background image

4-16

 

Using the Performance Manager GUI

 

Hitachi Universal Storage Platform V/VM Hitachi Performance Manager User’s Guide 

 

Gathering Interval

 indicates that the statistics are collected at the 

interval displayed here. If the number of the CUs monitored is 64 or less, 
the value between 1 and 15 appears as a gathering interval by minutes. 

For example, if 

1 min.

 is displayed, the information obtained every one 

minute is displayed in the list and the graph. In case 65 or more CUs are 
monitored, the statistics are displayed every 5, 10 or 15 minutes. 

 

The list on the right of 

Monitoring Data

 indicates storing period of 

statistics (monitoring data). The statistics displayed in the 

Port-LUN

 tab 

are stored only in short range. The range of monitoring data that can be 
displayed in the window is between 8 hours and 15 days depending on the 

gathering interval. 
For details on the types of storing period of statistics, see Understanding 

Statistical Storage Ranges. 
For details on the relationship between collection interval and the storing 

period of the statistics, see Monitoring Options Window. 

 

Monitoring Term

 let you narrow the range of statistics that should be 

displayed in the window.  
The starting and ending time for collecting statistics is displayed on both 

sides of the slide bar. Performance Monitor stores the monitoring data 
between these times, and you can specify desired term within this range as 
the target to display in lists and graphs. 
For example, if you want to view statistics within the range of 10:30 July 1 
2007 to 10:30 July 2 2007, you set 

2007/07/01 10:30

 to the 

From

 box, set 

2007/07/02 10:30

 to the 

To

 box, and then click 

Apply

To set a date and time in 

From

 and 

To

, do either of the following: 

 

Move the slider to the left or to the right. 

 

In the text box, select the number that you want to change. Next, click 
the upward or downward arrow button. 

When you specify dates and time in 

From

 and 

To

, Performance Monitor 

calculates the length (in minutes) of the specified period and displays the 

calculated length. When calculating the length in minutes, Performance 
Monitor rounds up the fraction. 

 

 

 

Note: From

 and 

To

 are unavailable if the monitoring data (that is, 

obtained statistics) is not stored in the storage system.

 

 

The 

Real Time

 option lets you view statistics in real-time mode, where 

statistics are updated at a gathering interval you specify between 1 and 15 

minutes. 

Summary of Contents for MK-96RD617-08

Page 1: ...versal Storage Platform V Hitachi Universal Storage Platform VM Hitachi Performance Manager User s Guide Performance Monitor and Server Priority Manager FASTFIND LINKS Document Organization Product Version Getting Help Contents ...

Page 2: ...s of Hitachi Data Systems applicable agreements All of the features described in this document may not be currently available Refer to the most recent product announcement or contact your local Hitachi Data Systems sales office for information on feature and product availability This document contains the most current information available at the time of publication When new and or revised informa...

Page 3: ...nnel Processor Usage Statistics 2 6 Disk Processor Usage Statistics 2 6 DRR Processor Usage Statistics 2 9 Write Pending Rate and Cache Memory Usage Statistics 2 9 Access Path Usage Statistics 2 10 Hard Disk Drive Workload Statistics 2 11 Port Traffic Statistics 2 12 LU Paths Traffic Statistics 2 12 Traffic between HBAs and Storage System Ports 2 13 Performance of High Priority Hosts 2 13 Upper Li...

Page 4: ...es in External Volume Groups 5 16 Viewing Usage Statistics on Channel Processors 5 18 Viewing Usage Statistics on Disk Processors 5 19 Viewing Usage Statistics on Data Recovery and Reconstruction Processors 5 21 Viewing Write Pending and Cache Memory Usage Statistics 5 22 Viewing Usage Statistics on Access Paths 5 24 Viewing I O Rates for Disks 5 27 Viewing Transfer Rates for Disks 5 30 Viewing I ...

Page 5: ... the Export Tool 7 1 Requirements for Using the Export Tool 7 16 Installing the Export Tool on a Windows Computer 7 17 Installing the Export Tool on a UNIX Computer 7 18 Preparing a Command File 7 19 Preparing a Batch File 7 22 Running the Export Tool 7 24 Command Syntax 7 30 svpip Subcommand 7 32 retry Subcommand 7 33 login Subcommand 7 34 show Subcommand 7 35 group Subcommand 7 37 short range Su...

Page 6: ...vi Contents Hitachi Universal Storage Platform V VM Hitachi Performance Manager User s Guide ...

Page 7: ...rth referred to as SPM Please read this document carefully to understand how to use this product and maintain a copy for reference purposes This preface includes the following information Intended Audience Product Version Document Revision Level Source Document s for this Revision Changes in this Revision Document Organization Referenced Documents Document Conventions Convention for Storage Capaci...

Page 8: ...age Navigator remote console software Note There are different types of users for Hitachi Universal Storage Platform V VM storage administrators and storage partition administrators The functions described in this manual are limited depending on the user type For details on the limitations see Storage Partition Administrators Limitations For details on the user types see the Storage Navigator User...

Page 9: ... sections in that chapter Chapter Description Chapter 1 Overview of Performance Manager Describes the performance management software products that allow you to monitor and tune storage system performance Chapter 2 About_Performance_Manager _Operations Provides an overview of Performance Manager operations Chapter 3 Preparing for Performance Manager Operations Explains the preparations for Perform...

Page 10: ...ms Universal Storage Platform V and Universal Storage Platform VM refer to all models of the Hitachi Universal Storage Platform V and VM storage systems unless otherwise noted This document uses the following typographic conventions Convention Description Bold Indicates text on a window other than the window title including menus menu options buttons fields and labels Example Click OK Italic Indic...

Page 11: ... Tip Provides helpful information guidelines or suggestions for performing tasks more effectively Caution Warns the user of adverse conditions and or consequences e g disruptive operations WARNING Warns the user of severe conditions and or consequences e g destructive operations Convention for Storage Capacity Values Physical storage capacity values e g disk drive capacity are calculated based on ...

Page 12: ...vigator User s Guide The service information messages SIMs including reference codes and severity levels displayed by Storage Navigator The Hitachi Data Systems customer support staff is available 24 hours day seven days a week If you need technical support please call United States 800 446 0744 Outside the United States 858 547 4526 Comments Please send us your comments on this document Make sure...

Page 13: ...Platform V and Hitachi Universal Storage Platform VM herein after referred to as USP V VM includes a suite of performance management software products that allow you to monitor and tune storage system performance The Performance Manager suite includes the following Performance Monitor Server Priority Manager Restrictions The Auto Migration function is not supported in this version ...

Page 14: ...lyze trends in disk I Os and detect peak I O time If system performance is poor you can use information in the window to detect bottlenecks in the system When using Performance Monitor you must specify the volumes to be monitored in control units Therefore depending on your disk subsystem configuration the list may display performance statistics for some volumes and not display performance statist...

Page 15: ...s Performance Monitor Analysis of performance bottleneck Load Balanced HDD Arrangement Server Priority Mgr Host I O controlling to specific port Prioritized Host I O Controlling Process scheduling to prioritized host I O Volume Migration Effective use of HDD resource Performance Monitoring Base component of performance management Total performance monitoring Data migration tuning to maximize subsy...

Page 16: ... balancing required Turn Monitoring Options Long Range or Short Range off Start Storage Navigator Start Performance Monitor YES NO YES Is additional monitoring required YES NO Set and Start Monitoring Options Use Volume Migration Is system tuning required to prioritized hosts Use Server Priority Manager Exit Performance Monitor Exit Storage Navigator Is additional monitoring required NO YES Figure...

Page 17: ...Hitachi Performance Manager User s Guide About Performance Manager Operations This chapter gives an overview of performance manager operations Components Overview of Performance Monitor Overview of Server Priority Manager Overview of Export Tool Interoperability with Other Products ...

Page 18: ...e Storage Navigator program which is a Java applet automatically downloads to the WWW client computer You can perform Performance Manager operations in the Storage Navigator window For details about requirements for WWW client computers see the Storage Navigator User s Guide Cautions If Performance Monitor is not enabled you cannot use Server Priority Manager Performance management operations Perf...

Page 19: ...he Export Tool see Overview of Export Tool Understanding Statistical Storage Ranges Performance Monitor has two kinds of periods ranges for collecting and storing statistics short range and long range The difference of the two ranges and the statistics at which they are targeted is as follows Storing in short range If the number of CUs to be monitored is 64 or less Performance Monitor collects sta...

Page 20: ...tionship between collection interval and the storing period of the statistics see Monitoring Options Window Parity Group Usage Statistics A parity group is a group of hard disk drives HDDs that form the basic unit of storage for the USP V VM storage system All HDDs in a parity group must have the same physical capacity The USP V VM supports three types of parity groups as follows RAID 1 parity gro...

Page 21: ...he Hitachi Data Systems Support Center For details on how to view usage statistics about volumes see Viewing Usage Statistics on Volumes in Parity Groups External Volume Group Usage Statistics If the USP V VM storage system is connected to an external storage system by Universal Volume Manager Performance Monitor can also monitor the usage conditions on external hard disk drives When you use Unive...

Page 22: ...CHAs If monitoring data shows that CHP usage is not balanced you should consider moving some devices that are defined on overloaded ports to ports with lower usage CHPs to balance front end usage For details on how to view usage statistics about channel adapters and channel processors groups see Viewing Usage Statistics on Channel Processors Disk Processor Usage Statistics A disk processor DKP whi...

Page 23: ...or Migrating Volumes in USP V Storage System 1 DKA1AU DKP40 1AU DKP41 1AU DKP42 1AU DKP43 1AU Migrate volumes from parity groups with the following IDs to another parity group 1 X 3 X 11 X 1 DKA 1BU DKP50 1BU DKP51 1BU DKP52 1BU DKP53 1BU Migrate volumes from parity groups with the following IDs to another parity group 2 X 4 X 12 X 1 DKA AL DKP44 1AL DKP45 1AL DKP46 1AL DKP47 1AL Migrate volumes f...

Page 24: ...arity groups with the following IDs to another parity group 5 X 13 X 2 DKA 2NL DKPD4 2NL DKPD5 2NL DKPD6 2NL DKPD7 2NL Migrate volumes from parity groups with the following IDs to another parity group 6 X 14 X 2 DKA 2XU DKPE0 2XU DKPE1 2XU DKPE2 2XU DKPE3 2XU Migrate volumes from parity groups with the following IDs to another parity group 7 X 15 X 2 DKA 2WU DKPF0 2WU DKPF1 2WU DKPF2 2WU DKPF3 2WU...

Page 25: ...conditions If the monitor data shows that DRR usage is not balanced you should consider relocating volumes using Volume Migration to balance DRR usage within the storage system For information on using Volume Migration contact the Hitachi Data Systems Support Center see Calling the Hitachi Data Systems Support Center For details on how to view usage statistics on DRRs see Viewing Usage Statistics ...

Page 26: ...memory When hosts issue commands the commands are transferred via channel adapters to the shared memory SM The content of the shared memory is checked by disk adapters DKA DKA DKA DKA CHA CHA CHA CHA cache switch CSW cache memory CHA channel adapter DKA disk adapter shared memory Figure 2 1 Access Paths Performance Monitor tracks and displays the usage rate for the following access paths Paths bet...

Page 27: ...s I O rate The I O rate indicates how many I Os are made to the hard disk drive in one second If the I O rate is high the hosts might consume a lot of time for accessing disks and the response time might be long Transfer rate The transfer rate indicates the size of data transferred to the hard disk drive in one second If the transfer rate is high the hosts might consume a lot of time for accessing...

Page 28: ... Performance Monitor can obtain statistics about traffics of ports connected to open system host groups only The statistics about traffics of ports connected to mainframe host groups cannot be obtained LU Paths Traffic Statistics Performance Monitor tracks LU paths to obtain statistics about I O rates and transfer rates at these LU paths If you analyze these I O rates and transfer rates you can de...

Page 29: ... performance are given higher priority over I O operations from other hosts Performance of High Priority Hosts In an SAN storage area network environment the storage system is usually connected with a lot of host servers Some types of the host servers often require high performance but others might not require as high performance For example production servers usually require high performance Prod...

Page 30: ...rs even after 3 00 p m Development servers should be free from upper limit control when production servers are not busy Server Priority Manager provides a function called threshold control If threshold control is used upper limit control is automatically disabled when traffic between production servers and the storage system decreases to a certain level A threshold is a value that indicates the ti...

Page 31: ...stem type Indicates that the data was obtained from 18 57 to 19 01 on March 28 2007 Sampling rate 1 indicates that monitoring was performed every minute at a one minute interval Notes In this LU_IOPS csv file the last four digits of a table column heading such as 0001 and 0002 indicate an LUN For example the heading CL1 A 00 1A G00 0001 indicates the port CL1 A the host group ID 00 the host group ...

Page 32: ...archive file To be able to open a text file you must use decompress the ZIP file to extract the text files Text files are in CSV comma separated value format in which values are delimited by commas Many spreadsheet applications can be used to open CSV files Do not run multiple instances of the Export Tool simultaneously If you run multiple instances the SVP may be overloaded and a timeout error ma...

Page 33: ... the Physical tab You will be able to view usage statistics that have been obtained for the last three months i e 93 days in long range monitoring and for the last 15 days in short range monitoring You will not be able to view usage statistics that expired after these storing periods because such statistics are erased from the storage system In short range if I O workloads between hosts and the st...

Page 34: ... the gathering interval allots might be required for updating the display of monitoring data In this case some portion of monitoring data will not be displayed in the window For example suppose that the gathering interval is 1 minute In this case if the display in the Performance Management window is updated at 9 00 and the next update occurs at 9 02 the window including the graph does not display...

Page 35: ...esholds to the average I O rate or the average transfer rate calculated every gathering interval For example in Figure 2 3 in which the gathering interval is 1 minute if you set an upper limit of 150 IO s to the port 1A the highest data point in the line CL1 A in Graph 2 and the line Ave 1 min in Graph 3 is somewhere around 150 IO s It is possible that the lines Max 1 min and Min 1 min in Graph 3 ...

Page 36: ...though you can set Prioritize or Non Prioritize to initiator ports and external ports by using Server Priority Manager the initiator ports and the external ports become the prioritized ports that are not under threshold control regardless of whether the setting of the ports are Prioritize or Non Prioritize If the port attributes are changed from Initiator External into Target RCU Target the settin...

Page 37: ...i Universal Storage Platform V VM Hitachi Performance Manager User s Guide Preparing for Performance Manager Operations This chapter explains the preparations for performance manager operations System Requirements Storage Partition Administrators Limitations ...

Page 38: ...torage Navigator window For a summary of Web client computer requirements see the Storage Navigator User s Guide Performance Manager operations require the Storage Navigator program which is downloaded to your WWW client computer Your WWW client computer must be connected to the USP V VM storage system via LAN Browser settings are also required on your WWW client computer For details see the Stora...

Page 39: ...management logical partition allocated to the user ID The Volume Migration button is not displayed Therefore the user cannot start Volume Migration For information on using Volume Migration contact the Hitachi Data Systems Support Center see Calling the Hitachi Data Systems Support Center LDEV tab in the Performance Management window The tree and list display only the information in the SLPR alloc...

Page 40: ...UR Monitor window URz Monitor window and the Monitoring Options window are not displayed The WWN tab is not displayed The tree and list display only the information in the SLPR allocated to the user ID The SPM button and the Volume Migration button are not displayed Figure 3 1 Performance Management Window displayed When You Logged in as a Storage Partition Administrator ...

Page 41: ... PPCG or PPCGWWN operand to export the monitoring data about SPM groups or the host bus adapters belonging to these SPM groups an error will occur in the following conditions One SPM group contains multiple host bus adapters which are allocated to different SLPRs One host bus adapter is connected to multiple ports which exist in different SLPRs The monitoring data about remote copy operations perf...

Page 42: ...3 6 Preparing for Performance Manager Operations Hitachi Universal Storage Platform V VM Hitachi Performance Manager User s Guide ...

Page 43: ...itachi Universal Storage Platform V VM Hitachi Performance Manager User s Guide Using the Performance Manager GUI This chapter explains performance manager windows Using the Performance Monitor Windows Using the Server Priority Manager Windows ...

Page 44: ...ns Performance Monitor Window Performance Monitor has the following windows Performance Management window This window displays the monitoring results about the storage system performance collected by Performance Monitor You can change the information to be viewed by selecting each tab in the tree The information displayed by selecting each tab is as follows Physical tab Displays the usage statisti...

Page 45: ...essors etc In addition when you use Universal Volume Manager to map volumes in an external storage system storage system other than USP V VM to the internal volumes the Physical tab also lets you view usage conditions of volumes in the external storage system i e external volumes and the groups of external volumes For details on how to use this window see Monitoring Resources in the Storage System...

Page 46: ... Figure 4 2 Storing Period of Statistics Physical Tab The storing period of statistics is the range of monitoring data statistics collected by monitoring that can be displayed You can specify a part of term within the selected range to narrow the statistics to be displayed in the list and graph on the Performance Management window The differences in selecting shortrange and longrange are described...

Page 47: ...played below the CHA folder an ESCON channel adapter a FICON channel adapter a Fibre Channel adapter in Standard mode a Fibre Channel adapter in High Speed mode a Fibre Channel adapter in Initiator External MIX mode The channel adapter number and number of ports that displayed on the right side of the icon are examples Icons displayed below the DKA folder a disk processor DKP a data recovery and r...

Page 48: ...ed parity groups contact the maintenance personnel The list displays statistics about parity group usage processor usage etc The list displays up to a maximum of 4 096 resources at a time If the number of resources exceeds 4 096 use Previous and Next to display the remaining resources If you select connected parity groups in the tree the list displays usage statistics for all the connected parity ...

Page 49: ...nges in usage statistics The vertical axis indicates the usage rates in percentage The horizontal axis indicates dates and or times If you select connected parity groups in the tree the graph displays changes in usage statistics for all the connected parity groups When you illustrate a graph of the following information with specifying shortrange you can select an item to be displayed in the graph...

Page 50: ...al is fixed to 15 minutes regardless of the displayed value You cannot view the statistics of external volume groups and external volumes and hyphens appear in the list instead of these values In this case you cannot draw the graph To view this data select shortrange For details on viewing the usage statistics of external volume groups and external volumes see Viewing Usage Statistics on External ...

Page 51: ...erformance Monitor Window When you click Go Performance Manager and then Performance Management on the menu bar of the Storage Navigator main window Performance Monitor starts and the Performance Management window is active The Performance Management window includes the LDEV tab which lets you view statistics about disk access performance For example the window displays the I O rate the number of ...

Page 52: ...s For details on the relationship between collection interval and the storing period of the statistics see Monitoring Options Window Monitoring Term lets you narrow the range of statistics that should be displayed in the window Starting and ending times for collecting statistics are displayed on both sides of the slide bar Performance Monitor stores the monitoring data between these times and you ...

Page 53: ... the right of IDs A volume existing in an external storage system and mapped to a volume in the USP V VM storage system by using Universal Volume Manager is called an external volume An external volume group is a quantity of external volumes grouped together for managing and that does not contain any parity information unlike a parity group However Performance Management window treats external vol...

Page 54: ...ut disk access performance for example I O rate transfer rate read hit ratio write hit ratio and average response time For details on the list contents see Monitoring Hard Disk Drives If you select connected parity groups in the tree the list displays statistics about disk access performance for all the connected parity groups The list displays up to a maximum of 4 096 resources at a time If the n...

Page 55: ... 4 6 Selecting an Item to be Displayed in the Graph LDEV Tab The items that can be selected in the list change depending on the type of statistics you selected Some items can be selected only when you select I O rate IOPS or the transfer rate MB s The items you can select in the list and the corresponding type of statistics are shown in Table 4 1 Table 4 1 Items You Can Select in the List and the ...

Page 56: ...h LDEV Tab Select Detail and this Item in the List The Graph Contains IO Rate Read Write Read Hit Write Hit statistics in sequential access mode statistics in random access mode statistics in CFW cache fast write mode Note If the read hit ratio or the write hit ratio is high random access mode is used for transferring data instead of sequential access mode For example random access mode is likely ...

Page 57: ...sfer rates and average response time at storage system ports host groups LU paths etc Performance Monitor can obtain statistics about traffics of ports connected to open system host groups only The statistics about traffics of ports connected to mainframe host groups cannot be obtained For details on how to use this window see Monitoring Ports and Monitoring LU Paths Figure 4 8 Port LUN tab of the...

Page 58: ...itoring Term let you narrow the range of statistics that should be displayed in the window The starting and ending time for collecting statistics is displayed on both sides of the slide bar Performance Monitor stores the monitoring data between these times and you can specify desired term within this range as the target to display in lists and graphs For example if you want to view statistics with...

Page 59: ...ollowed by its fibre address the port is a Fibre Channel port For example CL1 A EF indicates that the CL1 A port is a Fibre Channel port This port icon indicates either of the following A Fibre Channel port in Standard mode LUN security is not applied to this port A Fibre Channel port in High Speed mode LUN security is applied to this port A Fibre Channel port in High Speed mode LUN security is no...

Page 60: ...The graph can display up to eight lines simultaneously The line graph illustrates changes in the I O rate or the transfer rate The vertical axis indicates the I O rate or the transfer rate The horizontal axis indicates dates and or times When the graph displays I O rates or the transfer rates for a port controlled by an upper limit or a threshold the graph also displays a line that indicates the u...

Page 61: ...is specified as the gathering interval The graph contents changes depending on the selection of the Detail check box The figure shows the following The workload on the port CL1 A is 200 IO s at 8 00 and 300 IO s at 10 00 refer to the graph on the left For the period of 7 59 to 8 00 the maximum workload on CL1 A is 300 IO s The average workload on CL1 A is 200 IO s The minimum workload on CL1 A is ...

Page 62: ...s per second Read Hit the read hit ratio Write Hit the write hit ratio statistics in sequential access mode statistics in random access mode Note If the read hit ratio or the write hit ratio is high random access mode is used for transferring data instead of sequential access mode For example random access mode is likely to be used for transferring data to disk areas to which the Cache Residency M...

Page 63: ...age response time about traffic between host bus adapters in the hosts and ports on the storage system Caution The WWN tab is unavailable if Server Priority Manager is not enabled A WWN Worldwide Name is a 16 digit hexadecimal number used as the unique identifier for a host bus adapter Host bus adapters are contained in hosts and serve as ports for connecting the hosts and the storage system One W...

Page 64: ...collection interval and the storing period of the statistics see Monitoring Options Window Monitoring Term let you narrow the range of statistics that should be displayed in the window The starting and ending time for collecting statistics are displayed on both sides of the slide bar Performance Monitor stores the monitoring data between these times and you can specify the desired term within this...

Page 65: ... in red in the tree the host bus adapter is connected to two or more ports but the traffic between the HBA and some of the ports are not monitored by Performance Monitor When many to many connections are established between HBAs and ports make sure that all the traffic between HBAs and ports is monitored see Monitoring All Traffic between HBAs and Ports for instructions The list displays statistic...

Page 66: ...al axis indicates dates and or times When the graph displays I O rates or the transfer rates for a host bus adapter or an SPM group controlled by an upper limit the graph also displays a line that indicates the upper limit When you draw a graph the Chart Y Axis Rate list lets you select the highest value of the Y axis the vertical axis of the graph Figure 4 12 Chart Y Axis Rate List Detail Check B...

Page 67: ...he statistics of volumes that are displayed in the LDEV tab In the above tabs performance statistics of unused volumes are displayed as hyphens if the range of monitored CUs does not match the range of CUs used in the disk storage system or registered as external volumes In addition depending on your disk subsystem configuration the list may display performance statistics for some volumes and not ...

Page 68: ...storage system for short range monitoring This option is activated when you specify Enable for Current Status If CUs to be monitored are 64 or less you can specify the value between 1 and 15 minutes by minutes and the default setting is 1 minute For example if you specify 1 minute for the gathering interval Performance Monitor collect statistics such as I O rates and transfer rates every one minut...

Page 69: ...list is accompanied by an icon Click PG on the header to sort the parity groups by ID If you click the cell for an individual parity group the CUs that belong to that parity group are displayed in the CU table on the right LDKC list Indicates LDKC numbers To select an LDKC as a monitoring target click the LDKC number All the CUs that belong to that LDKC are displayed CU table The CU table consists...

Page 70: ... in black N in black italics R in blue italics S in black The Release button removes the CU from monitoring targets Table 4 6 Characters Indicated in a Cell When Release Button is Clicked Before Click After Click N in black Hyphen in black bold S in black R slanted in blue italics The Apply button applies settings in the Monitoring Options window to the storage system The Reset button resets the s...

Page 71: ... OS Therefore if you use the Monitoring Options window to start or stop monitoring or to change the gathering interval the monitoring settings of these remote copy functions will also change Conversely if the settings in each Usage Monitor window are changed the settings in the Monitoring Options window of Performance Monitor also change automatically Other Windows Apart from the Performance Monit...

Page 72: ... Priority Manager windows The remaining sections explain procedures for monitoring performance and setting the upper limit and threshold for I O rates and transfer rates If the user type of your user ID is storage partition administrator you cannot use Server Priority Manager For details on the limitations when using Performance Manager logged in as a storage partition administrator see Storage Pa...

Page 73: ...eshold specified in the WWN tab If No Control is displayed the system performance is not controlled by Server Priority Manager Tip If WWN Control is displayed when the Port tab is active click Apply to switch control so that Port Control is displayed Tip To return the control status to No Control specify Prio for attributes of all the ports and then click Apply The list near the upper right corner...

Page 74: ...ansfer rate for the specified period The Peak column indicates the peak I O rate or the peak transfer rate of the ports for the specified period This value means the top of the Max line in the detailed port traffic graph drawn in the Port LUN tab of Performance Monitor For details see Viewing I O Rates for Disks and Viewing Transfer Rates for Disks The Attribute column indicates the priority of ea...

Page 75: ...u check the Delete ports if CHA is removed check box Server Priority Manager will delete from SVP the setting information of Server Priority Manager on ports in channel adapters that have been removed When a channel adapter is removed the port and its settings are removed from the Server Priority Manager window automatically but they remain in SVP This may cause that the old setting for Server Pri...

Page 76: ...splays the following Current Control Status can display either Port Control or WWN Control If Port Control is displayed the system is controlled by the upper limits and threshold specified in the Port tab If WWN Control is displayed the system is controlled by the upper limits and threshold specified in the WWN tab If No Control is displayed the system performance is not controlled by Server Prior...

Page 77: ...nd SPM names of the host bus adapters are displayed on the right of the host bus adapter icon below Monitor WWNs Worldwide Name are 16 digit hexadecimal numbers used to uniquely identify host bus adapters SPM names are nicknames assigned by the system administrator so that they can easily identify each host bus adapter Only the WWN is displayed on the right of the host bus adapter icon below Non M...

Page 78: ...ter that appears below Monitor and does not registered on any other SPM group yet If you select a host bus adapter below Non Monitor or a host bus adapter already registered on an SPM group the Add NNW button is deactivated The list at the upper left corner of the list enables you to change the type of performance statistics to be displayed in the list If IOPS I Os per second is selected the list ...

Page 79: ...iod Max Indicates the maximum I O rate or the maximum transfer rate for the specified period The WWN Total column indicates the sum of the traffic I O rate or transfer rate between the host bus adapter and all the ports connected to the host bus adapter This value means the total traffic of that host bus adapter This item is displayed only when you select an icon in the upper left tree Whichever p...

Page 80: ...limit values for I O rates and transfer rates all together for different non prioritized WWNs Notes If one host bus adapter connects to multiple ports the setting of the upper limit value for a non prioritized WWN is common to all the ports Therefore if you specify a upper limit value of non prioritized WWN for one port the setting is applied to all the other connected ports automatically You cann...

Page 81: ...the old setting for Server Priority Manager are applied to a different channel adapter that is installed on the same location newly The Delete ports if CHA is removed check box is available only when the following Server Priority Manager settings on ports in a removed channel adapter remains on SVP The setting of prioritized ports or non prioritized ports The setting of prioritized WWNs or non pri...

Page 82: ...4 40 Using the Performance Manager GUI Hitachi Universal Storage Platform V VM Hitachi Performance Manager User s Guide ...

Page 83: ...ce Manager User s Guide Performance Monitor Operations This chapter explains the following performance monitor operations Overview of Performance Monitor Operations Monitoring Resources in the Storage System Monitoring Hard Disk Drives Monitoring Ports Monitoring LU Paths Viewing HBA Information ...

Page 84: ...mance statistics of unused volumes are displayed as hyphens if the range of monitored CUs does not match the range of CUs used in the disk storage system or registered as external volumes In addition depending on your disk subsystem configuration the list may display performance statistics for some volumes and not display performance statistics for other volumes To correctly display performance st...

Page 85: ... system and saves the statistics at the specified interval If the number of CUs to be monitored is 64 or less you can select a gathering interval between 1 and 15 minutes The gathering interval you selected here determines the storing period of the statistics in short range which is up to 15 days For example if you specify the gathering interval as 1 minute the statistics can be stored 1 day and i...

Page 86: ...Therefore if you use the Monitoring Options window to start or stop monitoring or to change the gathering interval the monitoring settings of these remote copy functions will also change Conversely if the settings in each Usage Monitor window are changed the settings in the Monitoring Options window of Performance Monitor will also change automatically View the Monitoring Results To view the resul...

Page 87: ...on the left is 2007 03 27 16 00 and the date and time on the right is 2007 03 28 16 00 you can view usage statistics for the period of 2007 03 27 16 00 to 2007 03 28 16 00 If you change the dates and times in From and To you can specify the range of statistics that should be displayed in the window For example if the window displays statistics for the last one month you can change the values in Fr...

Page 88: ... mode by taking the following steps a Check to see if the background color of the lock icon is blue If the background color is red you will not be able to switch from View mode to Modify mode Wait for a while and click the button If the background color turns blue you can go to the next step b Click the icon A message appears asking whether you want to change the mode c Click OK to close the messa...

Page 89: ...ed on servers Therefore the client processing might slow down To stop monitoring the storage system 1 Start Performance Monitor and select the Monitoring Options tab The Monitoring Options window is displayed 2 In Monitoring Switch select Disable for the Current Status option The Gathering Interval list is unavailable 3 Click Apply Performance Monitor stops monitoring the storage system ...

Page 90: ...played in the list by selecting longrange and shortrange are the same 4 In the tree select the Parity Group folder The list on the right displays usage statistics about parity groups The displayed statistics are the average and the maximum usage rates for the period specified in the From and To boxes The list displays up to a maximum of 4 096 resources at a time If the number of resources exceeds ...

Page 91: ...e is no volume in a parity group hyphens are displayed in place of performance statistics on a parity group If the CU is not the monitoring target all items in the row are displayed in italics If you want to monitor those items specify the CU as the monitoring target by using the Monitoring Option window The list displays the following items When the green checkmark icon is displayed to the left o...

Page 92: ...e or shortrange If you want to use Volume Migration to migrate volumes select longrange This enables you to confirm the estimated usage rate of parity groups after migration For information on using Volume Migration contact the Hitachi Data Systems Support Center see Calling the Hitachi Data Systems Support Center If you want to examine the ratio of ShadowImage processing and so on to all the proc...

Page 93: ...ge rate is likely to be inaccurate because the configuration has changed e g volumes have been moved by Volume Migration or ShadowImage or formatted by Virtual LVI or Open Volume Management For information on using Volume Migration contact the Hitachi Data Systems Support Center see Calling the Hitachi Data Systems Support Center If a plus mark is displayed before a usage rate 0 such as 0 the usag...

Page 94: ...lation types Usage The Ave Total column displays the average usage rate in the specified period The Max column displays the maximum usage rate in the specified period Read Rate The Rnd column indicates random read rates A random read rate is the ratio of random read requests to read and write requests The Seq column indicates sequential read rates A sequential read rate is the ratio of sequential ...

Page 95: ... access time to physical drives by the following programs by all the access time to physical drives ShadowImage for IBM z OS ShadowImage Compatible FlashCopy Compatible FlashCopy V2 Volume Migration For information on using Volume Migration contact the Hitachi Data Systems Support Center see Calling the Hitachi Data Systems Support Center Copy on Write Snapshot The Ave Total column displays the av...

Page 96: ...tree select the External Group folder The list on the right displays usage statistics about external volume groups The displayed statistics are the usage statistics for the period specified in the From and To boxes Notes The list displays up to a maximum of 4 096 resources at a time If the number of resources exceeds 4 096 use Previous and Next to display the remaining resources If you change the ...

Page 97: ...n indicates IDs of external volume groups The letter E at the beginning of IDs indicates the group is an external volume group Response Time This column indicates the time for replying from an external volume group when I O accesses are made from USP V VM storage system to the external volume group The unit is milliseconds The average response time in the period specified at Monitoring Term is dis...

Page 98: ... no statistics appears in the list 4 In the tree select the External Group folder The folder opens and a list of external volume groups is displayed below the folder 5 Select the desired external volume group The list on the right displays usage statistics about external volumes in the specified external volume group The displayed statistics are the average and the maximum usage rates for the peri...

Page 99: ...n usage rate for the external volume ExLDEV This column indicates external volumes in this format LDKC CU LDEV A number ending in indicates the volume is an external volume Emulation This column indicates device emulation types Response Time This column indicates the time for replying from an external volume when I O accesses are made from USP V VM storage system to the external volume The unit is...

Page 100: ...one of the following If you want to view usage statistics about all the channel processors in your storage system select the Client Host Interface Processor CHIP folder If you want to view usage statistics about channel processors in a channel adapter double click the Client Host Interface Processor CHIP folder and then select the desired channel adapter The list on the right displays usage statis...

Page 101: ... maximum usage rate in a specified period Performance Monitor also displays a graph illustrating changes in disk processor usage within that period To view usage statistics about disk processors 1 Ensure that the Performance Management window is displayed 2 In the tree click the Physical tab 3 In the list above the tree select the storing period of statistics from longrange and shortrange for disp...

Page 102: ...s in usage rate for disk processors select the desired disk processors in the list and then click Draw Note The range of monitoring and the gathering interval affects the time period represented by a graduation on the horizontal axis Figure 5 8 Example of Disk Processor Usage Rates Displayed The list displays the following items When the green checkmark icon is displayed on the left of a disk proc...

Page 103: ...usage statistics about DRRs the items displayed in the list by selecting longrange and shortrange are the same 4 In the tree double click the ACP folder 5 Click DRR from below the ACP folder The list on the right displays usage statistics about DRRs The displayed statistics are the average and the maximum usage rates for the period specified in the From and To boxes Note If you change the date and...

Page 104: ...eriod To view the write pending rate or usage statistics of the cache memory 1 Ensure that the Performance Management window is displayed 2 In the tree click the Physical tab 3 In the list above the tree select the storing period of statistics from longrange and shortrange for display For details on the types of storing period of statistics see Understanding Statistical Storage Ranges The items di...

Page 105: ...elect shortrange for the storing period of statistics you can select the item to be illustrated in the graph from the list at the upper right on the graph Select Write Pending to view the write pending rate graph and select Usage to view that of the usage statistics for cache memory The graph will be updated without clicking Draw You can also select the item to be displayed before clicking Draw Fi...

Page 106: ...ax column displays the maximum usage rate of the cache in the specified period Write Pending The Ave Total column displays the average write pending rate for the specified period The Moment Max column displays the maximum write pending rate for the specified period Viewing Usage Statistics on Access Paths The channel adapters CHAs and the disk adapters DKAs transfer data to the cache switch CSW an...

Page 107: ...er To check usage statistics about paths between cache switches and the cache memory select CSW Cache from below the Access Path Usage folder The list on the right in Figure 5 12 displays the average and maximum usage rate for the specified paths The displayed statistics are the average and the maximum usage rates for the period specified in the From and To boxes Note If you change the date and ti...

Page 108: ...ndicates shared memories Cache This column indicates the cache memories Usage The Ave Total column displays the average usage rate for the specified period The Max column displays the maximum usage rate for the specified period Monitoring Hard Disk Drives The LDEV tab of the Performance Management window lets you check workloads on physical hard disk drives parity groups or on volumes The LDEV tab...

Page 109: ... is displayed 2 Click the LDEV tab The tree displays a list of parity groups and external volume groups 3 Select IOPS from the list on the right side of the window 4 In the tree do one of the following If you want to view the I O rate for each parity group and external volume group select the Subsystem folder or a Box folder The list on the right displays the I O rate for each group Note If you se...

Page 110: ...mation that you want to view in the graph For details on the information that can be displayed see Table 4 1 c Click Draw A graph appears below the list The horizontal axis indicates the time Caution If the graph does not display changes in the I O rate for example if the line in the graph runs vertically it is recommended that you change the value in the Chart Y Axis Rate list For example if the ...

Page 111: ...rget all items in the row are displayed in italics If you want to monitor those items specify the CU as the monitoring target by using the Monitoring Option window The list displays the following When the green checkmark icon is displayed on the left of an item the graph displays workload statistics about the parity group the external volume group or the volume PG Indicates the parity group ID or ...

Page 112: ...m The unit is milliseconds The average response time in the period specified at Monitoring Term is displayed CLPR This column indicates numbers and names of CLPRs corresponding to each parity group external volume group or volume in the format CLPR number CLPR name For details on CLPRs see the Virtual Partition Manager User s Guide Viewing Transfer Rates for Disks Performance Monitor audits hard d...

Page 113: ...on in the list To change the date and time in From and To boxes use the arrow buttons and the sliders for details see LDEV Tab of the Performance Monitor Window 5 If you want to display a graph to find out how the transfer rate has been changed take the following steps a In the list select the parity group s the external volume groups or the volume s that you want b Use the list on the right to se...

Page 114: ...5 14 Transfer Rates for Disks Notes It is possible that the transfer rate for a parity group or an external volume group is not equal to the sum of the transfer rate for each volume in that group This is because the Performance Management window omits fractions below the decimal point when displaying the transfer rate for each volume If there is no volume in a parity group hyphens are displayed in...

Page 115: ... the external volume group or the volume per second Read Hit Indicates the read hit ratio Write Hit Indicates the write hit ratio Back Trans Indicates the number of data transfers per second between the parity group or the external volume group or the volume and the cache memory Response Time This column indicates the time for replying from the parity group the external volume group or the volume ...

Page 116: ...the Performance Management window is displayed 2 Select the Port LUN tab The tree displays a Subsystem folder 3 Select the Subsystem folder The Target folder and the Initiator External folder are displayed 4 Select IOPS from the list on the right side of the window 5 In Monitoring Term do one of the following To view the I O rate in real time you must select the Real Time option specify the number...

Page 117: ...Draw Caution If the graph does not display changes in the I O rate for example if the line in the graph runs vertically it is recommended that you change the value in the Chart Y Axis Rate list For example if the largest value in the list is 200 and the value in Chart Y Axis Rate is 100 you should select a value larger than 200 from Chart Y Axis Rate I O rate for ports When the Subsystem folder is...

Page 118: ... that you can easily identify each host bus adapter in the LUN Manager windows Current Indicates the current I O rate Ave Indicates the average I O rate for the specified period Peak Indicates the peak I O rate of the ports for the specified period This value is shown in the list when you select the Subsystem folder in the tree If you select a port in the list click Draw and select the Detail chec...

Page 119: ... 2 Select the Port LUN tab The tree displays a Subsystem folder 3 Select the Subsystem folder The Target folder and the Initiator External folder are displayed 4 Select MB s from the list on the right side of the window 5 In Monitoring Term do one of the following To view the transfer rate in real time you must select the Real Time option specify the number of recent collections of statistics whic...

Page 120: ...been changed take the following steps a In the list select one or more ports or host bus adapters WWNs b Click Draw Caution If the graph does not display changes in the transfer rate for example if the line in the graph runs vertically it is recommended that you change the value in the Chart Y Axis Rate list For example if the largest value in the list is 200 and the value in Chart Y Axis Rate is ...

Page 121: ...adapter so that you can easily identify each host bus adapters in the Server Priority Manager windows Nickname Indicates the nickname for the host bus adapters LUN Manager allows you to assign a nickname to each host bus adapter so that you can easily identify each host bus adapter in the LUN Manager windows Current Indicates the current transfer rate Ave Indicates the average transfer rate for th...

Page 122: ...lect a host group icon in the tree nicknames defined by LUN Manager appear We recommend that you specify the same name for an SPM name and a nickname for convenience of host bus adapter management Initiator External Indicates the port attribute Initiator indicates an initiator port External indicates an external port Both of the ports are not controlled by Server Priority Manager Viewing Details a...

Page 123: ...wing LU Paths I O Rates Performance Monitor monitors LU paths and measures I O rates that is the number of disk I Os per second To view I O rates 1 Ensure that the Performance Management window is displayed 2 Select the Port LUN tab The tree displays a list of ports on the storage system 3 Select IOPS from the list on the right side of the window 4 In Monitoring Term do one of the following To vie...

Page 124: ...able 4 3 Note If more than one row is selected in the list you cannot select the Detail check box Figure 5 17 I O Rates for LU Paths Note If the CU is not the monitoring target all items in the row are displayed in italics If you want to monitor those items specify the CU as the monitoring target by using the Monitoring Option window The list displays the following When the green checkbox icon is ...

Page 125: ...ld be displayed in the graph and then click Apply To view transfer rates for a certain period of time in the last 24 hours you must select the From option change the date and time in the From and To boxes and then click Apply Use the arrow button and the sliders when you change the date and time in the From and To boxes For details on the Real Time option and the From option see Port LUN Tab of th...

Page 126: ...played on the left of an item the graph displays changes in workload statistics about the item LUN Indicates LUNs logical unit numbers LDEV Indicates IDs of volumes in the following format LDKC CU LDEV An ID ending in indicates the volume is an external volume An ID ending in V or X indicates the volume is a virtual volume Emulation Indicates emulation types Paths Indicates the number of LU paths ...

Page 127: ...on Viewing I O Rates between HBAs Performance Monitor monitors traffic between HBAs in the hosts and ports on the storage system and measures I O rates that is the number of disk I Os per second To view I O rates 1 Ensure that the Performance Management window is displayed 2 Click the WWN tab The tree displays a list of SPM groups Below that list an item named Not Grouped To display host bus adapt...

Page 128: ... In the list select one or more SPM groups WWNs or ports b Click Draw Caution If the graph does not display changes in the I O rate for example if the line in the graph runs vertically try changing the value in the Chart Y Axis Rate list For example if the largest value in the list is 200 and the value in Chart Y Axis Rate is 100 you should select a value larger than 200 from Chart Y Axis Rate Not...

Page 129: ...st bus adapters Server Priority Manager allows you assign an SPM name to each host bus adapter so that you can easily identify each host bus adapters in the Server Priority Manager windows Port Indicates ports on the storage system Current Indicates the current I O rate Ave Indicates the average I O rate for the specified period Max Indicates the maximum I O rate for the specified period Response ...

Page 130: ...layed in the graph and then click Apply To view transfer rates for a certain period of time in the last 24 hours you must select the From option change the date and time in the From and To boxes and then click Apply Use the arrow button and the sliders when you change the date and time in the From and To boxes For details on the Real Time option and the From option see WWN Tab of the Performance M...

Page 131: ...me of the ports are not monitored by Performance Monitor When many to many connections are established between HBAs and ports you should make sure that all the traffic between HBAs and ports is monitored For details on the measures when a WWN is displayed in red see Monitoring All Traffic between HBAs and Ports Transfer rate at host bus adapters Displayed when an SPM group or Not Grouped is select...

Page 132: ...he current transfer rate Ave Indicates the average transfer rate for the specified period Max Indicates the maximum transfer rate for the specified period Response Time This column indicates the time for replying from the host bus adapter SPM group or port when I O accesses are made from the host to them The unit is milliseconds The average response time in the period specified at Monitoring Term ...

Page 133: ...al Storage Platform V VM Hitachi Performance Manager User s Guide Server Priority Manager Operation This chapter explains the following server priority manager operations Overview of Server Priority Manager Operations Port Tab Operations WWN Tab Operations ...

Page 134: ...efine the server priority by the port because one port can connect to multiple host bus adapters and also multiple ports can connect to one host bus adapter Therefore in the many to many connection environment you specify the priority of I O operations and upper limit value on each host bus adapter In this case you specify one threshold value for the entire storage system If one to one connections...

Page 135: ... 0000000000000002 Figure 6 1 Network A One to one Connections between HBAs and Ports If one to one connections are established between HBAs and ports take the following major steps 1 Set priority to ports on the storage system using the Port tab of the Server Priority Manager window In network A the ports 1A and 1C are connected to high priority production servers The port 2A is connected to a low...

Page 136: ...ng changes in traffic Figure 6 3 is a graph illustrating changes in the I O rate for the three ports 1A 1C and 2A According to the graph the I O rate for 1A and 1C was approximately 400 IO s at first The I O rate for 2A was approximately 100 IO s at first However as the I O rate for 2A gradually increased from 100 IO s to 200 IO s the I O rate for 1A and 1C decreased from 400 IO s to 200 IO s This...

Page 137: ...el If production server performance is not improved to a desirable level you can change the upper limit to a smaller value and then apply the new upper limit to the storage system In network A if the upper limit is set to 180 IO s but the I O rate for 1A and 1C is still below 400 IO s the administrator needs to change the upper limit until the I O rate reaches 400 IO s 5 If necessary apply a thres...

Page 138: ...A CHA channel adapter Host bus adapter HBA Figure 6 4 Network B Many to Many Connections are Established between HBAs and Ports If many to many connections are established between HBAs and ports take the following major steps 1 Find WWNs of host bus adapters Before using Server Priority Manager you must find the WWN Worldwide Name of each host bus adapter in host servers WWNs are 16 digit hexadeci...

Page 139: ...n Monitor icon 3 Set priority to host bus adapters using the WWN tab of the Server Priority Manager window In network B the production server is given high priority and the development server is given low priority If your network is configured as in Figure 6 4 you must give high priority to wwn01 and also give low priority to wwn02 and wwn03 To give priority to the three host bus adapters take the...

Page 140: ...easure traffic between the port 1C and the three host bus adapters wwn01 wwn02 and wwn03 Measure traffic between the port 2A and the three host bus adapters wwn01 wwn02 and wwn03 Measure traffic between the port 2C and the three host bus adapters wwn01 wwn02 and wwn03 Figure 6 7 illustrates a graph that describes the I O rate at the paths between each port and the host bus adapters According to th...

Page 141: ...paths between port 1C and the non prioritized WWNs is also 200 IO s The peak I O rate at the paths between port 2A and the non prioritized WWNs is also 200 IO s The peak I O rate at the paths between port 2C and the non prioritized WWNs is also 200 IO s So the recommended upper limit for the non prioritized WWNs is 720 IO s 200 4 0 90 If your network is configured as in Figure 6 4 you must do the ...

Page 142: ...st cannot be connected to the storage system in some cases 7 If necessary apply a threshold If you want to use threshold control set a threshold in the WWN tab in the Server Priority Manager window In the WWN tab you can specify only one threshold for the entire storage system regardless of the number of prioritized WWNs For example if there are three prioritized WWNs in the network and the thresh...

Page 143: ... specified upper limit always takes effect Starting Server Priority Manager To start Server Priority Manager take the following steps To start Server Priority Manager 1 Ensure that the Storage Navigator main window is in Modify mode i e with the background color of the pen tip icon showing light yellow If the background color is gray the window is in View mode and you must change it to Modify mode...

Page 144: ...ndow is displayed Use the Port tab if one to one connection is established between host bus adapters and storage system ports For details on operations in the Port tab see Port Tab Operations Use the WWN tab if many to many connection is established between host bus adapters and storage system ports For details on operations in the WWN tab see WWN Tab Operations ...

Page 145: ...details on the system configuration of one to one connections between host bus adapters and ports see If One to One Connections Link HBAs and Ports This section explains operation procedures you can perform for ports and the entire storage system Analyzing Traffic Statistics The traffic statistics reveal the number of I Os that have been made via ports The traffic statistics also reveal the amount...

Page 146: ...rioritized ports are ports on which the processing has high priority and non prioritized ports are ports on which the processing has low priority Specify a port that connects to a high priority host bus adapter as a prioritized port Specify a port that connects to a low priority host bus adapter as a non prioritized port To set priority to ports on the storage system 1 Start Server Priority Manage...

Page 147: ...ollowing To limit the I O rate for the non prioritized port select IOPS from the list at the upper left corner of the list To limit the transfer rate for the non prioritized port select MB s from the list at the upper left corner of the list 4 Locate the non prioritized port in the list Notes The Attribute column of the list indicates whether ports are prioritized or non prioritized If you cannot ...

Page 148: ...re storage system The procedures for these operations are explained below To set threshold values to traffic at prioritized ports 1 Start Server Priority Manager The Server Priority Manager window is displayed 2 Select the Port tab 3 To set a threshold value for each prioritized port select the type of rates for the threshold value from the list at the upper lest corner of the list To use the I O ...

Page 149: ...set to multiple prioritized ports depending on the transfer rate following controls are executed If I O rate or transfer rate exceeds the threshold in any prioritized port upper limits of all the non prioritized ports take effect If I O rate or transfer rate goes below the threshold in any prioritized port upper limits of all the non prioritized ports do not take effect The threshold control of th...

Page 150: ...HBAs and Ports This section explains operation procedures you can perform for host bus adapters and the entire storage system Monitoring All Traffic between HBAs and Ports When many to many connections are established between host bus adapters HBAs and ports you should make sure that all the traffic between HBAs and ports is monitored To make all the traffics between host bus adapters and ports mo...

Page 151: ...ected WWN of the host bus adapter is moved from Non Monitor to Monitor Note If the specified host bus adapter is also connected to other ports after clicking OK a message appears asking whether to change the settings of that host bus adapter for other ports too Make the same setting for all the ports 9 Repeat step 6 to 8 to move all the host bus adapters displayed below Non Monitor to below Monito...

Page 152: ...will be obliged to be excluded from the monitoring target Consider the intended use of each host and move the host bus adapters which you think not necessary to be monitored to Non Monitor by the following steps To exclude traffic between a host bus adapter and a port from the monitoring target 1 Start Server Priority Manager and ensure that the WWN tab is displayed 2 Select All from the list at t...

Page 153: ...nager window The settings on the window are applied to the storage system Analyzing Traffic Statistics The traffic statistics reveal the number of I Os that have been made via ports from HBAs They also reveal the amount of data that have been transferred between ports and HBAs You must analyze the traffic statistics to determine upper limit values that should be applied to I O rates or transfer ra...

Page 154: ...ost Bus Adapters 6 Analyze the information in the list and then determine upper limit values that should be applied to non prioritized WWNs If necessary determine threshold values that should be applied to prioritized WWNs For details see If Many to Many Connections Link HBAs and Ports Setting Priority for Host Bus Adapters If many to many connection is established between host bus adapters HBAs a...

Page 155: ...ntained in an SPM group see Switching Priority of an SPM Group 9 Right click a host bus adapter WWN in the list and then select Prio Non Prio from the pop up menu The Attribute column of the selected WWN in the list displays Non Prio If you want to specify more than one non prioritized WWN repeat this operation Note You cannot change the priority of a WWN which is contained in an SPM group For det...

Page 156: ... non prioritized WWN 1 Start Server Priority Manager The Server Priority Manager window is displayed 2 Ensure that the WWN tab is displayed 3 Do one of the following To limit the I O rate of the non prioritized WWN select IOPS from the list at the upper left corner To limit the transfer rate of the non prioritized WWN select MB s from the list at the upper left corner 4 In the upper left tree clic...

Page 157: ...y an upper limit value for an SPM group see Setting an Upper Limit Value to HBAs in an SPM Group If one host bus adapter is connected to multiple ports and you specify an upper limit value of the host bus adapter for one port the specified upper limit value will be applied to the host bus adapter settings for other connected ports automatically 7 Click Apply The settings in the window are applied ...

Page 158: ...pter HBA Although you can identify HBAs by WWNs Worldwide Names you will be able to identify HBAs more easily if you assign SPM names WWNs are 16 digit hexadecimal numbers and cannot be changed However SPM names should not necessarily be 16 digit hexadecimal numbers and can be changed The following is the procedure for changing an already assigned SPM name For details on how to assign an SPM name ...

Page 159: ...ily To register a new host bus adapter after replacement 1 Start Server Priority Manager The Server Priority Manager window is displayed 2 Select the WWN tab 3 In the upper left tree select the old host bus adapter from below Monitor and then right click the selection 4 From the pop up menu select Change WWN and SPM Name The Change WWN and SPM Name window is displayed 5 Enter the WWN of the new ho...

Page 160: ...ps To contain multiple HBAs in an SPM group 1 Start Server Priority Manager The Server Priority Manager window is displayed 2 Select the WWN tab 3 In the lower left tree select and right click the Subsystem folder 4 From the pop up menu select Add New SPM Group 5 In the Add New SPM Group window enter the name of the SPM group and then select OK An SPM group is created An SPM group icon is added to...

Page 161: ...ct Delete WWN from the pop up menu The selected host bus adapter icon is deleted from the tree 6 Click Apply The settings on the window are applied to the storage system Switching Priority of an SPM Group All the host bus adapters HBAs in one SPM group must be of the same priority Prioritized WWNs i e high priority HBAs and non prioritized WWNs i e low priority HBAs cannot be mixed in one SPM grou...

Page 162: ...er window is displayed 2 Select the WWN tab 3 In the lower left tree select and right click the Subsystem folder or an SPM group 4 If you selected the Subsystem folder take the following steps a Select IOPS or MB s from the list at the upper left corner of the list Select IOPS if you want to assign an upper limit to the I O rate Select MB s if you want to assign an upper limit to the transfer rate...

Page 163: ... you can confirm each upper limit value Renaming an SPM Group To rename an SPM group take the following steps 1 Start Server Priority Manager The Server Priority Manager window is displayed 2 Select the WWN tab 3 In the lower left tree select and right click an SPM group 4 Select Rename SPM Group from the pop up menu The Rename SPM Group window is displayed 5 Enter the new name and select OK 6 In ...

Page 164: ...1 Start Server Priority Manager The Server Priority Manager window is displayed 2 Select the WWN tab 3 In the lower left tree select and right click an SPM group 4 Select Delete SPM Group from the pop up menu 5 In the Server Priority Manager window click Apply The settings in the window are applied to the storage system ...

Page 165: ... Universal Storage Platform V VM Hitachi Performance Manager User s Guide Using the Export Tool This chapter explains using the Export Tool Files to be Exported Preparing for Using the Export Tool Using the Export Tool Command Reference ...

Page 166: ... 7 2 Statistics about parity groups external volume groups or V VOL groups Table 7 3 LDEV tab in the Performance Management window Statistics about volumes in parity groups in external volume groups or in V VOL groups Table 7 4 Statistics about ports Table 7 5 Statistics about host bus adapters connected to ports Table 7 6 Port LUN tab in the Performance Management window Statistics about volumes ...

Page 167: ...s in a parity group in short range PHY_ExG_Response csv Average response time milliseconds for external volume groups PhyExG_dat ZIP PHY_ExG_Trans csv Amount of transferred data for external volume groups KB sec PHY_ExLDEV_Response_x y csv Average response time milliseconds for volumes in an external volume group PhyExLDEV_dat ZIP PHY_ExLDEV_Trans_x y csv Amount of data transferred for volumes in ...

Page 168: ..._Pending_Rate csv Write pending rates in long range PHY_Short_Write_Pending_Rat e csv Write pending rates in short range PHY_Short_Cache_Usage_Rate csv Usage rates for cache memory Notes 1 millisecond is one thousandth of 1 second The letters x y in CSV filenames indicate a parity group or external volume group Both long range and short range statistics are stored for resource usage and write pend...

Page 169: ... operations from hard disk drives i e parity groups external volume groups or V VOL groups to cache memories in sequential access mode PG_D2CR_Trans csv The number of data transfer operations from hard disk drives i e parity groups external volume groups or V VOL groups to cache memories in random access mode PG_Response csv The average response time microsecond at parity groups external volume gr...

Page 170: ...ratio in sequential access mode LDEV_Rnd_Write_Hit ZIP LDEV_Rnd_Write_Hit_x y csv The write hit ratio in random access mode LDEV_CFW_Write_Hit ZIP LDEV_CFW_Write_Hit_x y csv The write hit ratio in cache fast write mode LDEV_BackTrans ZIP LDEV_BackTrans_x y csv The number of data transfer operations between cache memories and hard disk drives i e volumes per second LDEV_C2D_Trans ZIP LDEV_C2D_Trans...

Page 171: ...te 1 microsecond is one millionth of 1 second Table 7 6 Files with Statistics about Host Bus Adapters Connected to Ports ZIP File CSV File Data Saved in the File PortWWN_xx_IOPS csv The I O rate that is the number of read and write operations per second for HBAs that are connected to a port PortWWN_xx_KBPS csv The size of data transferred per second KB sec between a port and the HBAs connected to ...

Page 172: ...it csv The write hit ratio in sequential access mode LU_Rnd_Write_Hit csv The write hit ratio in random access mode LU_C2D_Trans csv The number of data transfer operations from cache memories and hard disk drives i e LUs LU_D2CS_Trans csv The number of data transfer operations from hard disk drives i e LUs to cache memories in sequential access mode LU_D2CR_Trans csv The number of data transfer op...

Page 173: ...icroseconds for HBAs belonging to an SPM group PPCGWWN_NotGrouped_ IOPS csv The I O rate that is the number of read and write operations per second for HBAs that do not belong to any SPM group PPCGWWN_NotGrouped_ KBPS csv The transfer rate KB sec for HBAs that do not belong to any SPM group PPCGWWN_dat ZIP PPCGWWN_NotGrouped_ Response csv The average response time microseconds for HBAs that do not...

Page 174: ...te copy The number of restore copy remote I Os The number of hits of restore copy remote I Os The number of asynchronous update copy remote I Os The number of asynchronous recordsets The average transfer rate KB sec for asynchronous update copy remote I Os The average response time milliseconds for asynchronous update copy The number of scheduled recordsets The number of recordsets that do not arr...

Page 175: ...Update_Copy_Response csv The average response time milliseconds for the update copy of each volume LU RCLU_Restore_Copy_RIO csv The number of restore copy remote I Os RCLU_Restore_Copy_Hit csv The number of hits of restore copy remote I Os RCLU_Asynchronous_RIO csv The number of asynchronous update copy remote I Os RCLU_Recordset csv The number of asynchronous recordsets RCLU_Asynchronous_Copy_Tra...

Page 176: ...ate copy remote I Os RCLDEV_Update_Copy_Hit ZIP RCLDEV_Update_Copy_Hit_xx csv The number of hits of update copy remote I Os RCLDEV_Update_Copy_Transfe r ZIP RCLDEV_Update_Copy_Transfe r_xx csv The average transfer rate KB sec for update copy remote I Os RCLDEV_Update_Copy_Respon se ZIP RCLDEV_Update_Copy_Respon se_xx csv The average response time milliseconds for the update copy at volumes RCLDEV_...

Page 177: ...sv Sidefile usage rate percent per CLPR Table 7 14 Files with Statistics about Remote Copy Operations by UR and UR for IBM z OS In the Whole Volumes ZIP File CSV File Data Saved in the File UniversalReplicator ZIP UniversalReplicator csv The following data in the whole volumes are saved The number of write I Os per second The amount of data that are written per second KB sec The initial copy hit r...

Page 178: ...rage transfer rate KB sec for journals in the primary storage system URJNL_M JNL_Asynchronous_Copy_Res ponse csv The remote I O average response time milliseconds on the primary storage system URJNL_R JNL_Asynchronous_RIO csv The number of asynchronous remote I Os per second at the secondary storage system URJNL_R JNL_Asynchronous_Journal cs v The number of journals at the secondary storage system...

Page 179: ... At Volumes Controlled by a Particular CU ZIP File CSV File Data Saved in the File URLDEV_Read_Record ZIP URLDEV_Read_Record_xx csv The number of read I Os per second URLDEV_Read_Hit ZIP URLDEV_Read_Hit_xx csv The number of read hit records per second URLDEV_Write_Record ZIP URLDEV_Write_Record_xx csv The number of write I Os per second URLDEV_Write_Hit ZIP URLDEV_Write_Hit_xx csv The number of wr...

Page 180: ... Export Tool is the same as the JRE version required for running Storage Navigator For detailed information about the JRE version required for running Storage Navigator see the Storage Navigator User s Guide A user ID exclusively for use with the Export Tool If you want to use the Export Tool you must create a user ID that will be used exclusively with the Export Tool When you create the user ID n...

Page 181: ... UNIX computer see Installing the Export Tool on a UNIX Computer Installing the Export Tool on a Windows Computer To install the Export Tool on a Windows computer 1 Create a directory on your Windows computer In later steps you will install the Export Tool on the new directory 2 Insert the Export Tool installation media into the CD ROM drive 3 Locate the self extracting file export EXE in the dire...

Page 182: ...ram monitor solaris in your CD ROM disc and then copy export tar to the new directory that you created earlier If you are using HP UX locate the archive file export tar in the directory program monitor HP UX in your CD ROM disc and then copy export tar to the new directory that you created earlier 4 Decompress export tar on your computer The Export Tool is installed Also a new directory named expo...

Page 183: ...Specifies type of data to be exported and type of storing period group RemoteCopy Specifies type of data to be exported short range 200610010850 200610010910 Specifies term of data to be exported for data stored in short range long range 200609301430 200610011430 Specifies term of data to be exported for data stored in long range outpath out Specifies directory in which files will be saved option ...

Page 184: ...n example of information that the show subcommand outputs Short Range From 2006 10 01 01 00 To 2006 10 01 15 00 Interval 1min Long Range From 2006 09 01 00 00 To 2006 10 01 15 00 Interval 15min Short Range indicates the storing period and gathering interval of the monitoring data stored in short range Long Range indicates those of the monitoring data stored in long range In the above example the m...

Page 185: ... follows The short range subcommand is valid for monitoring data in short range You can use this subcommand to narrow the export target term for all the monitoring items you can specify by the group subcommand Specify a term within Short Range From XXX To XXX which is output by the show subcommand The long range subcommand is valid for monitoring data in long range You can use this subcommand only...

Page 186: ...option subcommand see option Subcommand apply The apply subcommand saves monitoring data in files For detailed information about the apply command see apply Subcommand When you install the Export Tool the file command txt will be stored in the export directory The command txt file contains sample scripts for your command file It is recommended that you customize scripts in command txt according to...

Page 187: ...xport Tool communicates with the SVP via a proxy host you need to edit the Java command script in your text editor When editing the Java command script you need to specify the host name or the IP address and the port number of the proxy host For example if the host name is Jupiter and the port number is 8080 the resulting command script as shown in Figure 7 3 Batch file for Windows computers runWi...

Page 188: ...unning the Export Tool To run the Export Tool and save monitoring data in files you need to execute your batch file To execute your batch file you need to enter the name of the batch file at the command prompt and then press the Enter key If you are using a Windows computer you can double click the batch file to execute the batch file c WINDOWS cd c export Å Go to the directory containing runWin b...

Page 189: ...re for decompressing ZIP files you need to obtain software for decompressing files For a complete list of files to be saved by the Export Tool see Using the Export Tool When an internal error occurs during export processing the exclamation mark appears to signal the error If this happens the Export Tool will make up to three more attempts at processing If export processing does not finish through ...

Page 190: ... invalid If you specify the nocompress operand for the option subcommand the Export Tool saves files in CSV format instead of ZIP format For detailed information see option Subcommand When files are saved in CSV format instead of ZIP format the file saving process could take longer and the resulting files could be larger Files saved by the Export Tool are often very large The total file size for a...

Page 191: ...rt Tool should save statistics about 8 192 volumes within a 24 hour period The Export Tool is used eight times Each time the Export Tool is used the tool obtains statistics within a 3 hour period LU 60 minutes This estimate assumes The Export Tool should save statistics about 12 288 LUs within a 24 hour period The Export Tool is used eight times Each time the Export Tool is used the tool obtains s...

Page 192: ...IBM z OS Universal Replicator and Universal Replicator for IBM z OS If you want to use a reference to a termination code in your batch file do the following To use such a reference in a Windows batch file write errorlevel in the batch file To use such a reference in a UNIX Bourne shell script write in the shell script To use such a reference in a UNIX C shell script write status in the shell scrip...

Page 193: ...f monitoring data stored in the SVP and the data collection interval that is called gathering interval and then outputs them to the standard output and the log file show Subcommand group Specifies the type of data that you want to export group Subcommand short range Specifies the term of monitoring data to be exported for short range monitoring data short range Subcommand long range Specifies the ...

Page 194: ...s in italics as they are Indicates one or more operands that can be omitted If two or more operands are enclosed by these square brackets and are delimited by vertical bars you can select one of the operands Indicates that you must select one operand from the operands enclosed by the braces Two or more operands are enclosed by the braces and are delimited by vertical bars Indicates that a previous...

Page 195: ...in your command file If you enter a semicolon in one line the remaining characters in that line will be regarded as a comment COMMAND FILE command txt svpip 158 214 135 57 IP address of SVP login expusr passwd Log onto SVP Figure 7 8 Examples of Comments Viewing the Online Help for subcommands You can display the online Help to view the syntax of subcommands when you are working at the command pro...

Page 196: ...th IPv6 Internet Protocol Version 6 you must specify the ip address operand to match the format of IPv6 If the Export Tool runs on Windows XP the interface identifier for example 5 must be added to the end of the specified IP address host name Specifies the host name of the SVP If the host name includes any character that is neither an alphanumeric nor a period the host name must be enclosed by do...

Page 197: ...try is two minutes You can change the interval by using the retry subcommand The retry subcommand must execute before the login subcommand executes Operands time m Specifies the interval between retries in minutes m is a value within the range of 1 to 59 If this operand is omitted the interval between retries is two minutes count n Specifies the maximum number of retries If n is 0 the number of re...

Page 198: ...erid Specifies the user ID for the SVP If the user ID includes any non alphanumeric character the user ID must be enclosed by double quotation marks Be sure to specify a user ID that should be used exclusively with the Export Tool For detailed information see Requirements for Using the Export Tool password Specifies the password of the user If the password includes any non alphanumeric character t...

Page 199: ...and in long range For example the show subcommand outputs the following information Short Range From 2006 10 01 01 00 To 2006 10 01 15 00 Interval 1min Long Range From 2006 09 01 00 00 To 2006 10 01 15 00 Interval 15min Short Range indicates the storing period and gathering interval of the monitoring data stored in short range Long Range indicates those of the monitoring data stored in long range ...

Page 200: ...Platform V VM Hitachi Performance Manager User s Guide The show subcommand outputs the period from May 2 2006 03 12 to May 3 2006 03 12 Figure 7 9 Information output by the show subcommand The login command must execute before the show subcommand executes ...

Page 201: ... group id port name host group id U RCLDEVU CU id CU id U RCCLPR UniversalReplicatorU URJNLU JNL group id JNL group id U URLUU port name host group id port name host group id U URLDEVU CU id CU id U Description The group subcommand specifies the type of monitoring data that you want to export This command uses an operand such as PhyPG and PhyLDEV above to specify a type of monitoring data Table 7 ...

Page 202: ...e 7 4 Port Statistics about ports Port_dat ZIP Table 7 5 PortWWN Statistics about host bus adapters connected to ports PortWWN_dat ZIP Table 7 6 LU Port LUN tab in the Performance Management window Statistics about LUs LU_dat ZIP Table 7 7 PPCG Statistics about SPM groups PPCG_dat ZIP Table 7 8 PPCGWWN WWN tab in the Performance Management window Statistics about host bus adapters belonging to SPM...

Page 203: ...ations by Universal Replicator and Universal Replicator for IBM z OS for volumes controlled by a particular CU URLDEV_XXXXX ZIP 4 Table 7 17 Notes 1 When you specify the PhyPG PhyLDEV PhyProc or PhyCSW operand you can select the storing period of the monitoring data to be exported from short range or long range When you specify other operands the monitoring data in short range is exported 2 A ZIP ...

Page 204: ... but you cannot specify PhyPG 1 5 1 1 Also you can specify PhyPG 1 5 2 1 but you cannot specify PhyPG 2 1 1 5 If parity group id is not specified the monitoring data of all the parity groups will be exported PhyLDEVU Short Long U parity group id parity group id U Use this operand when you want to export statistics about volume usage rates which are displayed in the Physical tab of the Performance ...

Page 205: ...the external volume groups will be exported PhyExLDEVU exg id exg id U Use this operand when you want to export statistics about volumes in external volume groups which are displayed in the Physical tab of the Performance Management window When statistics are exported to a ZIP file the file name will be PhyExLDEV_dat ZIP For details on the statistics exported by this operand see Table 7 2 When you...

Page 206: ...ysical tab of the Performance Management window Usage rates of access paths between channel adapters and cache memories Usage rates of access paths between disk adapters and cache memories Usage rates of access paths between channel adapters and the shared memory Usage rates of access paths between disk adapters and the shared memory Usage rates of access paths between cache switches and cache mem...

Page 207: ...s parity groups from 1 1 to 1 5 E1 1 E1 5 indicates external volume groups from E1 1 to E1 5 V1 1 V5 1 indicates V VOL groups from V1 1 to V5 1 X1 1 X5 1 indicates V VOL groups from X1 1 to X5 1 Ensure that the parity group id exg id or V VOL group id value on the left of the colon is smaller than the parity group id exg id or V VOL group id value on the right of the colon For example you can spec...

Page 208: ...ndicates V VOL groups from X1 1 to X5 1 Ensure that the parity group id exg id or V VOL group id value on the left of the colon is smaller than the parity group id exg id or V VOL group id value on the right of the colon For example you can specify LDEV 1 1 1 5 but you cannot specify LDEV 1 5 1 1 Also you can specify LDEV 1 5 2 1 but you cannot specify LDEV 2 1 1 5 If neither of parity group id ex...

Page 209: ...ent window When statistics are exported in a ZIP file the file name will be PortWWN_dat ZIP For details on the statistics exported by this operand see Table 7 6 When you specify variables port name you can narrow the range of ports whose monitoring data are to be exported port name is a port name The colon indicates a range For example CL3 a CL3 c indicates ports from CL3 a to CL3 c Ensure that th...

Page 210: ...s operand when you want to export statistics about SPM groups which are displayed in the WWN tab of the Performance Management window When statistics are exported in a ZIP file the file name will be PPCG_dat ZIP For details on the statistics exported by this operand see Table 7 8 When you specify variables SPM group name you can narrow the range of SPM groups whose monitoring data are to be export...

Page 211: ...SPM group name U Use this operand when you want to export statistics about host bus adapters WWNs belonging to SPM groups which are displayed in the WWN tab of the Performance Management window When statistics are exported in a ZIP file the file name will be PPCGWWN_dat ZIP For details on the statistics exported by this operand see ...

Page 212: ...rmed by TrueCopy and TrueCopy for IBM z OS in the whole volumes When statistics are exported to a ZIP file the file name will be RemoteCopy_dat ZIP For details on the statistics exported by this operand see Table 7 10 RCLUU port name host group id port name host group id U Use this operand when you want to export statistics about remote copy operations which are displayed in the TC Monitor window ...

Page 213: ...f all the volumes LUs will be exported RCLDEVU LDKC CU id LDKC CU id U Use this operand when you want to export statistics about remote copy operations which are displayed in the TC Monitor window and the TCz Monitor window By using this operand you can export monitoring data about remote copy operations performed by TrueCopy and TrueCopy for IBM z OS at volumes controlled by each CU When statisti...

Page 214: ...SLPRs that are SLPR0 corresponding to CLPR0 and CLPR2 and SLPR1 corresponding to CLPR1 those CLPRs are arranged as follows CLPR0 CLPR2 CLPR1 UniversalReplicator Use this operand when you want to export statistics about remote copy operations which are displayed in the UR Monitor window and the URz Monitor window By using this operand you can export monitoring data about remote copy operations perf...

Page 215: ... of all the journal volumes will be exported URLUU port name host group id port name host group id U Use this operand when you want to export statistics about remote copy operations which are displayed in the UR Monitor window and the URz Monitor window By using this operand you can export monitoring data about remote copy operations performed by Universal Replicator and Universal Replicator for I...

Page 216: ...onitoring data of all the volumes LUs will be exported URLDEVU LDKC CU id LDKC CU id U Use this operand when you want to export statistics about remote copy operations which are displayed in the UR Monitor window and the URz Monitor window By using this operand you can export monitoring data about remote copy operations performed by Universal Replicator and Universal Replicator for IBM z OS at vol...

Page 217: ... group 1 3 group PG 1 3 1 3 The following example exports statistics about the parity group 1 3 and other parity groups whose ID is larger than 1 3 for example 1 4 and 1 5 group PG 1 3 The following example exports statistics about the external volume groups E1 1 to E1 5 group PG E1 1 E1 5 The following example exports statistics about the parity group 1 3 and other parity groups whose ID is small...

Page 218: ...ed in short range Therefore you can use the short range subcommand whichever operand you specify to the group subcommand If you run the Export Tool without specifying the short range subcommand the data stored in the whole monitoring term will be exported The login subcommand must execute before the short range subcommand executes Operands The value on the left of the colon specifies the starting ...

Page 219: ...s time hhmm from yyyyMMddhhmm if yyyyMMddhhmm is specified For example 200601230000 0130 indicates Jan 22 2006 22 30 Subtracts time from the ending time for collecting monitoring data if yyyyMMddhhmm is omitted If the last two digit of the time on the left or right of the colon is not a multiple of the sampling interval the time will automatically be changed so that the last two digits is a multip...

Page 220: ...ta within the range of Jan 1 9 30 17 30 short range 200601010930 The Export Tool saves monitoring data within the range of Jan 1 9 30 to Jan 2 00 00 shortrange 200601011730 The Export Tool saves monitoring data within the range of Jan 1 0 00 17 30 short range 0001 The Export Tool saves monitoring data within the range of Jan 1 0 01 to Jan 2 00 00 short range 0001 The Export Tool saves monitoring d...

Page 221: ...chi Performance Manager User s Guide short range 200601010900 0130 200601011700 0130 The Export Tool saves monitoring data within the range of Jan 1 7 30 18 30 short range 200601010900 0130 The Export Tool saves monitoring data within the range of Jan 1 7 30 to Jan 2 00 00 ...

Page 222: ...e subcommand can be applied and also shows the operands to export those monitoring items Table 7 24 Monitoring Items To Which the long range Subcommand Can be Applied Monitoring Data Operands of the group subcommand Usage statistics about parity groups PhyPG Long Usage statistics about volumes PhyLDEV Long Usage statistics about channel processors disk processors and data recovery and reconstructi...

Page 223: ...he starting time for collecting monitoring data is assumed If yyyyMMddhhmm is omitted on the right of the colon the ending time for collecting monitoring data is assumed ddhhmm Adds time ddhhmm to yyyyMMddhhmm if yyyyMMddhhmm is specified For example 200601120000 010130 indicates Jan 13 2006 01 30 Adds time to the starting time for collecting monitoring data if yyyyMMddhhmm is omitted ddhhmm Subtr...

Page 224: ...an 1 0 00 17 30 long range 000015 The Export Tool saves monitoring data within the range of Jan 1 0 15 to Jan 2 00 00 long range 000015 The Export Tool saves monitoring data within the range of Jan 1 23 45 to Jan 2 00 00 longrange 000015 The Export Tool saves monitoring data within the range of Jan 1 0 00 00 15 longrange 000015 The Export Tool saves monitoring data within the range of Jan 1 0 00 2...

Page 225: ...Using the Export Tool 7 61 Hitachi Universal Storage Platform V VM Hitachi Performance Manager User s Guide The Export Tool saves monitoring data within the range of Jan 1 7 30 to Jan 2 00 00 ...

Page 226: ...acter the directory must be enclosed by double quotation marks If you want to specify a back slash in the character string enclosed by double quotation marks repeat the back slash twice such as If the specified directory does not exist this subcommand creates a directory that has the specified name If this operand is omitted the current directory is assumed Examples The following example saves fil...

Page 227: ...d compress is assumed compress Compresses data in ZIP files To extract CSV files out of a ZIP file you will need to decompress the ZIP file nocompress Does not compress data in ZIP files and saves data in CSV files The three operands below specify whether to overwrite or delete an existing file or directory when the Export Tool saves files If none of these operands is specified ask is assumed ask ...

Page 228: ...ing performance statistics The set subcommand also specifies the gathering interval interval of collecting statistics in short range monitoring If you want to use the set subcommand you must use the login subcommand see login Subcommand to log on to the SVP Ensure that the set subcommand executes immediately before the Export Tool finishes Executing the set subcommand generates an error in the fol...

Page 229: ...f you change the specified gathering interval during a monitoring the previously gathered monitoring data will be deleted Operands switch m off To start monitoring specify the gathering interval interval of collecting statistics of monitoring data at m Specify a value between 1 and 15 in minutes m is the gathering interval in short range monitoring by Performance Monitor The gathering interval in ...

Page 230: ... txt help Batch file c export runHelp bat Java classpath lib JSanExport jar lib JSanRmiServerSx jar Xmx536870912 Dmd command cmdHelp txt Dmd logpath log sanproject getmondat RJMdMain pause In the above script the symbol in this batch file example indicates the end of a command line In this example you must do one of the following to view the online Help Double click runHelp bat with the mouse Go t...

Page 231: ...xecuted You must specify this parameter The memory size must be 536870912 as shown in the Example later in this section If an installed memory size is smaller than the recommended memory size of Storage Navigator PC you must install more memory before executing the Export Tool If an installed memory size is larger than the recommended memory size of Storage Navigator PC you can specify a memory si...

Page 232: ... lib JSanExport jar lib JSanRmiServerSx jar Dhttp proxyHost Jupiter Dhttp proxyPort 8080 Xmx536870912 Dmd command command txt Dmd logpath log sanproject getmondat RJMdMain In the following example a log file named export log will be created in the log directory below the current directory when the Export Tool executes Java classpath lib JSanExport jar lib JSanRmiServerSx jar Xmx536870912 Dmd comma...

Page 233: ...and Table 7 15 If Disable is selected to stop monitoring in Monitoring Switch on the Monitoring Options window and longrange is specified as the gathering interval the monitoring data for the period when Performance Monitor stops monitoring is 1 If you added the CU during monitoring specified longrange as the gathering interval and collected monitoring data the value 1 is displayed as the monitori...

Page 234: ...V operand is specified the value of the monitoring data is 5 To solve this problem specify the CU as the monitoring target by using the Monitoring Options window of Performance Monitor not by using the Export Tool For details on specifying the CU as the monitoring target see Monitoring Options Window and Table 4 4 If the RemoteCopy UniversalReplicator or URJNL operand is specified the value 5 is n...

Page 235: ... information on Performance Monitor Server Priority Manager and Export Tool For troubleshooting information on Storage Navigator see the Storage Navigator User s Guide and Storage Navigator Messages Troubleshooting Performance Monitor Troubleshooting Server Priority Manager Troubleshooting the Export Tool Calling the Hitachi Data Systems Support Center ...

Page 236: ...s and Ports When a part of monitoring data is missing While displaying Performance Monitor in short range if I O workloads between hosts and the storage system become heavy the storage system gives higher priority to I O processing than monitoring processing If you notice that frequently monitoring data is missing use the Gathering Interval option located in the Monitoring Options window to change...

Page 237: ... add a path to the environment variable refer to the documentation for your operating system An incorrect version of Java Runtime Environment JRE might be installed on your computer To check the JRE version enter the following command at the Windows command prompt or the UNIX console window Java version If the version is incorrect install the correct version of JRE The Export Tool stops and the pr...

Page 238: ...ams are correct When a CSV file is opened the parity group ID and volume ID are displayed as following The parity group IDs are displayed as dates The volume IDs are displayed with a decimal point To display a CSV file correctly you need to perform following operations 1 Start Microsoft Excel 2 On the menu bar select Data Import External Data and Import Text File and specify a CSV file to import T...

Page 239: ...rrently executing the Export Tool Note If the error cause is step 4 or 5 above Do one of the following ask one of the users to display another window ask one of the users to log off wait for one of the users to quit the Export Tool Missing command file The command file is not specified Specify the name of the command file correctly Missing group name No operand is specified in the group subcommand...

Page 240: ... as a storage partition administrator Unable to use the group name operand The specified operand of the group subcommand is unavailable because you logged in as a storage partition administrator Unknown host host The Export Tool cannot resolve the host name Specify the correct host name Unsupported command command The Export Tool does not support the specified command Specify a correct command Uns...

Page 241: ... example suppose that the storage system contains 100 parity groups and the command file contains the following command line group PG 1 1 1 2 The Export Tool displays the message Target 2 Total 100 which means that the group subcommand specifies two parity groups and that the total number of parity groups in the storage system is 100 Syntax error line A syntax error is detected in a command line i...

Page 242: ...st system s The Volume Retention Manager or other error code s displayed by the Storage Navigator computer The USP V VM Storage Navigator configuration information saved on diskette using the FD Dump Tool see the Storage Navigator User s Guide The remote service information messages R SIMs logged on the Storage Navigator computer and the reference codes and severity levels of the recent R SIMs The...

Page 243: ...N Disk Controller Main DKP disk processor DRR data recovery and reconstruction ESCON Enterprise System Connection IBM trademark for optical channels GB gigabyte see Convention for Storage Capacity Values HBA host bus adapter HDD hard disk drive JRE Java Runtime Environment KB kilobyte see Convention for Storage Capacity Values LAN local area network LDEV logical device LDKC logical disk controller...

Page 244: ...D redundant array of independent disks SIM service information message SLPR storage management logical partition SM shared memory SMPL simplex SPM Server Priority Manager S VOL secondary volume SVP service processor TB terabyte see Convention for Storage Capacity Values TC TrueCopy TCz TrueCopy for IBM z OS UR Universal Replicator USP Universal Storage Platform VLL Virtual LVI LUN V VOL virtual vo...

Page 245: ...reconstruction processor H HBA Refer to host bus adapter host bus adapter 2 13 4 21 5 45 6 2 I I O rate 2 11 2 12 5 26 6 4 N nickname 5 36 5 39 non prioritized port 6 14 non prioritized port 6 3 non prioritized WWN 6 8 6 22 P parity group 2 4 Performance Manager system requirements 3 2 prioritized port 6 3 6 14 prioritized WWN 6 8 6 22 production server 2 13 R read hit ratio 2 11 5 26 real time mo...

Page 246: ...Index 2 Index Hitachi Universal Storage Platform V VM Hitachi Performance Manager User s Guide ...

Page 247: ...Hitachi Universal Storage Platform V VM Hitachi Performance Manager User s Guide ...

Page 248: ...5050 2627 U S A Phone 1 408 970 1000 www hds com info hds com Asia Pacific and Americas 750 Central Expressway Santa Clara California 95050 2627 U S A Phone 1 408 970 1000 info hds com Europe Headquarters Sefton Park Stoke Poges Buckinghamshire SL2 4HD United Kingdom Phone 44 0 1753 618000 info eu hds com ...

Reviews: