NEC Storage Performance Monitor/Optimizer, Storage Performance Monitor, Storage Performance Optimizer User Manual

NEC Storage
Performance Monitor/Optimizer
User’s Manual

© NEC Corporation 2001-200 3
No part of the contents of this book may be reproduced or

transmitted in any form without pe rmission of NEC Corporation.

The contents of this book may be m odif ie d without notic e in the f uture.

Preface

This manual describes NEC Storage PerformanceMonitor (performance monitoring function) and NEC Storage
PerformanceOptimizer (performance optimization function).
The performance monitoring function is for monitoring the performance of the Disk Array Subsystem (hereinafter may be
referred to as disk array), collecti ng performance information, and displaying the performance in real-ti me.
The performance optimization function is for optimizing the performance of the disk array by moving a logical disk in the
disk array, displaying the Busy Ratio, and estimating the Busy Ratio after it has been moved.
Refer to the “NEC Storage Manager Manual Guide” (IS901) for the overview of NEC Storage Manager and the related
manuals.

Remarks 1. This manual explains functions implemented by the following program products:

• NEC Storage Manager and NEC Storage BaseProduct

• NEC Storage PerformanceMonitor

• NEC Storage PerformanceOptimizer

2. This manual is applicable to the program products of the following versions:

• NEC St orage Manager Ver2.1

• NEC Storage BaseProduct Ver2.1

3. The term “iSM” in this text refers to all the NEC Storage Manager program products.

4. Trademarks and registered trademarks

• HP-UX is a registered trademark of Hewlett-Packard Co. in the United States.

• UNIX is a registered trademark of The Open Group in the United States and other countries.

• Microsoft®, Windows®, and Windows NT® are registered trademarks or trademarks of Microsoft

Corporation in the United States and other countries.

• So laris is a registered trademark of Sun Microsystems, Inc. in the United Stat es.

• Linux is a trademark or registered trademark of Mr. Linus Torvalds i n the United States and other

countries.
Other product names and company na mes, etc. are registered trademarks or trademarks of the associated
companies.

6. In this document, matters to which careful attention needs to be paid will be described as follows:
Be sure to observe the conten ts.
If the indications are ignored and the system is improperly operated, settings which have been already made
might be affected.

Type of Indication

Type Description

Describes contents which require special attention during operation.

The First Edition in May 2002
The Third Edition in April 2003

Contents

Part I Performance Monitori ng Function ..........................................................................................................I-1

Chapter 1 Overview of Performance Monitoring Function......................................................................................... I-2

1.1 Performance Monitoring Function............................................................................................................................I-2

1.2 NEC Storage PerformanceMonitor and Related Product .........................................................................................I-3

1.3 System Configuration ...............................................................................................................................................I-3

1.4 Operation of Performance Monitoring Function ......................................................................................................I-3

1.5 Function Overview....................................................................................................................................................I-5

Chapter 2 Installation of Performance Monitoring Functi on.................................................................................... I-25

2.1 Server Installation...................................................................................................................................................I-25

2.2 Client Installation....................................................................................................................................................I-26

Chapter 3 Operations of Performance Monitori ng F uncti on .................................................................................... I-27

3.1 Real-Time Display of Load Status..........................................................................................................................I-27

3.2 Monitoring Overloads.............................................................................................................................................I-41

3.3 Support for Analysis of Statistic Information .........................................................................................................I-50

Part II Perfo r ma n ce Opt im iz at i on Fu nc t io n ..................................................................................................... II-1

Chapter 4 Overview of Performance Optimization Function.....................................................................................II-2

4.1 Performance Optimization Function....................................................................................................................... II-2

4.2 NEC Storage PerformanceOptimizer and Related Product .................................................................................... II-3

4.3 System Configuration ............................................................................................................................................. II-3

4.4 Operation of Performance Optimization Function ................................................................................................. II-4

4.5 Function Overview.................................................................................................................................................. II-5

Chapter 5 Installation of Performance Optimizati on Funct ion..................................................................................II-7

5.1 Server Installation...................................................................................................................................................II-7

5.2 Client Installation.................................................................................................................................................... II-8

5.3 Installation of Work Disks for Optimization .......................................................................................................... II-9

Chapter 6 Operation of Performance Optimization Function (GUI) ......................................................................II-11

6.1 Description of Screen............................................................................................................................................ II-11

6.2 Operation on Screen.............................................................................................................................................. II-19

Chapter 7 Operation of Performance Optimization Function (CLI).......................................................................II-45

7.1 Logical Disk Movement Command...................................................................................................................... II-45

Appendix A Commands of Performance Monitoring/Optimization Function.................................................................1

A.1 Commands for Statistic Information File ................................................................................................................... 1

A.2 Command for Performance Tuning .......................................................................................................................... 17

Appendix B CSV File Structure.......................................................................................................................................... 20

Appendix C Report Format of Performance Report Edit or ............................................................................................ 36

Appendix D Estimation of NEC Storage PerformanceMonitor File Size .......................................................................46

Appendix E Estimati ng Size of NEC Storage PerformanceOptimizer Files................................................................... 48

i

Appendix F Example of Performance Improvement........................................................................................................ 49

Index ........................................................................................................................................................................... 51

ii

P

a

r

t

I

P

e

r

f

o

r

m

a

n

c

e

M

o

n

i

t

o

r

i

n

g

F

u

n

c

t

i

o

n

P

a

r

t

I

P

e

r

f

o

r

m

a

n

c

e

M

o

n

i

t

o

r

i

n

g

F

u

n

c

t

P

a

r

t

I

P

e

r

f

o

r

m

a

n

c

e

M

o

n

i

t

o

r

i

n

g

F

u

n

c

i

t

i

o

o

n

n

Chapter 1 Overview of Performance Monitoring Function

N

N

Chapter 1 Overview of Performance Monitoring

Function

1

.

1

P

e

r

f

o

r

m

a

n

c

e

M

o

n

i

t

o

r

i

n

g

F

u

n

c

t

i

o

n

1

.

1

P

e

r

f

o

r

m

a

n

c

e

M

o

n

i

t

o

r

i

n

g

F

u

n

c

1

.

1

P

e

r

f

o

r

m

a

n

c

e

M

o

n

i

t

o

r

i

n

g

F

u

The Performance Monitoring Function provides a performance monitoring function for centrally controlling the storage
performance under the control of NEC Storage Manager (hereafter, referred to as iSM). The use of this performance
monitoring function is capable of real-time monitoring of loads, detection of overload, and management of statistic
information (performance infor mat ion of the past). The function allows an administrat or to investigate the cause of access
performance deterioration , detect abrupt increases of accesses, and take p roper measures against symptoms of failures (Note

1) on the business server.
Thus, this function enables constantly stable operation of storage devices.

ARRAY1 ARRAY2

EC Storage Series

Figure 1-1 Configuration of the Performance Monitoring Function

Business Server

EC Storage

Performance Monitor

Performance
Monitoring Screen

LAN

Operations
Administrator

n

c

t

t

i

o

n

i

o

n

ARRAY1

ARRAY2

(Note 1)
The Performance Optimization function (NEC Storage PerformanceOptimizer) allows easy operation. Refer to Part II
“Performance Optimization Fu nction” for details.

I-2

Chapter 1 Overview of Performance Monitoring Function

1

.

2

N

E

C

S

t

o

r

a

g

e

P

e

r

f

o

r

m

a

n

c

e

M

o

n

i

t

o

r

a

n

d

n

n

n

g

g

g

d

d

1

.

2

N

E

C

S

t

o

r

a

g

e

P

e

r

f

o

r

m

a

n

c

e

M

o

n

i

t

o

r

1

.

2

N

E

C

S

t

o

r

a

g

e

P

e

r

f

o

r

m

a

n

c

e

M

o

n

i

t

R

e

l

a

t

e

d

P

r

o

d

u

c

t

R

e

l

a

t

e

d

P

r

o

n

n

n

r

o

o

o

d

o

d

n

f

i

n

f

i

n

f

i

o

f

o

f

o

f

R

e

l

a

t

e

d

P

NEC Storage PerformanceMonitor requires the following program product as a precondition.

• NEC Storage BaseProduct

1

.

3

S

y

s

t

e

m

a

a

a

t

t

m

m

i

i

t

i

t

t

t

o

o

o

C

C

C

i

o

i

o

i

o

n

n

n

1

.

3

S

y

s

t

1

.

3

S

Refer to Chapter 3 “System Configuration of NEC Storage Manager” of the “NEC Storage Manager Manual Guide”.

1

.

4

1

1

.

4

.

4

O

O

O

F

u

F

F

y

p

p

u

u

p

s

e

e

n

n

n

e

t

c

c

e

r

r

r

c

e

u

u

g

g

g

P

P

P

c

c

u

u

u

e

e

e

t

t

r

a

t

i

o

n

i

i

r

r

r

o

o

m

m

m

n

n

a

a

a

n

c

e

M

o

n

n

n

c

c

e

e

M

M

o

o

n

n

i

i

i

r

a

t

r

a

t

r

f

o

r

f

o

r

f

o

a

o

r

a

t

o

r

i

t

n

o

r

i

o

n

r

i

t

This section describes operations of the Performance Monitoring Function. The Performance Monitoring Function is
operated in the flows shown below:

Operation flow Reference

Installing Performance Monitoring Function
Installation of the Performance Monitoring Function is accompanied by

installing NEC Storage Manager at the same time.

Specifying targets of monitoring performances

For defining the targets of monitoring performances, specify disk array,
ports, logical disks, and physical disks composing logical disks used in
operations requiring responsibility such as online processing. Also,
specify monitoring items among those allowed for real-time monitoring
(I/O Density, transfer rate, etc.). For example, to monitor responses to
accesses from an application, average response time and I/O density
must be monitored.

Accumulate the statistic information of performance monitoring target
devices, with accesses from business programs. Then analyze the
statistic information by summarizing, extracting, and editing. On the
basis of the analyzed information, a maximum load l evel, load
fluctuation, and expected period of heavy load and future load
regulation are estimated. This analysis is performed regularl y. If a
problem about performances is expected, an appropriate measure must
be taken in advance.

Specifying threshold value and monitoring overloads

On the basis of performance analysis results, specify threshold values
as indexes for detecting o verl oads. Loads exceeding a specified
threshold value are detected by NEC Storage Manager automatically,
and are reported on the NEC Storage Manager Client screen.

Analyzing performances

Continued to next page

Chapter 2 Installation of Performance
Monitoring Function

1.5.1 Real-Time Display of Load State

3.1 Real-Time Display of Load Stat e

1.5.3 Analysis support for statistic
information

3.3 Support for Analysis of Statistic
Information
A.1 Commands for Statistic
Information File

1.5.2 Monitoring Overloads

3.2 Monitoring Overloads

Operation flow Reference

continued from previous page

Upon detection of overload

I-3

Chapter 1 Overview of Performance Monitoring Function

Reviewing cause of overlo ad

Display performance information on the real-time basis and ch eck
location of overload . Then, analyze the accumulated stati s t ic
information to determine the cause of the overload.

Improving performance

Analysis of statistic information makes it possible to improve
performance as shown in the examples provided below.

• If there is a problem with the file arrangement and the access load
concentrates in a specific logical disk, the I/O density of the logical
disk should be higher than that of other logical disks and its response
time should be longer. If this is the case, it is necessary to review
the file arrangement and distribute the load.

• If a write operation onto the disk is slow, the cache size is
insufficient. A write operation onto physical disks may be
simultaneously performed. This status is confirmed by checking to
see if the Write Hit ratio is less than 100%. If this is the case, it is
recommended that the cache size of the disk array be expanded.

• If response is not quick although the access density from the bu siness
server to the logical di sk is low, the access density to another logical
disk on the same RANK may be high. This state is confirmed by
the fact that the Busy Ratio of the RANK is high. If this is the case,
use the performance optimization function described in Part II to
move the logical di sk, which has the high access density, to another
RANK and level out the Busy Ratio of each RANK. On the other
hand, reviewing the processes of a business application to reduce
access operations to a disk or improving access efficiency by batch
accessing can be good so lutions to some cases.

Displaying statistic information on a
real-time basis

1.5.1 Real-Time Display of Load State

3.1 Real-Time Display of Load Stat e

Analyzing statistic information

1.5.3 Analysis support for statistic
information

3.3 Support for Analysis of
Statistic Information

A.1 Commands for Statistic
Information File

Against high busy ratio on RANK:
Part II Performance Optimization

Function

I-4

Chapter 1 Overview of Performance Monitoring Function

1

.

5

F

u

n

c

t

i

o

n

O

v

e

r

v

i

e

w

1

.

5

F

u

n

c

t

i

o

n

O

v

e

r

v

1

.

5

F

u

n

c

t

i

o

n

O

v

The Performance Monitori ng function includes Real-Time Display of Load Status, Monitorin g Overloads, and Statistic
Information Analysis Supporting.

s

i

D

e

m

i

T

-

l

a

e

R

1

.

5

.

1

Monitored Item

1

.

5

.

1

1

.

5

.

1

This function is capable of displaying the latest load state and usage of the disk array and disk array components. The
information is displayed upon the iSM client screen, on the real-time basis. The function, which can monitor
performances of multiple disk array, allows centralized monitoring on the same view of one iSM client. When storage
performance decreases, or symptom of a trouble is seen, use this function to display the performance information of disk
array and disk array components, and identify the cause of decreased performances or a fault.
For details of components composing disk array, refer to 3.3 “Hardware” in the “NEC Storage Manager Manual Guide”.
The iSM client screen is capable of displaying the index values for each calculation unit shown in Table 1-1. (Index val ues
applicable to the items indicated by “ √ ” in Table 1-1 are displayed.)

External I/O Density
External Transfer Rate
External Average Transfer Length
External Average Response Time
Busy Ratio - - ­Read Hit Ratio
Write Hit Ratio
Internal I/O Density - - ­Internal Transfer Rate - - ­Internal Average Transfer Length - - ­Internal Average Response Time - - -

e

R

e

R

T

-

l

a

T

-

l

a

Table 1-1 Available Combinations of Monitored Items and Component types

i

i

m

m

e

e

s

i

D

s

i

D

Disk Array Port Logical Disk Physical Disk

i

e

r

v

a

l

p

a

l

p

a

l

p

√ √ √
√ √ √
√ √ √
√ √ √

√
√

e

w

e

y

y

y

w

o

o

o

s

u

t

a

t

S

d

a

o

L

f

L

f

L

f

d

a

o

d

a

o

Component type

-

-

a

t

S

a

t

S

√
√

s

u

t

s

u

t

-

-

-

-

√

-

-

√
√
√
√

i

√: Item displayed -: Item not displayed

• Displays the latest load status in numerical values

Figure 1-2 Displaying the Numeric Table

I-5

Chapter 1 Overview of Performance Monitoring Function

• Displays the latest load state in bar graphs

Figure 1-3 Displaying the Bar Graph

I-6

Chapter 1 Overview of Performance Monitoring Function

• Displays the latest load state in time-series graphs

Figure 1-4 Displaying the Time-series Graph

I-7

Chapter 1 Overview of Performance Monitoring Function

(1) Monitored Items

Monitored items are types of index values which indicate status of load or performance. iSM displays values of the
following types of monitored items on the client screen.

(i) External I/O Density

This is the number of input/output requests received by the disk array from the external per unit time. The unit is
IOPS (Input Output Per Second). This is calculated by measuring the external I/O count during the unit
measurement period and dividing it by the time interval of the measurement p eriod.

(ii) External Transfer Rate

This is the Average Transfer Rate of the input/output process achieved in response to the input/output requests
received by the disk array from the extern al. The unit is megabyte/second. This is calculated by measuring the
total of the amount of external data transfer during the unit measurement period and dividing it by the time interval of
the measurement period.

(iii) External Average Transfer Length

This is the average input / output data length per one input/output request received by the d isk array from the external.
The unit is kilobyte. This is calculated by measuring the total of the amount of external data transfer and external I/O
count during the unit measurement period and dividing the former by the latter.

(iv) External Average Response Time

This is the Average Response Time for the input/output requests received by the disk array from the external. The
unit is millisecond. This is calculated by measuring the total of the external response time and external I/O count
during the unit measurement period and dividing the former by the latter.

(v) Busy Ratio

It is the ratio of operation of physical disk. The unit is percentage [%]. It is calculated by following expression;
dividing the operating time of physical disk by the time slot of measured segments.

(vi) Read Hit Ratio

It is the ratio of case where the READ request h as been completed using dat a st ored in the cache without reading fro m
physical disk (Read hit), when the disk array receives the input requests from outside. The unit is percentage [%]. It
is calculated by following expression; dividing the number of cache hit I/Os by the number of receiving READ
requests during the measuring interval.

(vii) Write Hit Ratio

This is the ratio of case where the WRITE request has been completed quickly by writing data only in the cache
(Write hit), when the disk array receives the output requests from outside. The unit is percentage [%]. It is calculated
by following expression; dividing the number of cache hi t I/Os by the number of receiving WRITE requests during the
measuring interval.

(viii) Internal I/O Density

This is the number of input/output requests issued to the internal disk devices by the control device of the disk array.
The unit is IOPS (Input Output Per Second). This is calculated by measuring the internal I/O count during the unit
measurement period and dividing it by the time interval of the measurement p eriod.

(ix) Intern al Transfer Rate

This is the average transfer rate of the input/output requests issued to the internal disk devices by the control device of
the disk array. The unit is megabyte/second. This is calculated by measuring the total of the amount of internal

I-8

Chapter 1 Overview of Performance Monitoring Function

data transfer during the unit measurement period and dividing it by the time interval of the measurement period.

(x) Internal Average Transfer Length

This is the average input/output data length of the input/output process performed for the internal disk devices by the
control device of the disk array. The unit is kilobyte. This is calculated by measuring the total of the amount of
internal data transfer and internal I/O count during the unit measurement period and dividing the former by the latter.

(xi) Internal Average Response Time

This is the average response time for the input/output requests issued to the internal disk devices by the control device
of the disk array. The unit is millisecond. This is calculated by measuring the total of the internal response time
and internal I/O count during the unit measurement period and dividing the former by the latter.

(2) Unit to sum up

iSM separately displays values of the monitored items collected in the following units.

(i) Disk array

Statistic information of the entire disk array to be monitored is collected and load status for each disk array is reported.
For this component type, the external I/O Density, external Transfer Rate, external Average Transfer Length, external
Average Response Time, Read Hit Ratio, and Write Hit Ratio can be reported as monitored items.

(ii) Port

For the monitored disk arrays, statist ic information related to each host port is collected separately, and load status for
each host port is reported. For this component type, the external I/O Density, external Transfer Rate, external
Average Transfer Length, and external Average Response Time can be reported as monitored items.
In principle, the sum of the values of a monitored item over all the host ports in one disk array is equal to the sum of
the values of the same monitored item over all the disk arrays. However, in a real-world situation, some error may
exist due to varied sampling time of the statistic information which is the basis of the values of the monitored item.

(iii) Logical disk

For the monitored disk arrays, stat istic information related to each logical disk is collected separately, and load status
for each logical disk is reported. For this component type, the external I/O Density, external Transfer Rate, external
Average Transfer Length, external Average Response Time, Read Hit Ratio and Write Hit Ratio can be reported as
monitored items.
In principle, the sum of the values of a monitored item over all th e lo gi cal disks in one disk array is equal to the sum
of the values of the same monitored item over all the disk arrays. However, in a real-world situation, some error may
exist due to varied sampling time of the statistic information which is the basis of the values of the monitored item.

(iv) Physical disk

Disk devices installed in a disk array are called physical disks. Statistic information related to each physical disk
installed in the monitored di sk arrays is collected separately, and load status for each physical disk is reported. For
this component type, the internal I/O Density, internal Transfer Rate, internal Average Transfer Length, internal
Average Response Time, and Busy Ratio can be reported as monitored items.

You can set the update frequency (Display Refresh Rate) of display on the Numeric Table and the Time-series Graph by
using the environment setting at system installation.
You can change the setting from the iSM server menu while the iSM server is operating if the performance monitoring

I-9

Chapter 1 Overview of Performance Monitoring Function

N

N

r

screen is not started. For details of environment setting, refer to 2.1.3 “Environment Setting”.
The Display Refresh Rate determines the resolution of performance monitoring in the direction of time. Specify the
Display Refresh Rate in the number of updates per minute. Table 1-2 shows relation between Display Refresh Rate and
Display Refresh Interval.

Table 1-2 Display Refresh Rate and Display Refresh Interval.

Display refresh rate (times/minute)

1 2 3 4 5 6

Display refresh interval (second)

You cannot change the Display Refresh Rate while the Performance Monitoring screen is started. Change to the Display
Refresh Rate applies to all the disk arrays monitored by the server.
Increasing the Display Refresh R at e detects change in the performance information in a shorter interval but the number of
components simultaneously display is decreased. This is because the number of collection of performance information by
a single disk array unit in certain period is restricted not to obstruct file I/O from the application host in the overhead at
collection of performance information. This tendency is eminent especially when statistic information is being stored
simultaneously with real-time displaying.

1

1

1

Specifying a threshold as an index value of overload allows iSM to automatically detect occurrence of overload in a disk
array or a disk array component (occurrence of a load exceeding specified threshold value). Upon detecting an o verl oad, a
message notifying overload is displayed. At the same time, asterisks (**) are displayed on the location of the Performance
Monitor screen. When occurrence of an o verload is reported by a message, an admini strator must identify location of the
overload on the Performance Monitor screen.

ARRAY1

60 30 20 15 12 10

s

d

a

o

l

r

e

v

O

g

n

i

r

o

t

i

n

o

M

2

.

5

.

.

2

.

5

2

.

5

.

o

M

o

M

EC Storage Series

o

t

i

n

o

t

i

n

Overload

g

n

i

r

g

n

i

r

ARRAY2

Business Serve

O

O

v

v

e

e

a

o

l

r

a

o

l

r

Performance
Monitoring Screen

EC Storage

PerformanceMonitor

d

d

LAN

s

s

ARRAY1
ARRAY2

Operations
Administrator

Overload
Occurrence
Display

**

I-10

Chapter 1 Overview of Performance Monitoring Function

Figure 1-5 Monitoring Overloads
A threshold value is specifiable fo r each calculation unit displ ayed by the Real -Time Display function (refer to Table
1-1). The unit of specifying a threshold is called a threshold monitoring element. Thresholds can be specified by
clients with the user level (Note 1) L2 or L3.

(Note 1)

For user levels, refer to 5.2 “Client Start/Stop” of the “NEC Storage Manager User’s Manual” of your OS.

(1) Notifying threshold excess by e-mail

You can also e-mail the message notifying you of occurrence o f an exceeded threshold to a speci fied address by using
the link function of the iSM server. For details of the link function of the iSM server, refer to 3.6 “Event Link” in the
“NEC Storage Manager User’s Manual” of your OS.

(2) Threshold monitoring conditions

During a background process of disk array, such as batch processing and fault recovery of physical disks, a threshold
value may be temporarily exceeded. Upon such a case, which can occur in usual operation in general, exceeding of
threshold should not be reported to an administrator. Specifying the monitoring conditions shown below can prevent
such unnecessary report i ng of exceeded threshold.

1. Threshold monitoring interval

Time interval of judging threshold. Default value is the same as Display Refresh Interval.

2. Minimum I/O count

If the number of I/Os in a threshold monitoring interval does not exceed an I/O count specified here, the threshold
is not monitored in this interval. A minimum I/O count is specified with the number of I/Os per minute.

Default value is 60/minute.
A threshold is monitored if the number of I/Os in a threshold monitoring interval exceeds the minimum I/O count, and
if the threshold is exceeded, threshold exceeding is reported. By operating busin esses, analyzing performances, and
specifying the threshold monitoring conditions on the basis of the analysis, monitoring of overload appropriate for the
businesses. Figure 1-6 shows an outline of the threshold monitoring interval.

I-11

Chapter 1 Overview of Performance Monitoring Function

value of

入出力回数

monitored
item

Threshold monitoring interval (scale: 1 minute)

しきい値監視インターバルが短いため、一時的な

Because of short threshold monitoring interval, exceeded

過負荷でしきい値超えが通知される

threshold is notified upon a temporary overload.

しきい値監視インターバル（目盛りの単位：1 分）

Threshold value

しきい値

Specifying “1 minute” for a

しきい値監視インターバルを

threshold monitoring interval

1 分と設定した場合

Specifying “5 minutes” for a

しきい値監視インターバルを

threshold monitoring interval

5分と設定した場合

Figure 1-6 Threshold Monitoring Interval

(3) Resetting threshold excess state

Once a threshold value is exceeded, the value is excluded from threshold monitoring target until the threshold excess
occurrence state is reset. This feature prevents repeated reporting of the same event of threshold excess state, under
largely fluctuating loads.
The threshold excess state is cancelled by operations on the Performance monitoring screen. Specifying th e
conditions for resetting threshold excess state allows reset of threshold excess state when the conditions are satisfied.
The following conditions are specifiable for resetting the threshold excess state:

1. Time of continued values under threshold

Specify the number of threshold monitoring intervals during which a value is kept under threshold. For each

monitoring item satisfying the conditions, threshold excess state is reset. If the number of I/Os does not reach a

minimum number of I/Os specified by threshold monitoring conditions, the load of applicable interval is

recognized as under threshold.

2. Time of day

At a specified time of each day, th e threshold excess state is reset for all monitoring items.
Figure 1-7 shows an example of resetting threshold excess state when “3” is specified as the number of threshold
monitoring intervals for a period of continuous values under threshold.

I-12

Chapter 1 Overview of Performance Monitoring Function

値監視

g

N

N

Threshold monitoring

しきい値監視インターバル

interval

otify threshold

しきい値超えの通知

しきい値超えの通知

excess

Detect threshold

しきい 値 超 え 検 出

しきい 値 超 え 検 出

しきい 値 超 え 検 出しきい 値 超 え 検 出

exceedin

しきい値超え状態

しきい値超え状態

しきい値超え状態しきい値超え状態

Threshold excess state

しきい値監視インターバル（３回）

しきい値監視インターバル（３回）

しきい

Threshold monitoring

インターバル（３回）しきい値監視インターバル（３回）

intervals (3 times)

iSM Client

iSMクライア ン ト

otify threshold

しきい値超えの通知

excess

Figure 1-7 Resetting Threshold Excess State

I-13

Chapter 1 Overview of Performance Monitoring Function

r

r

o

f

t

r

o

p

p

u

S

s

i

s

y

l

a

n

A

3

.

5

.

1

.

5

.

1

.

5

.

1

This function is cap able of to accumulating, concentrating, and editing statistic information about the performances of disk
array in a file. Using this function allows long-term accumulation of statistic information which lets you grasp long-term
load variations and analysis of performance, for efficient use of the disk array.
A file where statistic information is accumulated is called a stati st ic information history file. The statistic i nformation
history file is stored on the iSM management server, allowing concentrating, extracting, and editing data on the server. In
addition, downloading the statistic information history file allows concentrating, extracting, and editing data on an iSM
client.

3

3

A

A

NEC

Storage

l

a

n

a

n

s

i

s

y

s

i

s

y

l

Statistic information
history file

p

u

S

p

u

S

r

o

p

r

o

p

1. Accumulating statistic information

2. Concentrating, extracting, and editing statistic
information

r

o

f

t

r

o

f

t

NEC Storage

PerformanceMonitor

S

S

S

s

i

t

a

t

s

i

t

a

t

I

c

i

t

I

c

i

t

O

2. Downloading
accumulated statistic
information

3. Concentrating,
extracting, and editing
statistic information

n

n

r

o

f

r

o

f

m

m

a

a

t

t

n

o

i

n

o

i

n

o

i

t

a

m

r

o

f

n

I

c

i

t

s

i

t

a

t

iSM Client

Figure 1-8 Analyzing Statistic Information

I-14

Chapter 1 Overview of Performance Monitoring Function

N

N

1

.

5

.

3

.

1

A

c

c

u

m

u

l

a

t

i

n

g

S

t

a

t

i

s

t

i

c

I

n

f

o

r

m

a

t

i

o

n

1

.

5

.

3

.

1

A

c

c

u

m

u

l

a

t

i

n

g

S

t

a

t

i

s

t

i

c

I

n

f

o

r

m

1

.

5

.

3

.

1

A

c

c

u

m

u

l

a

t

i

n

g

S

t

a

t

i

s

t

i

c

I

n

f

The statistic information collected from disk array is accumulated in a statistic information history file. One statistic
information history file stores the statistic information for one day collected from one disk array. A statistic information
history file is automatically created in a directory specified by environment definition.

Statistic information history files are created based on the following naming conversion.
Naming Convention for Statistic Information History Files:

ARRAY1

LAN

EC Storage Series

Figure 1-9 Accumulating Statistic Information

Business Servers

EC Storage

PerformanceMonitor

ARRAY2

o

a

r

m

a

t

i

o

n

t

i

o

n

Statistic Information

History File

yyyymmdd Disk Array Name [#nnn].psl

(i) yyyymmdd

The year, month, and day when accumulation to the statistic information history file started. If date changes while
statistic information is being accumulated, accumulation is done to a new statistic information history file.

(ii) Disk Array Name

This is the name of the disk array. Stat i stic i nformation history files are created for each disk array.

(iii) nnn

This is a file serial number (between 2 and 999). If a file with the same name exists when accumulation of statistic
information starts up, a serial number is assigned. For example, if the iSM server is shut down and started up in
operation of one day, the serial number is assigned to accumulated statistic information from the second startup of the
iSM server, and the value increments by one. The serial number has the upper limit. If the number exceeds this
limit, accumulation of statistic information fails.
To avoid it, move the statistic information history files to the different directory at each shutdown of the iSM server,
or summarize/extract statistic information as required, delete the statistic information history files. Then, restart the
iSM server.

I-15

Chapter 1 Overview of Performance Monitoring Function

If accumulation start and sto p operations are repeated without shut down and start up of the iSM server, t he file serial
number is not assigned or in cremented and accumulation of statistic information to the same file continues.
For information on how to estimate the size of a statistic information history file, refer to Appendix D “Estimation of
NEC Storage PerformanceMoni tor File Size”.

The period of reading statistic information is called the logging Interval. The user can specify the logging Interval from 1
minute to 60 minutes at environment definition of the iSM server. The logging Interval cannot be changed while the iSM
server is operating. To change the logging Interval, you must terminate the iSM server.
The accumulating processes of statistic information limits the number of times for collecting stati stic information within a
specified time, in order not to affect input/output process from the business host. Therefore, too many disk array
components may prevent collecting statistic information within a specified logging interval, and may disable starting of the
data accumulation pr ocess. In such a case, specifying the automatic adjustment of logging i nterval in the environment
definition of the iSM server adjusts the intervals appropriately, and prevents such failures in accumulating processes.
When a logging interval is automatically adjusted , a message notifies the adjustment.
The monitored disk arrays collect various types of statistic information by component/load type in the unit of summarizing.
From the statistic information, iSM reads the statistic information o f the types shown in Table 1-3 and accumulates t he time
changes in the statistic information history file. Such statistic information is called basic statistic information.
iSM also records information required for the following purposes in the statistic information history file.

 Component information required to interpret accumulated statistic information
 Name tags used for displaying the results of analysis

I-16

Chapter 1 Overview of Performance Monitoring Function

Unit of Summarizing
By Logical Disk By Host Port By Disk Port (Note1) By Physical Disk By RANK
Write External I/O Count

External Average

Response Time

Exter n al Maximum

Response Time

External Transfer Rate

Write Hit External I/O Count

External Average

Response Time

Exter n al Maximum

Response Time

External Transfer Rate

Read External I/O Count

External Average

Response Time

Exter n al Maximum

Response Time

External Transfer Rate

Read Hit External I/O Count

External Average

Type of Load

Prefetch Hit External I/O Count

Busy Internal average Busy

Others External I/O Count

Response Time

Exter n al Maximum

Response Time

External Transfer Rate

External Average

Response Time

Exter n al Maximum

Response Time

External Transfer Rate

Ratio

External I/O Count
External Average

Response Time

Exter n al Maximum

Response Time

External Transfer Rate

External I/O Count
External Average

Response Time

Exter n al Maximum

Response Time

External Transfer Rate

Internal average Busy

External Average

Response Time

Exter n al Maximum

Response Time

External Transfer Rate

Internal I/O Count
Internal Average

Response Time

Internal Maximum

Response Time

Internal Transfer Rate

Int. I/O Count
Int. Average Response

Time

Int. Maximum

Response Time

Int. Transfer Rate

Internal I/O Count
Internal Average

Response Time

Internal Maximum

Response Time

Internal Transfer Rate

Int. I/O Count
Int. Average Response

Time

Int. Maximum

Response Time

Int. Transfer Rate

Ratio

Internal operating

time

Table 1-3 Types of Statistic Information Accumulated in Statistic Information History Files

Internal I/O Count
Internal Average

Response Time

Internal Maximum

Response Time

Internal Transfer Rate

Int. I/O Count
Int. Average Response

Time

Int. Maximum

Response Time

Int. Transfer Rate

Internal average Busy

Ratio

Internal operating

time

(Note 1) Port of a disk director (called a “disk port” hereafter).
(Note 2) For a disk array that is not provided with function for collecting information of operating time, internal Busy

Ratio and internal op erating time is not accumulated in a statistic information history file.

(Note 3) For a disk array that is not provided with function for collecting information about RANK, information about

I-17

Chapter 1 Overview of Performance Monitoring Function

RANK is not accumulated in a statistic i nformation history file.

I-18

Chapter 1 Overview of Performance Monitoring Function

(1) Types of statistic information

iSM accumulates the following t ypes of statistic information in statistic information history files.

(i) External I/O count

This is the number of input/output requests received by the disk array from the external in each measurement period.
The unit is the number of times.

(ii) External Average Response Time

This is the Average Response Time for the input/output requests received by the disk array from the external in each
measurement period. The unit is microsecond. This is calculated by measuring the total of the external response
time and external I/O count during the unit measurement period and dividing the former by the latter.

(iii) External Maximum Response Time

This is the maximum response time for the input/output requests received by the disk array from the external in each
measurement period. The unit is microsecond.

(iv) E xternal Transfer Rate

This is the average Transfer Rate of the input/output process achieved in response to the input/output requests received
by the disk array from the external i n each measurement period. The unit is kilobyte/second. 1 kilobyte is 1024
bytes. This is calculated by measuring the total of the amount of external data transfer during the unit measurement
period and dividing it by the time interval of the measurement period.

(v) Internal I/O Count

This is the number of input/output requests issued to the internal disk devices by the control device of the disk array in
each measurement period. The unit is the number of times.

(vi) Internal Average Response Time

This is the Average Response Time for the input/output requests issued to the internal disk devices by the control
device of the disk array in each measurement period. The unit is microsecond. This is calculated by measuring the
total of the internal response time and internal I/O count during the unit measurement period and dividing the former
by the latter.

(vii) Internal Maximum Response Time

This is the maximum response time for the input/output requests issued to the internal disk devices by the control
device of the disk array in each measurement period. The unit is microsecond.

(viii) Internal Transfer Rate

This is the average Transfer Rate of the input/output requests issued to the internal disk devices by the control device
of the disk array in each measurement period. The unit is kilob yte/second. 1 kilobyte is 1024 bytes. This is
calculated by measuring the total of the amount of internal data transfer during the unit measurement period and
dividing it by the time interval of the monitoring period.

(ix) Internal average Busy Ratio

For physical disk and RANK, the valu e indicates the rate of operation. Unit is percent [%]. The value is calculated
by measuring operating time physical disk and RANK, and by dividing the operating time by a time slot of measuring
segment.
A Busy Ratio of logical disk is found by dividing the Busy Ratio of RANK by the ratio of loads on the logical disk.

(x) Internal Operating Time

The value indicates the operating time of physical disk and RANK within a measurement time of unit. Unit is

I-19

Chapter 1 Overview of Performance Monitoring Function

millisecond.

(2) Unit to sum up

Units to sum up are the units used for summarizing statistic information. iSM summarizes statistic information by
the following types of components and accumulates them separately.

(i) By logical disk

Load state of each logical di sk of the monitored disk array is accumulated. Statistic information is accumulated for
the number of logical di sks.

(ii) B y host port

Load state of each host port of the mon itored disk array is accumulated. Statistic information is accumulated for the
number of host ports.

(iii) By disk port

Load state of each disk port of the monitored disk array is accumulated. Statistic information is accumulat ed for the
number of disk ports.

(iv) By physical disk

Load state of each physical disk of the monitored disk array is accumulated . Statistic information is accu mulated for
the number of physical disks.

(v) By RANK

Load state of each RANK of the monitored disk array is accumulated. Stat istic information is accumulated for th e
number of RANKs.

(3) Load types

Load types are the types of loads of the monitored disk array. iSM distinguishes the following types of loads when it
accumulates statistic information.
Write Statistic information regarding data write operation.
Write Hit Statistic information about operations that could respond quickly, by writing data to cache only.

It is a subset of Write.
Read Statistic information regarding data read operation.
Read Hit Statistic information regardi ng data read operation which hit cache. It is a subset of Read.
Prefetch Hit Statistic information regarding data read operation which hit data transferred from the physical

disk to cache in advance b y the prefetch function of the disk device. It is a subset of Read Hit.
Busy Statistic information on the operating rate of a physical disk.
Others Statistic information regarding SCSI command process other than data write and data read.

1

.

5

.

3

.

2

D

o

w

n

l

o

a

d

i

n

g

S

t

a

t

i

s

t

i

c

I

n

f

o

r

m

a

t

i

o

n

1

.

5

.

3

.

2

D

o

w

n

l

o

a

d

i

n

g

S

t

a

t

i

s

t

i

c

I

n

f

o

r

m

1

.

5

.

3

.

2

D

o

w

n

l

o

a

d

i

n

g

S

t

a

t

i

s

t

i

c

I

n

f

The statistic informatio n accumulated on the iSM management server can be summarized, extracted and edited by
downloading on the iSM client. Downloading is allowed for clients of levels L2 or L3. If the iSM server is operating,
downloading is performed on the Performance Monitor screen. If the iSM server is not operating, downloading is allowed
with an FTP tool.

o

a

r

m

a

t

i

o

n

t

i

o

n

I-20

Chapter 1 Overview of Performance Monitoring Function

1

.

5

.

3

.

3

S

u

m

m

a

r

i

z

i

n

g

S

t

a

t

i

s

t

i

c

I

n

f

o

r

m

a

t

i

o

n

1

.

5

.

3

.

3

S

u

m

m

a

r

i

z

i

n

g

S

t

a

t

i

s

t

i

c

I

n

f

o

r

m

1

.

5

.

3

.

3

S

u

m

m

a

r

i

z

i

n

g

S

t

a

t

i

s

t

i

c

I

n

f

The statistic information accumulation function described above accumulates statistic information collected in every
logging Interval in statistic information history file. If statistic information collected in relatively short intervals is
accumulated in the long term, the amount of data in the statistic information history file will become enormous and
eventually exhaust t he free disk space.
For saving disk space, the accumulated statistic data is summarized into the information of a period longer than the logging
interval, reducing amount of information included in a file, downsizing the data. This function is called summarizing
statistic information. The information after summarizing is output to statistic information summarized file.

When you want to accumulate statistic information in the long term, you can save the disk space by using this function as
required to summarize statistic information and deleting th e st atistic information originall y accu mul ated. For information
on how to estimate the size of a statistic information summarized file, refer to Appendix D “Estimation of NEC Storage
PerformanceMonitor File S i ze” of this manual.

(1) Summarizing basic statistic information

o

a

r

m

a

t

i

o

n

t

i

o

n

The summarizing function statistic information summarizes all basic information stored (refer to table 1-3), and
outputs the information to a statistic information summarized file. The following describes basic statistic
information after summarizing.

• For statistic information regarding I/O count, the I/O counts within all the measurement periods contained in the

period of summarizing are accumulated, and the result is the I/O count of th e period of summarizing.

• Statistic information of average response time: On the basis of all average response times and I/O counts within

applicable summarizing segments, total response time and total I/O count are found. Average response time is
calculated by dividing the former by the latter.

• For statistic information regarding maximum response time, the maximum value is taken from the maximum

response times within all the measurement periods contained in the period of summarizing, and it is the maximum
response time of the period of summarizing.

• Statistic information of transfer rate: On the basis of all transfer rates within applicable summarizing segments, total

transfer length is found. A transfer rate of the summarizing segment is calculated by dividing the total transfer
length by the measurement time of the summarizing segment.

• Stat istic information of Busy Ratio: All busy time within applicable summarizi ng segments is accumulated.

Average Busy Ratio of the summarizi ng segment is calculated b y divi ding the total busy time by the measu r ement
time of the summarizing segment.

• For statistic information regarding operating time, the operating time within all the measurement periods contained

in the period of summarizing are accumulated and the result i s th e operating time of the period of summarizin g.

(2) Inserting extended statistic information

For allowing reference to the fluctuation width of statistic information even after summarizing, extension of statistic
information is calculated in addition to the summarized basic statist ic information and stored in the summari zed
statistic information file. The extension of statistic information includes the following types.

I-21

Chapter 1 Overview of Performance Monitoring Function

Maximum/minimum
External I/O Density

Maximum/minimum
External Transfer Rate

Maximum/minimum
External Busy Rate

Maximum/minimum
Internal I/O Density

Maximum/minimum
Internal Transfer Rate

Maximum/minimum
Internal Busy Ratio

This is the maximum and minimum values of the external I/O Density in each
measurement period contained in the period of summarizing. The unit is
count/1000 seconds.

This is the maximum and minimum values of the external transfer rates in each
measurement period contained in the period of summarizing. The unit is
kilobyte/second.

This is the maximum and mini mum values of the external bu s y ratios in each
measurement period contained in the period of summarizing. The unit is %
(percent).

This is the maximum and minimum values of the internal I/O density in each
measurement period contained in the period of summarizing. The unit is
count/1000 seconds.

This is the maximum and minimum values of the internal transfer rates in each
measurement period contained in the period of summarizing. The unit is
kilobyte/second.

This is the maximum and mini mum values of the internal busy ratios in each
measurement period contained in the period of summarizing. The unit is %
(percent).

(3) Inserting configuration information

In addition to the statistics information summarized in the method described in previous sections, configuration
information is also stored in the summarized statistic information file. This feature allows easy identification of the
various types of statistic information.

(4) Types of summarized files

In order to select an appropriate balance between the time resolution and amount of accumulated information. You
can create summarized files whose average time interval in the p eriod of summarizing is one hour and summarized
files whose average time interval is one day.
A file which contains statistic information summarized in units of hours is called a primary summarized file, and file
which contains statistic information summarized in units of days is called a secondary summarized file. In other
words, iSM has three types of files which store statistic information, as shown in Table 1-5.

Table 1-5 Types of Files in Which Statistic Information Is Stored

Type of File

Statistic Information History File Logging Interval For max. of one day
Statistic Information Primary

Summarized File
Statistic Information Secondary

Summarized File

Average Time Interval of

Period of Summariz ing

One hour For max. of one day

One day For max. of one month

Amount Recorded in One File

(5) Types of summarizing operations

iSM provides the following three types of summarizing functions to deal with the two types of summarized files.

I-22

Chapter 1 Overview of Performance Monitoring Function

(i) History file → Primary summarized file (primary summarizing)

The input is a statistic information history file, and the output is a primary summarized file. In other words, statistic
information in each lo gging Interval within each perio d of summarizing in the input file is su mmari zed in units of
hours and the result is recorded in the output file.

(ii) History file → Secondary summarized file (direct primary summarizing)

The input is a statistic information history file, and the output is a secondary summarized file. In other words,
statistic information in each logging interval within each period of summarizing in the input fil e i s summarized in
units of days and the result is recorded in the output file.

(iii) Primary summarized file → Secondary summarized file (secondary summarizing)

The input is a primary summarized file, and the output is a secondary summarized file. In other words, statistic
information in each hour within each period of summarizing in t he input file is summarized in units of days.
For the enhanced statisti c information, the maximum and minimum values are selected from th e enhanced statistic
information of the same type recorded in the primary summarized file.

1

.

5

.

3

.

4

E

x

t

r

a

c

t

i

n

g

S

t

a

t

i

s

t

i

c

I

n

f

o

r

m

a

t

i

o

n

1

1

.

5

.

3

.

4

E

x

t

r

a

c

t

i

n

g

S

t

a

t

i

s

t

i

c

I

n

f

o

r

m

.

5

.

3

.

4

E

x

t

r

a

c

t

i

n

g

S

t

a

t

i

s

t

i

c

I

n

f

o

r

m

a

a

t

i

o

n

t

i

o

n

Statistic information about disk array collected by iSM is accumulated in statistic information h i sto r y files an d statistic
information summarized files. This function can extract and output the information to a CSV format file (delimited by
commas).
Use of this function allows displaying values of accumulated statistic information. Furthermore, a spreadsheet program
can display the data of CSV format file in graphs, allowing review of long-term load fluctuation and performance analysis.
By specifying addition of header upon extracting a CSV file, the header record for the values is added to top of the file.
Editing the statistic information with a header record using a spreadsheet program allows easy identification of the statistic
data values.
CSV Conversion Tool creates CSV files according to the following naming con vention. For information on the structure
of a CSV file, refer to Appendix B “CSV File Structure” of this manual.

Naming Convention for CSV Files

“Name of Statistic Information History (Summarized) File”_”Extension of Statistic
Information History (Summarized) File”.csv

Example: Name of the CSV file for the statistic information history file “20020401NECStorage4100.psl”

20020401NECStorage4100_psl.csv

In statistic information history/summarized files, various types of statistic information regarding components of the disk
array are accumulated. You can extract the specified statistic information from the statistic information by giving
extraction conditions to CSV Conversion Tool depending on your purpose. The following extraction conditions can be

I-23

Chapter 1 Overview of Performance Monitoring Function

specified for CSV Conversion Tool.

 Period of extraction
 Component of disk array
 Type of statistic information

In statistic information history/summarized files, the component information of the disk array is accumulated in addition to
statistic information. CSV Conversion Tool can also extract component information.

I-24

Chapter 1 Overview of Performance Monitoring Function

(1) Extracting statistic information in the specified period

To extract statistic information in the specified period, specify the period in CSV Conversion Tool. To specify a
period, you can specify the extraction starting time and end time, or either one of them.

(i) Specifying the extraction starting time and end time

Statistic information from the extraction starting time to the extraction end time is extracted.

(ii) Specifying the extraction starting time only

Statistic information after the extraction starting time is extracted.

(iii) Specifying the extraction end time only

Statistic information before the extraction end time is extracted.

(2) Extracting statistic information regarding the specified component

To extract statistic information of the specified component of the disk array, specify the component of the disk array
in CSV Conversion Tool. The following components can be specified.

• Host port

• Disk port

• Logical disk

• Physical disk

• RANK

(3) Extracting statistic information of the specified type

Statistic information can be generally categorized into the following types.

(i) Information regarding the number of inputs/outputs

This information contains the number of inputs/outputs, the maximum values of input/output density (IOPS) and
minimum values of input/output density.

(ii) Information regarding the response time of the I/O process

This information contains the average response time and the maximum response time.

(iii) Information regarding the Transfer Rate of the I/O process

This information contains Transfer Rate and the maximum and minimum values of Transfer Rate.

(iv) Information regarding the operating status of the devices

Operating time and maximum and minimum values of the operating time are included. A Busy Ratio and maximum
and minimum values of the Busy Ratio are included.

In (i) to (iv) above, to extract statistic information of the specified type, specify the type in CSV Conversion Tool.

(4) Extracting configuration information

There are the following types for configuration information of a disk array.

(i) Information regarding the disk array and configurations

Information regarding:

 Disk array
 Host port

I-25

Chapter 1 Overview of Performance Monitoring Function

 Disk port
 Logical Disk
 Physical Disk
 RANK

(ii) Information regarding changes in logical disk names

This is information regarding changes in logical disk names.

(iii) Information regarding changes in disk array configuration

This is information regarding changes in disk array configuration.

(iv) Information regarding changes in RANK configuration

This is information regarding Logical Disk moving between RANKs by the performance optimization function.

To extract (i) and (ii), you must specify extraction of configuration information in CSV Conversion Tool. (iii) and (iv) is
always extracted regardless of specification to CSV Conversion Tool.
When configuration of the disk array and RANK changes, statistic information before and after the chan ge are no longer
related. Therefore, you must consider the following to analyze statistic information.
When information (iii) is output, statistic information regarding all configuration s collected before and after the output is
no longer related.
When information (iv) is output, only statistic information on the RANK collected before and after the output is no longer
related.

1

.

5

.

3

.

5

E

d

i

t

i

n

g

S

t

a

t

i

s

t

i

c

I

n

f

o

r

1

1

.

5

.

3

.

5

E

d

i

t

i

n

g

S

t

a

t

i

s

t

i

c

I

.

5

.

3

.

5

E

d

i

t

i

n

g

S

t

a

t

i

s

n

t

i

c

I

n

m

f

o

r

m

f

o

r

m

a

a

a

t

i

o

n

t

i

o

n

t

i

o

n

As described in 1.5.3.4 “Extracting Statistic Informatio n”, a user can create CSV format files using the CSV conversion tool,
and can edit the data using sp readsheet software as required. This process makes analysis of the statistic information
easier.
Furthermore, use of the functions provided by iSM allows easy analysis without a spreadsheet program. iSM provides the
following edit functions for statistic information:

 A program called Performance Report Editor for the user to edit/modify in a format easy for performance analysis and

output to a file the statistic information accumulated in statistic information history files and statistic information
summarized files.

 Function of displaying graphs (Graph making tool) for files created with the edit tool (performance report).

(1) Performance Report Editor

The Performance Report Editor uses statistic information history/summarized files as inputs and edits/modifies the
statistic information into a text-format Performance Report. The user can reference the Performance Report to
readily analyze the performance of a disk array.
Types and overview of Performance Report are given below. For details of the Performance Report, refer to
Appendix C “Report Format of Performance Report Editor” of this manual.

(i) Performance Summary Report

The Performance Summary Report is a component-based summary of statistic information on:
 whole disk array

I-26

Chapter 1 Overview of Performance Monitoring Function

 host direc tor ports
 disk director ports
 logical disks
 physical disks
 RANKs

Analysis of the Performance Summary Report provides understanding of general load status in the entire disk array
and each component of the statistic information collection period.

(ii) Performance Detail Report

The Performance Detail Report summarizes the following statistic information per statistic information logging
Interval of the iSM and is assigned chronologically:

 whole disk array
 host direc tor ports
 disk director ports
 logical disks
 physical disks
 RANKs

Analysis of the Performance Detail Report provides understanding of chronological change in the load status of the
entire disk array and each component as well as detection of a performance bottleneck.
The Performance Detail Report has six types of report:

 detailed report on the whole disk array
 detaile d rep ort on hos t dire c tor po rts
 detailed report on disk director ports
 detailed report on logical disks
 detailed report on physical disks
 detailed report on RANKs

The Performance Report Editor creates a Performance Report in accordance with the following naming rule:
 When input is a statistic information history file (xxxxxx.psl):

xxxxxx_psl_ edit type.txt

 When input is a statistic information summarized file (xxxxxx.psa):

xxxxxx_psa_edit type.txt
One of the following strings is set in the “edit type” depending on the type of Performance Report:
sum: summary report
array: detailed report on the whole disk array
hp: detailed report on host direct or po r ts
dp: detailed report on disk director ports
ld: detailed report on logical disks
pd: detailed report on physical disks
rank: detailed report on RANKs

(2) Performance Report Viewer

I-27

Chapter 1 Overview of Performance Monitoring Function

The Performance Report Viewer i s a t ool that uses detailed report on the whole disk arrays created via the
Performance Report Editor as inputs to provide graphic representation of statistic information. The user references a
graph to understand the load state of disk array and chronological change in the load.
The Performance Report Viewer can be used in an environment where M icrosoft® Excel2000 is installed. An iSM
client must be installed in the personal computer for using the Performance Report Viewer.

I-28

Chapter 2 Installation of Performance Monitoring Function

I-29

Chapter 2 Installation of Performance Monitoring

Function

2

2

2

.

.

.

1

1

1

S

S

S

e

e

e

r

r

r

v

v

v

e

e

e

r

r

r

I

I

I

n

n

n

s

s

s

t

t

t

a

a

a

l

l

l

l

l

l

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

2

2

2

.

.

.

1

1

1

.

.

.

1

1

1

S

S

S

y

y

y

s

s

s

t

t

t

e

e

e

m

m

m

R

R

R

e

e

e

q

q

q

u

u

u

i

i

i

r

r

r

e

e

e

m

m

m

e

e

e

n

n

n

t

t

t

s

s

s

For HW, OS, memory, and disk capacity, the same system requirements as those for iSM are appl i cable. Refer to Part
I “Installation and Setting of NEC Storage Manager” of the “NEC Storage Manager User’s Manual” for your OS.
Required software and appli cable storage devices are as follows:

Table 2-1 System requirements

Required software NEC Storage Manager
Applicable storage

device

NEC Storage 4000 series
NEC Storage 3000 series
NEC Storage 2000 series
NEC Storage 1000 series

2

2

2

.

.

.

1

1

1

.

.

.

2

2

2

I

I

I

n

n

n

s

s

s

t

t

t

a

a

a

l

l

l

l

l

l

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

Installation of iSM is accompanied by installing the NEC Storage PerformanceMonitor at the same time.
For installing and uninstalling, refer to Part I “Installation and Setting of NEC Storage Manager” of the “NEC Storage
Manager User’s Manual” for your OS.

2

2

2

.

.

.

1

1

1

.

.

.

3

3

3

E

E

E

n

n

n

v

v

v

i

i

i

r

r

r

o

o

o

n

n

n

m

m

m

e

e

e

n

n

n

t

t

t

S

S

S

e

e

e

t

t

t

t

t

t

i

i

i

n

n

n

g

g

g

To use the performance monitoring function, it is necessary to make the environment setting of the iSM server.
Create settings for the items below. For information on how to make settings, refer to the Part I “Installation and
Setting of NEC Storage Manager” of the “NEC Storage Manager User’s Manual” of your OS.

(i) Specify the location of the statistic information history file.
(ii) Specify an interval for collecting statistic information and outputting it into the statistic information history file.
(iii) Specify the number of data updates per minute on the Performance Monitoring screen.
(iv) Specify whether or not to automatically start the output of statistic information with regard to all the disk arrays

that have the performance moni t ori ng function available at the st art of the iSM server.
(v) Interval for monitoring threshold
(vi) Lower limit value for I/Os within threshold monitoring interval

Chapter 2 Installation of Performance Monitoring Function

I-30

2

2

2

.

.

.

2

2

2

C

C

C

l

l

l

i

i

i

e

e

e

n

n

n

t

t

t

I

I

I

n

n

n

s

s

s

t

t

t

a

a

a

l

l

l

l

l

l

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

2

2

2

.

.

.

2

2

2

.

.

.

1

1

1

S

S

S

y

y

y

s

s

s

t

t

t

e

e

e

m

m

m

R

R

R

e

e

e

q

q

q

u

u

u

i

i

i

r

r

r

e

e

e

m

m

m

e

e

e

n

n

n

t

t

t

s

s

s

The same system requirements as those for iSM are applicable to the NEC Storage PerformanceM onitor. Refer to
Part I “Installation and Setting of NEC Storage Manager” of the “NEC Storage Manager User’s Manual” for your OS.

2

2

2

.

.

.

2

2

2

.

.

.

2

2

2

I

I

I

n

n

n

s

s

s

t

t

t

a

a

a

l

l

l

l

l

l

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

For installing the NEC Storage PerformanceMonitor, install the iSM client with specifying a setup type that includes
extended functions.
For installation procedures, refer to Part I “Installation and Setting of NEC Storage Manager” of the “NEC Storage
Manager User’s Manual” for your OS.

Chapter 3 Operations of Performance Monitoring Function

I-31

Chapter 3 Operations of Performance Monitoring

Function

3

3

3

.

.

.

1

1

1

R

R

R

e

e

e

a

a

a

l

l

l

-

-

-

T

T

T

i

i

i

m

m

m

e

e

e

D

D

D

i

i

i

s

s

s

p

p

p

l

l

l

a

a

a

y

y

y

o

o

o

f

f

f

L

L

L

o

o

o

a

a

a

d

d

d

S

S

S

t

t

t

a

a

a

t

t

t

u

u

u

s

s

s

Explanation will be made about the operation method for monitoring the load status in real time by using the
Performance screen.

(1) Performance Monitoring Starting

Clicking the button for activating the performance monitor function opens the Performance Monitor screen,
which starts performance monitoring. The Performance Monitor screen displays the following forms for
monitoring latest load states.

 Displays the latest load status in numerical values (Numeric Table)
 Displays changes of the load status in a line graph (Time-series Graph)
 Displays the latest load status in a Bar Graph (Bar Graph)

(2) Numeric Table Display

The Numeric Table screen appears upon activating the performance monitor function. The screen displays the
latest load states in the form of numeric table. The Numeric Table screen allows you to monitor the latest load
status as well as to perform settings of real-time display. On this screen, a list with rows of monitoring objects
and columns of monitored items is displayed according to the specified component type. The latest values are
updated according to specified intervals. For setting of the interval, refer to 2.1.3 “Environment Setting” of Part
I “Performance Monitoring Function” of this manual.
Figure 3-1 is an example of display when ports are selected as the component type. This display allows you to
monitor the latest valu es of load status and use status of each po r t.

Figure 3-1 Numeric Table Screen (When the Port is Selected)

(i)
(ii)

(iii)

(iv)

(v)

Chapter 3 Operations of Performance Monitoring Function

I-32

The performance monitor screen, as shown in Figure 3-1, is composed of areas (i) thorough (v). The following
describes the areas.
(i) Menu bar

The menu bar is used for selecting necessary items from the menu for various operations. For details, refer to
Help.

(ii) Tool bar

Among the menu items, the following functions that are frequently used can be activated by a single click of a
button. Refer to Help for details of the buttons.

 [File] → [Save of Setting], [Performance Analysis Supporting Tool]
 [View] → [Numeric Table], [Time -s e rie s Graph], [Bar G r aph ], [Th r e shold ], [S how Threshold in graph],

[Release Threshold in graph], [I/O Density], [Transfer Rate], [Average Transfer Length], [Average Response
Time], [Read Hit Ratio], [Write Hit Ratio], [Busy Ratio]

 [Setting] → [Monito rin g Ob ject Logical Disk], [Monitoring Object Physical Disk], [Set Graph Scale]
 [Threshold Monitoring] → [Set Threshold], [Show All Items Specified Threshold]
 [Operation] → [Start/Stop Accumulation of Statistic Information], [Download Statistic Information files]

(iii) Information display area

A numeric table and graph indicating load states are displayed (Note 1).

(iv) Status bar

The status bar at the bottom displays the current status of performance monitoring function. The following
describes details of the displayed items.
(a) Display Refresh Interval

A time interval for updating the Performance screen is indicated by the number of seconds. Any one of 10,
12, 15, 20, 30, and 60 is displayed. For specifying a refreshing interval, refer to 2.1.3 “Environment
Setting”.
Example 10: Update every 10 seconds (specify 6 as number of updates per minute)

(b) Operating state

 Information acquiring:

Indicates that the initial information necessary for displaying the load status on the Performance
Monitoring screen is being collected from the iSM server.

 Working:

Indicates that various processing on the Performance Monitoring screen is being performed.

 Stop:

Indicates that various processing on the Performance Monitoring screen has been terminated due to
disconnection of the iSM client from the iSM server or cancellation instruction in the Information
acquiring dialog screen. If the system is connection to the iSM server, you can select and execute
[Refresh] from the menu function to restart various processing on the Performance screen.

(v) Statistic information storing state

It indicates whether or not the iSM is storing statistic information into a statistic information history file.
 Statistic Information starting:

Indicates that the iSM is storing statistic information into a statistic information history file.

 Statistic Information stopped:

Indicates that the iSM is not storing statistic information.

 Checking:

Chapter 3 Operations of Performance Monitoring Function

I-33

Indicates that iSM has not completed in obtaining statistic information required for displaying client.

(Note 1)
A performance monitor server using older version software may not support some of the displaying functions. In
such a case, a hyphen “-” is displayed for an applicable item. For displaying such items, software o f the latest
version is required.

Figure 3-2 shows an example of display when logical disks are selected as the component type. In this display, you
can monitor the latest values of load status and use status of each logical disk.

Figure 3-2 Numeric Table Screen (When [Logical Disk] is selected)

Left-clicking on a tab label of calculation unit (such as disk array and port) switches the numeric table into a table
indicting applicable calculation unit. The numeric table displays the following information, in accordance with the
calculation unit selected by the procedure.
(i) When the [Disk Array] tab is selected

The Numeric Table indicating load statuses by disk array is displayed . The rows are all the disk arrays which
are currently being monitored by the iSM. The columns indicate:

 External I/O Density
 External Transfer Rate
 External Average Transfer Length
 External Average Response Time.
 Read Hit Ratio
 Write Hit Ratio

However, the string “External” is omitted in the labels.
In this display, the list does not change when you change the disk array to be monitored by using the combo box.

(ii) When the [Port] tab is selected

The Numeric Table indicating load statuses by port of the disk array specified in the combo box is displayed.
The rows are all the ports which belong to the disk array specified in the combo box. The columns indicate:
 External I/O Density

Chapter 3 Operations of Performance Monitoring Function

I-34

 External Transfer Rate
 External Average Transfer Length
 External Average Response Time

However, the string “External” is omitted in the labels.
When you change the disk array to be monitored by using the combo box, the display switches to the list of load
status by port of the selected disk array.

(iii) When the [Logical Disk] tab is selected

The Numeric Table indicat ing load state of by logical disk of the disk array specified in the combo box is
displayed. The rows are the logical disks registered as monitoring objects among th e logical disks created in the
disk array specified in the combo box. The columns indicate:

 External I/O Density
 External Transfer Rate
 External Average Transfer Length
 External Average Response Time
 Read Hit Ratio
 Write Hit Ratio

However, the string “External” is omitted in the labels.
When you change the disk array to be monitored by using the combo box, the display switches to the list of load
status by logical disk of th e sel ected disk array.

(iv) When the [Physical Disk] tab is selected

The Numeric Table indicati ng load statuses by physical disk of the disk array specified in the combo box is
displayed. The rows are the physical disks registered as monitoring objects among the p hysical disks created in
the disk array specified in the combo box. The columns indicate:

 Internal I/O Density
 Internal Transfer Rate
 Internal Average Transfer Length
 Internal Average Response Time
 Busy Ratio

However, the string “Internal” is omitted in the labels.
When you change the disk array to be monitored by using the combo box, the display switches to the list of load
status by logical disk of th e sel ected disk array.

If an overload occurs during overlo ad monitoring, asterisks (**) appear on the left of the applicable item. Cells
of the items displayed in graphs are displayed in gray.

(3) Sorting the load status list

By clicking a label indicating a type of the monitored item ([Number], [I/O Density], etc.) in the list of load status,
you can sort the lines of the list in an ascending or descending order by using the current value of the monitored
item you click as a key. Repeatedly clicking the label will switch between ascending and descending orders.

Chapter 3 Operations of Performance Monitoring Function

I-35

(4) Registering/Deleting logical disks to be monitored

When you click [Setting] and then select [Monitoring Object Logical Disk] on the Numeric Table screen (Figure
3-2), the Registration of Logical Disks dialog box appears (Figure 3-3). This dialog allows you to change the
logical disks for performance monitoring in the disk array specified in the combo box of the Numeric Table.

Figure 3-3 Registration o f Logical Disks Dialog

[Monitoring Candidate List] displays unregistered logical disks among all the logical disks created in the
specified disk array. [Monitor Object ] displays all the logical disks currently registered as monitoring objects.
Selecting logical disks in [Monitoring Candidate List] and clicking the [Add] button will register the specified
logical disks to the [Monitor Object] list. On the other hand, selecting logical disks in the [Monitor Object] list
and clicking the [Delete] button will delete the specified logical disks from the [Monitor Object] list.
When you click the [OK] button, all the logical disks currently displayed in the [Monitor Object] list are formally
registered as the monitored logical disks and the dialog box closes. When you click the [Can cel] button, the
current [Monitor Object] list is ignored and the dialog box clo s es wi th the monitored logical di sks registered
when the dialog box opened unchanged.

(5) Registering/Deleting physical disks to be monitored

When you click [Setting] and select [Monitoring Object Physical Disk] on the Numeric Table screen, the
Registration of Physical Disks dialog box appears (Figure 3-4). This screen allows you to register physical disks
for performance monitoring among the physical disks installed in the disk array specified in the combo box of the
original screen.

Chapter 3 Operations of Performance Monitoring Function

I-36

Figure 3-4 Registration of Physical Disks Dialog

[Monitoring Candidate List] displays unregistered physical disks among all the physical disks created in the
specified disk array. [Monitor Object] displays all the physical disks currently registered as monitoring objects.
Selecting physical disks in the [Monitoring Candidate List] and clicking the [Add] button will register the
specified physical disks to the [Monitor Object] list. On the other hand, selecting physical disks in the [Monitor
Object] list and clicking the [Delete] button will delete the specified physical disks from the [Monitor Object] list.
When you click the [OK] button, all the physical disks currently displayed in the [Monitor Object] list are
formally registered as the monitored physical disks and t he dialog box closes. When you click the [Cancel]
button, the current [Monitor Object] list is ignored and the dialog box closes with the monitored physical disks
registered when the dial og box opened unchanged.

(6) Preparation for graph display

For displaying load states on Time-series Graph screen and Bar Graph screen, items to be displayed on a graph
must be registered on the Numeric Table scre en. The maximum number of monitoring objects that can b e
registered in one graph is 16.

Chapter 3 Operations of Performance Monitoring Function

I-37

Figure 3-5 Registering to Graphs Menu

On the Numeric Table screen, when you speci fy a line which shows the latest value (place t he cursor over the left
cell and click the cell. In Figure 3-5, the line of logical disk 008ch is specified), click [Setting], and then point to
[Registration to Graph], all the monitored items for the line are registered as items to be displayed in Time-series
Graphs. The cells which have been registered as the items to be displayed in graphs are displayed in gray.
On the other hand, when you specify a line which shows the latest value, click [Setting], and then point to [Delete
from Graph], the monitored items of the monitoring object is no longer displayed in Time-series Graphs. In this
case, the corresponding cells are displayed in the original background color.

(7) Time-Series Graphs display

If you select [View] → [Time-series Graph], the screen will change to the Time-series Graph screen. The
Time-series Graph screen displays the fluctuations of loads in line graphs for seven monitoring items. Figure
3-6 shows an example of the display that appears when a Time-series Graph is selected for port and logical disk
and physical disk.

Chapter 3 Operations of Performance Monitoring Function

I-38

Figure 3-6 Time-series Graph Screen

The “Time-series Graph” screen consists of the menu area and tool bar for performing various operations, the
load status display area for showing load status, the legend display area for showing the items displayed in
Time-series Graphs, and the status bar for displaying the connection state.
Seven graphs are displayed in the load status display area. The following graphs are individually displayed
(Note 1):

 I/O Density
 Transfer Rate
 Average Transfer Length
 Average Response Time
 Read Hit Ratio
 Write Hit Ratio
 Busy Ratio

This section describes the procedures for displaying a line indicating a threshold (index value for overloads) on
the graph. For threshold, refer to 3.2 “Monitoring Overloads”.
 On the “Time-series Graph” screen, select a line or multiple lines for which you want to display threshold from

the legend display area, and then select [View] → [Show Th reshold in graph].

 On the “Time-series Graph” screen, select a line or multiple lines for which you want to display threshold from

the legend display area, and then select [Show Threshold in graph] from the tool bar.

 On the “Time-series Graph” screen, select a line or multiple lines for which you want to display threshold from

the legend display area, and then select [Show Threshold in graph] from the right-click menu.

Chapter 3 Operations of Performance Monitoring Function

I-39

The threshold line is displayed on the graph. The line is displayed for time zone from the time the threshold is
set to the time it is unset. When past information is displayed, a threshold line is displayed in the time zone for
which thresholds have been set. When a value exceeded the threshold line, a time line is displayed in a dark
color that shows the time from when a value exceeded the threshold to the time when the Release Thresho l d
Excess function was executed.

Immediately after display of Time-series Graphs has started, only the latest values of the monitored items are
displayed, and then, the latest values of the monitored items will be plotted at specified time intervals. When
line graphs come to the end of th e screen width, they scroll so that the oldest values are out of the screen.
Operating the scroll bar will allow you to see the past information. The past information that can be displayed
varies depending on the setting for Display Refresh Rate. For example, setting 1 for Display Refresh Rate
allows you to see the past information of 24 hours. Setting 6 for Display Refresh Rate allows you to see the past
information of 3 hours.
If viewing many time-series graphs of monitoring items displayed on a screen is difficult, whether to display/hide
time-series graph and displaying order of graphs can be specified for each mon itoring item. To specify
display/hide time-series graphs for each mon i toring item, select [View] → [Customize Time-series Graph] on
menu, and specify whether to display or hide desired monitoring items on the check boxes of the Customize
Time-series Graph dialog. To specify displaying order of graphs, select a desired item on the Customize
Time-series Graph dialog, and move the item by clicking the [Up] or [Down] button. Figure 3-7 shows the
Customize of Graph dialog.

Figure 3-7 Customize Time-series Graph Dialog

If viewing the lines is difficult behind many overlapping time-series graphs of registered items, double-clicking
on the legend for the graph line moves the lines onto the front. Selecting a legend and pressing the Enter key
also moves the lines to the front.

Chapter 3 Operations of Performance Monitoring Function

I-40

(Note 1)
A performance monitor server using older version software may not support some of the displaying functions. In
such a case, a graph frame only is displayed and graph lines are not displayed. For displaying graph lines, software
of the latest version is required.

(8) Showing Bar Graphs

Selecting [View] → [Bar Graph] menu on Numeric Table screen switches the screen to the Bar Graph screen.
The Bar Graph screen is capable of showing latest load states of seven monitoring items in bar-graph format.
Figure 3-8 shows an example of the display when the ports, and logical disks and physical disks are registered for
graph display.

Figure 3-8 Bar Graph Screen

The Bar Graph screen consists of the menu area and tool bar for performing various operations, the load status
display for showing the load status, the legend display area for showing the items displayed in Bar Graphs, and
the status bar for displaying the connection state.
The load status display area shows one item selected from the following monitored items.

 I/O Density
 Transfer Rate
 Average Transfer Length

Chapter 3 Operations of Performance Monitoring Function

I-41

 Average Response Time
 Read Hit Ratio
 Write Hit Ratio
 Busy Ratio

This section describes the procedures for displaying a line indicating a threshold (index value for overloads) on
the graph. For threshold, refer to 3.2 “Monitoring Overloads”.
 On the Bar Graph screen, select a line or multiple lines for which you want to display threshold from the legend

display area, and then select [View] → [Show Threshold in graph].

 On the Bar Graph screen, select a line or multiple lines for which you want to display threshold from the legend

display area, and then select [Show Threshold in graph] from the popup menu by right-click.

 On the Bar Graph screen, select a line or multiple lines for which you want to display threshold from the legend

display area, and then select [Show Threshold in graph] from the tool bar.
The threshold line is displayed on the graph. The line is displayed for time zone from the time the threshold is
set to the time it is unset. When a value exceeded the threshold line, hatch lines are displayed until the time
when the Release Threshold Excess fun ct ion is executed.

The Bar Graph screen allows changing display items by selecting [View] menu (similar operation is available by
toolbar buttons). For example, selecting [I/O Density] allows displaying a bar graph that shows latest values of
I/O Density. Switching to other items is allowed by similar operation.

(Note 1)
A performance monitor server using older version software may not support some of the displaying functions. In
such a case, a graph frame only is displayed and a bar graph is not displayed. For displaying a bar graph, software
of the latest version is required.

Chapter 3 Operations of Performance Monitoring Function

I-42

(9) Changing Graph Scales

A maximum value of a graph scale displayed on the Bar Graph screen is changeable freely on the Setting Graph
Scale dialog. The Setting Graph Scale dialog is displayed by selecting [Setting] → [Set Graph Scale] menu.
Figure 3-9 shows an example of display of the Set Graph Scale dialog screen.

Figure 3-9 Set Graph Scale Dialog

For specifying a desired maximum value of a graph scale, uncheck the check box of [Autoscale] on the Setting
Graph Scale dialog, and specify a new maximum value. If [Autoscale] ch eck box is checked, graph scales are
automatically calculated based on the past load states.

(10) Record Sc reen In fo rmation

When you select [Record Screen Information] from the [View] menu, th e current location and size of the
Performance Monitoring screen, information on display/non-display of the tool bar and status bar, and the size
and arrangement of the graph displ ay area an d legend display area can be recorded. When screen information is
recorded, next time when you op en the Performance Monitoring screen, it is displayed in the state when the
location and size of the screen, display/non-display of tool bar and status bar, and the ratio of the graph display
area to the legend display area was recorded.
For screen images, refer to Figure 3-6 “Time-series Graphs Screen”.

Chapter 3 Operations of Performance Monitoring Function

I-43

(11) Saving Settings

To save registration and deletion settings for graphs performed in the [Setting] menu and change settings of
logical/physical disks to be monitored, click [File], and then point to [Save of Setting] as shown in Figure 3-10.
The saved settings are restored when the Performance Monitoring screen opens next time.

Figure 3-10 Save of Setting Menu

Chapter 3 Operations of Performance Monitoring Function

I-44

(12) Performance Monitoring Stop

To close the Performance Monitoring screen, click [File] and then click [Close] Menu as shown in Figure 3-11.

Figure 3-11 Close Menu

Chapter 3 Operations of Performance Monitoring Function

I-45

3

3

3

.

.

.

2

2

2

M

M

M

o

o

o

n

n

n

i

i

i

t

t

t

o

o

o

r

r

r

i

i

i

n

n

n

g

g

g

O

O

O

v

v

v

e

e

e

r

r

r

l

l

l

o

o

o

a

a

a

d

d

d

s

s

s

(1) Thresholds display

When you click [View] and then click [Threshold] on the Numeric Table screen as shown in Figure 3-12, the
threshold column appears next to the current value column, as shown in Figure 3-13, to display thresholds of the
monitored items specified for each monitoring target.

Figure 3-12 “Threshold” Menu

Figure 3-13 Numeric Table Screen (Displaying Thresholds)

A blank threshold column indicates that a threshold for the thresh old monitoring element has not been specified.
The [Threshold] menu is a toggle switch. Clicking the menu again will delete the threshold column and restore
the original screen.

Chapter 3 Operations of Performance Monitoring Function

I-46

(2) Thresholds setting

On the Numeric Table screen, select the line (Note 1) or cell (Note 2) of the threshold monitoring element for
which you want to set a threshold. Then, select [Threshold Monitoring] → [Set Threshold] menu. The Set
Threshold dialog appe a rs .
Figures 3-14 and 3-15 are display samples for setting a threshold by selecting the cell of I/O Density of the logical
disk number 0003h. Figures 3-16 and 3-17 are display samples for setting a threshold by selecting the line of
the logical disk number 0003h.

(Note 1) To select a line, left-click at the left end of the line.
(Note 2) To select a cell, left-click the cell.

Figure 3-14 Set Threshold Menu (Select a cell)

Chapter 3 Operations of Performance Monitoring Function

I-47

Figure 3-15 Set Threshold Dialog (When displayed by selecting a cell)

Figure 3-16 Set Threshold Menu (Select a line)

Chapter 3 Operations of Performance Monitoring Function

I-48

Figure 3-17 Set Threshold Dialog (When displayed by selecting a line)

When you specify a threshold value in the [Set Threshold] area and click the [OK] button, the val ue is set as a
threshold and the dialog box closes. If the value of the item for which the threshold has been changed is
exceeding the thresho ld , the threshold exceeding state is cleared and the monitoring of the threshold resumes with
the new threshold. On the other hand, when you cli ck the [Cancel] button, the values specified in the [Set
Threshold] area are ignored, and the dialog box closes without changing the thresholds which had been registered
when the dialog box opened.
Furthermore, when you specify multiple cells in the list and select [Set Threshold], the Set Threshold dialog box
appears. If the component type on the original screen is disk array, the thresholds of the selected monitored
items for the selected disk array can be changed simultaneously. If the component type on the original screen is
port, logical disk or physical disk, the thresholds of the selected monitored items for the selected monitoring
targets (all the logical di sks, etc.) in the disk array specified in the combo box of the original screen can be
changed simultaneously.
Thresholds are centrally control led by the iSM server. If different thresholds are set for the same monitoring
target from multiple clients, the threshold most recently specified becomes effective. Therefore, pay careful
attention to the settings.

Chapter 3 Operations of Performance Monitoring Function

I-49

(Note 1)
A performance monitor server using older version software does not support some of the threshold value setting
functions. In such a case, the applicable fields for setting threshold values are displayed in gray, accepting no
settings. For specifying the fields displayed in gray, a performance monitor server using the latest version software
is required.

(3) Thresholds monitoring condition setting

Selecting [Threshold Monitoring] → [Customize Threshold Monitoring Conditions] menu displays the Customize
Threshold Monitoring Conditions dialog (Figure 3-18) appears. (Note 1)

Figure 3-18 Customize Threshold Monitoring Conditions Dialog

The Customize Threshold Monitoring Conditions dialog specifies the following information:
(1) Monitoring interval

Specifies a time interval for ju dging threshold. For specifying the same value as display refresh time of
real-time display screen, select [Same value as the display refresh rate]. For specifying the same value as
definition in the environment setting file, click [Default].

(2) Minimum I/O count

Specifies a lower limit of I/O count within the threshold monitoring interval. If the number of I/Os is
under the setting value, a value is not judged. For specifying the same value as definition in the

environment setting file, click [Default].
After specifying the above settings, clicking [OK] button defines the values as the conditions for threshold
monitoring and the Customize Threshold Monitoring Conditions dialog closes. By clicking [Cancel] button,
specified values are ignored. Retaining the values shown at opening Customize Thresh old Monitoring
Conditions dialog, the dialog closes.

Chapter 3 Operations of Performance Monitoring Function

I-50

(Note 1)
A performance monitor server using older version software may not support some of the threshold monitoring
conditions specifying functions. In such a case, the Customize Threshold Monitoring Conditions dialog is not
displayed. For displaying the dialog, software of the latest version is required.

(4) Customize Resetting Threshold Excess State

On the Numeric Table screen, selectin g [Threshold Monitoring] → [Customize Resetting Threshold Excess State]
menu displays the Customize Resetting Threshold Excess State dialog (Figure 3-19) appears. (Note 1)

Figure 3-19 Customize Resetting Threshold Excess State Dialog

The Customize Resetting Threshold Excess State dialog specifies the following information:
 It cancels in the period which the value below a threshold continues.

When exceeding the number of times of the specified threshol d monitoring interval, threshold excess state is
canceled individual l y for each monitoring items. In case of no set ting for releasing threshold excess, uncheck
[Reset Threshold Excess state according to the period below a threshold] check box.

 It cancels at the appointed ti me.

At the appointed time, threshold excess state is canceled for the entire monitoring disk array. In case of no

setting for releasing threshold excess, uncheck [Reset Threshold Excess state at the appointed time] check box.
After specifying the above settings, clicking [OK] button defines the values as the condition to auto release threshold
excess state and the Customize Resetting Threshold Excess State dialog closes. By clicking [Cancel] button, specified
values are ignored. Retaining the values shown at opening Customize Resetting Threshold Excess State dialog, the
dialog closes.

Chapter 3 Operations of Performance Monitoring Function

I-51

(Note 1)
A performance monitor server using older version software may not support some of the threshold excess release
specifying functions. In such a case, the Customize Resetting Threshold Excess State dialog is not displayed. For
specifying release of threshold excess, software of the latest versio n is required.

(5) Thresholds deletion

For deleting a threshold that has been specified, select a threshold value to be deleted on the Set Threshold dialog
and press the Delete key. Then, click the [OK] button. If the value of the monitored item from which the
threshold has been delet ed is exceeding the threshold, the threshold exceeding state i s cleared. By clicking
[Cancel] button, sp ecified values are ignored. Retaining the values shown at opening Set Threshold dialog, the
dialog closes. As is the case with specifying thresholds, deleting can be performed for two or more monitoring
targets and monitoring items.

Figure 3-20 Set Threshold Dialog (Deleting Thresholds)

Chapter 3 Operations of Performance Monitoring Function

I-52

(6) All thresholds deletion

The threshold values for all monitoring targets included in specified disk array subsystem can be deleted by batch
processing. On the Numeric Table screen, selecting [Threshold Monitoring] → [Delete all Thresholds] and
clicking [OK] button on the Delete all Thresholds dialog executes delete all Thresholds. If a monitoring target is
under the state of threshold excess, the excess state is released. By clicking [Cancel] button, the dialog closes
without executing delete all Thresholds.

(7) Show all items specified threshold

On the Numeric Table screen, selectin g [Threshold Monitoring] → [Show All Items Specified Threshold] menu
displays the Show All Items Specified Threshold dialog appears. The Show All Items Specified Threshold
dialog displays a list of devices with threshold values specified. (Figure 3-21)

Figure 3-21 Show All Items Specified Threshold Dialog

The Show All Items Specified Threshold dialog screen displays elements for threshold monitoring by component
type, such as disk array, port, logical disk, and physical disk. The following describes the display items of each
calculation unit.
 Disk array

Displays the name of the disk arra y for which a threshold is specified for each monitored item, such as I/O
Density, Transfer Rate, Average Transfer Length, Average Response Time, Read Hit Ratio, and Write Hit
Ratio. The disk array that has a value which has exceeded the threshold is displayed alo ng with the “**”
marks appended to the name.

Chapter 3 Operations of Performance Monitoring Function

I-53

 Port

Displays the name of ports, by disk array, for which a threshold is specified for each monitored item, such as
I/O Density, Transfer Rate, Average Transfer Length, and Average Response Time. The port that has a value
which has exceeded the threshold is displayed along with the “**” marks appended to the name.

 Logical disk

Displays the number of logical disks, by disk array, for which a threshold is specified for each monitored item,
such as I/O Density, Transfer Rate, Average Transfer Length, Average Response Time, Read Hit Ratio and
Write Hit Ratio. The logical disk that has a value which has exceeded the threshold is displayed along with
the “**” marks appended to the number.

 Physical disk

Displays the number of physical disks, by disk array, for which a threshold is speci fied for each monit ored item,
such as Busy ratio, I/O Density, Transfer Rate, Average Transfer Length, and Average Response Time. The
physical disk that has a value which has exceeded the threshold is displayed along with the “**” marks

appended to the number.
On the Threshold specified items dialog, selecting a device with threshold indicated and clicking [Delete] button
deletes the specified threshold value.

(8) Thresholds exceeding state clearing

When you click [Threshold Monitoring] and then click [Reset Threshold Excess] on the Numeric Table screen,
the threshold exceeding states which have occurred to the disk array specified in the combo box are all cleared.
The marks indicating th e th reshold exceeding state are removed and the threshold monitoring operation resumes
with regard to the items for which a threshold has been specified. Before this operation is carried out, the
Confirm Clear of Threshold Exceeding State dialog appears.

Clicking the [OK] button will clear the threshold exceeding state and then close the dialog box. Clicking the
[Cancel] button will close the dialog box without clearing the threshold exceeding state.

Chapter 3 Operations of Performance Monitoring Function

I-54

3

3

3

.

.

.

3

3

3

S

S

S

u

u

u

p

p

p

p

p

p

o

o

o

r

r

r

t

t

t

f

f

f

o

o

o

r

r

r

A

A

A

n

n

n

a

a

a

l

l

l

y

y

y

s

s

s

i

i

i

s

s

s

o

o

o

f

f

f

S

S

S

t

t

t

a

a

a

t

t

t

i

i

i

s

s

s

t

t

t

i

i

i

c

c

c

I

I

I

n

n

n

f

f

f

o

o

o

r

r

r

m

m

m

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

For analyzing statistic information, specify settings to accumulate statistic information history files on the iSM
Management server first. By summarizing, extracting, and editing the accumulated statistic information history files
on the iSM Management server, the statistic information history is managed. Otherwise, by downloading the
accumulated statistic information files and summarizing, extracting, and editing the data on the hard disk of an iSM
client, the statistic information history is managed.

3

3

3

.

.

.

3

3

3

.

.

.

1

1

1

A

A

A

c

c

c

c

c

c

u

u

u

m

m

m

u

u

u

l

l

l

a

a

a

t

t

t

i

i

i

n

n

n

g

g

g

S

S

S

t

t

t

a

a

a

t

t

t

i

i

i

s

s

s

t

t

t

i

i

i

c

c

c

I

I

I

n

n

n

f

f

f

o

o

o

r

r

r

m

m

m

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

To accumulate statistic information in a file by using this fu nction, the following requirements for the accumulation of
statistic information must be met.

 It is a di sk array which is registered as a target of control by the iSM server.
 It is a disk array which is a target of monitoring by the iSM server.

The following methods are available for controlling the operation of accumulating statistic information of the disk
arrays which satisfy the above requirements.

 Method for using the iSMprflog command
 Method for controlling from the real-time display screen
 Method for performing settings in the environment definition file

Each method will be described below.

(1) Operations by using the iSMprflog command

(i) Storing of statistic information

Two methods are available to start the accumulation of statistic information: a method for specifying a specific
disk array and a method for specifying all the disk arrays monitored by the iSM server simultaneously.
To start the accumulation of stati st ic information of a specific disk array, assi gn a disk array name to the end of -d
option and then execute the iSMprflog start command. For example, when you start the accumulation of
statistic information of a disk array (NECStorage4100), perform the operation below.

iSMprflog start -d NECStorage4100

If the specified disk array does not satisfy the requirements for accumulating statisti c i nformation or if statistic
information is being accu mul at ed, activating this command results in fault.
On the other hand, when you start the accumulation of statistic information of all the disk arrays which satisfy the
above requirements and for which stati st ic information has not been accumulated, p erform the operation below.

iSMprflog start -a

Chapter 3 Operations of Performance Monitoring Function

I-55

(ii) Stop storing of statistic information

Two methods are available to terminate the accumulation of statistic in formatio n: a method for specifying a
specific disk array and a method for specifying all the disk arrays monitored by the iSM server simultaneously.
To terminate the accumulation of statistic information of a specific disk array, assign a disk array name to the end
of -d option and then execut e t he iSMprflog terminate command. For example, when you terminate the
accumulation of statistic in format ion of a disk array (NECStorage4100), perform the operation below.

iSMprflog stop -d NECStorage4100

If a specified disk array has terminated accumulating information already, thi s command results in an error.
On the other hand, when you terminate the accumulation of current statistic information of all the disk arrays,
perform the operation below.

iSMprflog stop -a

(2) Operations on the real-time display screen

The operation procedures will be described below. To utilize this function, it is required that the user’s level be
L2 or L3.

(i) Select [Operation] → [Start/Stop Accumulation of Statistic Information] from the menu to display the Start/Stop

Accumulation Statistic Information dialog scree n.

(ii) From [Disk Array name] on the dialog screen, select and click t he disk array for which the accumulation of

statistic information is started or stopped, and then click the [Start] button to start accumulation and click the
[Stop] button to terminate accumulation.

Figure 3-22 Start/Stop Accumulation of Statistic Information Dialog

You can confirm the settings performed on this dialog screen by looking at the statistic information storing state
filed in the Numeric Table (Refer to Figure 3-1 “Numeric Table Screen (When the Port is Selected)”).

Chapter 3 Operations of Performance Monitoring Function

I-56

(3) Setting in the environment definition file

The operation of accumulating statistic information can be controlled by performing setting in the environment
definition file. For detailed setting procedures, refer to 1.3 “Environment Setting” of the “NEC Storage
Manager User’s Manual”.
By performing setting for automatic start of the accumulation of statistic information in the environment
definition file, it is possible to automatically start the accumulation of statistic information at the start of the iSM
server with regard to the disk array for which st atistic information had been accumulated when the iSM server
was previously in operation.

3

3

3

.

.

.

3

3

3

.

.

.

2

2

2

D

D

D

o

o

o

w

w

w

n

n

n

l

l

l

o

o

o

a

a

a

d

d

d

S

S

S

t

t

t

a

a

a

t

t

t

i

i

i

s

s

s

t

t

t

i

i

i

c

c

c

I

I

I

n

n

n

f

f

f

o

o

o

r

r

r

m

m

m

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

This section describes the procedures for downloading statistic information history files accumulated on the iSM server
onto an iSM client. The following two methods are available for downloading statistic information history files:
 Downloading on performance monitoring function screen

If the iSM server is operating, downloading is executed on the performance monitoring function screen.

 Downloading with FTP tool

If the iSM server is not operating downloading with an FTP tool is available.

For file names of accumulated statistic information, refer to 1.5.3.1 “Accumulatin g S tatistic Information”.

The statistic information history files remains after downloading onto the iSM Management server. In
consideration of disk spaces on iSM Management server, the statisti c information history files must be summarized
as necessary. For summarizing operations, refer to 3.3.3 “Summarizing Statistic Information”.

(1) Downloading Statistic Information on the performance monitoring function screen

The following describes the operating procedures for downloading statistic information on the performance
monitoring function screen.

(i) Select [Operation] → [Download Statistics Information files] menu to display the Download statistics

information files dialog (Figure 3-23). Or, this dialog is displayed by clicking [Download Statistic Information
files] button on tool bar.

Chapter 3 Operations of Performance Monitoring Function

I-57

Figure 3-23 Download Statistic Information File Dialog

(ii) Select statistic information files to download, from the [Statistic Information files].
(iii) Sp ecify a downloadin g target directo ry for [ Do wnload place] field. Specifying by clicking [Browse] is allowed

also. By default, data is downloaded in C:\Program Files\NEC\iSMclient\DATA.

(iv) Click [Download] button.

Clicking the [Download] button sta r ts downloa ding , dis playing a dialog that indicates pr ogre ss. “finished
downloading” displayed on the dia l og indic a te s suc ces sful completion of downloading. The downloaded statistic
information file allows summarizing, ex tracting, and e diting by the performanc e analysis s upport tool.

(2) Downloading with FTP tool

If the iSM server is not operating, downloading is available using an FTP tool. For downloading, log in the
management server, specify applicable files and downloading target directory, and then execute the FTP tool.

Chapter 3 Operations of Performance Monitoring Function

I-58

3

3

3

.

.

.

3

3

3

.

.

.

3

3

3

S

S

S

u

u

u

m

m

m

m

m

m

a

a

a

r

r

r

i

i

i

z

z

z

i

i

i

n

n

n

g

g

g

S

S

S

t

t

t

a

a

a

t

t

t

i

i

i

s

s

s

t

t

t

i

i

i

c

c

c

I

I

I

n

n

n

f

f

f

o

o

o

r

r

r

m

m

m

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

3

3

3

.

.

.

3

3

3

.

.

.

3

3

3

.

.

.

1

1

1

D

D

D

e

e

e

s

s

s

c

c

c

r

r

r

i

i

i

p

p

p

t

t

t

i

i

i

o

o

o

n

n

n

o

o

o

f

f

f

O

O

O

p

p

p

e

e

e

r

r

r

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

s

s

s

(

(

(

U

U

U

N

N

N

I

I

I

X

X

X

)

)

)

Operations with the Archiver (iSMprfarc) command for summarizing statistic information will be described below.

(1) Files to be summarized and determination of the summarizing method

Before executing Archiver, specify the following items:
 Files to be summarized

Specify statistic information files you want to summarize. You can directly specify files as summarizing

objects, or you can specify files in a specified directory in a specific period as su mmarizing objects.

The names of the statistic information files to be summarized must be i n accordance with the naming

convention for statistic information files. For naming conditions and rules of statistic information files, refer

to 1.5.3.1 “Accumulating Statistic Information”.

[Naming Convention for Statistic Information Files]

<YYYY><MM><DD><NN-N>.psl (History file)

<YYYY><MM><DD><NN-N>.psa (Primary summarized file)

<YYYY><MM><NN-N>.psa (Secondary summarized file)

<YYYY> indicates year (4 digits), <MM> indicates month (2 digits), <DD> indicates day (2 digits), and

<NN-N> indicates the disk array name.
 Summarizing method

Select a method (primary summarizing, secondary summarizing, or direct secondary summarizing) of statistic

information files.

If a summarizing period is not an integral multiple of the logging interval specified by an accumulation process,
summarizing is not performed evenly. For such cases as I/O count applicable to that condi t io n, refer to statistic
information items with no fluctuation by changing period of summarizing, such as I/O density and transfer rate.

(2) Executing Archiver

Specify files, directory and option according to the specified co ntents and execute Archiver. Archiver operates
regardless of the iSM server process. Archiver can be exe cuted in any directory. The names of the
summarized files output by Archiver are au tomatically created in acco rdance with the naming convention for
statistic information files.
Examples of execution of Archiver will be provided below.
Example: Example of summarizing when a file is specified
Assume that the statistic information history file (20020401NECStorage4100.psl) on April 1, 2002

regarding “NECStorage4100” is located in the “/opt/iSMsvr/etc/mon” directory. To summarize this
file and output a primary su mmar ized file to the current directo r y, e nter the following command an d
execute it.

Chapter 3 Operations of Performance Monitoring Function

I-59

iSMprfarc /opt/iSMsvr/etc/mon/20020401NECStorage4100.psl

As a result, the primary summarized file (20020401NECStorage4100.psa) on April 1, 2002 is created
in the current directory.

Example: Exa mple 1 of summarizing when a period is sp eci fied
Assume that the statistic information history files (20020401NECStorage4100.psl -

20020430NECStorage4100.psl) from April 1, 2002 to April 30, 2002 regarding “NECStorage4100”
are located in the “/opt/iSMsvr/etc/mon” directory. Among all files in this directory, if you want to
summarize the statistic information history files from April 1, 2002 to April 15, 2002 and output
primary summarized files to the same directory, enter the following command in a directory and
execute it.

iSMprfarc -p /opt/iSMsvr/etc/mon -hour 20020401.20020415

As a result, the primary summarized files (20020401NECStorage4100.psa ­20020415NECStorage4100.psa) from April 1, 2002 to April 15, 2002 are created in the
“/opt/iSMsvr/etc/mon” direct ory.

Example: Exa mple 2 of summarizing when a period is sp eci fied

Assume that the statistic information history files (20010401NECStorage4100.psl ­20020331NECStorage4100.psl) from April 1, 2001 to March 31, 2002 regarding “NECStorage4100”
are located in the “/opt/iSMsvr/etc/mon” directory. Among all files in this directory, if you want to
summarize all the statistic information history files collected one month before the current time and
output secondary summarized files to the same directory, enter the following command in a directory
and execute it.
If the current time is April 15, 2002, the statistic information files in the period from April 1, 2001 to
March 15, 2002 are the targets of summari zing.

iSMprfarc -p /opt/iSMsvr/etc/mon -day 1m

As a result, the secondary summarized files (200104NECStorage4100.psa ­200203NECStorage4100.psa) from April, 2001 to March, 2002 are created in the
“/opt/iSMsvr/etc/mon” direct ory.

3

3

3

.

.

.

3

3

3

.

.

.

3

3

3

.

.

.

2

2

2

D

D

D

e

e

e

s

s

s

c

c

c

r

r

r

i

i

i

p

p

p

t

t

t

i

i

i

o

o

o

n

n

n

o

o

o

f

f

f

O

O

O

p

p

p

e

e

e

r

r

r

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

s

s

s

(

(

(

W

W

W

i

i

i

n

n

n

d

d

d

o

o

o

w

w

w

s

s

s

)

)

)

Explanation will be made about the operations to summarize statistic information.
Before summarizing statistic information, specify the following items:
 Files to be summarized

Specify statistic information files you want to summarize. You can directly specify files as summarizing objects, or
you can specify files in a specified directory in a specific period as summarizin g objects.
The names of the statistic information files to be summarized must be in accordance with the naming convention for

Chapter 3 Operations of Performance Monitoring Function

I-60

statistic information files (For details, refer to Part I “Performance Monitoring Function”, 1.5.3.1 “Accumulating
Statistic Information” of this manual).
[Naming Convention for Statistic Information Files]
<YYYY><MM><DD><NN-N>.psl (History file)
<YYYY><MM><DD><NN-N>.psa (Primary summarized file)
<YYYY><MM><NN-N>.psa (Secondary summarized file)
<YYYY> indicates year (4 digits), <MM> indicates month (2 digits), <DD> indicates day (2 digits), and <NN-N>
indicates the disk array name.

 Summarizing method

Select a summarizing method (primary summarizing, secondary summarizing, or direct secondary summarizing) of
static information files.

If a summarizing period is not an integral multiple of the logging interval specified by an accumulation process,
summarizing is not performed evenly. For such cases as I/O count applicable to that condi t io n, refer to statistic
information items with no fluctuation by changing period of summarizing, such as I/O density and transfer rate.

Next, summarize statistic information. Archiver provides the following two operation methods:

 Operations on the “Performance Analysis Suppor t in g Tool” screen

Select [Performance Analysis Supporting Tool] on [Start] menu to display the Performance Analysis Supporting
Tool screen. Specify the operations with [Archiver] tab on the Performance Analysis Supporting Tool screen to
execute summarizing.

 Operations with the Archiver command

Specify an option in the iSMprfarc command and execute the command to perform a summarizing operation.
The two methods of operation will be described below.

(1) Operations on the "Performance Analysis Supporting Tool" screen

Select the [Archiver] tab on the Performance Analysis Supporting Tool screen, and enter parameters for
performing a summarizing operation. Screen images and operations will be described below.

Chapter 3 Operations of Performance Monitoring Function

I-61

Figure 3-24 Performance Analysis Supporting Tool Screen (Archiver)

(i) File Specification

Select this function when you want to perform a summarizing operation by specifying statistic information files.
This function cannot be sel ected together with Period Speci ficat ion.

(ii) Statistic Info File

Specify statistic information history /summarized files. Multiple files can be specified; however, statistic
information files with different summarizing levels, such as statistic information history files and primary
summarized files cannot be mixed.

(iii) Output Directory

Specify the directory to which summarized files are output. If specification of the output directory is omitted, the
summarized files are output to the same directory as the statistic information file specified first. If the file with
the same name exists in the output directory, the file is overwritten.

(iv) Direct Secondary Summarizing

Select this function when you want to enter statistic information history files and directly create secondary
summarized files. If a primary summarized file is specified as an input file, a normal secondary summarizing
operation is conducted.

(v) Period Specification

Select this function when you want to perform a summarizing operation by specifying the directory in which
statistic information files are located and the summarizing period. This function cannot be selected together
with File Specification.

(vi) Summarize Method

Select either Primary Summarizing or Secondary Summarizing.

(vii) Input Directory

Specify the directory in which input statistic information files exist. All of the summarized files are output to
the specified directory.

Chapter 3 Operations of Performance Monitoring Function

I-62

(viii) Date Specification

Specify the target period of summarizing in a Year/Month/Day format (from starting date to end date). If the
starting date is omitted, all the days before the end date are set to be the target period of summarizing. The end
date cannot be omitted.

(ix) Relative Specification

Select this function to specify the target period of summarizing in a relative period by regarding the current time
as the reference point.

(2) Operations with the Archiver command (iSMprfarc command)

Specify files, directory or option and execute Archiver. Archiver operates regardless of the iS M server process.
Archiver can be executed in any directory. The names of the summarized files output by Archiver are
automatically created in accordance with the naming conventio n for statistic information files.
Examples of execution of the Archiver will be provided below.
Example: Example of summarizing when a file is specified

Assume that the statistic information history file (20020401NECStorage4100.psl) on April 1, 2002
regarding “NECStorage4100” is located in the “C:\Program files\NEC\iSMsvr\etc\mon” directory.
To summarize this file and output a primary summarized file to the current directory, enter the
following command and execute it.

iSMprfarc “C:\Program files\NEC\iSMsvr\etc\mon\20020401NECStorage4100.psl”

As a result, the primary summarized file (20020401NECStorage4100.psa) on April 1, 2002 is created
in the current directory.
To specify a file name or directory name with a space, enclose it in double quotation marks.

Example: Exa mple 1 of summarizing when a period is sp eci fied

Assume that the statistic information history files (20020401NECStorage4100.psl ­20020430NECStorage4100.psl) from April 1, 2002 to April 30, 2002 regarding “NECStorage4100”
are located in the “C:\Program files\NEC\iSMsvr\etc\mon” directory. Among all files in this
directory, if you want to summarize the statistic information history files from April 1, 2002 to April
15, 2002 and output primary summarized files to the same directory, enter the following command in
a directory and execute it.

iSMprfarc -p “C:\Program files\NEC\iSMsvr\etc\mon” -hour 20020401.20020415

As a result, the primary summarized files (20020401NECStorage4100.psa ­20020415NECStorage4100.psa) from April 1, 2002 to April 15, 2002 are created in the “C:\Program
files\NEC\iSMsvr\etc\mon” directory.

Example: Exa mple 2 of summarizing when a period is sp eci fied

Assume that the statistic information history files (20010401NECStorage4100.psl ­20020331NECStorage4100.psl) from April 1, 2001 to March 31, 2002 regarding “NECStorage4100”
are located in the “C:\Program files\NEC\iSMsvr\etc\mon” directory. Among all files in this

Chapter 3 Operations of Performance Monitoring Function

I-63

directory, if you want to summarize all the statistic information history files collected one month
before the current time and output secondary summarized files to the same directory, enter the
following command in a directory and execute it.
If the current time is April 15, 2002, the statistic information files in the period from April 1, 2001 to
March 15, 2002 are the targets of summari zing.

iSMprfarc -p “C:\Program files\NEC\iSMsvr\etc\mon” -day 1m

As a result, the secondary summarized files (200104NECStorage4100.psa ­200203NECStorage4100.psa) from April, 2001 to March, 2002 are created in the “C:\Program
files\NEC\iSMsvr\etc\mon” directory.

3

3

3

.

.

.

3

3

3

.

.

.

4

4

4

E

E

E

x

x

x

t

t

t

r

r

r

a

a

a

c

c

c

t

t

t

i

i

i

n

n

n

g

g

g

S

S

S

t

t

t

a

a

a

t

t

t

i

i

i

s

s

s

t

t

t

i

i

i

c

c

c

I

I

I

n

n

n

f

f

f

o

o

o

r

r

r

m

m

m

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

3

3

3

.

.

.

3

3

3

.

.

.

4

4

4

.

.

.

1

1

1

D

D

D

e

e

e

s

s

s

c

c

c

r

r

r

i

i

i

p

p

p

t

t

t

i

i

i

o

o

o

n

n

n

o

o

o

f

f

f

O

O

O

p

p

p

e

e

e

r

r

r

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

s

s

s

(

(

(

U

U

U

N

N

N

I

I

I

X

X

X

)

)

)

Operations with the CSV conversion command (iSMprfext) to extract statistic information will be described below.

(1) Extracting statistic information

When you specify statistic information history files and summarized files in the CSV conversion command, the
CSV conversion command extracts stati stic information and creates CSV files. The CSV conversion command
creates CSV files in accordance with the following rules:
If a statistic information history/summarized file is specified, a CSV format file corresponding to the file is
created in the same path. If a creating path of CSV format file is specified (-p option), the CSV format files are
created in the specified path . Two or more statistic information history/summarized files and -p option are
specified, all CSV format files correspo nding to the files are created in the path specified by -p option. If files
under the same names exist in the path where the CSV format files are created, the existing files are overwritten.
To specify files or directory that include blanks in their names, the names of file or directory must be enclosed by
double quotation mark s .
For syntax of iSMprfext command, refer to Appendix A “Commands of the Performance
Monitoring/Optimization Function”.
Examples of extraction of statistic information are provided below.

Example 1: Extracting statistic information from the statistic information history file

“20020401NECStorage4100.psl”

iSMprfext -file 20020401NECStorage4100.psl

Example 2: Extracting statistic information from the statistic information history files

“20020401NECStor a g e 410 0.ps l” a nd “2 00 20402NECStorage 4100 . ps a ”

Chapter 3 Operations of Performance Monitoring Function

I-64

iSMprfext -file 20020401NECStorage4100.psl 20020402NECStorage4100.psa

Example 3: Extracting statistic information from the statistic information history file

“20020401NECStorage4100.psl” and creating a CSV file in “/temp”

iSMprfext -file 20020401NECStorage4100.psl -p /temp

Example 4: Extracting statistic information from the statistic information history files

“20020401NECStorage4100.psl” and “20020402NECStorage4100.psl” and creating CSV files in
“/temp”

iSMprfext -file 20020401NECStorage4100.psl 20020402NECStorage4100.psl -p
/temp

(2) Extracting specific statistic information

You can extract specific statistic information by specifying extracting conditions, such as the period of extraction,
component of the disk array, type of statistic information, etc. in the CSV conversion command. Multiple
conditions can be specified simultaneously. Examples of extraction are provided below.

(a) Extracting statistic information in the specified period

Example 1: Extracting statistic information from 10:00 to 15:30 on April 1, 2002

iSMprfext -file file1 -from 20020401/1000 -to 20020401/1530

Example 2: Extracting statistic information after 17:30 on April 1, 2002

iSMprfext -file file1 -from 20020401/1730

(b) Extracting statistic information of the specific component

Example 1: Extracting statistic information of the host port with the director number 10h and port number 0ah

iSMprfext -file file1 -hp 10-a

Example 2: Extracting statistic information of the logical disk of 001eh and the physical disk with the group

number 00h and disk number 01

iSMprfext -file file1 -ld 1e -pd 0-1

Chapter 3 Operations of Performance Monitoring Function

I-65

(c) Extracting statistic information of the specific type

Example 1: Extracting statistic information regarding the number of inputs/outputs

iSMprfext -file file1 -iocnt

Example 2: Extracting statistic information regarding the number of inputs/outputs and Transfer Rate

iSMprfext -file file1 -iocnt -rate

(d) Extracting statistic information of the specific component in the specified period

Example 1: Extracting statistic information of the logical disk of 0020h from 10:00 to 15:30 on April 1, 2002

iSMprfext -file file1 -from 20020401/1000 -to 20020401/1530 -ld 20

(e) Extracting statistic information of the specific type in the specified period

Example 1: Extracting statistic information regarding the response time after 17:30 on April 1, 2002

iSMprfext -file file1 -from 20020401/1730 -resp

(f) Extracting statistic information of the specific component regarding the specific type in the specified period

Example 1: Extracting statistic information of the logical disk of 0020h regarding the number of inputs/outputs

from 10:00 to 15:30 on April 1, 2002

iSMprfext -file file1 -from 20020401/1000 -to 20020401/1530 -ld 20 -iocnt

Example 2: Extracting statistic information of the logical disk of 0020h and the physical disk with the group

number 00h and disk number 01h regarding the Transfer Rate before 16:00 on April 1, 2002

iSMprfext -file file1 -to 20020401/1600 -ld 20 -pd 0-1 -rate

(3) Notes

(i) If the CSV file with the same name exists in the path in which CSV files are created, the file is overwritten.
(ii) The maximum number of record s of a CSV file is 65,536. If the number of records of a CSV file exceeds

65,536, the CSV Conversion Tool outputs an error message and terminates processing.

(iii) CSV file concatenation

The CSV Conversion Tool creates one CSV file for a statistic information history/summarized file. Therefore, it
is not possible to put statistic information of multiple statistic information history/summarized files together in
one CSV file by using the CSV Conversion Tool.
To put statistic information of multiple statistic information history/summarized files together in one CSV file,
follow the procedures below.

Chapter 3 Operations of Performance Monitoring Function

I-66

(a) Specify multiple files to the CSV Conversion Tool and create corresponding CSV files.
(b) Link the CSV files created in procedure (a) by using the cat c ommand to put the files together in one CSV

file.
The following example illustrates how to put statistic information of multiple statistic information history
files together in one CSV file.
Example: Extracting statistic information from the statistic information history files

“20020401NECStorage4100.psl” and “20020402NECStorage4100.psl” and put them together
in a CSV file “NECStorage4100.csv”.

iSMprfext -file 20020401NECStorage4100.psl 20020402NECStorage4100.psl cat
20020401NECStorage4100_psl.csv 20020402NECStorage4100_psl.csv >
NECStorage4100.csv

3

3

3

.

.

.

3

3

3

.

.

.

4

4

4

.

.

.

2

2

2

D

D

D

e

e

e

s

s

s

c

c

c

r

r

r

i

i

i

p

p

p

t

t

t

i

i

i

o

o

o

n

n

n

o

o

o

f

f

f

O

O

O

p

p

p

e

e

e

r

r

r

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

s

s

s

(

(

(

W

W

W

i

i

i

n

n

n

d

d

d

o

o

o

w

w

w

s

s

s

)

)

)

This section will explain how to extract statistic information. The CSV Conversion Tool provides the following two
operation methods:
 Operations on the Performance Analysis Supporti ng Tool sc re e n

Select [Performance Analysis Supporting Tool] on [Start] menu to display Performance Analysis Supporting Tool
screen. Specify the operations with [CSV Conversion Tool] tab on the Performance Analysis Supporting Tool
screen to execute summarizing.

 Operations with the CSV conversion command

You can perform an extraction operation by specifying an option in the iSMprfext command and executing it.
The two operation methods will be described in detail below.

(1) Operations on the Performance Analysis Supporting Tool screen

Perform an extraction operation by selecting the [CSV Conversion Tool] tab on the Performance Analysis
Supporting Tool screen and entering parameters for the extraction. Screen images and operations will be
described below.

Chapter 3 Operations of Performance Monitoring Function

I-67

Figure 3-25 Performance Analysis Supporting Tool Screen (CSV Conversion Tool)

(i) Statistic Info File

Specify statistic information history/summarized files. Multiple files can be specified, and statistic information
history files and statistic information summarized files can be mixed.

(ii) Output Directory

Specify a directory in which output files (CSV files) are created. If multiple statistic information files are
specified, all CSV files of the statist i c information files are created in the di rectory specified here. If the
specification of the output directory is omitted, a CSV file is created in the same directory as the statistic
information file. If the file with the same name exists in the output directory, the file is overwritten.

(iii) Summarizing Condition

Select this function to extract statistic information by specifying extracting conditions. In this case, at least one
extracting condition must be selected from component, type, and period. If summarizing conditions are not
specified, all statistic information in the specified statistic information file is extracted.

(iv) Component

Select components for the extraction. Multiple components can be selected. Only statistic information that
matches the selected component identification numbers is extracted. If no component is selected, statistic
information of all components is extracted.

(v) Type

Select types of statistic information for the extraction. Multiple types can be selected. Only statistic
information that matches the selected types is extracted. If no type is selected, statistic information of all types
is extracted.

(vi) Period

Only statistic information in the period specified here is extracted. You can specify the extraction starting time

Chapter 3 Operations of Performance Monitoring Function

I-68

and end time, or either one of them. If no period is specified, statistic information in all periods is extracted.

(vii) Output Component Info

Select this function to output component information of the disk array in addition to statistic information.

(viii) Output Header Info
Select this function to output header record showing field name to the head of file.

(2) Operations with the CSV conversion command

(i) Extracting statistic information

When you specify statistic informat ion history/summarized files in the CSV conversion command, the CSV
conversion command extracts statistic information and creates CSV files. The CSV conversion command
creates CSV files in accordance with the following rules:
If a statistic information history/summarized file is specified, a CSV format file corresponding to the file is
created in the same path. If a creating path of CSV format file is specified (-p option), the CSV format files are
created in the specified path . Two or more statistic information history/summarized files and -p option are
specified, all CSV format files correspo nding to the files are created in the path specified by -p option. If files
under the same names exist in the path where the CSV format files are created, the existing files are overwritten.
To specify files or directory that include blanks in their names, the names of file or directory must be enclosed by
double quotation mark s .
For syntax of iSMprfext command, refer to Appendix A “Commands of the Performance
Monitoring/Optimization Function”.
Examples of extraction of statistic information are provided below.
Example 1: Extracting statistic information from the statistic information history file

“20020401NECStorage4100.psl”

iSMprfext -file 20020401NECStorage4100.psl

Example 2: Extracting statistic information from the statistic information history files

“20020401NECStor a g e 410 0.ps l” a nd “2 00 20402NECStorage 4100 . ps a ”

iSMprfext -file 20020401NECStorage4100.psl 20020402NECStorage4100.psa

Example 3: Extracting statistic information from the statistic information history file

“20020401NECStorage4100.psl” and creating a CSV file in “C:\temp”

iSMprfext -file 20020401NECStorage4100.psl -p C:\temp

Example 4: Extracting statistic information from the statistic information history files

“20020401NECStorage4100.psl” and “20020402NECStorage4100.psl” and creating CSV files in
“C:\temp”

Chapter 3 Operations of Performance Monitoring Function

I-69

iSMprfext -file 20020401NECStorage4100.psl 20020402NECStorage4100.psl -p
C:\temp

(ii) Extracting specific statistic information

You can extract specific statistic information by specifying extracting conditions, such as the period of extraction,
component of the disk array, type of statistic information, etc. in the CSV conversion command. Multiple
conditions can be specified simultaneously. Examples of extraction are provided below.

(a) Extracting statistic information in the specified period
Example 1: Extracting statistic information from 10:00 to 15:30 on April 1, 2002

iSMprfext -file file1 -from 20020401/1000 -to 20020401/1530

Example 2: Extracting statistic information after 17:30 on April 1, 2002

iSMprfext -file file1 -from 20020401/1730

(b) Extracting statistic information of the specific component
Example 1: Extracting statistic information of the host port with the director number 10h and port number 0ah

iSMprfext -file file1 -hp 10-a

Example 2: Extracting statistic information of the logical disk of 001eh and the physical disk with the group

number 00h and disk number 01

iSMprfext -file file1 -ld 1e -pd 0-1

(c) Extracting statistic information of the specific type
Example 1: Extracting statistic information regarding the number of inputs/outputs

iSMprfext -file file1 -iocnt

Example 2: Extracting statistic information regarding the number of inputs/outputs and Transfer Rate

iSMprfext -file file1 -iocnt -rate

(d) Extracting statistic information of the specific component in the specified period
Example 1: Extracting statistic information of the logical disk of 0020h from 10:00 to 15:30 on April 1, 2002

Chapter 3 Operations of Performance Monitoring Function

I-70

iSMprfext -file file1 -from 20020401/1000 -to 20020401/1530 -ld 20

(e) Extracting statistic information of the specific type in the specified period
Example 1: Extracting statistic information regarding the response time after 17:30 on April 1, 2002

iSMprfext -file file1 -from 20020401/1730 -resp

(f) Extracting statistic information of the specific component regarding the specific type in the specified period
Example 1: Extracting statistic information of the logical disk of 0020h regarding the number of inputs/outputs

from 10:00 to 15:30 on April 1, 2002

iSMprfext -file file1 -from 20020401/1000 -to 20020401/1530 -ld 20 -iocnt

Example 2: Extracting statistic information of the logical disk of 0020h and the physical disk with the group

number 00h and disk number 01h regarding the Transfer Rate before 16:00 on April 1, 2002

iSMprfext -file file1 -to 20020401/1600 -ld 20 -pd 0-1 -rate

(3) Notes

(i) If the CSV file with the same name exists in the path in which CSV files are created, the file is overwritten.
(ii) The maximum number of record s of a CSV file is 65,536. If the number of records of a CSV file exceeds

65,536, the CSV Conversion Tool outputs an error message and terminates processing.

(iii) Linking CSV files

The CSV Conversion Tool creates one CSV file for a statistic information history/summarized file. Therefore, it
is not possible to put statistic information of multiple statistic information history/summarized files together in
one CSV file by using the CSV Conversion Tool.
To put statistic information of multiple statistic information history/summarized files together in one CSV file,
follow the procedures below.

(a) Specify multiple files to the CSV Conversion Tool and create corresponding CSV files.
(b) Link the CSV files created in procedure (a) by using the cat command to put them to gether in one CSV file.

The following example illustrates how to put statistic information of multiple statistic information history files
together in one CSV file.

Example: Extracting statistic information from the statistic information history files

“20020401NECStorage4100.psl” and “20020402NECStorage4100.psl” and put them together in a
CSV file “NECStorage4100.csv”.

Chapter 3 Operations of Performance Monitoring Function

I-71

iSMprfext -file 20020401NECStorage4100.psl 20020402NECStorage4100.psl
copy 20020401NECStorage4100_psl.csv+20020402NECStorage4100_psl.csv
NECStorage4100.csv

3

3

3

.

.

.

3

3

3

.

.

.

5

5

5

E

E

E

d

d

d

i

i

i

t

t

t

i

i

i

n

n

n

g

g

g

S

S

S

t

t

t

a

a

a

t

t

t

i

i

i

s

s

s

t

t

t

i

i

i

c

c

c

I

I

I

n

n

n

f

f

f

o

o

o

r

r

r

m

m

m

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

3

3

3

.

.

.

3

3

3

.

.

.

5

5

5

.

.

.

1

1

1

D

D

D

e

e

e

s

s

s

c

c

c

r

r

r

i

i

i

p

p

p

t

t

t

i

i

i

o

o

o

n

n

n

o

o

o

f

f

f

O

O

O

p

p

p

e

e

e

r

r

r

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

s

s

s

(

(

(

U

U

U

N

N

N

I

I

I

X

X

X

)

)

)

This section will explain how to operate the editing tool and the graph making tool.

(1) Editing tool

You can perform an editing operation by specifying an option in the iSMprfedit command and executing it.
Multiple statistic information history/summarized files, output directory, and the type of editing reports to be
created can be specified. For syntax and operation rules of the editing tool command, refer to Appendix A
“Commands of the Performance Monitoring/Optimization Function” of this manual.
Examples of execution of the iSMprfedit commands will be provided below.
Example 1: Creating a summary report of the statistic information history file “20020430NECStorage4100.psl”

iSMprfedit 20020430NECStorage4100.psl

Example 2: Creating a summary report of the statistic information history file “20020430NECStorage4100.psl”

in “/tmp”.

iSMprfedit -o /tmp 20020430NECStorage4100.psl

Example 3: Creating a summary report of the statistic information history file “20020430NECStorage4100.psl”

and all detail reports

iSMprfedit -det -all 20020430NECStorage4100.psl

Example 4: Creating only the detailed report on the whole disk array of the statistic information history file

“20020430NECStorage4100.psl”

iSMprfedit -nosum -det 20020430NECStorage4100.psl

(2) Graph Making Tool

The graph making tool can be used in an environment in which Microsoft Excel2000 is installed. An iSM
client must be installed in the personal computer for using the graph making tool. For information on how to
operate the graph making tool, refer to 3.3.5.2 “Description of Operations (Windows)”.

Chapter 3 Operations of Performance Monitoring Function

I-72

3

3

3

.

.

.

3

3

3

.

.

.

5

5

5

.

.

.

2

2

2

D

D

D

e

e

e

s

s

s

c

c

c

r

r

r

i

i

i

p

p

p

t

t

t

i

i

i

o

o

o

n

n

n

o

o

o

f

f

f

O

O

O

p

p

p

e

e

e

r

r

r

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

s

s

s

(

(

(

W

W

W

i

i

i

n

n

n

d

d

d

o

o

o

w

w

w

s

s

s

)

)

)

This section will explain how to operate the editing tool and the graph making tool, and the procedures for editing
statistic information using spreadsheet software.

(1) Editing Tool

The editing tool provides the following two operation methods:
 Operations on the Performance Analysis Supporti ng Tool sc re e n

Select [Performance Analysis Supporting Tool] on [Start] menu to display the Performance Analysis

Supporting Tool screen. Specify the operations with [Edit Tool] tab on the Performance Analysis Supporting

Tool screen to execute summarizing.

Figure 3-26 Performance Analysis Supporting Tool Screen (Edit Tool)

(i) Statistic Info File

Specify statistic information history/summarized files. Multiple files can be specified, and statistic information
history files and statistic information summarized files can be mixed. Specification of the statistic information
file cannot be omitted.

(ii) Output Directory

Specify a directory in which editing reports (text file) are created. If multiple statistic information files are
specified, all editing reports of each statistic information file are created in the directory specified here. If
specification of the output directory is omitted, an editing report is created in the same directory as the statistic
information file.

Chapter 3 Operations of Performance Monitoring Function

I-73

(iii) Select Edit Report

Select this function to output editing reports.

(iv) Summary Report

Specify this function to output summary reports.

(v) Detail Report

Select the detailed report to be output.

(vi) Detail Report About Disk Array

Select this parameter to output a detailed report on the whole disk array.

(vii) Detail Report About HP

Select this parameter to output a detailed report on host director ports.

(viii) Detail Report About DP

Select this parameter to output a detailed report on disk director ports.

(ix) Detail Report About LD

Select this parameter to output a detailed report on logical disks.

(x) Detail Report About PD

Select this parameter to output a detailed report on physical disks.

(xi) Detail Report About RANK

Select this parameter to output a detailed report on RANK.

You can create only a desirable editing report by selecting a specific report and execute the editing tool. You can also
create all editing reports by selecting all reports.

 Operations with the editing tool command

To perform an editing operation, specify an option in the iSMprfedit command and then execute it. Similar to
the case where the editing tool is operated on the Performance Analysis Supporting Tool screen, multiple statistic
information history/summarized files, output directory, type of editing reports to be created can be specified.
For syntax and operation rules of the editing tool command, refer to Appendix A “Commands of the Performance
Monitoring/Optimization Function” of this manual.
Examples of execution of the iSMprfedit commands are provided bel ow.
Example 1: Creating a summary report of the statistic information history file “20020430NECStorage4100.psl”

iSMprfedit 20020430NECStorage4100.psl

Example 2: Creating a summary report of the statistic information history file “20020430NECStorage4100.psl”

in “C:\tmp”.

iSMprfedit -o C:\tmp 20020430NECStorage4100.psl

Example 3: Creating a summary report of the statistic information history file “20020430NECStorage4100.psl”

and all detail reports.

iSMprfedit -det -all 20020430NECStorage4100.psl

Chapter 3 Operations of Performance Monitoring Function

I-74

Example 4: Creating only an detailed report on the whole disk array of the statistic information history file

“20020430NECStorage4100.psl”.

iSMprfedit -nosum -det 20020430NECStorage4100.psl

(2) Graph Making Tool

To create graphs, select Storage Performance Report Viewer from the Start menu and specify necessary items on
the Storage Performance Report Viewer screen. Screen images and operations will be described below.
The graph making tool (Storage Performance Report Viewer) can be used in an environment in which
Microsoft Excel2000 is installed. An iSM client must be installed in the personal computer for using the
graph making tool.

Figure 3-27 Storage Performance Report V iewer Screen

(i) File

You can specify only a detailed report on the whole disk array created by using the editing tool. If other files are
specified, the creation of the graph will fail.

(ii) Display items in the graph

Specify statistic information to be displayed in a graph. Up to two items can be specified. Applicable statistic
information includes:
 I/O Density

This is the number of input/output requests per second (IOPS).
 Transfer Rate

This is the data transfer volume per second. The unit is MB (megabyte)/second.
 Average Transfer Length

This is the Average Transfer Length of a single input/output request. The unit is KB (kilobyte)/second.

Chapter 3 Operations of Performance Monitoring Function

I-75

 Average Response Time

This is the average response time of a single input/output request. The unit is ms (millisecond).
 Read Hit Ratio

This is a ratio of the number of inputs that hit the cache to the total number of input requests.
 Prefetch Hit Ratio

This is a ratio of the number of inputs that hit the cache via the disk array prefetch function to the total number

of inputs that hit the cache.
 Write Hit Ratio

This is a ratio of the number of outputs that hit the cache to the total number of outpu t requests.
 Write I/O Ratio

This is a ratio of output requests to the total number of input/output requests.

(iii) Display Graph

Clicking the [Display Graph] button will display a graph in a separate book.
When you create a graph and then want to create another graph with different settings, return to the Storage
Performance Report Viewer start screen, change the settings, and then click the [Display Graph] button. A
separate book is created to display the graph.
The following illustrates an example in which a graph is created by specifying the I/O density and Transfer Rate:

Figure 3-28 Example of Creating a Graph

Items displayed in a graph will be described below.
disk array name: Displays the name of the disk array.
sampling term: Displays the collection period of the statistic information shown in a graph.
Ordinate: Displays the scale of statistic information selected in the Storage Performance Report Viewer start

screen. If two types of statistic information are selected, scales are displayed in both ordinates.
Abscissa: Displays the time.
Legend: Displays the name of the statistic information selected on the Storage Performance Report

Viewer start screen.

Chapter 3 Operations of Performance Monitoring Function

I-76

In “Figure 3-28 Example of Creating a Graph”, some points are not linked by lines. The graph making tool
(Storage Performance Report Viewer) does not link points with lines when statistic information is no longer
continuous in order to accurately exp r ess t he continuity of the statistic information in the graph. The statistic
information loses its continuity in the following cases:

 Configuration of the disk array was changed during the monitoring of performance.
 A fault occurred in the disk array during the monitoring of the performance and the monitoring of the disk

array performance could not be continued.

 A user terminat ed the accumulation of statistic information due to the specificatio n during the monitoring of

performance.

If log accumulation inte rval is adjusted automaticall y ( for giving a higher priori ty to file input/output from a
business host), the intervals between the points increase in accordance with the adjusted time interval.

(3) Editing with spreadsheet software

The statistic information histo ry files ext racted with h eader o ption s specified can be u sed on sp readsheet software,
such as Microsoft Excel2000. On the software, sorting the output values makes it easier to identify the values.
Figure 3-29 shows an example of editing a statistic information history file extracted with header option specified
(CSV file), using Microsoft Excel2000.

この列をもとに並び替え

Figure 3-29 Editing CSV file

Sorting on the basis of
this column.

P

a

r

t

I

I

P

e

r

f

o

r

m

a

n

c

e

O

p

t

i

m

i

z

a

t

i

o

n

P

a

r

t

I

I

P

e

r

f

o

r

m

a

n

c

e

O

p

t

i

m

i

z

a

t

P

a

r

t

I

I

P

e

r

f

o

r

m

a

n

c

e

O

p

t

i

m

i

z

F

u

n

c

t

i

o

n

F

u

n

c

t

F

u

n

c

i

t

i

o

o

n

n

a

i

t

i

o

o

n

n

Chapter 4 Overview of Performance Optimization Function

II-2

Business serve

r

NEC Storage Series

I/O

concentration

Large number ofdiversified

accesses

Cancellation
of bottleneck

Large number of diversified

accesses

Performance deterioration
due to bottleneck

Optimal perf ormance with
no bottleneck

Dynamic execution of

rearrangement without stopping

business operations

NEC Storage

PerformanceOptimizer

Performance analysis/tuning

Chapter 4 Overview of Performance Optimization

Function

The Performance Optimization function (NEC Storage PerformanceOptimizer) is capable of analyzing the causes of lowered
responses in the NEC Storage series Disk Array Subsystem and improving its performances. An administrator, with use of the
Performance Optimization function, analyzes the performances of disk array under the control of iSM, by centralized operations
on an iSM client and tunes the performances as necessary.

4

4

4

.

.

.

1

1

1

P

P

P

e

e

e

r

r

r

f

f

f

o

o

o

r

r

r

m

m

m

a

a

a

n

n

n

c

c

c

e

e

e

O

O

O

p

p

p

t

t

t

i

i

i

m

m

m

i

i

i

z

z

z

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

F

F

F

u

u

u

n

n

n

c

c

c

t

t

t

i

i

i

o

o

o

n

n

n

As the volume of business dat a increase s day by day, the scale and capacity of disk array become larger. Access
patterns have also been diverted due to the use by multiple business systems.
To maintain quick response of the business system, it is necessary to monitor the load state of disk arrays and detect a
bottleneck and improve it. This work, however, requires advanced technical knowledge and techniques of
performance analysis and tuning operations. Furthermore, when it is necessary to tune the performance, business
operations may be stopped for a while, causing inconvenience to business operations.
The NEC Storage PerformanceOpti mizer sol ves such problems. Introduction of the NEC Storage
PerformanceOptimizer makes it possible to properly and easily conduct painstaking performance analysis and tuning
operations. A tuning operation can be done while business is in operation, thereby maintaining optimal disk
performance around the clock without stopping business operations.

Figure 4-1 Concept of NEC Storage PerformanceOptimizer

Chapter 4 Overview of Performance Optimization Function

II-3

4

4

4

.

.

.

2

2

2

N

N

N

E

E

E

C

C

C

S

S

S

t

t

t

o

o

o

r

r

r

a

a

a

g

g

g

e

e

e

P

P

P

e

e

e

r

r

r

f

f

f

o

o

o

r

r

r

m

m

m

a

a

a

n

n

n

c

c

c

e

e

e

O

O

O

p

p

p

t

t

t

i

i

i

m

m

m

i

i

i

z

z

z

e

e

e

r

r

r

a

a

a

n

n

n

d

d

d

R

R

R

e

e

e

l

l

l

a

a

a

t

t

t

e

e

e

d

d

d

P

P

P

r

r

r

o

o

o

d

d

d

u

u

u

c

c

c

t

t

t

The NEC Storage PerformanceOptimizer is for the following program products:

 NEC Storage BaseProduct
 NEC Storage PerformanceMonitor
 NEC Sto r age ReallocationControl
 NEC Storage AccessControl

4

4

4

.

.

.

3

3

3

S

S

S

y

y

y

s

s

s

t

t

t

e

e

e

m

m

m

C

C

C

o

o

o

n

n

n

f

f

f

i

i

i

g

g

g

u

u

u

r

r

r

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

For system configuration examples, refer to Chapter 3 “Basic Functions” in the “NEC Storage Manager User’s
Manual”.

Chapter 4 Overview of Performance Optimization Function

II-4

4

4

4

.

.

.

4

4

4

O

O

O

p

p

p

e

e

e

r

r

r

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

o

o

o

f

f

f

P

P

P

e

e

e

r

r

r

f

f

f

o

o

o

r

r

r

m

m

m

a

a

a

n

n

n

c

c

c

e

e

e

O

O

O

p

p

p

t

t

t

i

i

i

m

m

m

i

i

i

z

z

z

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

F

F

F

u

u

u

n

n

n

c

c

c

t

t

t

i

i

i

o

o

o

n

n

n

This section describes operations of the performance optimization function. The performance optimization function is
operated as shown in the following flow:

Operation flow Reference

Installing Performance optimization function
Installation of NEC Storage Manager is accompanied by installing

the Performance optimization function at the same time. For using
the Performance optimization function, Work Disk for Optimization
must be specified.

Chapter 5 Installation of Performance
Optimization Function

Monitoring and analyzing load state
Activate the Performance opt imization function screen and analyze

the load state on the basis of Busy Ratios displayed on the screen.
Because the busy ratio are displ ayed in different colors and the
information can be displayed in graphs, the bottlenecks of
concentrated I/Os can easily be iden tified. Use of the performance
monitoring function also allows more effective monitoring and
analyzing.

Part I Performance Monitoring Function

4.5.1 Bottleneck Detection Support

6.2 Operation on Screen

Replacement Plan
After detecting bottlenecks, replace the logical disks to distribute the

loads, removing the bottlenecks. Use of the replacement plan
function can easily prepare an effective planning of replacement.

4.5.2 Replacement Plan

6.2 Operation on Screen

Replacement Effect Prediction
Effectiveness of a replacement plan can be estimated before

practicing the replacement process. The effectiveness of
replacement can be verified by comparin g the busy ratio before after
replacement with each other, whi ch are indicated in values and
graphs. After verifying sufficient effectiveness of replacement,
proceed to the next step of performance tuning shown below.

4.5.3 Replacement Effect Prediction

6.2 Operation on Screen

Performance tuning
Apply the planned repl acement practically, and remove the

bottlenecks by distributing loads.

4.5.4 Performance Tuning

6.3 Operation on Screen

7.1 Logical Disk Movement Command
A.2 Command for Performance Tuning

Verifying arrangement of Work Disks for Optimization
The replacement causes the ch anges in arrangement of Work Disks

for performance optimization. Verify that the arrangement h as no
problems, and if a problem is found, change the settings of Work
Disks for performance optimization.

5.3 Installation of Work Disks for
Optimization

Chapter 4 Overview of Performance Optimization Function

II-5

4

4

4

.

.

.

5

5

5

F

F

F

u

u

u

n

n

n

c

c

c

t

t

t

i

i

i

o

o

o

n

n

n

O

O

O

v

v

v

e

e

e

r

r

r

v

v

v

i

i

i

e

e

e

w

w

w

The performance optimization function provides the capability of “Bottleneck Detection Support”, “Replacement Plan”,
“Replacement Effect Prediction”, and “Performance tuning”. This section describes outlines of the functions.

4

4

4

.

.

.

5

5

5

.

.

.

1

1

1

B

B

B

o

o

o

t

t

t

t

t

t

l

l

l

e

e

e

n

n

n

e

e

e

c

c

c

k

k

k

D

D

D

e

e

e

t

t

t

e

e

e

c

c

c

t

t

t

i

i

i

o

o

o

n

n

n

S

S

S

u

u

u

p

p

p

p

p

p

o

o

o

r

r

r

t

t

t

Concentration of I/O in a specific physical disk causes I/O competition thereby deteriorating response. The degree of
concentration of I/O in a physical disk can be indicated as th e physical disk's operating time per unit time. This value
is expressed as the physical disk's Busy Ratio.
The NEC Storage PerformanceOptimizer monitors the load state of physical disks at specified intervals an d displays
the obtained Busy Ratio for each p hysical disk on the dedicated clien t screen. Analysis of the Busy Ratio displayed
on the dedicated client screen allows you to detect a physical disk (bottleneck location) in which I/O concentrates.
The NEC Storage PerformanceOptimizer features the following display of th e Busy Ratio, which enables the analysis
suitable for the business system and visual detection of the bottleneck.

 The analysis period (Busy Ratio calculation period) can be specified in terms of the exponent condition for the date,

days of the week, and time zone.

 Display a Busy Ratio in tri-level with color-coding.
 Display over-ti me changes of Busy Ratio in three different colors.

4

4

4

.

.

.

5

5

5

.

.

.

2

2

2

R

R

R

e

e

e

p

p

p

l

l

l

a

a

a

c

c

c

e

e

e

m

m

m

e

e

e

n

n

n

t

t

t

P

P

P

l

l

l

a

a

a

n

n

n

Upon detecting a physical disk with concentrated I/Os (bottleneck part), logical di sks are moved (replaced) to tune
performances. This function displays information about the movement destination logical disks, which re best suited
for the source logical disk. This function automatically finds t he movement destination logical disks that are highly
effective for I/O distribution after moving disks, and displays the disks in the order of effectiveness. An administrator
is allowed to tune the performances on the basis of the information and remove the bottleneck.

4

4

4

.

.

.

5

5

5

.

.

.

3

3

3

R

R

R

e

e

e

p

p

p

l

l

l

a

a

a

c

c

c

e

e

e

m

m

m

e

e

e

n

n

n

t

t

t

E

E

E

f

f

f

f

f

f

e

e

e

c

c

c

t

t

t

P

P

P

r

r

r

e

e

e

d

d

d

i

i

i

c

c

c

t

t

t

i

i

i

o

o

o

n

n

n

An effect of load distribution after logical disk movemen t can be estimated before logical disk movement. This
function displays the changes of Busy Ratios in source and destination logical disks or RANK, in graph format. An
administrator is allowed to verify that I/O will not concentrate after moving disks, and tune the performances on the
basis of the estimated effects.

4

4

4

.

.

.

5

5

5

.

.

.

4

4

4

P

P

P

e

e

e

r

r

r

f

f

f

o

o

o

r

r

r

m

m

m

a

a

a

n

n

n

c

c

c

e

e

e

T

T

T

u

u

u

n

n

n

i

i

i

n

n

n

g

g

g

The NEC Storage PerformanceOp timizer moves logical disks locat ed in a high load physical disk in which I/ O
concentrates to a low load RANK so as to distribute the concentration of I/O thereby canceling the I/O competition and
removing the bottleneck. This is called performance tuning. The performance tuning can be executed instantly, or at
a registered time.
Figure 4-2 shows the concept of performance tuning implement by the performance optimization function. The work
disks shown in the figure are logical disks dedicated to the use for the performance tuning (The Work Disk for

Chapter 4 Overview of Performance Optimization Function

II-6

Optimization). By moving a logical disk, t he arrangement of the Moved Material Lo gi cal Disk and the Work Disk for
Optimization is switched.
The logical disks are moved inside the disk array without affecting any business system. As a result, performance
tuning is possible while business is in operation. Transfer of logical disks will not require any changes of SG or
access methods to business systems.

Figure 4-2 Concept of Performance Tuning

Due to performance tuning effect and so on, the performance optimization by the performance tuning function has
limitation. Logical disks cannot be moved in the cases described below. When you perform the tuning operation
or configuration setting of the disk array, please note the following:
*Cases in which logical disks cannot be moved

 A Moved Material Logical Disk is located i n t he same RANK as a Work Disk for Optimization.
 A Moved Material Logical Disk and a Work Disk for Optimization are different in capaci ty.
 A Moved Material Logical Disk is a multiple RANK type.

High-load physical disk (= Bottleneck)
I/O concentrates in logical disks (LDx, LDy, LDz)
causing a high load state.

I/O to LDx has been moved to the low-load physical
disk thereby canceling the high-load state.

Exchange

A logical disk in which
I/O concentrates is
replaced with a work
disk.

Distribution of I/O cancels the bottleneck

Work Disk

Low-load physical dis

k

Chapter 5 Installation of Performance Optimization Function

II-7

Chapter 5 Installation of Performance

Optimization Function

5

5

5

.

.

.

1

1

1

S

S

S

e

e

e

r

r

r

v

v

v

e

e

e

r

r

r

I

I

I

n

n

n

s

s

s

t

t

t

a

a

a

l

l

l

l

l

l

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

5

5

5

.

.

.

1

1

1

.

.

.

1

1

1

O

O

O

p

p

p

e

e

e

r

r

r

a

a

a

t

t

t

i

i

i

n

n

n

g

g

g

E

E

E

n

n

n

v

v

v

i

i

i

r

r

r

o

o

o

n

n

n

m

m

m

e

e

e

n

n

n

t

t

t

The operating environment of the target HW, operation OS, memory, and disk Capacity is the same as that of iSM.
For the operating environment, refer to Part I “Installation and Setting of NEC Storage Manager” of the “NEC Sto r age
Manager User’s Manual” of your OS.
Required software and target storage are as follows:

Table 5-1 Operating Environment

Required software NEC Storage Manager

NEC Storage PerformanceMonitor
NEC Storage Reallocation Control
NEC Storage AccessControl

Target storage NEC Storage 4000 series

NEC Storage 3000 series

5

5

5

.

.

.

1

1

1

.

.

.

2

2

2

I

I

I

n

n

n

s

s

s

t

t

t

a

a

a

l

l

l

l

l

l

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

The NEC Storage PerformanceOptimizer is simultaneously installed when the iSM is installed. For installation and
uninstall, refer to Part I “Installation and Setting of NEC Storage Manager” of the “NEC Storage Manager User’s
Manual” of your OS.

5

5

5

.

.

.

1

1

1

.

.

.

3

3

3

E

E

E

n

n

n

v

v

v

i

i

i

r

r

r

o

o

o

n

n

n

m

m

m

e

e

e

n

n

n

t

t

t

S

S

S

e

e

e

t

t

t

t

t

t

i

i

i

n

n

n

g

g

g

You can specify the operating environment of NEC Storage PerformanceOptimizer by using the environment setting of
iSM. The following is the items to be specified:

 Location of an optimization log file

Specify the location of a file which accumulates Busy Ratio information for the disk (optimization log file).

 Interval for outputting optimization logs

The NEC Storage PerformanceOptimizer outputs Busy Ratio information for the disk to the optimization log file at
specified intervals. You can specify either from 1 minute to 60 minutes (The default setting is 5 minutes) as the
interval. The interval must be specified in accordance with the statistic information output interval of the
performance monitoring function.

 Interval for updating the progress of logical disk movement

The NEC Storage PerformanceOp timizer checks the progress of logical d isk movement at specified intervals and
displays the state on the dedicated client screen. You can specify the interval t i me in t he range from 5 seconds to

30 seconds (The default setting is 10 seconds).
For specification method, refer to Part I “Installation and Setting of NEC Storage Manager” of the “NEC Storage
Manager User’s Manual” of your OS.

Chapter 5 Installation of Performance Optimization Function

II-8

5

5

5

.

.

.

2

2

2

C

C

C

l

l

l

i

i

i

e

e

e

n

n

n

t

t

t

I

I

I

n

n

n

s

s

s

t

t

t

a

a

a

l

l

l

l

l

l

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

5

5

5

.

.

.

2

2

2

.

.

.

1

1

1

O

O

O

p

p

p

e

e

e

r

r

r

a

a

a

t

t

t

i

i

i

n

n

n

g

g

g

E

E

E

n

n

n

v

v

v

i

i

i

r

r

r

o

o

o

n

n

n

m

m

m

e

e

e

n

n

n

t

t

t

The operating environ ment of the NEC Storage PerformanceOptimizer is the same as that of iSM. For the operating
environment, refer to Part I “Installation and Setting of NEC Storage Manager” of the “NEC Storage Manager User’s
Manual” of your OS.

5

5

5

.

.

.

2

2

2

.

.

.

2

2

2

I

I

I

n

n

n

s

s

s

t

t

t

a

a

a

l

l

l

l

l

l

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

To install the NEC Storage PerformanceOptimizer, specify a setup type th at includes the expanding fun ction and install
the iSM client. For the installation method, refer to Part I “Installation and Setting of NEC Storage Manager” of the
“NEC Storage Manager User’s Manual” of your OS.

Chapter 5 Installation of Performance Optimization Function

II-9

5

5

5

.

.

.

3

3

3

I

I

I

n

n

n

s

s

s

t

t

t

a

a

a

l

l

l

l

l

l

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

o

o

o

f

f

f

W

W

W

o

o

o

r

r

r

k

k

k

D

D

D

i

i

i

s

s

s

k

k

k

s

s

s

f

f

f

o

o

o

r

r

r

O

O

O

p

p

p

t

t

t

i

i

i

m

m

m

i

i

i

z

z

z

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

The NEC Storage PerformanceOptimizer moves logical disks on a high-load physical disk to a low-load physical disk
to distribute the concentration of I/O thereby canceling the bottleneck.
When a logical disk is moved, another logical disk which i s hidden from all business systems and no access is ensured
is required. This logical disk is called a Work Disk for Optimization.

5

5

5

.

.

.

3

3

3

.

.

.

1

1

1

S

S

S

e

e

e

t

t

t

t

t

t

i

i

i

n

n

n

g

g

g

W

W

W

o

o

o

r

r

r

k

k

k

D

D

D

i

i

i

s

s

s

k

k

k

s

s

s

f

f

f

o

o

o

r

r

r

O

O

O

p

p

p

t

t

t

i

i

i

m

m

m

i

i

i

z

z

z

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

You can set Work Disks for Optimization by using the LD Administrator function of the iSM (NEC Storage
ReallocationControl). For the setting method, refer to the “NEC Storage Manager Configuration Setting Tool User's
Manual (GUI)” (IS007).

Due to NEC Storage PerformanceOptimizer's limitation of logical disk movement and the nature of the Work Disk
for Optimization, logical disks listed below cannot be specified as Work Disks for Optimization. Please note this
point when you specify configuration of the disk array.

 A multiple RANK type logical disk
 A logical disk set in pairs of DDR/RDR (Note 1)

In addition, the maximum number of Work Disks for Optimization which can be set for each disk array is
predetermined. The maximum number of Work Disks for Optimization depends on the specification of each disk
array. Therefore, check the number when you configure the sett ings for the disk array. On the other hand, for
moving cache-resident logical disk, a logical disk of one-logical disk/1-RANK configuration (RAID1 only) must be
selected as a work disk for opti mization.
(Note 1) For details of DDR/RDR, refer to the “NEC Storage Data Replication User’s Manual (Function Guide)”
and “NEC Storage Data Replication User’s Manual (Installation and Operati on Guide for Windows)”.

5

5

5

.

.

.

3

3

3

.

.

.

2

2

2

A

A

A

r

r

r

r

r

r

a

a

a

n

n

n

g

g

g

e

e

e

m

m

m

e

e

e

n

n

n

t

t

t

o

o

o

f

f

f

W

W

W

o

o

o

r

r

r

k

k

k

D

D

D

i

i

i

s

s

s

k

k

k

s

s

s

f

f

f

o

o

o

r

r

r

O

O

O

p

p

p

t

t

t

i

i

i

m

m

m

i

i

i

z

z

z

a

a

a

t

t

t

i

i

i

o

o

o

n

n

n

Generally, a bottleneck in performance occurs due to an increase of the amount of data, which results from an increase
of the amount of work, or an access pattern change. Work Disks for Optimization are to be used when NEC Storage
PerformanceOptimizer eliminates the cause of a bottleneck in p erformance. There is no need to arrange them when
installing a disk array subsystem.
If the amount of work increases, usually distribute the load by adding physical disks. When tuning performance with
NEC Storage PerformanceOptimizer, arrange Work Disks for Optimization on th e added physical disks (RANK) and
move logical disks from high-load physical disks.
Note the following when arranging Work Disks for Optimization:

Chapter 5 Installation of Performance Optimization Function

II-10

 Capacity of a Work Disk for Optimization

The capacity of the Moved Material Logical Disk must be identical to that of the Work Disk for Optimization. Set

the Work Disk for Optimization in accordance with the capacity of the Mo ved Material Logical Disk.

 RAID type of a Work Disk for Optimization

A logical disk can be moved even if the RAID type is different between the logical disk and Work Disk for

Optimization. However, be careful that if the RAID types are different, the effect of tuning cannot be predicted.

The method of arranging Work Disks for Optimization at installation of a disk array subsystem is one of operation
modes. If Work Disks for Optimization are allocated beforehand, performance can be tuned without physical disks
being added. However, since it is difficult to predict occurrence of a bottleneck in performance, arrangement of Work
Disks for Optimization need s to be designed after due consideration.

Note the following when arranging Work Disks for Optimization at installation of a disk array subsystem:

 Load on physical disks (RANK) on which Work Disks for Optimization are arranged

When physical disks with Work Disks for Optimization being arranged are subjected to a high load, they cannot be

used as the move destinations of logical disks.

 Utilization ratio of a disk array subsystem

Work Disks for Optimization cannot be used for business. Be careful for the utilization ratio of the disk array

subsystem not to decrease because of the setting of Work Disks for Optimization.

Chapter 6 Operation of Performance Optimization Function (GUI)

II-11

Chapter 6 Operation of Performance Optimization

Function (GUI)

This chapter will describe the composition of the NEC Storage PerformanceOptimizer dedicated client screen and its method of
operation.

6

6

6

.

.

.

1

1

1

D

D

D

e

e

e

s

s

s

c

c

c

r

r

r

i

i

i

p

p

p

t

t

t

i

i

i

o

o

o

n

n

n

o

o

o

f

f

f

S

S

S

c

c

c

r

r

r

e

e

e

e

e

e

n

n

n

Figure 6-1 shows the NEC Storage PerformanceOptimizer dedicated client screen. This section will describe the
composition of the screen.

Figure 6-1 NEC Storage PerformanceOptimizer Screen

The screen is divided into eight areas from (1) to (8), as shown in Figure 6-1. Descriptions for each area are as
follows:

(1) Menu Bar

Select necessary items from the menu to perform operations. For details, refer to Help.

(4) Configuration Display Area

(5) Detailed Display Area

(6) Work Disk for Optimization Display Area

(7) Movement Progress Information Display Area

(1) Menu Bar

(2) Tool Bar

(3) Analysis Period Display Area

(8)

Status Ba

r

Chapter 6 Operation of Performance Optimization Function (GUI)

II-12

(2) Tool Bar

Among menu functions, buttons for frequently used menu functions are provided to enable the one-click
operation. For details about each button, refer to Help.
Menu functions provided as tool bar buttons

 Saving Settings
 Start LD Movement
 Stop LD Movement
 Change LD Movement Speed
 Change LD Movement Schedule
 Analysis Property
 Replacement Plan
 Replace ment Effect Prediction
 Busy Ratio Graph

(3) Analysis Period Display Area

Displays the current analysis period (Busy Ratio calculation period).

(4) Configuration Display Area

Configuration of the disk array that uses the NEC Storage PerformanceOptimizer is separated into the “disk array
layer” and the “RANK layer” and displayed in a tree view form. Figure 6-2 shows an example of the display.

Figure 6-2 Example of Display of Disk Array Configuration

At the start of the screen or when you select “Update to The Current Information” from the menu, only a disk array
layer which is the initial state of the screen is displayed.

In Figure 6-2, the number (i) indicates a disk array layer and (ii) indicates a RANK layer. Table 6-1 provides
descriptions of each layer.

(i) (ii)

Chapter 6 Operation of Performance Optimization Function (GUI)

II-13

Table 6-1 Disk Array Layer and RANK Layer

Layer Description
Disk Array layer Displays icons and the disk array name which correspond to respective disk array models. An icon

for the disk array which is not monitored by the iSM server is displayed in gray.

RANK layer Displays the number and icon for the RANKs built in the disk array. Signal colors indicating the

degree of the Busy Ratio are app ended to the icon. The signal colors can be changed on the Analysis
Property dialog ([Sort of Busy Ratio] tab). Refer to 6.2.2 “Setting Sort of Busy Ratio” for Analysis
Property dialog ([Sort of Busy Ratio] tab).

• When the RANK is in the Ready mode

Busy Ratio (High) ........

Busy Ratio (Medium) ........

Busy Ratio (Low) ........

Busy Ratio (No information) ........

• When the RANK is not in the Ready mode

Attn. ........

Fault ........

An icon for the disk array which is not monitored by the iSM server is displayed in gray.

(5) Detailed Display Area

Lists detailed information of the component located one layer below the layer selected in the configuration
display area.
 When th e iSM server is selected
Detailed information of the disk array is displayed.
 When th e disk array is selected
Detailed information of the RANK is displayed.
 When th e RANK is select ed
Detailed information of the logical disk is displayed.
The detail display items for the disk array, RANK, and logical disk will be described below.

(i) Detailed information of the disk array

Figure 6-3 shows an example of display of detailed information of the disk array. Table 6-2 provides
descriptions of each display item.

Figure 6-3 Example of Display of Detailed Information of Disk Array

Chapter 6 Operation of Performance Optimization Function (GUI)

II-14

Table 6-2 Detailed Information Display Items for the Disk Array

Display item Description

Disk Array
Subsystem

Displays the disk array name.

Monitoring State Running .......Indicates that the iSM server is monitoring the state.

Stop .......Indicates that the iSM server is stopping monitoring the state.

Logging State Accumulate .......Indicates that Busy Ratio information is being accumulated.

Stop .......Indicates that the accumulation of Busy Ratio information is stopping.

Logging Start Time Indicates time when accumulation of Busy Ratio information started.
Logging End Time Displays the time of latest accumulation of Busy Ratio information.

(ii) Detailed Information of the RANK

Figure 6-4 shows an example of display of detailed information of the RANK. Table 6-3 provides descriptions
of each display item.

Figure 6-4 Example of Display of Detailed Information of RANK

Table 6-3 Detailed Information Display Items for RANK

Display item Description

Number Displays icons and numbers of RANKs. Display format of the icon is the same as that of the

Configuration Display Area.

Busy Ratio [%] Displays the Busy Ratio of RANKs. For the RANK that does not have valid Busy Ratio information,

an asterisk (***) is displayed.
Note: When a logical disk in the RANK is moved, Busy Ratio information which has been

accumulated is no longer related with Busy Ratio information which is to be accumulat ed after
the movement. Therefore, immediatel y after a logical disk has been moved , there is no valid
Busy Ratio information for the RANK. This state will be cancelled when Busy Ratio
information is accumulated at t he next interval.

Completion Time Displays the time when the transfer of the last logical disk in th e RANK has been completed. When

logical disks are not moved, “Un-carrying” is displayed.

RAID Displays the RAID type of the RANK.

Status Ready ....... Indicates that the RANK is in the normal state.

Attn .......Indicates that an event (reduce, formatting, etc.) is occurring in the RANK and

attention is necessary.

Fault ....... Indicates that a fault is occurring in the RANK. When “fault” is displayed, logical

disks in the RANK cannot be moved.

(iii) Detailed Information of the logical disk

Figure 6-5 shows an example of display of detailed information of the logical disk. Table 6-4 provides
descriptions of each display item.

Chapter 6 Operation of Performance Optimization Function (GUI)

II-15

Figure 6-5 Example of Display of Detailed Information of Logical Disk

Table 6-4 Detailed Information Display Items for the Logical Disk

Display item Description

Number Displays icons and numbers of logical disks. Similar to RANKs’ icons, logical disks’ icons are also

displayed in the three stages expressed in different colors depending on Busy Ratio.

• When the logi cal disk is in the Ready mode

Busy Ratio (High) .....

Busy Ratio (Medium) .....

Busy Ratio (Low) .....

Busy Ratio (No information) .....

• When the logi cal disk is not in the Ready mode

Attn .....

Fault .....

Type Displays the type of volume of the logical disk. Displays the same information of the logical disk

type that is displayed on the iSM state monitoring screen.
LD Name Displays nicknames of logical disks.

Status Ready .....Indicates the normal state.

Moving .....Indicates that the logical disk is being moved.

Scheduled .....Indicates that movement of applicable logical disk has been registered in

schedule.

Attn .....Indicates that an event (formatting, etc.) is occurring and attention is required.

Fault (media error) .....Indicates that a media fault is occurring.

Fault ..... Indicates that a RANK fault is occurring.

Busy Ratio [%] Displays the Busy Ratio of the logical disk. For the RANK that does not have valid Busy Ratio

information, an asterisk (***) is displayed.

Note: When a logical disk in the RANK is moved, Busy Ratio information which has been

accumulated is no longer related with Busy Ratio i nformation which is to be accumulated after
the movement. Therefore, immediatel y after a logical disk has been moved , there is no valid
Busy Ratio information for the RANK. This state will be cancelled when Busy Ratio

information is accumulated at t he next interval.
RAID Displays the RAID type of the logical disk.
Capacity [GB] The capacity of the logical disk is displayed in GB.
RANK Displays the RANK number for which logical disks have been bound. For the multiple RANK types,

all RANKs’ numbers are displayed in a row.

(6) Work Disk for Optimization Display Area

When you double-click a [Logical Disk] listed in the detailed display area, the list of Work Disks for
Optimization which are the destination candidates are displayed in the Work Disk for Optimization Display Area.
Only Work Disks for Optimization which satisfy the following requirements are listed:
 The capacity of the optimization logical disk is the same as that of the logical disk selected in the detailed

display area.

Chapter 6 Operation of Performance Optimization Function (GUI)

II-16

 The optimization logical disk is bound for a different RANK from the logi cal disk selected in the detailed

display area.
Figure 6-6 shows an example of display of detailed information of the Work Disk for Optimization. Table 6-5
provides descriptions of each d isplay item.

Figure 6-6 Example of Display of Detailed Information of Work Disk for Optimization

Table 6-5 Detailed Information Display Items for the Work Disk for Optimization

Display item Description

Disk Array Subsystem in “Moved
Material Logical Disk”

Displays the disk array name for th e transfer target moved material logical disk
selected in the Detailed Display Area.

RANK in “Moved Material Logical
Disk”

Displays the RANK number for the tran sfer target moved material logical disk selected
in the Detailed Display Area.

LD No. in “Moved Material Logical
Disk”

Displays the logical di sk number for the transfer target moved material logical disk
selected in the Detailed Display Area.

RANK %Busy in “Moved Material
Logical Disk”

Displays the estimated Busy Ratio of the RANKs after target moved material logical

disk selected in the Det ai led Display Area have been moved.
Number Displays icons and logical disk number of Work Disks for Optimization.
LD Name Displays nicknames of Work Disks for Optimization.
Status Displays the state of Work Disks for Optimization. Detailed Information is the same

as that of the logical disks.
RANK Displays the RANK numbers of Work Disks for Optimization.
RANK %Busy When target moved material logical disk selected in the Detailed Display Area have

been moved to the Work Disks for Optimization, the estimated Busy Ratio of the

RANKs for the Work Disks for Optimization is displayed.

Note: If the RAID type of the Work Disk for Optimization is different from that of

the transfer target Material Logical Disk, the Busy Ratio after the disk is moved
cannot be estimated; therefore, an asterisk (***) is displayed.

RAID Displays the RAID type of Work Disks for Optimization.

(7) Movement Progress Information Display Area

A list of progress information about movement of logical disks is displayed.
Figure 6-7 shows an example of display of disk transfer progress information. Table 6-6 provides descriptions
of each display item.

Figure 6-7 Example of Display of Movement Progress Information

Chapter 6 Operation of Performance Optimization Function (GUI)

II-17

Table 6-6 Detailed Information Display Items for Movement Progress Information

Display item Description
Disk Array Subsystem Displays the disk array name for a logical disk being moved.
Source RANK Displays the RANK number for a logical disk being moved.
Source LD Displays the logical disk number being moved.
Destination RANK Displays the RANK number for the destination Work Disk for Optimization.
Destination LD Displays the logical disk number for the destination Work Disk for Optimization number.
Progress Ratio [%] Displays the movement progress rate in percentage.
State Displays the movement state. Displayed contents are as follows:

Moving ..... Indicates that a disk is being moved.

Complete ..... Indicates that the disk transfer has been finished normally.

Discontinue ..... Indicates that the disk transfer is being cancelled.

Discontinuation ..... Indicates that the disk transfer has cancelled due to a cancellation

request.

Scheduled ..... Indicates that movement has been registered in schedule.

Changing schedule .....Indicates that registered movement schedule is being changed.

Schedule canceled ..... Indicates that registered movement schedule has been canceled.

Schedule failed ..... Indicates that register movement schedule has failed.

Fault .....Indicates that abnormal termination of the disk transfer has occurred

due to a fault.

Speed of Movement By moving a logical disk, all data contained in the source logical disk is copied to the desti nation

Work Disk for Optimization. This area displays the speed of moving the data. Displayed
contents are as follows:

auto .... The movement speed is automatically adjusted according to the operating

state of the disk array.

high ....A disk is moved at maximum data transfer speed.

Start Time Displays the disk transfer start time.
End Time Displays the disk transfer end time. A blank is displayed if the state is “Moving” or “Scheduled”.

If the state is “Schedule can celed”, time of canceling the sch edule is displayed, and if the st ate is
“Interrupted” or “Fault”, time of interrupting movement is displayed.

Chapter 6 Operation of Performance Optimization Function (GUI)

II-18

(8) Status Bar

Displays the operating state of the NEC Storage PerformanceOptimizer client. Table 6-7 provides descriptions
of each display item.

Table 6-7 Display Items for Status Bar

Display item Description

Operating state Displays the current operating state. Displayed cont ents are as follows:

Information acquiring ....Indicates that disk array configuration information or Busy Ratio

information is being collected from the iSM server.

Working ....Indicates that the NEC Storage PerformanceOptimizer client is

operating.

Stop ....Indicates that the NEC Storage PerformanceOptimizer client has

stopped due to a disconnection with the iSM server or a cancellation
instruction provided on the Information acquiring dialog screen.
When the client is connect ed to the iSM server, the operation can be
resumed by selecting “Update to The Current Information” from the
menu.

Interval for updating logical
disk transfer progress
information

Numerical values displayed next to the operating state are the interval for updating logical disk
transfer progress information.

This interval is for updating logical disk transfer progress information shown on the screen.
The value is the same as the interval for checking transfer progress of a logical disk specified in the

environment setting of the iSM server. Numerical values in the range from 5 seconds to 30
seconds are displayed.