Hp XP Performance Advisor Software Manual de usuario

HP XP P9000 Performance Advisor SoftwareUser GuideAbstractThis document describes how to use the HP XP P9000 Performance Advisor Software product and

1 Introduction to HP XP P9000 Performance AdvisorOverviewHP XP P9000 Performance Advisor Software collects, monitors, and displays the performance ofX

NOTE: The LDEVs, journal groups, or the E-LUNs are referred as consumers on the Dashboardscreen.By default, the consumers are sorted in a descending o

DescriptionScreen elementsThe MBPS threshold value indicates the average MB/s that youdefine an individual port can handle over a specified duration.M

DescriptionScreen elementswhether the average sequential I/Os on each RAID group iswithin or beyond the set threshold limit.If the average sequential

DescriptionScreen elementsNOTE: The MP Blade Util (%) metric is applicable for MPblades on the P9000 disk arrays.Viewing dashboardHP XP P9000 Performa

NOTE:• Click Add New Licenses to add licenses for the XP and the P9000 disk arrays on the Licensescreen. For more information, see “Installing license

DescriptionStatus iconIndicates that the particular category is not applicable forthe selected array.appears in the MP Blade category for the XP disk

HP XP P9000 Performance Advisor considers the following factors to arrive at the average usagedata for a component in the Frontend, Cache, Backend, an

Component levels in the Statistics sectionWhen you click a status icon in the Frontend, Cache, Backend, or the MP Blade category, therelated component

DescriptionMetricsCategoryIn addition, the Side File Usage (%)data and the Cache Size (total in MB)are also displayed.RG Seq Reads (IOPS) (Avg Seq Rea

DescriptionMetricsCategoryNOTE: In a 100% ThP environment,the Dashboard Backend metrics showzero values for an XP or a P9000 diskarray. This is becaus

2 Working with the HP XP P9000 Performance Advisor GUIIntroductionThe HP XP P9000 Performance Advisor screen has the following sections:• Title bar• L

Related Topics• “XP/P9000 array health” (page 104)• “Dashboard busiest consumers” (page 110)• “Dashboard charts” (page 111)• “High watermark in dashbo

DescriptionMetricsThe frontend throughput in MB/s read and written to the LDEVduring the specified threshold duration.Block IO MBPSThe average of the

3. Select the check box for the metric, for which you want to view the performance or usagegraph of the selected component, and click OK.HP XP P9000 P

IMPORTANT:• High watermark is applicable only for components in the Frontend, Cache, Backend, and MPBlade categories. It is not applicable for LDEVs.•

7 Configuring alarms and managing eventsThis chapter discusses the following topics:• “Introduction” (page 114)• “Configuring alarms and viewing alarm

Once the alarms are activated, you can view history for these alarms, which provides data on thefollowing:• When the performance of components went be

NOTE:• If you configure alarms at the host group level, and then edit a host in any port, the alarmnotification is sent only for the common host group

When you click Add alarm(s), the record pertaining to 53046 and the SM CHIP BUS/Path Utilmetric is added to the Alarms table. The Resource column disp

all the alarm records configured on the selected XP and P9000 disk arrays, and component aredisplayed in the Alarms table.Filtering records is based o

recipients when the current performance value of a component goes beyond the threshold levelthat you configured.NOTE: You can also use the Ctrl + c an

• About: Click About to view the product part number, build, and version number.• Support: Click Support to view the HP XP P9000 Performance Advisor S

in the subject line of the email. If the alarm is entering the dispatch at threshold level, HP XP P9000Performance Advisor identifies the alarm as a n

The changes are updated in the HP XP P9000 Performance Advisor database and accordinglyreflected in the Email Destination box and the SNMP Destination

3. Provide the script location in the text box under Script Destination.HP XP P9000 Performance Advisor automatically executes the script when the per

2. In the Alarms table, select the component records for which you want to specify the thresholdlevel.You can also filter component records in the Ala

3. Select the records for which the copied settings should be applied. (It is not mandatory thatyou click the check box for a component record to sele

1. Click PA and DB Settings+Configure Alarms in the left pane.2. Select the record that you want to delete.3. Click Delete.The records are permanently

2. After all the host groups are traversed, the pool branch is traversed, followed by back-end,replication-volumes, LUSE branch, and the Drive-Types b

Searching for components 127

NOTE:• For the Raid Group, the Host Group branch is traversed first, followed by the Pool branch,Back-end, and finally the Drive Types branch.• You ca

IMPORTANT:• The search results are specific to an XP or a P9000 disk array. You cannot search forcomponents (LDEVS, RG, HG, POOL, PORT) physical LDEVs

Right paneThe right pane displays the screen based on the menu that you select in the left pane. You canselect related options on these screens to ach

In every data collection cycle, HP XP P9000 Performance Advisor retrieves and compares thecurrent performance value of a component with the set thresh

Table 7 Viewing alarm History records (continued)DescriptionScreen elementsNOTE: The Resource is displayed as PVOL: LDEVID(serial number) and SVOL: LD

Filtering records in Alarms History tableTo filter alarm history records based on Alarm History filters:1. Click Monitoring+Alarm History in the left

DescriptionScreen elementsXP P9000 Performance Advisor displays only zero items,that is the alarms that were successfully dispatched.Displays the disk

Related Topics• “Understanding alarms history” (page 129)• “Alarm History screen” (page 130)• “Filtering records in Alarms History table” (page 132)•

The performance graph also displays the Dispatch Threshold value that is the threshold value forwhich an alarm was configured to be dispatched. The Di

In addition, view the following details on the Event Log screen:• Historic data (data older than 24 hours) by specifying a date range for viewing the

4. Select one of the following severity level from the Severity list. By default, the event recordsfor all levels of severity are displayed:Descriptio

8 Managing the HP XP P9000 Performance AdvisordatabaseThis chapter discusses the following topics:• “Introduction” (page 138)• “Configuring database s

IMPORTANT:• You have to log on to HP XP P9000 Performance Advisor as an Administrator or a user withadministrator privileges to configure, purge, arch

• Columns are sorted depending on the type of information that appears in the respectivecolumns (alphabetical, numerical, or date related). For exampl

• “Importing data” (page 160)• “Deleting logs for archival and import activities” (page 162)Configuring database sizeYou can increase the HP XP P9000

the Event log screen:There is not enough space for the DB to autogrow;AutoGrow option is disabled.If free disk space is not available, HP XP P9000 Per

1. Click PA and DB Settings+Database Manager in the left pane.The Database Manager screen appears. By default, the DB Configuration/Purge is enabled.2

Manually purging dataYou can manually purge data that belongs to an XP or a P9000 disk array, or data that is olderthan the current specified date.CAU

Related Topics• “Automatically increasing the database size (AutoGrow)” (page 140)• “Manually increasing the database size” (page 141)• “Automatically

If you enter an invalid value, then by default, the maximum threshold value is considered as85. When the current database size reaches the default max

IMPORTANT:• HP recommends that you schedule the Delete and Shrink operations at a different time in sucha way that the Delete operation is performed f

Related Topics• “Creating Export DB CSV files” (page 150)• “Viewing Export DB CSV files” (page 155)Export DB CSV filesThis section describes the follo

• The percentage of writes that are held in the cache, yet to be transferred to the disks over anentire collection interval.• The MB/s of the continuo

This file includes the following details:• The P9000 disk array serial number for which the report is generated.• The MP blade IDs, the cluster # and

3 Managing licenses for XP and P9000 disk arraysThis chapter discusses the following topics:• “Introduction” (page 15)• “Instant-on license on HP XP P

Creating Export DB CSV filesIMPORTANT:• If you have logged in with user privileges, you cannot schedule the export DB activity.• 020000 is the support

3. Based on your requirement, select the Collection Period as One Time or Recurring.• If you select the Collection Period as One Time, proceed to step

◦ Collection Schedule: Displays Daily, Weekly, and Monthly.DescriptionCollection ScheduleBy default, Weekly is selected as the collectionschedule. The

4. Provide a name in the File Name box. The name must have a minimum of two characters andcan have a maximum of 80 characters. HP XP P9000 Performance

10. Select the check box for Display LDEV's of the Journal, if you want to view all the LDEVs thatbelong to a journal pool.11. Select the Start T

• “Importing data” (page 160)• “Deleting logs for archival and import activities” (page 162)• “Migrating data to another management station” (page 163

IMPORTANT:• The name of the user who created the report is displayed under User Name. If you logged into HP XP P9000 Performance Advisor as an Adminis

• “Migrating data to another management station” (page 163)• “Generating, saving, or scheduling reports” (page 297)Deleting Export DB reports and sche

IMPORTANT:• After the data is archived, it is permanently deleted from the HP XP P9000 Performance Advisordatabase and the free disk space is released

5. Click Export.HP XP P9000 Performance Advisor archives data for the specified duration. As part of thearchival process, HP XP P9000 Performance Advi

Table 1 License management during installation or upgrade (continued)License managementInstallation or upgradePerformance Advisor, after which a grace

Importing dataYou can import the archived data to another management station or back to the same managementstation from where the data was initially e

IMPORTANT: The following are a few important points:• After importing performance data for an XP or a P9000 disk array, ensure that you performa fresh

NOTE: <HPSS_HOME> translates to %PADB_HOME% in this context of importing data.4. Click Import. Based on whether the import is for an XP or a P90

2. On the Database Manager screen, click the Archive Export/Archive Import tab.3. Based on whether you want to delete the archival logs or the import

P9000 disk arrays during the specified duration is backedup into the following .dmp files:• PA<XP or P9000_Disk_Array>_Exp.dmp up toPA<XP or

2. Based on your requirement, select one of the following options:• DKC: Provide the 5 digit serial number of the XP or the P9000 disk array, for whic

Where, target-path is the location, such as a network drive or shared file system whereyou want to save the backup files.You can also backup data for

/ Port_Collection_ frequency) * PORTs * Port_Space] + [(SECONDS_PER_DAY/Dkc_Collection_ frequency) * Dkc_Space]where:• Free_Space (MB/day) = Total fre

Example 1 Determining the disk space requirements for HP XP P9000 Performance AdvisorConsider that the P9000 and the XP disk arrays, P9500 and XP24000

9 Viewing XP and P9000 disk array componentsThis chapter discusses the following topics:• “Introduction” (page 169)• “Viewing performance summary” (pa

Figure 2 License screenDescriptionScreen elementsIn this section, add the licenses (.dat files) that yougenerated at the HPAC license key website.Add

1. Click Monitoring+Array View in the left pane.All the XP and the P9000 disk arrays monitored by HP XP P9000 Performance Advisor aregrouped under Arr

Figure 11 Array View screenFurther, to view the performance and utilization metrics at the component level in the disk array,click the plus (+) sign f

Table 8 Array View component nodes (continued)For P9000 disk arraysFor XP disk arraysDocumentation LinksDescriptionComponent selection treegroups in t

Table 8 Array View component nodes (continued)For P9000 disk arraysFor XP disk arraysDocumentation LinksDescriptionComponent selection treeYesYes“Port

Table 8 Array View component nodes (continued)For P9000 disk arraysFor XP disk arraysDocumentation LinksDescriptionComponent selection treeYesNoProvid

The following table describes the Performance View screen elements. The images shown are for53036, which belongs to the P9500 Disk Array type.Descript

DescriptionPerformance View screen elementsDisplays the I/Os, MB/s, and theassociated port IDs for all thoseCHIPs/CHAs that are processingrequests.The

DescriptionPerformance View screen elementsby only DKA_1. If the combinedbackend transfers on ThP_Pool_1 is50 I/Os, and ThP_Pool_2 is 30I/Os, the comb

IMPORTANT:• The MIX CHIP displays only eight ports and four MPs though there are eight MPs on thatboard. The remaining four behave as ACP MPs.• If per

IMPORTANT: The RmLib Version displays zero if the configuration data is collected through theoutband mode.Volume InformationThe following table provid

Related Topics• “HP XP P9000 Performance Advisor licenses” (page 21)• “Generating licenses at the HPAC license key website” (page 29)• “Instant-on lic

• “10 busiest LDEVs/Ports” (page 205)• “10 busiest LDEVs/RAID groups” (page 206)• “RAID Group summary” (page 208)• “Port summary” (page 210)• “Viewing

• MP blade utilization, which includes the following:MP blade IDs.◦◦ DKCs, cluster #, and the blade locations for the MP blades.◦ The MPs on the MP bl

Advisory on CLPR utilizationHP XP P9000 Performance Advisor provides an advisory on the usage of individual CLPRs in anXP or a P9000 disk array. The a

The summary is displayed in the CHIP/CHA summary table for the XP disk arrays and the CHAsummary table for the P9000 disk arrays (see following images

The following table describes the CHIP/CHA summary table for an XP disk array and the CHAsummary table for a P9000 disk array.CHA summary table for P9

IMPORTANT:• The port type, such as Fibre or FCoE (applicable only for P9000 disk arrays) is also displayedbeside the port ID.• Since, the CHIP/CHA and

The individual performance data for CHA-1EU includes the following:• Summary:Fibre protocol is used◦◦ Eight ports are associated with CHA-1EU◦ Port Ac

Further, you can also click an individual ACP/DKA pair in one of the above-mentioned tables toview its metrics. For more information, see “Viewing sum

The following table describes the ACP/DKA summary table for an XP disk array and the DKAsummary table for a P9000 disk array.DKA summary table for P90

In addition, the combined backend transfer value is displayed for each ACP or DKA (applicableonly for XP24000 and P9000 disk arrays). For more informa

The Performance Advisor trial license expire on month, day, year. Please contact your HPRepresentative to purchase the requisite Performance Advisor l

Related Topics• “Viewing performance summary” (page 174)• “Viewing ACP/DKA data” (page 186)• “Viewing MP blade utilization for P9000 disk arrays” (pag

On the following MP Blades screen, you must click an MP blade ID in the MP Blade Configurationgroup box (see “MP Blades screen” (page 191)) to view th

Table 9 MP blade utilization summary (continued)DescriptionMP blade screen elements25% of the CPU cycles are utilized for processing the arraybackend

The MPB-1MB utilization data includes the following:• MPB-1MB is the MP blade ID that was selected in the MP Blades Util% group box.MPB-1MB is also li

Related Topics• “Viewing performance summary” (page 174)• “Viewing ACP/DKA data” (page 186)• “Viewing Smart and ThP pools data for P9000 disk arrays”

Figure 15 THP Pool ScreenIMPORTANT: The data on the Smart pools and the ThP pools are not displayed if the pools arenot configured in the selected P90

Table 11 Smart Pool monitoring information tableDescriptionLabel nameDisplays last available monitoring cycle start time withPADB.Last available start

Table 12 Pool Information table (continued)DescriptionColumn namesDisplays the total backend tracks associated with the Smart poolor the ThP pool. It

Table 13 Pool Details table (continued)DescriptionColumn namesDisplays RG level of a particular raid group. For External raidgroup this column is blan

DescriptionColumn namesDisplays the amount of tier space that is already utilized.Used CapacityDisplays the maximum storage that is accepted on a part

© Copyright 2014 Hewlett-Packard Development Company, L.P.Confidential computer software. Valid license from HP required for possession, use or copyin

DescriptionScreen elementsWhere, month, day, year refers to the date till whenthe grace period is valid.The above status message is also displayed on

Figure 16 Continuous Access JournalFigure 17 Continuous Access SyncFigure 18 Continuous Access AsyncTable 14 (page 201) describes the data displayed:2

Table 14 Continuous access configuration dataDescriptionScreen elementSerial number of the primary XP or P9000 disk array(primary data center).Primary

Table 14 Continuous access configuration data (continued)DescriptionScreen elementFence level of target device (Pair volume). Displays one ofthe follo

Table 15 CA volume performance data and journal information (continued)DescriptionScreen elementsAverage MB of data written per second to the LDEV bas

Table 17 CA port performance data (continued)DescriptionScreen elementsAverage I/O rate.Avg IOAverage throughput.Avg MBTable 18 (page 204) describes t

Table 19 (page 205) describes the performance metrics of LDEVs configured as journal volumesand associated with the P-VOL:Table 19 CA journal volumesC

IMPORTANT:• The response time is calculated from the time the I/Os are received by the CHA port till thetime they are dispatched from the CHA port.• I

groups are displayed under the RG (RAID Group) tab. This data is also displayed when you clickthe Backend Total Avg group box under the Performance Vi

Related Topics• “Viewing performance summary” (page 174)• “Viewing CHIP/CHA data” (page 182)• “Viewing ACP/DKA data” (page 186)• “Utilization Summary”

Figure 23 RAID Group summaryDescriptionScreen elementsThe RAID group to which the LDEV belongs.RGThe SLPR with which the RAID group is associated.NOTE

collect performance data for the current internal raw disk capacities of the monitored XP diskarrays or usable capacities of the monitored P9500 disk

DescriptionScreen elementswill be reported as an aggregate value for all the RAIDgroups.The random read utilization percentage for a RAID group.% RGUt

Figure 24 Port summaryDescriptionScreen elementsDisplays the port ID for the CHP port. Provides the optionto view information associated with a partic

effective way to exclude the impact of these transient spikes in the calculation of the bandwidthrequirements. In HP XP P9000 Performance Advisor, vie

Viewing LDEV dataHP XP P9000 Performance Advisor displays the following data on the Array View LDEV screen forall the LDEVs that belong to an XP or a

By default, the values displayed for the following are based on the performance values of all theLDEVs that are displayed for the last collection time

NOTE: The data for the following metrics sorts in the ascending order:• Host Group• Chip Port ID• ACP Pair ID• LDEV ID• Emulation• Cont. Access.The re

Table 20 Array View LDEV table - Sort By options (continued)DescriptionScreen elements• Sequential reads• Sequential writesSelect LUSE to sort LDEV da

3. Sort the LDEV data based on one of the options displayed in the Sort By list. By default, theLDEV data is sorted based on the average read response

2. Select the check box for the component that must be monitored.Choose the Select All check box, if you want to choose all components and add them as

Table 21 Components and metrics in LDEV Column Settings list (continued)DescriptionScreen elementsNOTE: If an array is connected to a host agent that

After installing a Permanent license, if you increase the internal raw disk capacity or the usablecapacity beyond the Permanent licensed capacity, the

Table 21 Components and metrics in LDEV Column Settings list (continued)DescriptionScreen elementsThe Luse master LDEV also lists an entry for the con

Table 21 Components and metrics in LDEV Column Settings list (continued)DescriptionScreen elementsAdvisor reports volume groups from LVM (an HP brand)

The following are the different replication pair statuses:DescriptionReplication pair statusesVolume is not configured for replication activity.SMPLex

Filter records based on existing selectionThis type of filter is applicable when you want to view the LDEV data based on your selection froman existin

Exporting LDEV dataYou can export LDEV data to an Excel spreadsheet for the date and time range that you specify.The data for all the LDEVs monitored

is configured as 7D+1P. The system supports RMLIB version 1.16.04 and later. If there is an LDEVthat is associated with two RAID groups, data about bo

If there are no associated continuous access journal groups configured, – is displayed in the JrnlGrp column.Viewing ThP Pool Occupancy informationThe

IMPORTANT:• The LDEV table does not display hyperlinks in the ACP Pair ID and ACP Pair Util fields for RAIDgroups spanning across multiple ACP pairs.

Additionally, the CLPR table displays the following details:• RAID group• LDEV IO/s• LDEV MB/s• Backend transfer data• Overall RAID group utilization

10 Using chartsThis chapter discusses the following topics:• “Introduction” (page 229)• “Plotting charts” (page 233)IntroductionYou can plot performan

IMPORTANT:• Additional usable capacity refers to the usable capacity that is beyond the Permanent licensedcapacity.• A Meter based Term license cannot

Figure 26 Charts screenCharts controls1Component selection tree for charts2Available Metrics Choose Metric Category list from where youselect metrics

DescriptionSections◦ Snapshot Pool◦ Pools◦ Replication Volumes◦ LUSE◦ Host Groups◦ Ext-RG(s)◦ Drive TypesIn addition to the above listed, the MP Blade

DescriptionSectionsThe Chart Work Area consists of the following:Chart Work Area• The individual chart windows that display the performance graphs of

Plotting chartsNOTE: The figures in the following procedure are an example for the XP disk array metricselection.PrerequisiteEnsure that the following

component selection tree, if you are aware of the LDEV name. For more information, see“Searching for components” (page 265):• Click the plus (+) sign

3. Choose the metrics for which you want to view the performance of the selected components.For more information, see “Choosing metrics” (page 237). B

DescriptionXP or P9500 Disk Array main categories – component selectiontreeFor a P9000 disk array, Front-end comprises of the frontendcomponents, such

DescriptionXP or P9500 Disk Array main categories – component selectiontreedisplayed for a P9000 disk array. For more information, see“Host Groups nav

based on the metric category to which they belong. Select a metric to view the correspondingperformance graph in the Chart Work Area. You can also cli

The Front-end main category comprises of the ports that further displays the associated MPs andCHAs. Following is the component selection path:Front-e

Generate 1950TB-Days of Meter based Term license to monitor 50TB additional usable capacityfor 39 days. The 1950TB-Days are derived based on the follo

The applicable metrics are displayed in the Available Metrics Choose Metric Category list. Selectthe metrics at the component type or the individual c

IMPORTANT: CLPRs do not exist in an XP1024 Disk Array. So, the Cache related metrics arenot displayed in the Available Metrics Choose Metric Category

Related Topics• “Front-end navigation path” (page 238)• “Back-end navigation path” (page 243)• “MP Blades navigation path” (page 242)• “Pools navigati

In the above image, under MP Blades for the P9000 disk array 53036:• MP Blades is the main category. The number 2 indicates the total number of MP bla

The Back-end main category comprises of the DKA pairs, associated MPs, RAID groups, and LDEVs,where DKA and RAID groups are the main component types t

In the above image, under Back-end for the XP disk array 10090:• DKA is a component type. The number (2) indicates the number of DKA pairs available o

In the above image, under Back-end for the P9000 disk array 53036:• DKA is a component type. The number (1) indicates the number of DKA pairs availabl

For P9000 disk arraysFor XP disk arraysMost used default metriccategoryBack-end categoryYesYesBackend MetricsRG(s)YesYesFrontend IO MetricsPhysical LD

In the above image, under THP Pool for the XP disk array 10090:• THP Pool is the main category. The number (2) indicates the total number of ThP pools

Pools > THP (component type) > Individual ThP pool IDs. Each individual ThP pool further includesthe following:• LDEVs (component type) > Ind

At the time of installing the Meter based Term license, if the usable capacity is within the Permanentlicensed capacity, the installed TB-Days remain

• Pool ID:5 is a Smart pool.• RG(s) is a component type under Smart Pool ID:5 and lists the RAID groups that are associatedwith the Smart pool. RG(s)

Snapshot Pool navigation pathThe Snapshot Pool main category comprises of the snapshot pools that contain the associated RAIDgroups, LDEVs, and the as

• LDEVs is a component type. The number (4) indicates the number of Ldevs associated with theSnapshot Pool ID:25.◦ 9:C9 is one of the individual LDEV.

• “Drive types navigation path” (page 261)• “Custom groups navigation path” (page 264)Replication Volumes navigation pathThe Replication Volumes main

The applicable metrics are displayed in the Available Metrics Choose Metric Category list. Selectthe metrics at the component type or the individual c

Following is the component selection path:LUSE > Individual LUSE masters > Components (component type) > Individual LDEVs that belongto the s

Related Topics• “Front-end navigation path” (page 238)• “Cache navigation path” (page 240)• “MP Blades navigation path” (page 242)• “Back-end navigati

Following are the component selection path:• Host Groups > Individual host groups > Ports (component type) > Individual Ports.• Host Groups &

• RG(s) is a component type under Host Group. The number (1) beside RG(s) displays the numberof RAID groups assigned for Host Group.• 1-7 is a RAID gr

In the above image, under Host Groups for the P9000 disk array 10090:• Under the main category Host Groups, XPPA247_HYP_V_NEW_BLD_BAY6 is one the indi

Consider that the usable capacity exceeds the 50TB Permanent licensed capacity by 10TB in thefirst half of 12/03/2010. As a result, the 90TB-Days are

For ports that are configured to communicate with the selected host groups, you can also view theassociated MPs and CHAs for the XP disk arrays, and o

The available metrics are displayed in the Available Metrics Choose Metric Category list. Selectthe metrics at the component type or the individual co

IMPORTANT: When you plot the performance data points for a RAID group, the associated drivetype is also displayed in the legend for the selected RAID

performance graphs in the Chart Work Area. For a description of these metrics, see “MetricCategory, metrics, and descriptions” (page 388).The followin

Custom groups navigation pathThe Custom Groups node comprises of individual custom groups that display the associated LDEVs.Following is the component

• “LUSE navigation path” (page 254)• “Replication Volumes navigation path” (page 253)• “Host Groups navigation path” (page 256)• “Ext-RG(s) navigation

266 Using charts

Plotting charts 267

NOTE:• For the Raid Group, the Host Group branch is traversed first, followed by the Pool branch,Back-end, and finally the Drive Types branch.• You ca

The Chart Work Area displays the following default settings. They are applicable across the chartwindows until you select the other available options:

DescriptionColumn Headings - License Status sectionZero days, as there are no TB-Days to use.Displays Capacity Insufficient.License StatusDisplays Exp

NOTE:◦ These selections work only on the active chart windows.◦ If the total number of data points from all the performance graphs exceeds 500 in a ch

An individual chart window can accommodate the performance graphs for up to 250 components.The 250 components that you select can belong to multiple c

For more information on the tasks that you can perform in the Chart Work Area, see “Using chartcontrols and settings” (page 276).Viewing top 20 consum

Example (see Figure 27 (page 272))MP blade utilization by top 20 consumerswhether the frontend or the backend requests have been high.Further to the a

Select an MP blade from MP Blades in the component selection tree and choose the MP BladeUtil/Processing Type metric in the Available Metrics Choose M

Viewing aggregate data for metricsYou can view the average utilization for the components in a metrics category using the Stackedbutton in the Charts

Example (see Figure 29 (page 275))Aggregate Data12110 (68.4%)Average utilization metrics value for the specific date and timestamp (average utilizatio

2. Click Add New to add a new chart window. The new chart window is automatically selected(blue border appears around the active chart window).The per

3. Click Save to save the selected charts as favorite charts. You can provide a name for thefavorite chart by clicking in the respective text box and

1. Click Load Fav Chart(s).A pop-up dialog appears displaying the favorites charts that you can view.2. Select one or more favorite charts from the li

• Term (Days): 9• End Date: 12/10/2010Nine days count from 12/02/2010If 85.5TB is used during the first half of 12/03/2010 and no additional TB-Days a

NOTE:• To create a report, it is mandatory that you provide the report name, array model, and reporttype.• The Report Name, Customer Name, Consultant

7. Click Generate to view the report immediately.Click Save to save and view the report later.HP XP P9000 Performance Advisor saves the report in its

Viewing current LDEV assignments for an MP bladeIMPORTANT: This section is applicable only for the P9000 disk arrays.You can view the LDEVs that are a

Example (see Figure 30 (page 282))LDEV - MP blade assignmentMPB-1MA is the MP blade ID, where 1 indicates the cluster #and MA indicates the blade loca

In the preceding utilization forecast graph, the threshold value is displayed as a blue referenceline and the forecast appears as a green line.IMPORTA

points available when the chart is initially updated for 5 minutes. The data points appear inthe next update cycle only for the delta duration.When yo

by taking the average of the previous data points. You can specify the number of data points forwhich the average needs to be calculated, using the Po

provides you an approximate idea of the performance of components if the data collection wasactive during the specified time interval. Once the data c

Zooming in on data points across performance graphsIn addition to zooming in on data points for a particular duration, you can also zoom in on acombin

In the Zoom Preview panel, if you plot the chart for more than one day, the chart displays datawith date stamp.Rearranging or moving chart windowsTo m

4. If the usable capacity rises beyond the 25TB Permanent licensed capacity on 11/30/2010and 3.5TB is used on the same day, HP XP P9000 Performance Ad

Removing chart windowsYou can remove all the charts currently displayed in the Chart Work Area by clicking Close Charts.All the active and passive cha

11 Using reportsThis chapter discusses the following topics:• “Generating, saving, or scheduling reports” (page 297)• “Viewing a report” (page 305)• “

For P9000 disk arraysFor XP disk arraysDescriptionReport typesPerformance report -Findings section.• Total I/O Rate Detail• Read-Write Ratio• Read-Wri

For P9000 disk arraysFor XP disk arraysDescriptionReport typesand ranges from 8 - 128 forthe frontend and the backendLDEVs, and 8 - 32 for thefrontend

For P9000 disk arraysFor XP disk arraysDescriptionReport typessnapshot volumes that areassigned to a pool.YesNoThe MP Blade Utilization reportprovides

For P9000 disk arraysFor XP disk arraysDescriptionReport typescomponents for thefollowing:• Random Read• Random Read Cache• Random Write• Sequential R

IMPORTANT:• Reports on the following are available only if they are configured in the selected XP or P9000disk array. If not configured, they are not

You can also edit or delete a schedule. For more information, see “Viewing a report” (page 305)and “Viewing a schedule” (page 306).Tasks you can perfo

2. Select or enter the following details:• Name of the report in the Report Name box. The name should not be less than 2 charactersor exceed 80 charac

You can also select multiple reports and view the corresponding data in a single reportdocument. The data for each report is arranged based on the ord

Contents1 Introduction to HP XP P9000 Performance Advisor...10Overview...

5. Provide the following details on the Array information input screen:• Enter the Array DKC serial number, which is a five digit number, such as 1090

3. Generate or save the report.• To generate a report, click Generate.HP XP P9000 Performance Advisor does not save the report in its database or disp

1. Collection Schedule: displays Daily, Weekly, and Monthly. By default, Weekly is selectedas the collection schedule.• Day of the Week: Displays the

4. Click Save. HP XP P9000 Performance Advisor does the following:• Saves the schedule and also displays a record for the schedule in the Scheduled Re

frontend and eight backend LDEVs, and eight frontend and eight backend RAID groups. Further,the report displays the graphs for only those LDEVs that h

(page 297). In addition, ensure that the following steps specific to an LDEV Activity report are alsocompleted:1. Select LDEV Activity from the Report

Viewing reportsIMPORTANT:• Report schedules with an asterisk (*) before the User Name indicate that they are generatedby a schedule. Following is the

• “Viewing a schedule” (page 306)• “Logging report details and exceptions” (page 309)Deleting reportsTo delete a report:1. Click Reports+View Reports

IMPORTANT:• The Scheduled Reports section appears only if you have logged in as an Administrator or auser with administrator privileges.• If the Email

In the preceding image, you can view the report, PA_ACP_Rep that is executed on 2009-10-1120:11:32 IST (Generation Time). The report provides data on

P9000 Performance Advisor is supposed to generate a report on the second Thursday of everymonth at 00:00 hours. Hence, the schedule is active and a re

5. Click Add License.CAUTION: After the licenses are installed, do not modify the date and time on themanagement station where HP XP P9000 Performance

12 Using Performance Estimator for XP and P9000 diskarraysThis chapter discusses the performance estimation for XP and P9000 disk arrays.IntroductionH

• Disk type –15K RPM• RAID type and RAID groups –144 RAID groups for RAID 1 (2D+2D)• Workload – 8K Random Writes• Intensity – 4096 threads/secHP XP P9

maximum of 288 RAID groups for RAID 1 (2D+2D) and 144 RAID groups for RAID 5(7D+1P).Accordingly, the text box on the right side of the # RGs horizonta

Based on the above selection, the Performance Estimator displays the estimated values in thefollowing non-editable text boxes:• Raw Capacity - Indicat

maximum of 512 RAID groups for RAID 1 (2D+2D) and 256 RAID groups for RAID 5(7D+1P).Accordingly, the text box on the right side of the # RGs horizonta

Based on the above selection, the Performance Estimator displays the estimated values in thefollowing non-editable text boxes:• Raw Capacity - Indicat

13 Troubleshooting issues for components associated withapplicationsThis chapter discusses troubleshooting issues for disk array components associated

you can collect the real-time performance data for a set of five LDEVs, RAID groups, ports, cache,and MP blades in a P9000 disk array. This data is co

Figure 32 RealTime screenDescriptionScreen elementsStart Collections tab• After the configuration data is collected for the XP orthe P9000 disk arrays

DescriptionScreen elementsYou can select the XP or the P9000 disk array and relatedcomponents for which you want to collect the real-timeperformance d

Related Topics• “Viewing aggregate License status” (page 32)• “Viewing status for individual licenses” (page 32)• “Removing licenses” (page 40)Viewing

You must wait for the real-time server update to complete if you want to use the same hostagent.Ensure that the above-mentioned steps are performed be

Additionally, the following are displayed:• HostAgent list: Displays the host agent that is connected to the selected XP or P9000 diskarray.• Command

7. From the Choose Metrics list, select the check boxes for the real-time metrics of your choice.For more information on the real-time metrics, see “R

3. Select the XP or the P9000 disk array for which you want to stop the real-time performancedata collection.4. Click Stop Plotting.The real-time data

IMPORTANT:• An application can reside on multiple hosts that connect to the XP and the P9000 disk arrays.• A host group can have multiple WWNs to conn

• Know the WWNs for the hosts.Run the XPInfo command at the command prompt of the host where your application resides.The HBA Port WWN in the P9000Inf

The following image shows the Configure Application dialog box for 53040, which belongsto the P9500 Disk Array type.The following are the possible com

4. Click Remove.5. Under Application Name, select the application that you want to remove.6. Click Add/Remove.You are provided an informational messag

The Search Results dialog box appears and displays the application and the host group orWWN of the host that are associated with the component.4. Clic

1. Click the plus (+) sign for an XP or a P9000 disk array in the component selection tree underTroubleshooting+Host Based.The list expands to display

3. Click View Details.The View License Detail section appears.The following image shows the license details for 53036, which belongs to the P9500 Disk

2. Based on your requirement, select an application or choose the host group or the WWNassociated with an application:If your selection is at the appl

Click an LDEV ID to view the associated port, CLPR, and the RAID group records highlightedin the respective tables. By default, the port, CLPR, and th

In addition, the following are displayed:• The MP blade ID with its corresponding average utilization percentage in brackets. Forexample, MPB-1MA [9.3

In addition, the following details are also displayed:• RAID group table:DKA Pair: Displays the DKA pair associated with the particular LDEV.◦◦ RG: Di

(page 104). For more information on setting threshold values, see “Configuring dashboard thresholdsettings” (page 97).You can also forecast the compon

The additional set of metrics that HP XP P9000 Performance Advisor supports for the RAID groups,Ports, and the CLPRs are as follows:Table 29 Additiona

the XP disk arrays), and the MP blades (applicable only for the P9000 disk arrays) to take theappropriate action.HP XP P9000 Performance Advisor analy

Plotting chartsYou can select and plot charts for components in the LDEVs, Port, CLPR, and the RAID group tables.To plot charts for the selected compo

Issue 1High utilization of CHA MP on port 5A causing response time to increase for all LDEVs associatedwith the application. The MP in question manage

9. Based on the trend of the utilization values of the RG and its LDEVs, the reason for poorresponse time on LDEV2 could be attributed to the overload

DescriptionScreen elementsDisplays the available license capacity.• If you select an XP disk array record, this columnalways displays the Installed Li

14 Launching HP XP P9000 Performance Advisor from otherStorage productsIntroductionYou can launch HP XP P9000 Performance Advisor from P9000 Tiered St

Viewing performance graphs for LDEVsTo access HP XP P9000 Performance Advisor from P9000 Tiered Storage Manager and view thecharts for the LDEVs that

7. Enter your user name, password, and click Login.By default, the Frontend IO Metrics chart window appears in the Chart Work Area displayingthe perfo

5. Click Analyze Performance.The HP XP P9000 Performance Advisor Login page is displayed.6. Enter your user name, password, and click Login.By default

provisioning decisions. HP XP P9000 Performance Advisor displays usage data for the followingcomponents:• Parity groups or RAID groups• MP blade proce

Updating the management station IP address and session name1. Navigate to the folder on your P9000 disk array SVP where you copied the XML files.2. Do

IMPORTANT: Whenever you update the appDefinition.xml file for the management stationIP address or the appProfile.xml file for the session name, execut

5. Click Settings+Launch Application+Performance Advisor.If you have updated a different session name in the appDefinition.xml file, that sessionname

5. Click Settings+Launch Application+Session Name (default: Performance Advisor).The data for the selected processor blade is displayed in the HP XP P

The following image shows the processing distribution for MPB-1MA.To view the utilization data for MPB2, click MPB-2MC in the MP Blade Configuration g

DescriptionScreen elementsIf you select an XP or a P9000 disk array record whoseusable capacity is monitored using only a Permanentlicense, this colum

4. Click Settings+Launch Application+Session Name (default: Performance Advisor).By default, the utilization data for the Overall RAID Group utilizati

1. Complete steps 1 and 2 mentioned for “Launching HP XP P9000 Performance Advisor”(page 346).2. Select Logical Devices in the list displayed for the

4. Click Settings+Launch Application+Session Name (default: Performance Advisor).The host group and the usage data of ports and LDEVs associated with

Sample on appDefinition.xml and appProfile.xml files• appDefinition.xml file<?xml version=”1.0" encoding=”UTF-8” standalone=”Yes"?><

• V6-1 enables you to view data related to LDEV in HP XP P9000 Performance Advisor. It isalso known as Logical Devices in HP XP P9000 Performance Advi

15 Support and other resourcesContacting HPHP technical supportFor world wide technical support information, see the HP support website:http://www.hp.

Websites• HP.comhttp://www.hp.com• HP Storagehttp://www.hp.com/go/storage• HP Manualshttp://www.hp.com/support/manuals• HP download drivers and softwa

Typographic conventionsTable 31 Document conventionsElementConventionCross-reference links and email addressesBlue text: Table 31 (page 357)Website ad

A Appendix AStorage management logical partitions (SLPRs)A disk array can be shared with the multiple organizations and with multiple departments with

host. This approach minimizes the effects of one administrator's operations on the volumes of otheradministrators.Figure 36 Example of a CLPR“Exa

Exceeding Permanent licensed capacity and grace periodWhen the internal raw disk capacity of an XP disk array or the usable capacity of a P9000 diskar

B Sample reportsReport typesHP XP P9000 Performance Advisor supports report generation for the following categories:• “Array performance reports” (pag

NOTE: The backend transfer is the block of data that is transferred between the XP or the P9000disk array cache and the RAID groups. Every read cache

Figure 37 Total I/O RateThe total backend transfers may be compared to the total frontend I/Os and the difference is dueto the effects of the array ca

Figure 38 Total I/O Rate by hour of dayThe total backend transfers may be compared to the total frontend I/Os and the difference is dueto the effects

Figure 39 Total I/O Rate DetailThe sequential frontend I/Os are when data is read from or written to consecutive addresses. Therandom frontend I/Os ar

Figure 40 Read/Write RatioFor example, the data point of X on the graph indicates X% read activity and (100-X)% of writeactivity.NOTE: If there are no

Figure 41 Read/Write Ratio by hour of dayNOTE: If there are no data points available for the dates selected, blank chart is displayed. Ifall the data

Figure 42 Read/Write DetailNOTE: If there are no data points available for the dates selected, blank chart is displayed. Ifall the data values are zer

NOTE: If there are no data points available for the dates selected, blank chart is displayed. Ifall the data values are zero for the dates selected, a

In the LDEV I/O Mapping table:• Hyphen (-) is displayed in the RAID Format column if that RAID format is not applicable forTHP Pool V-Vols.• Hyphen (-

◦ Term (Days): N/A◦ End Date: Never• After 1:00 PM on 11/30/2010:License Capacity: 50TB, +100TB-DaysConsider that 25TB-Days are used after installatio

throughput of the hardware. The maximum throughput varies depending on RAID level, diskmechanism type, and other factors such as the size of the indiv

Figure 48 Total Frontend I/O Rate First Top 8 Array Groups/PoolsRAID Group Utilization ReportThe Raid Group Utilization report consists of four charts

Cache Utilization reportThe Cache Utilization report displays in a chart format, the cache utilization in an XP or a P9000disk array.“Cache Utilizatio

Figure 52 Percentage read hitsTotal Backend Transfer reportThe Total Backend Transfer report displays in a chart format, the total number of transfers

Figure 54 Total Backend Transfer by Hour of the DayCache Side File Utilization reportThe Cache Side File Utilization report displays in a chart format

Figure 56 ACP utilization over the entire periodACP Utilization by Hour of the Day reportThe ACP Utilization by Hour of the Day report displays in a c

The CHIP utilization reports allow you to view in a chart format, the utilization data for all theinstalled CHIPs/CHAs in the array, and the average u

Figure 58 CHIP UtilizationCHIP Utilization by Hour of the Day reportThe CHIP Utilization by Hour of the Day report displays in a chart format, the uti

Figure 60 CHIP Processor UtilizationIn this sample report, the individual MP utilization for the CHA 1E is displayed. Similarly a reportis generated f

NOTE: HP XP P9000 Performance Advisor reports only those snapshot volumes in an XP or aP9000 disk array that are assigned to a pool.“Snapshot pool occ

Consider the following points:1. A P9000 disk array has a usable capacity of 50TB.2. A Permanent license is installed on 11/23/2010 to monitor the 50T

LDEV Activity reportYou can view the maximum and least busiest LDEVs in an XP or a P9000 disk array through theLDEV Activity report. The LDEV data can

IMPORTANT:• The threshold limits that you specify are independent of each other and applicable to only thecategory that you select. You can set both t

IMPORTANT:• The All report type for an XP or a P9000 disk array includes reports on the journal poolutilization, ThP pool, and the snapshot pool occup

MP blade utilization by the processing typesThe average MP blade utilization split up for the different processing types is displayed in a chartfor th

C Appendix CSupportability matrixThe following matrix displays the supportability of ThP, snapshot, and continuous access journalvolumes on the XP arr

D Appendix DArray mappingTo correctly map the ACP and CHIP pairs, see the following tables for the respective array:“XP128 (1 ACP Pair)” (page 385) li

Table 36 XP12000Slot IDPair IDSlot nameACP A = 0; M = 4ACP Pair 1A, MACP B = 1; N = 5ACP Pair 2B, NACP L = 2; X = 6ACP Pair 3L, XACP K = 3; W = 7ACP P

Table 38 XP24000 (continued)Slot IDPair IDSlot nameCHIP EL=1; QL=9CHIP Pair 3EL, QLCHIP FL=3; RL=11CHIP Pair 4FL, RLCHIP GU=4; TU=12CHIP Pair 5GU, TUC

E Metric Category, metrics, and descriptionsMetrics and descriptions“Metric Category, metrics, and descriptions” (page 388) provides the metric catego

Table 40 Metrics and descriptions (continued)DescriptionMetricMetric categoryThe total random frontendreads rate on this externalTotal RandomRead-Fron

5. As the usable capacity is beyond the Permanent licensed capacity, HP XP P9000 PerformanceAdvisor uses the 100TB-Days of Meter based Term license.Ba

Table 40 Metrics and descriptions (continued)DescriptionMetricMetric categoryLDEV, the number of randomreads available in thecache.The total random fr

Table 40 Metrics and descriptions (continued)DescriptionMetricMetric categoryexample, if collectioninterval is set to five minutes,the maximum port IO

Table 40 Metrics and descriptions (continued)DescriptionMetricMetric categoryThe total IO writes is obtainedby summing up IO writes ofThe total IO wri

Table 40 Metrics and descriptions (continued)DescriptionMetricMetric categoryThe sum total of randomfrontend I/Os on individualTotal Random IO - Front

Table 40 Metrics and descriptions (continued)DescriptionMetricMetric categoryThe frontend I/Os forrandom write requests thatTotal Random Write -Fronte

Table 40 Metrics and descriptions (continued)DescriptionMetricMetric categoryNOTE: This metric isdisabled in the Alarmscreen.Total number of I/Os on a

Table 40 Metrics and descriptions (continued)DescriptionMetricMetric categoryread from or written to theport in the last 30 secondsof the collection i

Table 40 Metrics and descriptions (continued)DescriptionMetricMetric categoryThe frontend throughput inMB/s read randomly froman ACP.ACP Random Read M

Table 40 Metrics and descriptions (continued)DescriptionMetricMetric categoryThe sum total of randomfrontend I/Os throughput inTotal Random MB – Front

Table 40 Metrics and descriptions (continued)DescriptionMetricMetric categoryThe frontend throughput inMB/s data writtenTotal Sequential Write MB –Fro

Stopping performance data collection schedules...66Restarting performance data collec

During a capacity violation phase, if you do one of the following:• Install a Permanent license for HP XP P9000 Performance Advisor to monitor the XP

Table 40 Metrics and descriptions (continued)DescriptionMetricMetric categoryThe utilization of the MP# onthe left ACP.• ACP Left Util MP0• ACP Left U

Table 40 Metrics and descriptions (continued)DescriptionMetricMetric categoryThe utilization of the RAIDgroup for writing randomparity.RAID Group Util

Table 40 Metrics and descriptions (continued)DescriptionMetricMetric categoryThe average MP bladeutilization by each of the 20MP Blade Util - Top 20Co

Table 40 Metrics and descriptions (continued)DescriptionMetricMetric categoryThe total backend tracksdestaged in sequential modefrom the specified ACP

Table 40 Metrics and descriptions (continued)DescriptionMetricMetric categoryof all the LDEVS associatedwith the given host group.the last 30 seconds

Table 41 Real-time metrics definitions (continued)DefinitionsReal-time metricsIO sizeTotal KB per IOIO sizeTotal random IOPSIO sizeTotal random read h

Table 41 Real-time metrics definitions (continued)DefinitionsReal-time metricsTotal backend reads percentageBe - Total cache lines staged percentageRa

F Appendix FForecasting ThP pool performanceGuidelines for selecting data range to receive an optimal forecastTo validate the forecasted data, we need

GlossaryAArray ControlProcessor (ACP)ACP is used in the XP disk arrays prior to the XP24000 Disk Array. With the introduction of theXP24000 Disk Array

Command View(CV)Replaced by the Command View Advanced Edition Suite Software.Command View AE(CV AE)The Command View Advanced Edition Suite Software re

case, HP XP P9000 Performance Advisor considers it as capacity insufficient violation and entersa grace period for that disk array. You can install th

FFC Fibre Channel. A network technology primarily used for storage networks.GGlobally uniqueidentifier (GUID)It is a special type of identifier used i

PHP XP P9000PerformanceAdvisorThe HP XP P9000 Performance Advisor is a software product from HP for monitoring the XP andthe P9000 storage subsystems.

TThin Provisioning(ThP, TP)Using the thin provisioning, you can operate with a global pool of LDEVs that are not assignedto a physical storage. The XP

IndexSymbols10 busiest back-end RAID groups, 20610 busiest front-end LDEVs, 205AACP Pair summary screen, 176AlamrsApply template, 114AlarmsAlarm notif

Chart Work AreaHigh watermark, 103LDEV InformationBusiest LDEVs, 103StatisticsFrontend, Cache, Backend, 103XP Array healthNormal, Critical, Major, 103

PP9000 array serial numberCapacityMeter based Term license, 15P9500 disk array, 15P9000 Command View AECoexistence, 10P9000 disk arraysReal-time monit

UtilizationStatusDKA, MP, RAID group, Cache write pending, 331utilization metrics, 399VView/Generate Reportslogging report details and exceptions, 309

4. Click Remove License(s).The Confirm Delete dialog box appears.5. Click Yes.The message indicating the removal of the license appears on top of the

4 Collecting configuration and performance dataThis chapter discusses the following topics:• “Introduction” (page 43)• “Configuring host information”

NOTE:• HP XP P9000 Performance Advisor also collects the real-time performance data from the XPand the P9000 disk arrays. For more information, see “T

DescriptionScreen elementsDisplays the list of command device records in theConfiguration Collection table. You can select a commandConfiguration Coll

Related Topics• “Collecting configuration data” (page 51)• “Scheduling configuration data collection” (page 52)• “Performance data” (page 56)Requestin

4. Click Request Info. The Request Info button is enabled only when you select the host agents.Use the Shft or the Ctrl key to select multiple host ag

4. Click Remove Host. The Remove Host button is enabled only when you select a host agentrecord.HP XP P9000 Performance Advisor deletes the host agent

DescriptionScreen elementsDisplays the DKC number and the user-friendly name ofthe XP or the P9000 disk array.ArrayDisplays the system name of the hos

Configuring notification and monitoring settings...117Filtering records based on m

The following are important notes applicable for both the one-time and scheduled configurationdata collection:• Select only one command device for an

Tasks you can perform under the Configuration Collection tab• “Collecting configuration data” (page 51)• “Scheduling configuration data collection” (p

:• The corresponding SVP IP address and RWC user name and password are displayed inthe respective text boxes, if you already saved these credentials i

1. Click Monitoring+Array View in the left pane.The Array View screen appears.2. Click the Configuration Collection tab. The Configuration Collection

7. Based on the disk array that you selected, following are the further course of steps:If you selected an XP disk array and Outband mode of configura

• “Filtering event records” (page 136)• “Configuring email and SNMP settings” (page 71)• “Starting real-time performance data collection” (page 319)•

ExamplesDescriptionCollectionScheduleDeleting configuration data collection schedulesTo delete a configuration data collection schedule:1. Click Monit

events. In case of performance data collection failure, the Event Log screen displays the failuremessages.NOTE: If you plot performance graphs when th

collection is not limited to the number of LDEVs that the host station is mapped to use. If youset the collection rate too narrow (less than 5 minutes

Example use casesThe following are the example use cases for understanding the split performance data collectionschedules:Activity Two2Activity One1Sc

Viewing Smart and ThP pools data for P9000 disk arrays...194Viewing continuous access data for

Creating performance data collection schedulesIMPORTANT:• Only one schedule can be created on a selected command device. For a better performance,sele

performance data collection schedule that you are creating, HP XP P9000 Performance Advisorvalidates the following and displays appropriate error mess

NOTE:• The THP Group(s), CA Journal Group(s), and the SNAP Group(s) component type lists aredisplayed only if the corresponding components are configu

discovered components are added to the appropriate schedule without impacting the othercomponents included in a performance data collection schedule.1

• “Stopping performance data collection” (page 66)• “Deleting performance data collection schedule” (page 68)• “Starting real-time performance data co

What happens...Automatic updatesScenariosyou can still enable Schedule 2 toreceive automatic updates.The newly discovered RAID groups andports are nei

NOTE:• The Stagger Collection is shown as false, if you have not configured a staggered collectionschedule.• The View button is enabled only when you

2. Click the Performance Data tab and select the XP or the P9000 disk array record for whichyou want to stop the performance data collection schedule.

Deleting performance data collection schedulesTo delete a performance data collection schedule:1. Click Monitoring+Array View in the left pane.The Arr

4. Enter the minimum and maximum java heap size values that are appropriate to your currentsetup.The Resize Heap tool stops the HP XP P9000 Performanc

Deleting favorite charts...279Creating reports for favorite c

5 Configuring common settings for HP XP P9000Performance AdvisorThis chapter discusses the following topics:• “Introduction” (page 70)• “Configuring e

IMPORTANT: You must log on to HP XP P9000 Performance Advisor as an administrator or auser with administrator privileges to perform the above-mentione

IMPORTANT:• The new email notification settings that you provide are automatically updated in theserverparameters.properties file. Hence, a manual reb

The default destination email address for receiving the alarm notifications isadministrator@localhost• An appropriate subject text for the alarm email

Trap not dispatched. It might be due to invalid IP address or servername, or the SNMP server is not accessible.4. Click Save.A message appears to indi

Related Topics• “Collecting configuration data” (page 51)• “Scheduling configuration data collection” (page 52)• “Performance data” (page 56)Registeri

4. Click Register.The SVP IP address that you specify is registered with the management station.HP XP P9000 Performance Advisor automatically uses the

NOTE: This change affects only those messages that are created after you instigated the severitychange. All messages that were logged before you set t

Complete the following steps to select the duration:1. Click PA and DB Settings+User Settings in the left pane.The User Settings screen appears.2. In

If the HP XP P9000 Performance Advisor Tomcat service is manually stopped, the HP XP P9000Performance Advisor Monitor service does not take any action

Viewing performance or usage data for components...328Viewing data for prominent set of metri

During the course of monitoring, if the HP XP P9000 Performance Advisor Monitor service identifiesthat the HP XP P9000 Performance Advisor Database an

The PAMonitor_mail.properties file is located in the <Install_drive>:\HPSS\paMonitor\conf folder on your management station.Configuring retry co

If there is a configuration change in the above-mentioned LUN attributes, edit the customgroups to add the corresponding LDEV records again. It ensure

The selection in each filter is independent of the selection in other filters. Example, if Array_1 isselected from the Arrays: Array Names list, the P

1. Click Customize Settings+Custom Groups in the left pane.The Custom Groups screen appears.2. Under List of Custom Groups, select the custom group yo

3. Click View. The View button is enabled only when you select LDEV records in the CustomGroups table.The View Custom Group Details screen appears pro

Table 5 Group Details screen (continued)DescriptionScreen elementsDisplays the host group name for the host. The hostgroup name is a user-defined grou

The records are removed and the list is refreshed. Click X on the View Custom Group Details screentitle bar to close the window.Deleting custom groups

DescriptionScreen elementsDisplays the emulation types. An array group is dividedinto open volumes of the same size. These volumes arecalled emulation

• Target: LUN list• Volume Group list• Device File list• RG list• LDEV listThe selection in each of the above-mentioned filters is independent of the

ACP utilization report...374ACP Utilization report

NOTE: If you enter values in the text boxes (see step 4) and also in the Data Grid Updatetable text boxes, HP XP P9000 Performance Advisor considers t

• Volume Group• Device File• SSID4. Clear the selection for the existing record and select the check boxes for those LDEV recordsthat you want to appl

Creating a user recordTo create a new user record:1. Click PA and DB Settings+Security in the left pane.The Security screen appears.2. Click New.3. En

3. Click Delete.Click Yes in the popup window that appears, to permanently delete the user record.Click No to retain the user record.Related Topics• “

6 Monitoring performance of XP and P9000 disk arraysThis chapter discusses the following topics:• “Introduction” (page 94)• “Configuring dashboard thr

For more information on the sections in the Dashboard screen, see “Viewing dashboard” (page 103).For more information on setting thresholds and specif

Figure 7 Dashboard screenThe Threshold Setting screen where you set the threshold levels.1The XP/P9000 Array Health section, where status icons aredis

Configuring dashboard threshold settingsIMPORTANT:• Since, the CHIP/CHA and the ACP/DKA MPs are moved to the MP blades in the P9000 diskarrays, the CH

2. Click the text box corresponding to a metric and category whose overall usage summary youwant to view.For example, to view the overall usage status

NOTE:• By default, the duration is set to 6 hrs in the Threshold Setting screen.• All the charts in the dashboard screen is displayed for 1 hour if th