 storage(s) * 6 database(s))
4000.00 (4000 mailboxes of 1.00 IOPS)
4491.71
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Detected JetstressUI version: 6.5.7830.0Detected operating system: Microsoft Windows Server 2003 R2 (5.2.3790.0) Service Pack 1Detected ESE.dll version: 6.5.7638.2Detected ESEPERF.dll version: 6.5.7638.1
8/31/2006 10:37:39 PM -- Validating input parameters, it may take a few minutes...8/31/2006 10:37:39 PM -- Attaching databases ... (it may take a few minutes if the databases are in dirty shutdown state)8/31/2006 10:37:43 PM -- Loading performance counters...8/31/2006 10:37:43 PM -- Instance2760.1: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 10:37:43 PM -- Instance2760.2: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 10:37:43 PM -- Instance2760.3: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 10:37:43 PM -- Instance2760.4: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 10:37:43 PM -- Start Jetstress test...8/31/2006 10:37:45 PM -- Starting Stress test run...
Counter Average Minimum Maximum
% Processor Time 5.922 4.322 7.226
Available MBytes 13859.13 13841.00 14524.00
Free System Page Table Entries 14799.00 14799.00 14799.00
Pages/Sec 2.628 0.000 3747.52
Pool Nonpaged Bytes 30975150.34 30916608.00 31080448.00
Pool Paged Bytes 20605757.73 18944000.00 22958080.00
Database Page Fault Stalls/sec 0.000 0.000 0.000
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Stress testing
8/31/2006 10:37:45 PM -- Performance logging started.8/31/2006 10:37:45 PM -- Performance data will be saved to C:\Program Files\Jetstress\Stress_2006_8_31_22-37-43.blg.9/1/2006 10:36:46 PM -- Adding new data to the performance log file...9/1/2006 10:37:44 PM -- Performance logging stopped.9/1/2006 10:37:44 PM -- Stopping Jetstress...9/1/2006 10:38:16 PM -- Creating test report ...9/1/2006 10:38:46 PM -- Volume L: has 0.0099 for Avg. Disk sec/Read.9/1/2006 10:38:46 PM -- Volume K: has 0.0107 for Avg. Disk sec/Read.9/1/2006 10:38:46 PM -- Volume N: has 0.0099 for Avg. Disk sec/Read.9/1/2006 10:38:46 PM -- Volume M: has 0.0107 for Avg. Disk sec/Read.9/1/2006 10:38:46 PM -- Volume G: has 0.0010 for Avg. Disk sec/Write.9/1/2006 10:38:46 PM -- Volume G: has 0.0000 for Avg. Disk sec/Read.9/1/2006 10:38:46 PM -- Volume H: has 0.0010 for Avg. Disk sec/Write.9/1/2006 10:38:46 PM -- Volume H: has 0.0000 for Avg. Disk sec/Read.9/1/2006 10:38:46 PM -- Volume I: has 0.0010 for Avg. Disk sec/Write.9/1/2006 10:38:46 PM -- Volume I: has 0.0000 for Avg. Disk sec/Read.9/1/2006 10:38:46 PM -- Volume J: has 0.0010 for Avg. Disk sec/Write.9/1/2006 10:38:46 PM -- Volume J: has 0.0000 for Avg. Disk sec/Read.9/1/2006 10:38:46 PM -- Test has 0 Max Database Page Fault Stalls/sec.9/1/2006 10:38:46 PM -- Test has 0 Database Page Fault Stalls/sec samples higher than 0.
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 37
38
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Performance tests
Performance tests
EXCH320-1 Database checksum statistics
The following section provides a quick overview of the checksum statistics for EXCH320-1.
Detected JetstressUI version: 6.5.7830.0Detected operating system: Microsoft Windows Server 2003 R2 (5.2.3790.0) Service Pack 1Detected ESE.dll version: 6.5.7638.2Detected ESEPERF.dll version: 6.5.7638.1
8/30/2006 11:03:56 PM -- Validating input parameters, it may take a few minutes...8/30/2006 11:54:12 PM -- Inserting records: 10286047 records have been inserted. Database creation process has completed 100%.8/30/2006 11:54:12 PM -- Database creation has completed and the test database file size is 26140 MB (with an approximate 66% overhead).8/31/2006 3:54:34 AM -- Duplicating 24 databases: 25.53 GB of 25.53 GB is duplicated (100.00% complete).8/31/2006 3:54:34 AM -- Attaching databases ... (it may take a few minutes if the databases are in dirty shutdown state)8/31/2006 3:54:37 AM -- Loading performance counters...8/31/2006 3:54:37 AM -- Instance3936.1: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 3:54:37 AM -- Instance3936.2: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)
Counter Average Minimum Maximum
% Processor Time 9.238 0.000 13.65
Available MBytes 14551.87 14547.00 14600.00
Free System Page Table Entries 13856.61 13857.00 13857.00
Pages/Sec 0.000 0.000 0.000
Pool Nonpaged Bytes 36689150.00 36679680.00 36716540.00
Pool Paged Bytes 77381210.00 75952130.00 77393920.00
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Performance tests
8/31/2006 3:54:37 AM -- Instance3936.3: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 3:54:37 AM -- Instance3936.4: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 3:54:37 AM -- Start Jetstress test...8/31/2006 3:54:38 AM -- Starting Performance test run...8/31/2006 3:54:39 AM -- Performance logging started.8/31/2006 3:54:39 AM -- Performance data will be saved to C:\Program Files\Jetstress\Performance_2006_8_31_3-54-37.blg.8/31/2006 5:54:32 AM -- Adding new data to the performance log file...8/31/2006 5:54:40 AM -- Performance logging stopped.8/31/2006 5:54:40 AM -- Stopping Jetstress...8/31/2006 5:56:01 AM -- Creating test report ...8/31/2006 5:56:05 AM -- Volume L: has 0.0114 for Avg. Disk sec/Read.8/31/2006 5:56:05 AM -- Volume K: has 0.0105 for Avg. Disk sec/Read.8/31/2006 5:56:05 AM -- Volume N: has 0.0108 for Avg. Disk sec/Read.8/31/2006 5:56:05 AM -- Volume M: has 0.0101 for Avg. Disk sec/Read.8/31/2006 5:56:05 AM -- Volume G: has 0.0011 for Avg. Disk sec/Write.8/31/2006 5:56:05 AM -- Volume G: has 0.0000 for Avg. Disk sec/Read.8/31/2006 5:56:05 AM -- Volume H: has 0.0012 for Avg. Disk sec/Write.8/31/2006 5:56:05 AM -- Volume H: has 0.0000 for Avg. Disk sec/Read.8/31/2006 5:56:05 AM -- Volume I: has 0.0012 for Avg. Disk sec/Write.8/31/2006 5:56:05 AM -- Volume I: has 0.0000 for Avg. Disk sec/Read.8/31/2006 5:56:05 AM -- Volume J: has 0.0012 for Avg. Disk sec/Write.8/31/2006 5:56:05 AM -- Volume J: has 0.0000 for Avg. Disk sec/Read.8/31/2006 5:56:05 AM -- Test has 0 Max Database Page Fault Stalls/sec.8/31/2006 5:56:05 AM -- Test has 0 Database Page Fault Stalls/sec samples higher than 0.8/31/2006 5:56:06 AM -- Performance logging started.8/31/2006 5:56:06 AM -- Performance data will be saved to C:\Program Files\Jetstress\DatabaseChecksum_2006_8_31_5-56-5.blg.8/31/2006 5:56:06 AM -- Checksum validation may take a while depending on the file sizes.8/31/2006 6:29:33 AM -- Database checksum in progress: Storage Group #1 (100%), Storage Group #2 (100%), Storage Group #3 (100%), and Storage Group #4 (100%).8/31/2006 6:29:33 AM -- Performance logging stopped.8/31/2006 6:29:33 AM -- Checksum is completed, please open C:\Program Files\Jetstress\DatabaseChecksum_2006_8_31_5-56-5.html for checksum result.
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 41
42
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Performance tests
EXCH320-1 Performance statistics
The following section provides a quick overview of the performance statistics for EXCH320-1
The purpose of this test is to verify the storage configuration which the customer is planning to deploy. The test run has been successful, meaning the database read latency and log write latency are below 20ms; Database page fault stalls/sec is 0. However, Microsoft strongly recommends that you perform further validation of this storage solution (additional tasks listed below):
1. You should refer to the table below to determine if the actual disk IO (achieved IO) has exceeded the targeted IO (expected IO). If not, you may want to increase the thread count to increase the load, provided that the disk latency will not exceed the threshold.
2. You need to confirm whether the storage solution has synchronous replication as part of the implementation. If the solution does not utilize synchronous replication, then you should check for the database write latency, the desired value should be under 20 ms. (Please refer to http://support.microsoft.com/?kbid=895847 for synchronous replication definitions.)
3. Please check the status pane in the Jetstress window, to make sure that no errors were logged during the database checksum validation.
Avg. Disk sec/Write Disk Reads/sec Disk Writes/sec Avg. Disk Bytes/Write
Data (L:) 0.011 0.003 695.21 313.85 (n/a)
Data (K:) 0.011 0.003 752.64 341.08 (n/a)
Data (N:) 0.011 0.004 731.77 331.09 (n/a)
Data (M:) 0.010 0.004 781.34 355.54 (n/a)
Log (G:) 0.000 0.001 0.000 73.43 7424.16
Log (H:) 0.000 0.001 0.000 68.68 7347.69
Log (I:) 0.000 0.001 0.000 75.86 7474.25
Log (J:) 0.000 0.001 0.000 71.90 7357.94
Counter Average Minimum Maximum
% Processor Time 5.922 2.937 7.684
Available MBytes 13679.30 13674.00 14329.00
Free System Page Table Entries 13857.00 13857.00 13857.00
Pages/Sec 0.001 0.000 0.133
Pool Nonpaged Bytes 36758017.07 36757504.00 36777984.00
Pool Paged Bytes 77553150.93 76513280.00 77565952.00
Database Page Fault Stalls/sec 0.000 0.000 0.000
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 43
44
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Performance tests
Detected operating system: Microsoft Windows Server 2003 R2 (5.2.3790.0) Service Pack 1Detected ESE.dll version: 6.5.7638.2Detected ESEPERF.dll version: 6.5.7638.1
8/30/2006 11:03:56 PM -- Validating input parameters, it may take a few minutes...8/30/2006 11:54:12 PM -- Inserting records: 10286047 records have been inserted. Database creation process has completed 100%.8/30/2006 11:54:12 PM -- Database creation has completed and the test database file size is 26140 MB (with an approximate 66% overhead).8/31/2006 3:54:34 AM -- Duplicating 24 databases: 25.53 GB of 25.53 GB is duplicated (100.00% complete).8/31/2006 3:54:34 AM -- Attaching databases ... (it may take a few minutes if the databases are in dirty shutdown state)8/31/2006 3:54:37 AM -- Loading performance counters...8/31/2006 3:54:37 AM -- Instance3936.1: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 3:54:37 AM -- Instance3936.2: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 3:54:37 AM -- Instance3936.3: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 3:54:37 AM -- Instance3936.4: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 3:54:37 AM -- Start Jetstress test...8/31/2006 3:54:38 AM -- Starting Performance test run...8/31/2006 3:54:39 AM -- Performance logging started.8/31/2006 3:54:39 AM -- Performance data will be saved to C:\Program Files\Jetstress\Performance_2006_8_31_3-54-37.blg.8/31/2006 5:54:32 AM -- Adding new data to the performance log file...8/31/2006 5:54:40 AM -- Performance logging stopped.8/31/2006 5:54:40 AM -- Stopping Jetstress...8/31/2006 5:56:01 AM -- Creating test report ...8/31/2006 5:56:05 AM -- Volume L: has 0.0114 for Avg. Disk sec/Read.8/31/2006 5:56:05 AM -- Volume K: has 0.0105 for Avg. Disk sec/Read.8/31/2006 5:56:05 AM -- Volume N: has 0.0108 for Avg. Disk sec/Read.8/31/2006 5:56:05 AM -- Volume M: has 0.0101 for Avg. Disk sec/Read.8/31/2006 5:56:05 AM -- Volume G: has 0.0011 for Avg. Disk sec/Write.8/31/2006 5:56:05 AM -- Volume G: has 0.0000 for Avg. Disk sec/Read.8/31/2006 5:56:05 AM -- Volume H: has 0.0012 for Avg. Disk sec/Write.8/31/2006 5:56:05 AM -- Volume H: has 0.0000 for Avg. Disk sec/Read.8/31/2006 5:56:05 AM -- Volume I: has 0.0012 for Avg. Disk sec/Write.8/31/2006 5:56:05 AM -- Volume I: has 0.0000 for Avg. Disk sec/Read.
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Performance tests
8/31/2006 5:56:05 AM -- Volume J: has 0.0012 for Avg. Disk sec/Write.8/31/2006 5:56:05 AM -- Volume J: has 0.0000 for Avg. Disk sec/Read.8/31/2006 5:56:05 AM -- Test has 0 Max Database Page Fault Stalls/sec.8/31/2006 5:56:05 AM -- Test has 0 Database Page Fault Stalls/sec samples higher than 0.
EXCH320-2 Database checksum statistics
The following section provides a quick overview of the checksum statistics for EXCH320-2.
Detected JetstressUI version: 6.5.7830.0Detected operating system: Microsoft Windows Server 2003 R2 (5.2.3790.0) Service Pack 1Detected ESE.dll version: 6.5.7638.2Detected ESEPERF.dll version: 6.5.7638.1
8/30/2006 11:02:56 PM -- Validating input parameters, it may take a few
Storage Volume
Avg. Disk sec/Read
Avg. Disk sec/Write Disk Reads/sec Disk Writes/sec Total Seconds
K: 0.342 0.000 808.97 0.000 3112.22
L: 0.342 0.000 809.01 0.001 3113.15
M: 0.342 0.000 808.30 0.002 3113.52
N: 0.342 0.001 809.49 0.003 3111.19
Counter Average Minimum Maximum
% Processor Time 5.466 0.000 12.11
Available MBytes 14747.44 14744.00 14780.00
Free System Page Table Entries 15120.00 15120.00 15120.00
Pages/Sec 0.000 0.000 0.000
Pool Nonpaged Bytes 31307030.00 31133700.00 31461380.00
Pool Paged Bytes 27701220.00 26308610.00 27742210.00
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 47
48
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Performance tests
minutes...8/30/2006 11:51:41 PM -- Inserting records: 10286047 records have been inserted. Database creation process has completed 100%.8/30/2006 11:51:41 PM -- Database creation has completed and the test database file size is 26140 MB (with an approximate 66% overhead).8/31/2006 3:51:08 AM -- Duplicating 24 databases: 25.53 GB of 25.53 GB is duplicated (100.00% complete).8/31/2006 3:51:08 AM -- Attaching databases ... (it may take a few minutes if the databases are in dirty shutdown state)8/31/2006 3:51:11 AM -- Loading performance counters...8/31/2006 3:51:11 AM -- Instance1836.1: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 3:51:11 AM -- Instance1836.2: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 3:51:11 AM -- Instance1836.3: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 3:51:11 AM -- Instance1836.4: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 3:51:11 AM -- Start Jetstress test...8/31/2006 3:51:12 AM -- Starting Performance test run...8/31/2006 3:51:13 AM -- Performance logging started.8/31/2006 3:51:13 AM -- Performance data will be saved to C:\Program Files\Jetstress\Performance_2006_8_31_3-51-11.blg.8/31/2006 5:50:58 AM -- Adding new data to the performance log file...8/31/2006 5:51:12 AM -- Performance logging stopped.8/31/2006 5:51:12 AM -- Stopping Jetstress...8/31/2006 5:51:46 AM -- Creating test report ...8/31/2006 5:51:49 AM -- Volume L: has 0.0099 for Avg. Disk sec/Read.8/31/2006 5:51:49 AM -- Volume K: has 0.0107 for Avg. Disk sec/Read.8/31/2006 5:51:49 AM -- Volume N: has 0.0099 for Avg. Disk sec/Read.8/31/2006 5:51:49 AM -- Volume M: has 0.0107 for Avg. Disk sec/Read.8/31/2006 5:51:49 AM -- Volume G: has 0.0010 for Avg. Disk sec/Write.8/31/2006 5:51:49 AM -- Volume G: has 0.0000 for Avg. Disk sec/Read.8/31/2006 5:51:49 AM -- Volume H: has 0.0010 for Avg. Disk sec/Write.8/31/2006 5:51:49 AM -- Volume H: has 0.0000 for Avg. Disk sec/Read.8/31/2006 5:51:49 AM -- Volume I: has 0.0010 for Avg. Disk sec/Write.8/31/2006 5:51:49 AM -- Volume I: has 0.0000 for Avg. Disk sec/Read.8/31/2006 5:51:49 AM -- Volume J: has 0.0010 for Avg. Disk sec/Write.8/31/2006 5:51:49 AM -- Volume J: has 0.0000 for Avg. Disk sec/Read.8/31/2006 5:51:49 AM -- Test has 0 Max Database Page Fault Stalls/sec.8/31/2006 5:51:49 AM -- Test has 0 Database Page Fault Stalls/sec samples higher than 0.8/31/2006 5:51:50 AM -- Performance logging started.
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Performance tests
8/31/2006 5:51:50 AM -- Performance data will be saved to C:\Program Files\Jetstress\DatabaseChecksum_2006_8_31_5-51-50.blg.8/31/2006 5:51:50 AM -- Checksum validation may take a while depending on the file sizes.8/31/2006 6:43:44 AM -- Database checksum in progress: Storage Group #1 (100%), Storage Group #2 (100%), Storage Group #3 (100%), and Storage Group #4 (100%).8/31/2006 6:43:44 AM -- Performance logging stopped.8/31/2006 6:43:44 AM -- Checksum is completed, please open C:\Program Files\Jetstress\DatabaseChecksum_2006_8_31_5-51-50.html for checksum result.
EXCH320-2 Performance statistics
The following section provides a quick overview of the performance statistics for EXCH320-2
The purpose of this test is to verify the storage configuration which the customer is planning to deploy. The test run has been successful, meaning the database read latency and log write latency are below 20ms; Database page fault stalls/sec is 0. However, Microsoft strongly recommends that you perform further validation of this storage solution (additional tasks listed below):
1. You should refer to the table below to determine if the actual disk IO (achieved IO) has exceeded the targeted IO (expected IO). If not, you may want to increase the thread count to increase the load, provided that the disk latency will not exceed the threshold.
2. You need to confirm whether the storage solution has synchronous replication as part of the implementation. If the solution does not utilize synchronous replication, then you should check for the database write latency, the desired value should be under 20 ms. (Please refer to http://support.microsoft.com/?kbid=895847 for synchronous replication definitions.)
3. Please check the status pane in the Jetstress window, to make sure that no errors were logged during the database checksum validation.
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 49
Detected JetstressUI version: 6.5.7830.0Detected operating system: Microsoft Windows Server 2003 R2 (5.2.3790.0) Service Pack 1Detected ESE.dll version: 6.5.7638.2Detected ESEPERF.dll version: 6.5.7638.1
8/30/2006 11:02:56 PM -- Validating input parameters, it may take a few minutes...8/30/2006 11:51:41 PM -- Inserting records: 10286047 records have been inserted. Database creation process has completed 100%.8/30/2006 11:51:41 PM -- Database creation has completed and the test database file size is 26140 MB (with an approximate 66% overhead).8/31/2006 3:51:08 AM -- Duplicating 24 databases: 25.53 GB of 25.53 GB is duplicated (100.00% complete).8/31/2006 3:51:08 AM -- Attaching databases ... (it may take a few minutes if the databases are in dirty shutdown state)8/31/2006 3:51:11 AM -- Loading performance counters...8/31/2006 3:51:11 AM -- Instance1836.1: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 3:51:11 AM -- Instance1836.2: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)
Counter Average Minimum Maximum
% Processor Time 5.976 4.567 7.679
Available MBytes 13872.72 13867.00 14530.00
Free System Page Table Entries 15120.00 15120.00 15120.00
Pages/Sec 0.002 0.000 0.266
Pool Nonpaged Bytes 29224712.02 28573696.00 29466624.00
Pool Paged Bytes 27815337.42 26873856.00 27852800.00
Database Page Fault Stalls/sec 0.000 0.000 0.000
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 51
52
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Performance tests
8/31/2006 3:51:11 AM -- Instance1836.3: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 3:51:11 AM -- Instance1836.4: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)8/31/2006 3:51:11 AM -- Start Jetstress test...8/31/2006 3:51:12 AM -- Starting Performance test run...8/31/2006 3:51:13 AM -- Performance logging started.8/31/2006 3:51:13 AM -- Performance data will be saved to C:\Program Files\Jetstress\Performance_2006_8_31_3-51-11.blg.8/31/2006 5:50:58 AM -- Adding new data to the performance log file...8/31/2006 5:51:12 AM -- Performance logging stopped.8/31/2006 5:51:12 AM -- Stopping Jetstress...8/31/2006 5:51:46 AM -- Creating test report ...8/31/2006 5:51:49 AM -- Volume L: has 0.0099 for Avg. Disk sec/Read.8/31/2006 5:51:49 AM -- Volume K: has 0.0107 for Avg. Disk sec/Read.8/31/2006 5:51:49 AM -- Volume N: has 0.0099 for Avg. Disk sec/Read.8/31/2006 5:51:49 AM -- Volume M: has 0.0107 for Avg. Disk sec/Read.8/31/2006 5:51:49 AM -- Volume G: has 0.0010 for Avg. Disk sec/Write.8/31/2006 5:51:49 AM -- Volume G: has 0.0000 for Avg. Disk sec/Read.8/31/2006 5:51:49 AM -- Volume H: has 0.0010 for Avg. Disk sec/Write.8/31/2006 5:51:49 AM -- Volume H: has 0.0000 for Avg. Disk sec/Read.8/31/2006 5:51:49 AM -- Volume I: has 0.0010 for Avg. Disk sec/Write.8/31/2006 5:51:49 AM -- Volume I: has 0.0000 for Avg. Disk sec/Read.8/31/2006 5:51:49 AM -- Volume J: has 0.0010 for Avg. Disk sec/Write.8/31/2006 5:51:49 AM -- Volume J: has 0.0000 for Avg. Disk sec/Read.8/31/2006 5:51:49 AM -- Test has 0 Max Database Page Fault Stalls/sec.8/31/2006 5:51:49 AM -- Test has 0 Database Page Fault Stalls/sec samples higher than 0.
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Backup
Backup
EXCH320-1 Backup database checksum statistics
The following section provides a quick overview of the backup database checksum statistics for EXCH320-1.
Detected JetstressUI version: 6.5.7830.0Detected operating system: Microsoft Windows Server 2003 R2 (5.2.3790.0) Service Pack 1Detected ESE.dll version: 6.5.7638.2Detected ESEPERF.dll version: 6.5.7638.1
9/5/2006 12:19:18 PM -- Validating input parameters, it may take a few minutes...9/5/2006 12:19:19 PM -- Attaching databases ... (it may take a few minutes if the databases are in dirty shutdown state)9/5/2006 12:19:24 PM -- Loading performance counters...9/5/2006 12:19:24 PM -- Instance4092.1: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:24 PM -- Instance4092.2: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:24 PM -- Instance4092.3: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:24 PM -- Instance4092.4: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:24 PM -- Start Jetstress test...9/5/2006 12:19:26 PM -- Starting StreamingBackup test run...
Counter Average Minimum Maximum
% Processor Time 9.91 0.000 19.81
Available MBytes 14717.09 14691.00 14776.00
Free System Page Table Entries 14580.00 14580.00 14580.00
Pages/Sec 0.003 0.000 5.997
Pool Nonpaged Bytes 33525530.00 33382400.00 33611780.00
Pool Paged Bytes 37262460.00 35639300.00 37621760.00
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 55
56
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Backup
9/5/2006 12:19:27 PM -- Performance logging started.9/5/2006 12:19:27 PM -- Performance data will be saved to C:\Program Files\Jetstress\Performance_LogGeneration_2006_9_5_12-19-24.blg.9/5/2006 12:57:12 PM -- Adding new data to the performance log file...9/5/2006 12:57:27 PM -- Performance logging stopped.9/5/2006 12:57:27 PM -- Stopping Jetstress...9/5/2006 12:57:59 PM -- Creating test report ...9/5/2006 12:58:01 PM -- Volume L: has 0.0117 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume K: has 0.0104 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume N: has 0.0108 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume M: has 0.0100 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume G: has 0.0010 for Avg. Disk sec/Write.9/5/2006 12:58:01 PM -- Volume G: has 0.0001 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume H: has 0.0010 for Avg. Disk sec/Write.9/5/2006 12:58:01 PM -- Volume H: has 0.0001 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume I: has 0.0009 for Avg. Disk sec/Write.9/5/2006 12:58:01 PM -- Volume I: has 0.0001 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume J: has 0.0009 for Avg. Disk sec/Write.9/5/2006 12:58:01 PM -- Volume J: has 0.0001 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Test has 0 Max Database Page Fault Stalls/sec.9/5/2006 12:58:01 PM -- Test has 0 Database Page Fault Stalls/sec samples higher than 0.9/5/2006 12:58:01 PM -- Soft recovery may take a while depending on the number of log files.9/5/2006 12:58:02 PM -- Performance logging started.9/5/2006 12:58:02 PM -- Performance data will be saved to C:\Program Files\Jetstress\SoftRecovery_2006_9_5_12-58-1.blg.9/5/2006 1:43:22 PM -- Adding new data to the performance log file...9/5/2006 1:43:25 PM -- Performance logging stopped.9/5/2006 1:43:25 PM -- Soft recovery is completed, please open C:\Program Files\Jetstress\SoftRecovery_2006_9_5_12-58-1.html for soft recovery result.9/5/2006 1:43:26 PM -- Performance logging started.9/5/2006 1:43:26 PM -- Performance data will be saved to C:\Program Files\Jetstress\DatabaseChecksum_2006_9_5_13-43-25.blg.9/5/2006 1:43:26 PM -- Checksum validation may take a while depending on the file sizes.9/5/2006 2:17:43 PM -- Database checksum in progress: Storage Group #1 (100%), Storage Group #2 (100%), Storage Group #3 (100%), and Storage Group #4 (100%).9/5/2006 2:17:43 PM -- Performance logging stopped.9/5/2006 2:17:43 PM -- Checksum is completed, please open C:\Program
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Backup
Files\Jetstress\DatabaseChecksum_2006_9_5_13-43-25.html for checksum result.
EXCH320-1 Performance statistics
The following section provides a quick overview of the performance statistics for EXCH320-1.
The purpose of this test is to verify the storage configuration which the customer is planning to deploy. The test run has been successful, meaning the database read latency and log write latency are below 20ms; Database page fault stalls/sec is 0. However, Microsoft strongly recommends that you perform further validation of this storage solution (additional tasks listed below):
1. You should refer to the table below to determine if the actual disk IO (achieved IO) has exceeded the targeted IO (expected IO). If not, you may want to increase the thread count to increase the load, provided that the disk latency will not exceed the threshold.
2. You need to confirm whether the storage solution has synchronous replication as part of the implementation. If the solution does not utilize synchronous replication, then you should check for the database write latency, the desired value should be under 20 ms. (Please refer to http://support.microsoft.com/?kbid=895847 for synchronous replication definitions.)
3. Please check the status pane in the Jetstress window, to make sure that no errors were logged during the database checksum validation.
Planned disk subsystem profile:
Total test database sizeProduction
data sizeTotal number of
databases Expected I/OAchieved
I/O
659.74 GB (based on the attached database)
(n/a) 24 (4 storage(s) * 6 database(s))
4000.00 (4000 mailboxes of 1.00 IOPS)
4316.65
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 57
Detected JetstressUI version: 6.5.7830.0Detected operating system: Microsoft Windows Server 2003 R2 (5.2.3790.0) Service Pack 1Detected ESE.dll version: 6.5.7638.2Detected ESEPERF.dll version: 6.5.7638.1
9/5/2006 12:19:18 PM -- Validating input parameters, it may take a few minutes...9/5/2006 12:19:19 PM -- Attaching databases ... (it may take a few minutes if the databases are in dirty shutdown state)9/5/2006 12:19:24 PM -- Loading performance counters...9/5/2006 12:19:24 PM -- Instance4092.1: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:24 PM -- Instance4092.2: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:24 PM -- Instance4092.3: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:24 PM -- Instance4092.4: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:24 PM -- Start Jetstress test...
Counter Average Minimum Maximum
% Processor Time 5.721 4.395 8.336
Available MBytes 13862.69 13852.00 14510.00
Free System Page Table Entries 14552.00 14552.00 14552.00
Pages/Sec 0.049 0.000 0.531
Pool Nonpaged Bytes 28762627.39 27201536.00 29122560.00
Pool Paged Bytes 37295544.79 36302848.00 37335040.00
Database Page Fault Stalls/sec 0.000 0.000 0.000
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 59
60
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Backup
9/5/2006 12:19:26 PM -- Starting StreamingBackup test run...9/5/2006 12:19:27 PM -- Performance logging started.9/5/2006 12:19:27 PM -- Performance data will be saved to C:\Program Files\Jetstress\Performance_LogGeneration_2006_9_5_12-19-24.blg.9/5/2006 12:57:12 PM -- Adding new data to the performance log file...9/5/2006 12:57:27 PM -- Performance logging stopped.9/5/2006 12:57:27 PM -- Stopping Jetstress...9/5/2006 12:57:59 PM -- Creating test report ...9/5/2006 12:58:01 PM -- Volume L: has 0.0117 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume K: has 0.0104 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume N: has 0.0108 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume M: has 0.0100 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume G: has 0.0010 for Avg. Disk sec/Write.9/5/2006 12:58:01 PM -- Volume G: has 0.0001 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume H: has 0.0010 for Avg. Disk sec/Write.9/5/2006 12:58:01 PM -- Volume H: has 0.0001 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume I: has 0.0009 for Avg. Disk sec/Write.9/5/2006 12:58:01 PM -- Volume I: has 0.0001 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume J: has 0.0009 for Avg. Disk sec/Write.9/5/2006 12:58:01 PM -- Volume J: has 0.0001 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Test has 0 Max Database Page Fault Stalls/sec.9/5/2006 12:58:01 PM -- Test has 0 Database Page Fault Stalls/sec samples higher than 0.
EXCH320-1 Log replay statistics
The following section provides a quick overview of the log replay statistics for 100 log files per storage group for EXCH320-1.
Detected JetstressUI version: 6.5.7830.0Detected operating system: Microsoft Windows Server 2003 R2 (5.2.3790.0) Service Pack 1Detected ESE.dll version: 6.5.7638.2Detected ESEPERF.dll version: 6.5.7638.1
9/5/2006 12:19:18 PM -- Validating input parameters, it may take a few minutes...9/5/2006 12:19:19 PM -- Attaching databases ... (it may take a few minutes if the databases are in dirty shutdown state)9/5/2006 12:19:24 PM -- Loading performance counters...9/5/2006 12:19:24 PM -- Instance4092.1: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:24 PM -- Instance4092.2: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:24 PM -- Instance4092.3: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:24 PM -- Instance4092.4: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:24 PM -- Start Jetstress test...9/5/2006 12:19:26 PM -- Starting StreamingBackup test run...
Counter Average Minimum Maximum
% Processor Time 1.619 0.000 10.84
Available MBytes 13844.27 13817.00 14752.00
Free System Page Table Entries 14573.09 14552.00 14580.00
Pages/Sec 0.026 0.000 10.00
Pool Nonpaged Bytes 33002050.00 30117890.00 33419260.00
Pool Paged Bytes 37135640.00 35688450.00 37314560.00
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 61
62
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Backup
9/5/2006 12:19:27 PM -- Performance logging started.9/5/2006 12:19:27 PM -- Performance data will be saved to C:\Program Files\Jetstress\Performance_LogGeneration_2006_9_5_12-19-24.blg.9/5/2006 12:57:12 PM -- Adding new data to the performance log file...9/5/2006 12:57:27 PM -- Performance logging stopped.9/5/2006 12:57:27 PM -- Stopping Jetstress...9/5/2006 12:57:59 PM -- Creating test report ...9/5/2006 12:58:01 PM -- Volume L: has 0.0117 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume K: has 0.0104 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume N: has 0.0108 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume M: has 0.0100 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume G: has 0.0010 for Avg. Disk sec/Write.9/5/2006 12:58:01 PM -- Volume G: has 0.0001 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume H: has 0.0010 for Avg. Disk sec/Write.9/5/2006 12:58:01 PM -- Volume H: has 0.0001 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume I: has 0.0009 for Avg. Disk sec/Write.9/5/2006 12:58:01 PM -- Volume I: has 0.0001 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume J: has 0.0009 for Avg. Disk sec/Write.9/5/2006 12:58:01 PM -- Volume J: has 0.0001 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Test has 0 Max Database Page Fault Stalls/sec.9/5/2006 12:58:01 PM -- Test has 0 Database Page Fault Stalls/sec samples higher than 0.9/5/2006 12:58:01 PM -- Soft recovery may take a while depending on the number of log files.9/5/2006 12:58:02 PM -- Performance logging started.9/5/2006 12:58:02 PM -- Performance data will be saved to C:\Program Files\Jetstress\SoftRecovery_2006_9_5_12-58-1.blg.9/5/2006 1:43:22 PM -- Adding new data to the performance log file...9/5/2006 1:43:25 PM -- Performance logging stopped.9/5/2006 1:43:25 PM -- Soft recovery is completed, please open C:\Program Files\Jetstress\SoftRecovery_2006_9_5_12-58-1.html for soft recovery result.
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Backup
EXCH320-2 Backup database checksum statistics
The following section provides a quick overview of the backup database checksum statistics for EXCH320-2.
Detected JetstressUI version: 6.5.7830.0Detected operating system: Microsoft Windows Server 2003 R2 (5.2.3790.0) Service Pack 1Detected ESE.dll version: 6.5.7638.2Detected ESEPERF.dll version: 6.5.7638.1
9/5/2006 12:19:34 PM -- Validating input parameters, it may take a few minutes...9/5/2006 12:19:34 PM -- Attaching databases ... (it may take a few minutes if the databases are in dirty shutdown state)9/5/2006 12:19:49 PM -- Loading performance counters...9/5/2006 12:19:49 PM -- Instance3316.1: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:49 PM -- Instance3316.2: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:49 PM -- Instance3316.3: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:49 PM -- Instance3316.4: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:49 PM -- Start Jetstress test...9/5/2006 12:19:51 PM -- Starting StreamingBackup test run...
Counter Average Minimum Maximum
% Processor Time 9.99 0.000 30.00
Available MBytes 14714.10 14685.00 14767.00
Free System Page Table Entries 15078.45 14991.00 15111.00
Pages/Sec 0.003 0.000 2.960
Pool Nonpaged Bytes 33623010.00 33570820.00 33705980.00
Pool Paged Bytes 23833260.00 22228990.00 24678400.00
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 65
66
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Backup
9/5/2006 12:19:51 PM -- Performance logging started.9/5/2006 12:19:51 PM -- Performance data will be saved to C:\Program Files\Jetstress\Performance_LogGeneration_2006_9_5_12-19-49.blg.9/5/2006 12:54:22 PM -- Adding new data to the performance log file...9/5/2006 12:54:36 PM -- Performance logging stopped.9/5/2006 12:54:36 PM -- Stopping Jetstress...9/5/2006 12:55:10 PM -- Creating test report ...9/5/2006 12:55:11 PM -- Volume L: has 0.0098 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume K: has 0.0107 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume N: has 0.0098 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume M: has 0.0105 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume G: has 0.0010 for Avg. Disk sec/Write.9/5/2006 12:55:11 PM -- Volume G: has 0.0004 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume H: has 0.0009 for Avg. Disk sec/Write.9/5/2006 12:55:11 PM -- Volume H: has 0.0001 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume I: has 0.0010 for Avg. Disk sec/Write.9/5/2006 12:55:11 PM -- Volume I: has 0.0001 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume J: has 0.0010 for Avg. Disk sec/Write.9/5/2006 12:55:11 PM -- Volume J: has 0.0004 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Test has 0 Max Database Page Fault Stalls/sec.9/5/2006 12:55:11 PM -- Test has 0 Database Page Fault Stalls/sec samples higher than 0.9/5/2006 12:55:11 PM -- Soft recovery may take a while depending on the number of log files.9/5/2006 12:55:12 PM -- Performance logging started.9/5/2006 12:55:12 PM -- Performance data will be saved to C:\Program Files\Jetstress\SoftRecovery_2006_9_5_12-55-11.blg.9/5/2006 1:08:36 PM -- Adding new data to the performance log file...9/5/2006 1:08:38 PM -- Performance logging stopped.9/5/2006 1:08:38 PM -- Soft recovery is completed, please open C:\Program Files\Jetstress\SoftRecovery_2006_9_5_12-55-11.html for soft recovery result.9/5/2006 1:08:39 PM -- Performance logging started.9/5/2006 1:08:39 PM -- Performance data will be saved to C:\Program Files\Jetstress\DatabaseChecksum_2006_9_5_13-8-38.blg.9/5/2006 1:08:39 PM -- Checksum validation may take a while depending on the file sizes.9/5/2006 1:43:06 PM -- Database checksum in progress: Storage Group #1 (100%), Storage Group #2 (100%), Storage Group #3 (100%), and Storage Group #4 (100%).9/5/2006 1:43:06 PM -- Performance logging stopped.9/5/2006 1:43:06 PM -- Checksum is completed, please open C:\Program
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Backup
Files\Jetstress\DatabaseChecksum_2006_9_5_13-8-38.html for checksum result.
EXCH320-2 Performance statistics
The following section provides a quick overview of the performance statistics for EXCH320-2.
The purpose of this test is to verify the storage configuration which the customer is planning to deploy. The test run has been successful, meaning the database read latency and log write latency are below 20ms; Database page fault stalls/sec is 0. However, Microsoft strongly recommends that you perform further validation of this storage solution (additional tasks listed below):
1. You should refer to the table below to determine if the actual disk IO (achieved IO) has exceeded the targeted IO (expected IO). If not, you may want to increase the thread count to increase the load, provided that the disk latency will not exceed the threshold.
2. You need to confirm whether the storage solution has synchronous replication as part of the implementation. If the solution does not utilize synchronous replication, then you should check for the database write latency, the desired value should be under 20 ms. (Please refer to http://support.microsoft.com/?kbid=895847 for synchronous replication definitions.)
3. Please check the status pane in the Jetstress window, to make sure that no errors were logged during the database checksum validation.
Planned disk subsystem profile:
Total test database sizeProduction
data sizeTotal number of
databases Expected I/OAchieved
I/O
658.73 GB (based on the attached database)
(n/a) 24 (4 storage(s) * 6 database(s))
4000.00 (4000 mailboxes of 1.00 IOPS)
4514.81
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 67
Detected JetstressUI version: 6.5.7830.0Detected operating system: Microsoft Windows Server 2003 R2 (5.2.3790.0) Service Pack 1Detected ESE.dll version: 6.5.7638.2Detected ESEPERF.dll version: 6.5.7638.1
9/5/2006 12:19:34 PM -- Validating input parameters, it may take a few minutes...9/5/2006 12:19:34 PM -- Attaching databases ... (it may take a few minutes if the databases are in dirty shutdown state)9/5/2006 12:19:49 PM -- Loading performance counters...9/5/2006 12:19:49 PM -- Instance3316.1: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:49 PM -- Instance3316.2: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:49 PM -- Instance3316.3: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:49 PM -- Instance3316.4: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:49 PM -- Start Jetstress test...
Counter Average Minimum Maximum
% Processor Time 5.861 4.400 8.363
Available MBytes 13853.91 13841.00 14501.00
Free System Page Table Entries 15111.00 15111.00 15111.00
Pages/Sec 0.047 0.000 0.267
Pool Nonpaged Bytes 29816268.06 29814784.00 29831168.00
Pool Paged Bytes 24129862.49 23224320.00 24145920.00
Database Page Fault Stalls/sec 0.000 0.000 0.000
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 69
70
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Backup
9/5/2006 12:19:51 PM -- Starting StreamingBackup test run...9/5/2006 12:19:51 PM -- Performance logging started.9/5/2006 12:19:51 PM -- Performance data will be saved to C:\Program Files\Jetstress\Performance_LogGeneration_2006_9_5_12-19-49.blg.9/5/2006 12:54:22 PM -- Adding new data to the performance log file...9/5/2006 12:54:36 PM -- Performance logging stopped.9/5/2006 12:54:36 PM -- Stopping Jetstress...9/5/2006 12:55:10 PM -- Creating test report ...9/5/2006 12:55:11 PM -- Volume L: has 0.0098 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume K: has 0.0107 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume N: has 0.0098 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume M: has 0.0105 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume G: has 0.0010 for Avg. Disk sec/Write.9/5/2006 12:55:11 PM -- Volume G: has 0.0004 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume H: has 0.0009 for Avg. Disk sec/Write.9/5/2006 12:55:11 PM -- Volume H: has 0.0001 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume I: has 0.0010 for Avg. Disk sec/Write.9/5/2006 12:55:11 PM -- Volume I: has 0.0001 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume J: has 0.0010 for Avg. Disk sec/Write.9/5/2006 12:55:11 PM -- Volume J: has 0.0004 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Test has 0 Max Database Page Fault Stalls/sec.9/5/2006 12:55:11 PM -- Test has 0 Database Page Fault Stalls/sec samples higher than 0.
EXCH320-2 Log replay statistics
The following section provides a quick overview of the log replay statistics for 100 log files per storage group for EXCH320-2.
Detected JetstressUI version: 6.5.7830.0Detected operating system: Microsoft Windows Server 2003 R2 (5.2.3790.0) Service Pack 1Detected ESE.dll version: 6.5.7638.2Detected ESEPERF.dll version: 6.5.7638.1
9/5/2006 12:19:34 PM -- Validating input parameters, it may take a few minutes...9/5/2006 12:19:34 PM -- Attaching databases ... (it may take a few minutes if the databases are in dirty shutdown state)9/5/2006 12:19:49 PM -- Loading performance counters...9/5/2006 12:19:49 PM -- Instance3316.1: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:49 PM -- Instance3316.2: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:49 PM -- Instance3316.3: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:49 PM -- Instance3316.4: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:49 PM -- Start Jetstress test...9/5/2006 12:19:51 PM -- Starting StreamingBackup test run...
Counter Average Minimum Maximum
% Processor Time 4.968 0.000 10.42
Available MBytes 13907.72 13812.00 14744.00
Free System Page Table Entries 15111.00 15111.00 15111.00
Pages/Sec 0.000 0.000 0.000
Pool Nonpaged Bytes 32131200.00 30064640.00 33587200.00
Pool Paged Bytes 23858300.00 22568960.00 24018940.00
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 71
72
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Backup
9/5/2006 12:19:51 PM -- Performance logging started.9/5/2006 12:19:51 PM -- Performance data will be saved to C:\Program Files\Jetstress\Performance_LogGeneration_2006_9_5_12-19-49.blg.9/5/2006 12:54:22 PM -- Adding new data to the performance log file...9/5/2006 12:54:36 PM -- Performance logging stopped.9/5/2006 12:54:36 PM -- Stopping Jetstress...9/5/2006 12:55:10 PM -- Creating test report ...9/5/2006 12:55:11 PM -- Volume L: has 0.0098 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume K: has 0.0107 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume N: has 0.0098 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume M: has 0.0105 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume G: has 0.0010 for Avg. Disk sec/Write.9/5/2006 12:55:11 PM -- Volume G: has 0.0004 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume H: has 0.0009 for Avg. Disk sec/Write.9/5/2006 12:55:11 PM -- Volume H: has 0.0001 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume I: has 0.0010 for Avg. Disk sec/Write.9/5/2006 12:55:11 PM -- Volume I: has 0.0001 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume J: has 0.0010 for Avg. Disk sec/Write.9/5/2006 12:55:11 PM -- Volume J: has 0.0004 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Test has 0 Max Database Page Fault Stalls/sec.9/5/2006 12:55:11 PM -- Test has 0 Database Page Fault Stalls/sec samples higher than 0.9/5/2006 12:55:11 PM -- Soft recovery may take a while depending on the number of log files.9/5/2006 12:55:12 PM -- Performance logging started.9/5/2006 12:55:12 PM -- Performance data will be saved to C:\Program Files\Jetstress\SoftRecovery_2006_9_5_12-55-11.blg.9/5/2006 1:08:36 PM -- Adding new data to the performance log file...9/5/2006 1:08:38 PM -- Performance logging stopped.9/5/2006 1:08:38 PM -- Soft recovery is completed, please open C:\Program Files\Jetstress\SoftRecovery_2006_9_5_12-55-11.html for soft recovery result.
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Backup-to-disk testing
Backup-to-disk testing
EXCH320-1 Streaming backup statistics
This test is to verify the storage configuration for a streaming backup operation for EXCH320-1.
This table reports the performance metrics of streaming backup for each storage group backed up.
This table reports the performance metrics of streaming backup for each database backed up.
Storage GroupStorage Group Size
(MB)Backup Time
(hh:mm:ss.msec) Average MB Backed Per Second
1 169112.05 02:33:07.50 18.41
2 168038.05 02:34:52.33 18.08
3 169511.05 02:30:21.84 18.79
4 168711.05 02:30:26.60 18.69
Storage Group Database Name Database Size (MB)
1
K:Jetstress.edb 28187.01
K:Jetstress1.edb 28177.01
K:Jetstress2.edb 28177.01
K:Jetstress3.edb 28188.01
K:Jetstress4.edb 28199.01
K:Jetstress5.edb 28184.01
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 73
74
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Backup-to-disk testing
Planned disk subsystem profile:
2
L:Jetstress.edb 28010.01
L:Jetstress1.edb 28006.01
L:Jetstress2.edb 28001.01
L:Jetstress3.edb 28006.01
L:Jetstress4.edb 28006.01
L:Jetstress5.edb 28009.01
3
M:Jetstress.edb 28259.01
M:Jetstress1.edb 28245.01
M:Jetstress2.edb 28244.01
M:Jetstress3.edb 28256.01
M:Jetstress4.edb 28254.01
M:Jetstress5.edb 28253.01
4
N:Jetstress.edb 28110.01
N:Jetstress1.edb 28137.01
N:Jetstress2.edb 28111.01
N:Jetstress3.edb 28110.01
N:Jetstress4.edb 28110.01
N:Jetstress5.edb 28133.01
Total test database sizeProduction
data sizeTotal number of
databases Expected I/OAchieved
I/O
659.74 GB (based on the attached database)
(n/a) 24 (4 storage(s) * 6 database(s))
4000.00 (4000 mailboxes of 1.00 IOPS)
1162.19
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Detected JetstressUI version: 6.5.7830.0Detected operating system: Microsoft Windows Server 2003 R2 (5.2.3790.0) Service Pack 1Detected ESE.dll version: 6.5.7638.2Detected ESEPERF.dll version: 6.5.7638.1
9/5/2006 12:19:18 PM -- Validating input parameters, it may take a few minutes...9/5/2006 12:19:19 PM -- Attaching databases ... (it may take a few minutes if the databases are in dirty shutdown state)9/5/2006 12:19:24 PM -- Loading performance counters...9/5/2006 12:19:24 PM -- Instance4092.1: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:24 PM -- Instance4092.2: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:24 PM -- Instance4092.3: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:24 PM -- Instance4092.4: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:24 PM -- Start Jetstress test...9/5/2006 12:19:26 PM -- Starting StreamingBackup test run...9/5/2006 12:19:27 PM -- Performance logging started.
Counter Average Minimum Maximum
% Processor Time 2.492 1.551 3.656
Available MBytes 13786.87 13730.00 14776.00
Free System Page Table Entries 14580.00 14580.00 14580.00
Pages/Sec 0.160 0.000 88.20
Pool Nonpaged Bytes 33525561.49 33218560.00 33947648.00
Pool Paged Bytes 38231289.80 36974592.00 38744064.00
Database Page Fault Stalls/sec 0.000 0.000 0.000
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Backup-to-disk testing
9/5/2006 12:19:27 PM -- Performance data will be saved to C:\Program Files\Jetstress\Performance_LogGeneration_2006_9_5_12-19-24.blg.9/5/2006 12:57:12 PM -- Adding new data to the performance log file...9/5/2006 12:57:27 PM -- Performance logging stopped.9/5/2006 12:57:27 PM -- Stopping Jetstress...9/5/2006 12:57:59 PM -- Creating test report ...9/5/2006 12:58:01 PM -- Volume L: has 0.0117 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume K: has 0.0104 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume N: has 0.0108 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume M: has 0.0100 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume G: has 0.0010 for Avg. Disk sec/Write.9/5/2006 12:58:01 PM -- Volume G: has 0.0001 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume H: has 0.0010 for Avg. Disk sec/Write.9/5/2006 12:58:01 PM -- Volume H: has 0.0001 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume I: has 0.0009 for Avg. Disk sec/Write.9/5/2006 12:58:01 PM -- Volume I: has 0.0001 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Volume J: has 0.0009 for Avg. Disk sec/Write.9/5/2006 12:58:01 PM -- Volume J: has 0.0001 for Avg. Disk sec/Read.9/5/2006 12:58:01 PM -- Test has 0 Max Database Page Fault Stalls/sec.9/5/2006 12:58:01 PM -- Test has 0 Database Page Fault Stalls/sec samples higher than 0.9/5/2006 12:58:01 PM -- Soft recovery may take a while depending on the number of log files.9/5/2006 12:58:02 PM -- Performance logging started.9/5/2006 12:58:02 PM -- Performance data will be saved to C:\Program Files\Jetstress\SoftRecovery_2006_9_5_12-58-1.blg.9/5/2006 1:43:22 PM -- Adding new data to the performance log file...9/5/2006 1:43:25 PM -- Performance logging stopped.9/5/2006 1:43:25 PM -- Soft recovery is completed, please open C:\Program Files\Jetstress\SoftRecovery_2006_9_5_12-58-1.html for soft recovery result.9/5/2006 1:43:26 PM -- Performance logging started.9/5/2006 1:43:26 PM -- Performance data will be saved to C:\Program Files\Jetstress\DatabaseChecksum_2006_9_5_13-43-25.blg.9/5/2006 1:43:26 PM -- Checksum validation may take a while depending on the file sizes.9/5/2006 2:17:43 PM -- Database checksum in progress: Storage Group #1 (100%), Storage Group #2 (100%), Storage Group #3 (100%), and Storage Group #4 (100%).9/5/2006 2:17:43 PM -- Performance logging stopped.9/5/2006 2:17:43 PM -- Checksum is completed, please open C:\Program Files\Jetstress\DatabaseChecksum_2006_9_5_13-43-25.html for checksum result.
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 77
78
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Backup-to-disk testing
9/5/2006 2:17:45 PM -- Performance logging started.9/5/2006 2:17:45 PM -- Performance data will be saved to C:\Program Files\Jetstress\LogChecksum_2006_9_5_14-17-43.blg.9/5/2006 2:17:45 PM -- Checksum validation may take a while depending on the file sizes.9/5/2006 2:19:43 PM -- Log checksum in progress: (100 files(s) passed), (100 files(s) passed), (100 files(s) passed), and (100 files(s) passed).9/5/2006 2:19:43 PM -- Performance logging stopped.9/5/2006 2:19:43 PM -- Storage Groups being Backed up... The Backup Time may take hours depending on the size of the Storage Group.9/5/2006 2:26:10 PM -- Performance logging started.9/5/2006 2:26:10 PM -- Performance data will be saved to C:\Program Files\Jetstress\Backup_To_Disk_2006_9_5_14-19-43.blg.9/5/2006 2:26:10 PM -- Loading performance counters...9/5/2006 5:00:56 PM -- Adding new data to the performance log file...9/5/2006 5:00:58 PM -- Backup Complete!9/5/2006 5:01:00 PM -- Performance logging stopped.9/5/2006 5:01:00 PM -- Creating test report ...
EXCH320-2 Streaming backup statistics
This test is to verify the storage configuration for a streaming backup operation for EXCH320-2.
This table reports the performance metrics of streaming backup for each storage group backed up.
Storage GroupStorage Group Size
(MB)Backup Time
(hh:mm:ss.msec) Average MB Backed Per Second
1 168874.05 02:37:17.09 17.89
2 169705.05 02:35:25.01 18.20
3 168860.05 02:33:52.87 18.29
4 169717.05 02:33:11.87 18.46
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Backup-to-disk testing
This table reports the performance metrics of streaming backup for each database backed up.
Storage Group Database Name Database Size (MB)
1
K:Jetstress.edb 28141.01
K:Jetstress1.edb 28148.01
K:Jetstress2.edb 28142.01
K:Jetstress3.edb 28142.01
K:Jetstress4.edb 28150.01
K:Jetstress5.edb 28151.01
2
L:Jetstress.edb 28282.01
L:Jetstress1.edb 28286.01
L:Jetstress2.edb 28280.01
L:Jetstress3.edb 28283.01
L:Jetstress4.edb 28286.01
L:Jetstress5.edb 28288.01
3
M:Jetstress.edb 28149.01
M:Jetstress1.edb 28149.01
M:Jetstress2.edb 28136.01
M:Jetstress3.edb 28134.01
M:Jetstress4.edb 28150.01
M:Jetstress5.edb 28142.01
4
N:Jetstress.edb 28301.01
N:Jetstress1.edb 28286.01
N:Jetstress2.edb 28261.01
N:Jetstress3.edb 28295.01
N:Jetstress4.edb 28293.01
N:Jetstress5.edb 28281.01
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 79
80
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Detected JetstressUI version: 6.5.7830.0Detected operating system: Microsoft Windows Server 2003 R2 (5.2.3790.0) Service Pack 1Detected ESE.dll version: 6.5.7638.2Detected ESEPERF.dll version: 6.5.7638.1
9/5/2006 12:19:34 PM -- Validating input parameters, it may take a few minutes...9/5/2006 12:19:34 PM -- Attaching databases ... (it may take a few minutes if the databases are in dirty shutdown state)9/5/2006 12:19:49 PM -- Loading performance counters...9/5/2006 12:19:49 PM -- Instance3316.1: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:49 PM -- Instance3316.2: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:49 PM -- Instance3316.3: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:49 PM -- Instance3316.4: IO parameters are thread (8), insert (17), replace (70), delete (5), and lazy commit (90)9/5/2006 12:19:49 PM -- Start Jetstress test...9/5/2006 12:19:51 PM -- Starting StreamingBackup test run...
Counter Average Minimum Maximum
% Processor Time 2.502 0.832 4.058
Available MBytes 13742.50 13718.00 14757.00
Free System Page Table Entries 14991.00 14991.00 14991.00
Pages/Sec 0.011 0.000 0.467
Pool Nonpaged Bytes 33460977.66 33288192.00 33669120.00
Pool Paged Bytes 25001748.07 23695360.00 25616384.00
Database Page Fault Stalls/sec 0.000 0.000 0.000
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 81
82
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Backup-to-disk testing
9/5/2006 12:19:51 PM -- Performance logging started.9/5/2006 12:19:51 PM -- Performance data will be saved to C:\Program Files\Jetstress\Performance_LogGeneration_2006_9_5_12-19-49.blg.9/5/2006 12:54:22 PM -- Adding new data to the performance log file...9/5/2006 12:54:36 PM -- Performance logging stopped.9/5/2006 12:54:36 PM -- Stopping Jetstress...9/5/2006 12:55:10 PM -- Creating test report ...9/5/2006 12:55:11 PM -- Volume L: has 0.0098 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume K: has 0.0107 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume N: has 0.0098 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume M: has 0.0105 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume G: has 0.0010 for Avg. Disk sec/Write.9/5/2006 12:55:11 PM -- Volume G: has 0.0004 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume H: has 0.0009 for Avg. Disk sec/Write.9/5/2006 12:55:11 PM -- Volume H: has 0.0001 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume I: has 0.0010 for Avg. Disk sec/Write.9/5/2006 12:55:11 PM -- Volume I: has 0.0001 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Volume J: has 0.0010 for Avg. Disk sec/Write.9/5/2006 12:55:11 PM -- Volume J: has 0.0004 for Avg. Disk sec/Read.9/5/2006 12:55:11 PM -- Test has 0 Max Database Page Fault Stalls/sec.9/5/2006 12:55:11 PM -- Test has 0 Database Page Fault Stalls/sec samples higher than 0.9/5/2006 12:55:11 PM -- Soft recovery may take a while depending on the number of log files.9/5/2006 12:55:12 PM -- Performance logging started.9/5/2006 12:55:12 PM -- Performance data will be saved to C:\Program Files\Jetstress\SoftRecovery_2006_9_5_12-55-11.blg.9/5/2006 1:08:36 PM -- Adding new data to the performance log file...9/5/2006 1:08:38 PM -- Performance logging stopped.9/5/2006 1:08:38 PM -- Soft recovery is completed, please open C:\Program Files\Jetstress\SoftRecovery_2006_9_5_12-55-11.html for soft recovery result.9/5/2006 1:08:39 PM -- Performance logging started.9/5/2006 1:08:39 PM -- Performance data will be saved to C:\Program Files\Jetstress\DatabaseChecksum_2006_9_5_13-8-38.blg.9/5/2006 1:08:39 PM -- Checksum validation may take a while depending on the file sizes.9/5/2006 1:43:06 PM -- Database checksum in progress: Storage Group #1 (100%), Storage Group #2 (100%), Storage Group #3 (100%), and Storage Group #4 (100%).9/5/2006 1:43:06 PM -- Performance logging stopped.9/5/2006 1:43:06 PM -- Checksum is completed, please open C:\Program Files\Jetstress\DatabaseChecksum_2006_9_5_13-8-38.html for checksum
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server
Backup-to-disk testing
result.9/5/2006 1:43:07 PM -- Performance logging started.9/5/2006 1:43:07 PM -- Performance data will be saved to C:\Program Files\Jetstress\LogChecksum_2006_9_5_13-43-6.blg.9/5/2006 1:43:07 PM -- Checksum validation may take a while depending on the file sizes.9/5/2006 2:18:48 PM -- Log checksum in progress: (100 files(s) passed), (100 files(s) passed), (100 files(s) passed), and (100 files(s) passed).9/5/2006 2:18:48 PM -- Performance logging stopped.9/5/2006 2:18:48 PM -- Storage Groups being Backed up... The Backup Time may take hours depending on the size of the Storage Group.9/5/2006 2:27:22 PM -- Performance logging started.9/5/2006 2:27:22 PM -- Performance data will be saved to C:\Program Files\Jetstress\Backup_To_Disk_2006_9_5_14-18-48.blg.9/5/2006 2:27:22 PM -- Loading performance counters...9/5/2006 5:03:38 PM -- Adding new data to the performance log file...9/5/2006 5:03:40 PM -- Backup Complete!9/5/2006 5:03:42 PM -- Performance logging stopped.9/5/2006 5:03:42 PM -- Creating test report ...
EMC CLARiiON CX3-20 (8000 Users) Storage Solution for Microsoft Exchange Server 83