Fujitsu SPARC Enterprise M8000, SPARC Enterprise M9000 Overview Manual

SPARC Enterprise

™

M8000/M9000 Servers

Overview Guide

Manual Code C120-E324-06EN
Part No. 819-7876-13
August 2009, Revision A

Copyright 2007-2009 FUJITSU LIMITED, 1-1, Kamikodanaka 4-chome, Nakahara-ku, Kawasaki-shi, Kanagawa-ken 211-8588,Japan. All rights
reserved.

Sun Microsystems, Inc. provided technical input and review on portions of this material.
Sun Microsystems,Inc.and FujitsuLimitedeach ownorcontrol intellectual propertyrightsrelating to productsandtechnology describedin

this document,and such products,technologyand thisdocumentare protected bycopyrightlaws, patentsandother intellectualpropertylaws
and internationaltreaties.The intellectualpropertyrights of SunMicrosystems,Inc. andFujitsuLimited insuchproducts, technology andthis
document include,without limitation, oneor more oftheUnited Statespatentslisted athttp://www.sun.com/patents andone or more
additional patentsor patent applicationsin the UnitedStates or othercountries.

This documentand the productandtechnology towhichit pertainsaredistributed under licensesrestrictingtheir use,copying,distribution,
and decompilation.No part ofsuch product ortechnology, orofthis document,maybe reproduced inany formbyany meanswithoutprior
written authorizationof Fujitsu Limitedand Sun Microsystems,Inc.,and theirapplicablelicensors, ifany. Thefurnishingof thisdocumentto
you doesnot give youany rights orlicenses, express orimplied,with respect to theproductor technology towhich it pertains,and this
document doesnot contain orrepresentany commitment ofany kind onthe part ofFujitsu Limited orSun Microsystems, Inc.,orany affiliate of
either ofthem.

This documentand the productandtechnology describedinthis documentmayincorporate third-party intellectual property copyrighted by
and/or licensedfromsuppliers toFujitsuLimited and/orSunMicrosystems, Inc., includingsoftwareand fonttechnology.

Per theterms of theGPL or LGPL,a copy ofthe source codegovernedby theGPLor LGPL,asapplicable, isavailableupon requestbythe End
User.Pleasecontact FujitsuLimitedor SunMicrosystems,Inc

This distribution may include materials developed by third parties.
Parts of the product may be derived from Berkeley BSD systems, licensed from the University of California. UNIX is a registered trademark

in the U.S. and in other countries, exclusively licensed through X/Open Company, Ltd.
Sun, Sun Microsystems, the Sun logo, Java, Netra, Solaris, Sun Ray, Answerbook2, docs.sun.com, OpenBoot, and Sun Fire are trademarks or

registered trademarks of Sun Microsystems, Inc., or its subsidiaries, in the U.S. and other countries.
Fujitsu and the Fujitsu logo are registered trademarks of Fujitsu Limited.
All SPARC trademarks are used under license and are registered trademarks of SPARC International, Inc. in the U.S. and other countries.

Products bearing SPARC trademarks are based upon architecture developed by Sun Microsystems, Inc.
SPARC64 is a trademark of SPARC International, Inc., used under license by Fujitsu Microelectronics, Inc. and Fujitsu Limited.
The OPEN LOOK and Sun™ Graphical User Interface was developed by SunMicrosystems, Inc. for its users and licensees. Sun acknowledges

the pioneering efforts of Xerox in researching and developing the concept of visual or graphical user interfaces for the computer industry. Sun
holds anon-exclusive license fromXeroxto the XeroxGraphicalUser Interface,whichlicense alsocoversSun’s licenseeswhoimplement OPEN
LOOK GUIs and otherwise comply with Sun’s written license agreements.

United StatesGovernment Rights -Commercialuse. U.S.Governmentusers are subject tothestandard government userlicense agreements of
Sun Microsystems,Inc.and FujitsuLimitedand theapplicableprovisions of theFAR and its supplements.

Disclaimer: The only warranties granted by Fujitsu Limited, Sun Microsystems, Inc. or any affiliate of either of them in connection with this
document or any product or technology described herein are those expressly set forth in the license agreement pursuant to which the product
or technology is provided. EXCEPT AS EXPRESSLY SET FORTH IN SUCH AGREEMENT, FUJITSU LIMITED, SUN MICROSYSTEMS, INC.
AND THEIRAFFILIATESMAKE NO REPRESENTATIONSOR WARRANTIES OF ANYKIND (EXPRESSOR IMPLIED)REGARDING SUCH
PRODUCT OR TECHNOLOGY OR THIS DOCUMENT, WHICH ARE ALL PROVIDED AS IS, AND ALL EXPRESS OR IMPLIED
CONDITIONS, REPRESENTATIONS AND WARRANTIES, INCLUDING WITHOUT LIMITATION ANY IMPLIED WARRANTY OF
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE OR NON-INFRINGEMENT, ARE DISCLAIMED, EXCEPT TO THE
EXTENT THAT SUCH DISCLAIMERS ARE HELD TO BE LEGALLY INVALID. Unless otherwise expressly set forth in such agreement, to the
extent allowed by applicable law, in no event shall Fujitsu Limited, Sun Microsystems, Inc. or any of their affiliates have any liability to any
third party under any legal theory for any loss of revenues or profits, loss of use or data, or business interruptions, or for any indirect, special,
incidental or consequential damages, even if advised of the possibility of such damages.

DOCUMENTATION IS PROVIDED “AS IS” AND ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND WARRANTIES,
INCLUDING ANYIMPLIED WARRANTY OFMERCHANTABILITY,FITNESS FOR APARTICULAR PURPOSEOR NON-INFRINGEMENT,
ARE DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD TO BE LEGALLY INVALID.

Please

Recycle

Copyright 2007-2009 FUJITSU LIMITED, 1-1, Kamikodanaka 4-chome, Nakahara-ku, Kawasaki-shi, Kanagawa-ken 211-8588, Japon. Tous
droits réservés.

Entrée et revue tecnical fournies par Sun Microsystems, Incl sur des parties de ce matériel.
Sun Microsystems, Inc. et Fujitsu Limited détiennent et contrôlent toutes deux des droits de propriété intellectuelle relatifs aux produits et

technologies décrits dans ce document. De même, ces produits, technologies et ce document sont protégés par des lois sur le copyright, des
brevets, d’autreslois sur lapropriété intellectuelleet des traitésinternationaux. Les droits de propriété intellectuelle deSun Microsystems,Inc.
et Fujitsu Limited concernant ces produits, ces technologies et ce document comprennent, sans que cette liste soit exhaustive, un ou plusieurs
des brevets déposésaux États-Unis etindiqués à l’adresse http://www.sun.com/patents de même qu’un ou plusieursbrevets ou applications
brevetées supplémentaires aux États-Unis et dans d’autres pays.

Ce document, le produit et les technologies afférents sont exclusivement distribués avec des licences qui en restreignent l’utilisation, la copie,
la distribution et la décompilation. Aucune partie de ce produit, de ces technologies ou de ce document ne peut être reproduite sous quelque
forme quece soit,par quelquemoyen quece soit,sans l’autorisation écrite préalable deFujitsu Limitedet deSun Microsystems, Inc., etde leurs
éventuels bailleurs de licence. Ce document, bien qu’il vous ait été fourni, ne vous confère aucun droit et aucune licence, expresses ou tacites,
concernant le produitou la technologie auxquels ilse rapporte. Parailleurs, il ne contient nine représente aucun engagement, dequelque type
que ce soit, de la part de Fujitsu Limited ou de Sun Microsystems, Inc., ou des sociétés affiliées.

Ce document, et le produit et les technologies qu’il décrit, peuvent inclure des droits de propriété intellectuelle de parties tierces protégés par
copyright et/ou cédés sous licence par des fournisseurs à Fujitsu Limited et/ou Sun Microsystems, Inc., y compris des logiciels et des
technologies relatives aux polices de caractères.

Par limites du GPL ou du LGPL, une copie du code source régi par le GPL ou LGPL, comme applicable, est sur demande vers la fin utilsateur
disponible; veuillez contacter Fujitsu Limted ou Sun Microsystems, Inc.

Cette distribution peut comprendre des composants développés par des tierces parties.
Des parties de ce produit pourront être dérivées des systèmes Berkeley BSD licenciés par l’Université de Californie. UNIX est une marque

déposée aux Etats-Unis et dans d’autres pays et licenciée exclusivement par X/Open Company, Ltd.
Sun, Sun Microsystems, le logo Sun, Java, Netra, Solaris, Sun Ray, Answerbook2, docs.sun.com, OpenBoot, et Sun Fire sont des marques de

fabrique ou des marques déposées de Sun Microsystems, Inc., ou ses filiales, aux Etats-Unis et dans d’autres pays.
Fujitsu et le logo Fujitsu sont des marques déposées de Fujitsu Limited.
Toutes les marques SPARC sont utilisées sous licence et sont des marques de fabrique ou des marques déposées de SPARC International, Inc.

aux Etats-Unis et dans d’autres pays. Les produits portant les marques SPARC sont basés sur une architecture développée par Sun
Microsystems, Inc.

SPARC64 est une marques déposée de SPARC International, Inc., utilisée sous le permis par Fujitsu Microelectronics, Inc. et Fujitsu Limited.
L’interface d’utilisation graphique OPEN LOOK et Sun™ a été développée par Sun Microsystems, Inc. pour ses utilisateurs et licenciés. Sun

reconnaît les effortsde pionniers de Xerox pour la recherche et le développement duconcept des interfaces d’utilisation visuelle ou graphique
pour l’industrie de l’informatique. Sun détient une license non exclusive de Xerox sur l’interface d’utilisation graphique Xerox, cette licence
couvrant également les licenciés de Sun qui mettent en place l’interface d’utilisation graphique OPEN LOOK et qui, en outre, se conforment
aux licences écrites de Sun.

Droits du gouvernement américain - logiciel commercial. Les utilisateurs du gouvernement américain sont soumis aux contrats de licence
standard de Sun Microsystems, Inc. et de Fujitsu Limited ainsi qu’aux clauses applicables stipulées dans le FAR et ses suppléments.

Avis de non-responsabilité:lesseules garantiesoctroyées par FujitsuLimited, SunMicrosystems,Inc. outoute sociétéaffiliéede l’uneou l’autre
entité enrapport avecce documentou toutproduitou toutetechnologie décrit(e)dans les présentescorrespondent auxgaranties expressément
stipulées dans le contrat de licence régissant le produit ou la technologie fourni(e). SAUF MENTION CONTRAIRE EXPRESSÉMENT
STIPULÉE DANS CE CONTRAT, FUJITSU LIMITED, SUN MICROSYSTEMS, INC. ET LES SOCIÉTÉS AFFILIÉES REJETTENT TOUTE
REPRÉSENTATION OU TOUTE GARANTIE, QUELLE QU’EN SOIT LA NATURE (EXPRESSE OU IMPLICITE) CONCERNANT CE
PRODUIT,CETTE TECHNOLOGIEOUCE DOCUMENT, LESQUELSSONT FOURNISEN L’ÉTAT. EN OUTRE,TOUTESLES CONDITIONS,
REPRÉSENTATIONS ET GARANTIES EXPRESSES OU TACITES, Y COMPRISNOTAMMENT TOUTE GARANTIEIMPLICITE RELATIVE À
LA QUALITÉ MARCHANDE, À L’APTITUDE À UNE UTILISATION PARTICULIÈRE OU À L’ABSENCE DE CONTREFAÇON, SONT
EXCLUES, DANS LA MESURE AUTORISÉE PAR LA LOI APPLICABLE. Sauf mention contraire expressément stipulée dans ce contrat, dans
la mesure autoriséepar la loiapplicable, en aucun cas Fujitsu Limited, Sun Microsystems,Inc. ou l’une de leurs filiales ne sauraient être tenues
responsables envers une quelconque partie tierce, sous quelque théorie juridique que ce soit, de tout manque à gagner ou de perte de profit,
de problèmes d’utilisation ou de perte de données, ou d’interruptions d’activités, ou de tout dommage indirect, spécial, secondaire ou
consécutif, même si ces entités ont été préalablement informées d’une telle éventualité.

LA DOCUMENTATION EST FOURNIE “EN L’ETAT” ET TOUTES AUTRES CONDITIONS, DECLARATIONS ET GARANTIES EXPRESSES
OU TACITES SONTFORMELLEMENT EXCLUES, DANSLAMESURE AUTORISEE PAR LALOI APPLICABLE,YCOMPRIS NOTAMMENT
TOUTE GARANTIE IMPLICITE RELATIVE A LA QUALITE MARCHANDE, A L’APTITUDE A UNE UTILISATION PARTICULIERE OU A
L’ABSENCE DE CONTREFACON.

Contents

Preface ix

1. System Overview 1–1

1.1 Product Overview 1–1

1.2 System Specifications 1–8

1.2.1 Environmental Specifications 1–10

1.2.2 Power Specifications 1–11

1.2.3 M8000 Server Components 1–12

1.2.4 M9000 Server Components (Base Cabinet Only) 1–14

1.2.5 M9000 Server Components (With an Expansion Cabinet) 1–16

1.2.6 Operator Panel Overview 1–17

1.3 Server Components 1–20

1.3.1 CPU Module 1–20

1.3.2 CPU/Memory Board Unit 1–21

1.3.3 I/O Unit 1–21

1.3.4 FAN Unit 1–22

1.3.5 Power Supply Unit 1–22

1.3.6 Crossbar Unit 1–22

1.3.7 Clock Control Unit 1–22

1.3.8 Operator Panel 1–22

v

1.3.9 XSCF Unit 1–23

1.3.10 Internal Drive Units 1–23

1.4 Component Mounting Conditions 1–24

1.5 Optional Products 1–24

1.5.1 Power Supply Options 1–25

1.5.2 External I/O Expansion Unit 1–26

1.5.3 SPARC Enterprise M9000 Server (Expansion Cabinet) Option 1–
26

1.6 Software Features 1–27

2. System Features 2–1

2.1 Hardware Configuration 2–1

2.1.1 CPU 2–1

2.1.1.1 SPARC64 VI and SPARC64 VII Processors and CPU

Operational Modes 2–2

2.1.2 Memory Subsystem 2–5

2.1.3 I/O Subsystem 2–5

2.1.4 System Bus 2–5

2.1.5 System Control 2–7

2.2 Partitioning 2–7

2.2.1 Features 2–7

2.2.2 Domain Hardware Requirements 2–8

2.2.3 Domain Configuration 2–10

2.3 Resource Management 2–12

2.3.1 Dynamic Reconfiguration 2–12

2.3.2 PCI Hot-plug 2–13

2.3.3 Capacity on Demand 2–13

2.3.4 Zones 2–13

2.4 RAS 2–14

2.4.1 Reliability 2–14

vi SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

2.4.2 Availability 2–15

2.4.3 Serviceability 2–16

3. About Software 3–1

3.1 Solaris OS Functions 3–1

3.1.1 Domain Management 3–2

3.1.2 PCI Hot-plug 3–2

3.2 XSCF Firmware Function 3–2

3.2.1 XSCF Features 3–2

3.2.1.1 Command Line-based User Interface (XSCF Shell) 3–3

3.2.1.2 Browser-Based User Interface (XSCF Web) 3–4

3.2.2 XSCF Functional Overview 3–4

3.2.2.1 System Management 3–4

3.2.2.2 Security Management 3–4

3.2.2.3 System Status Management 3–5

3.2.2.4 Error Detection and Management 3–5

Index Index–1

3.2.2.5 Remote System Control and Monitoring 3–5

3.2.2.6 Resource Management 3–5

3.2.2.7 Airflow Indicator 3–6

Contents vii

viii SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

Preface

The SPARC Enterprise™ M8000/M9000 Servers Overview Guide describes system
features, system configurations, hardware functions, and software functions of the
SPARC Enterprise M8000/M9000 servers.

This section explains:

■ “Glossary” on page ix

■ “Structure and Contents of This Manual” on page x

■ “SPARC Enterprise M8000/M9000 Servers Documentation” on page x

■ “Text Conventions” on page xiii

■ “Prompt Notations” on page xiii

■ “Syntax of the Command- Line Interface (CLI)” on page xiv

■ “Environment Requirements for Using This Product” on page xiv

■ “Conventions for Alert Messages” on page xv

■ “Notes on Safety” on page xvi

■ “Alert Labels” on page xix

■ “Product Handling” on page xxii

■ “Fujitsu Welcomes Your Comments” on page xxiv

Glossary

For the terms used in the “SPARC Enterprise M8000/M9000 Servers

Documentation” on page x, refer to the SPARC Enterprise

M3000/M4000/M5000/M8000/M9000 Servers Glossary.

ix

Structure and Contents of This Manual

This manual is organized as described below:

■ Chapter 1 System Overview

Provides an overview of the SPARC Enterprise SPARC Enterprise
M8000/M9000 servers.

■ Chapter 2 System Features

Describes system features and functions.

■ Chapter 3 About Software

Describes the software.

■ Index

Provides keywords and corresponding reference page numbers so that the
reader can easily search for items in this manual as necessary.

SPARC Enterprise M8000/M9000
Servers Documentation

The manuals listed below are provided for reference.

Book Titles Manual Codes

SPARC Enterprise M8000/M9000 Servers Site Planning Guide C120-H014

SPARC Enterprise Equipment Rack Mounting Guide C120-H016

SPARC Enterprise M8000/M9000 Servers Getting Started Guide C120-E323

SPARC Enterprise M8000/M9000 Servers Overview Guide C120-E324

Important Safety Information for Hardware Systems C120-E391

SPARC Enterprise M8000/M9000 Servers Safety and Compliance Guide C120-E326

External I/O Expansion Unit Safety and Compliance Guide C120-E457

SPARC Enterprise M8000/M9000 Servers Unpacking Guide C120-E327

SPARC Enterprise M8000/M9000 Servers Installation Guide C120-E328

SPARC Enterprise M8000/M9000 Servers Service Manual C120-E330

x SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

Book Titles Manual Codes

External I/O Expansion Unit Installation and Service Manual C120-E329

SPARC Enterprise M3000/M4000/M5000/M8000/M9000 Servers RCI
Build Procedure

SPARC Enterprise M3000/M4000/M5000/M8000/M9000 Servers
Administration Guide

SPARC Enterprise M3000/M4000/M5000/M8000/M9000 Servers XSCF
User’s Guide

SPARC Enterprise M3000/M4000/M5000/M8000/M9000 Servers XSCF
Reference Manual

SPARC Enterprise M4000/M5000/M8000/M9000 Servers Dynamic
Reconfiguration (DR) User’s Guide

SPARC Enterprise M4000/M5000/M8000/M9000 Servers Capacity on
Demand (COD) User’s Guide

SPARC Enterprise M3000/M4000/M5000/M8000/M9000 Servers RCI
User’s Guide

SPARC Enterprise M8000/M9000 Servers Product Notes Go to the Web

External I/O Expansion Unit Product Notes C120-E456

SPARC Enterprise M3000/M4000/M5000/M8000/M9000 Servers
Glossary

SPARC Enterprise/PRIMEQUEST Common Installation Planning
Manual

C120-E361

C120-E331

C120-E332

Go to the Web

C120-E335

C120-E336

C120-E360

C120-E514

C120-H007

1. Manuals on the Web

The latest versions of all the SPARC Enterprise Series manuals are available at the
following websites.

Global Site

http://www.fujitsu.com/sparcenterprise/manual/

Japanese Site

http://primeserver.fujitsu.com/sparcenterprise/manual/

Note – Product Notes are available on the website only. Please check for the most

recent update on your product.

2. Documentation CD

For the Documentation CD, please contact your local sales representative.

■ SPARC Enterprise M8000/M9000 Servers Documentation CD (C120-E364)

Preface xi

3. Manual on the Enhanced Support Facility x.x CD-ROM disk

■ Remote maintenance service

Book Title Manual Code

Enhanced Support Facility User's Guide for REMCS C112-B067

4. Manual (man page) provided in the system
XSCF man page

Note – The man page can be referenced on the XSCF Shell, and it provides the same

content as the SPARC Enterprise M3000/M4000/M5000/M8000/M9000 Servers XSCF
Reference Manual.

5. Sun Microsystems Software (for Solaris OS, etc.) Related Manuals

http://docs.sun.com

6. Information on Using the RCI function
The manual does not contain an explanation of the SPARC Enterprise

M3000/M4000/M5000/M8000/M9000 Servers RCI Build Procedure. For information
on using the RCI function, refer to the SPARC Enterprise

M3000/M4000/M5000/M8000/M9000 Servers RCI Build Procedure and the SPARC
Enterprise M3000/M4000/M5000/M8000/M9000 Servers RCI User’s Guide provided

on the website.

xii SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

Text Conventions

This manual uses the following fonts and symbols to express specific types of
information.

Fonts/symbols Meaning Example

AaBbCc123 What you type, when contrasted

with on-screen computer output.
This font represents the example of

command input in the frame.

AaBbCc123 The names of commands, files, and

directories; on-screen computer
output.

This font represents the example of
command input in the frame.

Italic Indicates the name of a reference

manual

" " Indicates names of chapters,

sections, items, buttons, or menus

XSCF> adduser jsmith

XSCF> showuser -P
User Name: jsmith
Privileges: useradm

auditadm

See the SPARC Enterprise
M3000/M4000/M5000/M8000/M
9000 Servers XSCF User’s Guide .

See Chapter 2, "System Features."

Prompt Notations

The following prompt notations are used in this manual.

Shell Prompt Notations

XSCF XSCF>

C shell machine-name%

C shell super user machine-name#

Bourne shell and Korn shell $

Bourne shell and Korn shell
super user

OpenBoot™ PROM ok

#

Preface xiii

Syntax of the Command- Line Interface
(CLI)

The command syntax is as follows:

■ A variable that requires input of a value must be enclosed in <>.

■ An optional element must be enclosed in [ ].

■ A group of options for an optional keyword must be enclosed in [ ] and delimited by |.

■ A group of options for a mandatory keyword must be enclosed in {} and delimited by |.

■ The command syntax is shown in a box.

Example:

XSCF> showuser -a

Environment Requirements for Using
This Product

This product is a computer that is intended to be used in a computer room.

xiv SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

Conventions for Alert Messages

This manual uses the following conventions to show alert messages, which are
intended to prevent injury to the user or bystanders as well as property damage, and
important messages that are useful to the user.

WARNING:
This indicates a hazardous situation that could result in death or serious personal
injury (potential hazard) if the user does not perform the procedure correctly.

CAUTION:
This indicates a hazardous situation that could result in minor or moderate personal
injury if the user does not perform the procedure correctly. This signal also indicates
that damage to the product or other property may occur if the user does not perform
the procedure correctly.

IMPORTANT:
This indicates information that could help the user to use the product more
effectively.

Alert Messages in the Text

An alert message in the text consists of a signal indicating an alert level followed by
an alert statement. Alert messages are indented to distinguish them from regular
text. Also, a space of one line precedes and follows an alert statement.

WARNING:
The tasks listed below for this product and optional product provided by Fujitsu
should be performed only by authorized service personnel.

The user must not perform these tasks. Incorrect operation of these tasks may cause
electric shock, injury, or fire.

■ Installation and reinstallation of all components

■ Removal of front, rear, or side covers

■ Mounting/unmounting of optional internal devices

■ Connecting/disconnecting of external interface cables

■ Maintenance (repair and regular diagnosis and maintenance)

Also, important alert messages are shown in “Important Alert Messages” on

page xvi.

Preface xv

Notes on Safety

Important Alert Messages

This manual provides the following important alert signals:

Caution – The WARNING signal indicates a dangerous situation could result in

death or serious injury if the user does not perform the procedure correctly.

Task Warning

Normal
operation

Electric shock, fire

Do not damage, break, or modify the power cords. Cord damage may
cause electric shock or fire.

xvi SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

Caution – The CAUTION signal indicates a hazardous situation could result in

minor or moderate personal injury if the user does not perform the procedure
correctly. This signal also indicates that damage to the product or other property
may occur if the user does not perform the procedure correctly.

Task Warning

Normal
operation

Equipment damage

Be sure to follow the precautions below when installing the main unit.
Otherwise, the equipment may be damaged.

• Do not block ventilation slits.

• Avoid installing the equipment in a place exposed to direct sunlight or
near equipment that becomes extremely hot.

• Avoid installing the equipment in a dusty place or a place directly
exposed to corrosive gas or salty air.

• Avoid installing the equipment in a place exposed to strong vibration.
Also, install the equipment on a level surface so that it is stable.

• The equipment can be grounded using shared grounding. However, the
grounding method varies with the building where it is installed.
Be sure to confirm the related standards to ground the equipment correctly.
When using shared grounding, ground the equipment ensuring that the
grounding resistance is not greater than 10

• Do not run any cable beneath any equipment. Also, prevent cables from
becoming taut. Never disconnect any power cord from the equipment
while power is being supplied to the equipment.

• Do not place anything on top of the main unit. Do not use the main unit
as a workspace.

• Avoid exposing the equipment to rapid changes in the ambient
temperature, such as a rapid increase during transport in winter. A
rapid increase in the ambient temperature causes moisture to condense
in the equipment. Use the equipment only after the difference between
its temperature and the ambient temperature is negligible.

• Avoid installing the equipment near a copy machine, air conditioner, or
welding machine, which is noisy.

• Take preventive action to minimize static electricity at the installation
location. Note that static electricity is easily generated in some carpets
and can cause the equipment to malfunction.

• Confirm that the power supply voltage and frequency during operation
match the rated values indicated on the equipment.

• Do not insert any object into an opening in the equipment. Components
inside the equipment use high voltage. Conductive foreign matter, such
as a metal object, inserted into the equipment, may cause a short circuit
between components, resulting in fire, electric shock, or equipment
damage.

• For maintenance of the equipment, contact your authorized service
personnel.

Ω.

Preface xvii

Task Warning

Normal
operation

Data destruction

Confirm the items listed below before turning off the power. Otherwise,
data may be destroyed.

• All applications have completed processing.

• No user is using the equipment.

• When the main unit power is turned off, the POWER LED on the
operation panel is turned off. Be sure to confirm that the POWER LED
is off before turning off the main power (uninterruptible power supply
[UPS], power distribution box, main line switch, etc.).

If necessary, back up files before turning off the system power.

Data destruction

Do not forcibly stop a domain that is operating normally. Otherwise, data
may be destroyed.

Data destruction

Do not disconnect the power cord from the AC power input while power
is being supplied. Otherwise, data stored on hard disk units may be
destroyed.

xviii SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

Alert Labels

The labels shown below are affixed on this product.

Caution – Do not peel off the labels.

SPARC Enterprise M8000 Server (Front View)

Preface xix

SPARC Enterprise M9000 Server (Front View)

xx SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

SPARC Enterprise M9000 Server (Rear View)

Preface xxi

SPARC Enterprise M9000 Server with Expansion Cabinet (Rear View)

Product Handling

Maintenance

Caution – Certain tasks in this manual should only be performed by a certified

service engineer. User must not perform these tasks. Incorrect operation of these
tasks may cause electric shock, injury, or fire.

■ Installation and reinstallation of all components, and initial settings

■ Removal of front, rear, or side covers

■ Mounting/de-mounting of optional internal devices

xxii SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

■ Plugging or unplugging of external interface cards

■ Maintenance and inspections (repairing, and regular diagnosis and maintenance)

Caution – The following tasks regarding this product and the optional products

provided from Fujitsu should only be performed by a certified service engineer.
Users must not perform these tasks. Incorrect operation of these tasks may cause
malfunction.

■ Unpacking optional adapters and such packages delivered to the users

■ Plugging or unplugging of external interface cards

Remodeling/Rebuilding

Caution – Any modification and/or recycling of this product and its components

may be carried out only by a certified service engineer and must not be done by the
customer under any circumstances. Otherwise, electric shock, injury or fire may
result.

Emission of Laser Beam (Invisible)

Caution – The main unit and high-speed optical interconnect cabinet contain

modules that generate invisible laser radiation. Laser beams are generated while the
equipment is operating, even if an optical cable is disconnected or a cover is
removed. Do not look at any light-emitting part directly or through an optical
apparatus (e.g., magnifying glass, microscope).

Preface xxiii

Fujitsu Welcomes Your Comments

If you have any comments or requests regarding this document, or if you find any
unclear statements in the document, please state your points specifically on the form
at the following URL.

For Users in U.S.A., Canada, and Mexico:

http://www.computers.us.fujitsu.com/www/support_servers.shtml?support
/servers

For Users in Other Countries:

SPARC Enterprise contact

http://www.fujitsu.com/global/contact/computing/sparce_index.html

xxiv SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

CHAPTER

1

System Overview

This chapter provides an overview of features, specifications, and configurations of
the SPARC Enterprise

■ Section 1.1, “Product Overview” on page 1-1

■ Section 1.2, “System Specifications” on page 1-8

■ Section 1.3, “Server Components” on page 1-20

■ Section 1.4, “Component Mounting Conditions” on page 1-24

■ Section 1.5, “Optional Products” on page 1-24

■ Section 1.6, “Software Features” on page 1-27

™

M8000/M9000 servers.

1.1 Product Overview

SPARC Enterprise M8000/M9000 servers have been developed as UNIX servers
using a symmetric multi-processing (SMP) architecture. Each of these systems
merges mainframe technologies for high reliability, and the associated know-how
accumulated over time, with the high-speed technologies of super computers and
the openness of UNIX server development.

If a problem occurs during operation, the errors causing them can be corrected or
isolated without stopping the system. This feature minimizes problems in many
cases, thereby improving job continuity.

Each of the SPARC Enterprise M8000/M9000 servers contains one or more
SPARC64™ VI/SPARC64™ VII CPUs. They can operate as multiple servers that
permit flexible use of resources, including more efficient execution of job operations.
In the SPARC Enterprise M8000/M9000 servers, the SPARC64 VI processor and the
SPARC64 VII processor can be mounted in combination.

1-1

Each server consists of a cabinet containing various mounted components, a front
door, rear door, and side covers as parts of the server structure. An operator panel is
mounted on the front door and is always accessible. Take special care in handling
and storing the dedicated key that is provided for the front door and the operator
panel.

FIGURE 1-1 through FIGURE 1-3 show exterior views of the servers.

SPARC Enterprise M8000 Server Appearance

FIGURE 1-1 SPARC Enterprise M8000 Server (Front View)

1-2 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

SPARC Enterprise M9000 Server (Base Cabinet Only) Appearance

FIGURE 1-2 SPARC Enterprise M9000 Server (Base Cabinet Only)

Chapter 1 System Overview 1-3

SPARC Enterprise M9000 Server (With an Expansion Cabinet)
Appearance

The expansion cabinet is an M9000 option connected to the M9000 (type for the base
cabinet only).

FIGURE 1-3 SPARC Enterprise M9000 Server (With an Expansion Cabinet)

1-4 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

SPARC Enterprise M8000/M9000 servers have the following features:

■ Multicore SPARC64 VI/SPARC64 VII gigahertz processors

These processors provide superior performance, due to their high scalability
allowing expansion to up to 64 dual-core CPU modules, and technologies
enabling high-speed arithmetic operations and data transfers.

Reliability and availability are enhanced with Error Checking and Correction
(ECC) data protection and instruction retry.

As faster and higher-performing CPU modules become available, they can be
added to or replace existing installed CPU modules to further improve
performance.

The system uses symmetric multiple-processing (SMP), so each CPU can access
any part of system memory regardless of its mounting location. Adding more
CPUs does not affect memory access to any of the installed CPUs.

■ High-speed crossbar-type system bus

The high-speed crossbar-type system bus provides high-speed wide-band data
transfer.

■ ECC memory

ECC functionality protects data on all system buses and in memory, so that any
errors in data are automatically corrected. In addition to ECC memory, Chipkill
memory protection is supported.

■ PCIe is mounted as I/O buses

PCIe, with a maximum bus width of eight lanes is used for the inter-connect bus
with the I/O device.

■ An optional External I/O Expansion Unit enables I/O slot expansion in the

system.
Connect an External I/O Expansion Unit to add more PCIe and PCI-X slots to the

server.
An External I/O Expansion Unit is connected by a cable to a link card plugged

into a PCIe slot in an I/O Unit.

■ The main components, Power Supply Units, and FAN Units can be configured to

be redundant
Redundant configurations can be used for the main components, such as a Power

Supply Unit, FAN Unit, hard disk drive, and PCI card. Implementation of
redundant configurations enables operation to continue without interruption
even if one of the units making up part of the system fails.

Chapter 1 System Overview 1-5

■ The main components, Power Supply Units, and FAN Units support active (hot)

replacement/addition
Component replacement and addition during system operation supported for the

main components, such as a Power Supply Unit, FAN Unit, hard disk drive,
System Control Facility (board), system board, and PCI card, with some
exceptions.

Dynamic reconfiguration (DR) is used for active replacement and addition of
CMU and IOU configuring the system board.

PCI hot-plug (PHP) function enables replacement and addition of PCI Cards
while the system is running.

■ Automatic reboot on failure

If a failure occurs, the faulty component is automatically isolated from the system,
and the system is rebooted. If 1-bit errors occur frequently in the cache memory
configuring a CPU, the faulty memory can be dynamically isolated without
rebooting the Solaris

™

Operating System. This type of graceful degradation
function enables the operation of the other resources to continue without
interruption, and also provides high fault-tolerance in case of failure.

■ Uninterruptible Power Supply (UPS) controller

For measures against commercial power failure, the server is equipped with UPS
controller (UPC) ports. Using a UPS enables stable power supply to the system
when a power failure or an extensive power interruption occurs.

■ eXtended System Control Facility (XSCF)

This product has a built-in service processor (called the eXtended System Control
Facility (XSCF)), which monitors the system temperature, the hardware status of
the Power Supply Unit and FAN Unit, and the operating status of domains.

You can configure the system to selectively degrade a faulty component for
operation if supply failure is detected.

Scheduling is supported to enable automatic power-on and power-off of the
SPARC Enterprise system according to the specified operation schedule.

The console of each domain can be controlled from the XSCF via a network.
A browser-based user interface (BUI) and the Command- Line Interface (CLI)

facilitate operations for making configuration changes and status monitoring in
the system.

Note – A console display terminal is required for console control. Prepare it before

installation. The devices that can be used as the terminal are listed below.

■ PC

■ Workstation

■ ASCII terminal

1-6 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

■ Terminal server (or a touch panel connected to a terminal server)

Note – For the console connection method, see the SPARC Enterprise M8000/M9000

Servers Installation Guide.

■ Partitioning function

One high-end server can be divided into multiple areas, or domains, for more
effective scalability. Each domain manages resources in linkage with the XSCF. A
domain may consist of optimized resources depending on its intended use,
enabling more efficient system configurations.

Dynamic Reconfiguration (DR) enables adding, deleting, and relocating resources
of domains without stopping processing in the domain. This enables dynamic
reconfiguration of resources without stopping a job, even when the job load
increases suddenly or when a faulty component is replaced.
For details on domain functions, see the SPARC Enterprise

M3000/M4000/M5000/M8000/M9000 Servers Administration Guide.
For details of the DR function, see the SPARC Enterprise
M4000/M5000/M8000/M9000 Servers Dynamic Reconfiguration (DR) User’s Guide.

■ The Solaris OS (Solaris 10 or later) is supported.

With an added function for error prediction and self-recovery by the system
(Predictive Self-Healing) and enhanced process privilege management and
network functions, the Solaris OS sets new standards for performance, efficiency,
availability, and security.

■ Capacity on Demand (COD)

Capacity on Demand (COD) enables instantaneous increases in the CPU capacity
according to increases in the job load. Spare CPUs that are mounted in advance
can be used immediately upon purchase of a corresponding number of CPU
licenses, thereby accommodating such needs for increased processing capacity.
For details, see the SPARC Enterprise M3000/M4000/M5000/M8000/M9000 Servers

Administration Guide.

Chapter 1 System Overview 1-7

1.2 System Specifications

This section describes the specifications and the environmental conditions of both
high-end servers, shows their appearance, and provides an overview of the operator
panel.

Note – Contact your sales representative for tape drive unit options on SPARC

Enterprise M8000/M9000 servers.

TABLE 1-1 Main Unit Specifications

Item M8000

Type Floor-stand type

‡

CPU Type SPARC64 VI: 2 cores/1 CPU modules

SPARC64 VI compatible mode

Number of
CPUs

32 cores (maximum 16
CPU modules)

Type SPARC64 VII: 4 cores/1 CPU modules

SPARC64 VI compatible mode/SPARC64 VII enhanced mode

Main storage
(memory
module)

Number of
CPUs

Maximum
memory size

Error

64 cores (maximum 16
CPU modules)

512 MB

**

Error Checking and Correction (ECC)
checking
function

PCI slot built into SPARC
Enterprise (PCI Express)

External I/O Expansion Unit

Maximum 32 slots Maximum 64 slots Maximum 128 slots

*

8 units (16 boats) 16 units (32 boats) 16 units (32 boats)

(maximum number of
connections)

Maximum number of slots,

112 slots 224 slots 288 slots

with I/O boats mounted

Hard disk drive

†

16 slots 32 slots 64 slots

Base cabinet only

64 cores (maximum 32
CPU modules)

128 cores (maximum 32
CPU modules)

**

1TB

M9000

Base cabinet + expansion
cabinet

128 cores (maximum 64
CPU modules)

256 cores (maximum 64
CPU modules)

**

2TB

1-8 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

TABLE 1-1 Main Unit Specifications (Continued)

M9000

Item M8000

CD-RW/DVD-RW Drive

1 drive 2 drives

Base cabinet only

Base cabinet + expansion
cabinet

Unit

Tape Drive Unit 1 drive can be mounted (option) 2 drives can be mounted

(option)

FAN Unit 4 units (type A)

16 units (type A) 32 units (type A)

8 units (type B)

Power Supply Unit

9 units 15 units 30 units
(Maximum number of
mounted units) (single phase,
one system)

Redundant configuration Power Supply Unit, FAN Unit, XSCF, power system (dual power feed option),

and clock supply system

Components that can be
active replacement

CPU/Memory Board Unit, I/O Unit, XSCF Unit, hard disk drive,

Link Card, CD-RW/DVD-RW Drive Unit, Tape Drive Unit, PCI cassette,

Power Supply Unit, FAN Unit, DC-DC Converter

Components that can be hot
replacement

CPU/Memory Board Unit, I/O Unit, XSCF Unit, Link Card, CD-RW/

DVD-RW Drive Unit, Tape Drive Unit, PCI cassette, Power Supply Unit,

FAN Unit, DC-DC Converter

System control interface LAN, serial, UPS (Uninterruptible Power Supply) interface, Remote Cabinet

Interface (RCI), and USB

††

Number of domains 16 24 24

Operating environment Solaris OS

‡‡

Architecture Platform group: sun4u

Platform name: SUNW, SPARC-Enterprise

Outside
dimensions

Width [mm] 750 850 1674

Depth [mm] 1260 1260 1260

Height [mm] 1800 1800 1800

Weight [kg] 700 940 1880

* Up to eight lanes of PCIe bus are connected to each slot.
† A built-in IOU Onboard Device Card_A (IOUA) is required for using hard disk drive.

Active replacement of IOUA is not possible.
‡ The upper part of the SPARC Enterprise M8000 server cabinet has a 12 rack units (RU) space.
**This is the maximum capacity when 4-GB dual inline memory modules (DIMM) are installed.

Chapter 1 System Overview 1-9

††This interface is only used for maintenance by authorized service personnel. It does not support except the

maintenance-purpose USB devices.

‡‡For the latest information on the operating system, visit our website, or contact your sales representative.

For up-to-date URL information, see the website information about the messages described in the reference
manuals noted in the Preface.

1.2.1 Environmental Specifications

TABLE 1-2 Environmental Specifications

Operating Range Non-Operating Range Optimum

Ambient
temperature

Relative
humidity

Altitude
restriction

Temperature
conditions

* There is no condensation regardless of the temperature and humidity.
† All altitudes are above sea level.

5 ˚C to 32 ˚C (41 ˚F to 89.6 ˚F) Unpacked:

0˚Cto50˚C
(32 ˚F to 122 ˚F)

Packed:

-20 ˚C to 60 ˚C
(-4˚F to 140 ˚F)

20% RH to 80% RH to 93% RH 45% RH to 50%

*

3,000 m (10,000 ft) 12,000 m (40, 000 ft)

†

5 ˚C to 32 ˚C (41 ˚F to 89.6 ˚F) at an
installation altitude ranging from 0 to less
than 1500 m (4921 ft) above sea level

5 ˚C to 30 ˚C (41 ˚F to 86 ˚F) at an
installation altitude ranging from 1500 m
(4921 ft) to less than 2000 m (6562 ft)
above sea level

5 ˚C to 28 ˚C (41 ˚F to 82.4 ˚F) at an
installation altitude ranging from 2000 m
(6562 ft) to less than 2500 m (8202 ft)
above sea level

5 ˚C to 26 ˚C (41 ˚F to 78.8 ˚F) at an
installation altitude ranging from 2500 m
(8202 ft) to 3000 m (9843 ft) above sea
level

21 ˚C to 23 ˚C
(70 ˚F to 74 ˚F)

RH

1-10 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

1.2.2 Power Specifications

Two power input modes are available; single-phase power feed and three-phase
power input.

To use a three-phase power source, a three-phase power feed option and a power
supply cabinet for mounting the option are required. The three-phase power feed
has two connection options: a star connection that connects a neutral line and each
phase, and a delta connection that connects each phase.

For details, see the SPARC Enterprise M8000/M9000 Servers Site Planning Guide.

TABLE 1-3 shows samples of power consumption of specific configurations and

program load The power consumption of the system varies depending on
configuration of the system, characteristics of your running programs and ambient
temperature.

TABLE 1-3 Power consumption Examples

Item M8000 M9000

Base cabinet only

Ambient temperature 25 ˚C 25 ˚C 25 ˚C

*

Configuration

Power consumption

* 17Watt PCIe cards are installed.
† These powerconsumptionsare justsamples. You cansee higherpower consumption valuesdepending oncharacteristics of yourwork-

load.

CMU :

2.52GHz CPU x 4,
4GB DIMM x 32

IOU :
73GB HDD x 4,

PCIe card x 8

†

48 16

48 16

7.0 kW 15.8 kW 31.6 kW

Base cabinet +
expansion cabinet

Chapter 1 System Overview 1-11

1.2.3 M8000 Server Components

FIGURE 1-4 shows the front of the SPARC Enterprise M8000 server with a power

cabinet connected to it, and
component names are shown in each figure.

The dual power feed option and three-phase power feed option can be mounted in
the power cabinet. One power cabinet is connected to the M8000.

FIGURE 1-4 M8000 Server and Power Cabinet Front View

Power Cabinet

Power Supply Unit

DC-DC Converter
DC-DC Converter

FIGURE 1-5 shows the server rear view. System

19-inch Rack Space

Power Supply Unit

CPU Memory Board Unit

XSCF Unit

AC Section

1-12 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

Tape Drive Unit

CD-RW/DVD-RW Drive Unit

CPU Memory Board Unit

FAN Unit

FIGURE 1-5 M8000 Server and Power Cabinet Rear View

FAN Unit

Power Cabinet

AC Section

Power Supply Unit

I/O Unit

AC Section

Chapter 1 System Overview 1-13

1.2.4 M9000 Server Components (Base Cabinet Only)

FIGURE 1-6 shows the front of the SPARC Enterprise M9000 server (base cabinet only)

with a power cabinet connected to it, and
The names of components of the system are shown in each figure.
One power cabinet is connected to the M9000 (base cabinet only).

FIGURE 1-6 M9000 Server (Base Cabinet Only) and Power Cabinet Front View

Power Cabinet

FIGURE 1-7 shows the rear of the server.

FAN Unit

Power Supply Unit

AC Section

Power Supply Unit

Tape Drive Unit

AC Section *

Crossbar Unit

Clock Unit

XSFC Unit

I/O Unit

CD-RW/DVD-RW

Drive Unit

* Single-phase

1-14 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

FIGURE 1-7 M9000 Server (Base Cabinet Only) and Power Cabinet Rear View

FAN Unit

CPU Memory Board Unit

I/O Unit

Power Cabinet

Power Supply Unit

AC Section *

* Three-phase

Chapter 1 System Overview 1-15

1.2.5 M9000 Server Components (With an Expansion Cabinet)

FIGURE 1-8 and FIGURE 1-9 show the front and rear views of the SPARC Enterprise

M9000 server with an expansion cabinet and power cabinets connected. One power
cabinet is connected to each of the SPARC Enterprise M9000 server base cabinet and
expansion cabinet. The names of the components of the server are identified in each
figure.

FIGURE 1-8 M9000 Server (With an Expansion Cabinet) and Power Cabinet Front View

Power Cabinet

Power Supply Unit

Power Supply Unit

XSCF Unit

Tape Drive Unit

AC Section *

Base Cabinet

Power Cabinet

FAN Unit

AC Section

Crossbar Unit

Clock Unit

I/O Unit

CD-RW/DVD-RW

Drive Unit

* Single-phase

Expansion Cabinet

1-16 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

FIGURE 1-9 M9000 Server (With an Expansion Cabinet) and Power Cabinet Rear View

Power Cabinet

FAN Unit

CPU Memory Board
Unit

I/O Unit

Expansion Cabinet

Base Cabinet

1.2.6 Operator Panel Overview

The operator panel has LEDs indicating different states of the M8000 and M9000
servers, a power switch for power control, and a mode switch for setting the
operation mode.

Power Cabinet

Power Supply Unit

CPU Memory Board
Unit

I/O Unit

AC Section *

* Three-phase

For details about the operator panel, see the SPARC Enterprise M8000/M9000 Servers
Service Manual.

The following figure shows the operator panel, and its LEDs and switches are
described below.

Chapter 1 System Overview 1-17

Operator Panel Appearance

FIGURE 1-10 shows the operator panel.

FIGURE 1-10 Operator Panel

Locked

Service

POWER (LED)

POWER switchCHECK (LED)STANDBY (LED)

MODE switch

Operator Panel LEDs

TABLE 1-4 lists the operating states indicated by the LEDs on the operator panel.

TABLE 1-4 Operator Panel LEDs

LEDs Name Light color Description of function and operating state

POWER Green Indicates whether the main unit power is on.

If this LED is on, the power is on.
If this LED is blinking, the power-off sequence is in

progress.

STANDBY Green Indicates the standby state of the main unit.

If this LED is on, the power can be turned on.

CHECK Amber Indicates the main unit operating status. (This is used to

indicate a maintenance target, or it indicates that the unit
cannot be started.)

If this LED is on, a system error has been detected.

1-18 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

Operator Panel Switches

The switches on the operator panel include the mode switch for setting the operation
mode and the POWER switch for turning on and off the SPARC Enterprise server. To
switch between system operation mode and maintenance mode, insert the dedicated
key of the high-end server and change the mode switch setting.

TABLE 1-5 lists functions of the switches on the operator panel.

TABLE 1-5 Operator Panel Switches

Switch Name Function

POWER switch Controls the main unit power.

MODE switch Selects between maintenance and normal operation. Use the

dedicated key managed by the customer to switch between
normal and maintenance modes.

Locked This mode is set for normal operation.

Service This mode is set for maintenance.

Chapter 1 System Overview 1-19

1.3 Server Components

This section describes the components of both high-end servers.
For details on each, see the SPARC Enterprise M8000/M9000 Servers Service Manual.

■ CPU Module

■ CPU/Memory Board Unit

■ I/O Unit

■ FAN Unit

■ Power Supply Unit

■ Crossbar Unit

■ Clock Control Unit

■ Operator Panel

■ XSCF Unit

■ Internal Drive Units

■ Hard Disk Drive

■ CD-RW/DVD-RW Drive Unit/Tape Drive Unit

1.3.1 CPU Module

The CPU Module (CPUM) contains a SPARC64 VI/SPARC64 VII CPU and a DC-DC
converter (DDC). Up to four CPUMs can be mounted on a CPU/Memory Board
Unit.

The CPUM has the following features:

■ The CPUM contains a SPARC64 VI/SPARC64 VII, a high-performance multicore

CPU that uses the latest LSI process.

■ If an unforeseen fault is detected, the SPARC64 VI/SPARC64 VII CPU enables

operation to continue without interruption by using an automatic recovery
function, automatic retry function, or automatic degradation function, depending
on how the system is configured.

■ A redundant DDC configuration enables continuous operation even if a DDC

fails.

1-20 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

1.3.2 CPU/Memory Board Unit

The CPU/Memory Board Unit (CMU) contains CPUMs, memory modules, and a
DDC. The CMU with an I/O Unit can be combined to construct one or more
domains.

The CMU has the following features:

■ Contains an interconnect LSI module that uses the latest LSI process.

■ Uses Double Data Rate (DDR)II DIMM memory.

■ Supports the DR function that enables hot maintenance and replacement of CMUs

during system operation, and enables addition and deletion of active CMUs
during system operation.

■ A redundant DDC configuration enables continuous operation even if a DDC

fails.

1.3.3 I/O Unit

The I/O Unit (IOU) consists of a PCIe bridge control LSI module, a printed circuit
board containing a DDC, a hard disk drive (HDD), PCIe slots, and PCI cassettes for
the IOU. The IOU and the CMU can be combined to configure a server.

The IOU has the following features:

■ It contains eight PCIe slots.

■ The IOU Onboard Device Card_A (IOUA) can be used to connect the in-cabinet

Drive Unit (2.5-inch SAS interface), the in-cabinet CD-RW/DVD-RW Drive Unit,
and the Tape Drive Unit. The LAN port (1000BASE-T/100Base-TX/10Base-T)
mounted on the card can be used.

■ It supports PCI hot-plug for External I/O Expansion Units and PCIe slots.

■ Link Card can be used to connect IOU to External I/O Expansion Unit.

■ It supports the DR function that enables active maintenance and replacement of

IOUs during system operation and enables addition and deletion of active IOUs
during system operation.

■ Insert the PCI Card into one of the supplied cassettes before inserting it into a

built-in PCIe slot in the IOU. A PCI card whose length is up to 177.8 mm (short
size) can be mounted in a slot.

■ A redundant DDC configuration enables continuous operation even if a DDC

fails.

Chapter 1 System Overview 1-21

1.3.4 FAN Unit

The FAN Unit is used to cool the server. There are two types of FAN Units, with the
following features:

■ A redundant fan configuration enables continuous system operation even if a fan

fails during system operation.

■ Active (hot) system maintenance or replacement of a faulty FAN Unit can be

performed during system operation.

1.3.5 Power Supply Unit

The Power Supply Unit (PSU) feeds power to each unit, and has the following
features:

■ A redundant configuration enables the system operation to continue without

interruption even if a Power Supply Unit fails during system operation.

■ Active (hot) system maintenance or replacement of a faulty Power Supply Unit

can be performed during system operation.

1.3.6 Crossbar Unit

The crossbar unit (XBU) consists of crossbar switches that logically connect CMUs
and IOUs.

The XBU has redundant bus routes. If one route fails, the system can be restarted
through the other route to continue operation.

1.3.7 Clock Control Unit

The clock control unit (CLKU) contains an LSI module used for the clock.

The CLKU has redundant clock supply routes. If one route fails, the system can be
restarted through the other route to continue operation.

1.3.8 Operator Panel

The operator panel can be used to turn on and off the server power, switch between
operation modes, and display system status information.

1-22 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

The operations of switches on the operator panel can be limited by switching the
operation mode with the dedicated key supplied for the panel.

1.3.9 XSCF Unit

The XSCF unit (XSCFU) includes a dedicated processor, which operates
independently from the main unit processors. The XSCFU in the servers adopts a
duplicated configuration to increase fault tolerance.

The XSCFU is equipped with hardware interfaces for network connections to remote
devices such as personal computers and workstations. A remote device can be
connected via a network to the XSCF to control startup, settings, and operation
management of the system.

The XSCFU provides the following hardware interfaces for network connections:

■ Serial port

■ LAN ports (10/100BASE-T/100Base-TX)

The XSCF can be accessed through network connections using these interfaces. The
commandline interface (XSCF Shell) and browser-based user interface (XSCF Web
pages) provided by the XSCF enable operation and management of the servers.

For details, see the SPARC Enterprise M3000/M4000/M5000/M8000/M9000 Servers
XSCF Reference Manual.

1.3.10 Internal Drive Units

The SPARC Enterprise M8000/M9000 servers contain the following in-cabinet drive
units. These allow active replacement or addition:

Hard Disk Drive

The hard disk drive is a 2.5-inch hard disk drive with a serial attached SCSI (SAS)
interface. It can be mounted in an IOU.

Chapter 1 System Overview 1-23

CD-RW/DVD-RW Drive Unit/Tape Drive Unit

The CD-RW/DVD-RW Drive Unit cannot be directly shared by multiple domains in
a server. However, if the multiple domains are connected to one another through a
LAN and a certain function of the Solaris OS is used, the CD-RW/DVD-RW Drive
Unit can be shared by the domains. Adequate consideration of security is necessary
for LAN connections between domains.

Note – Contact your sales representative for tape drive unit options on SPARC

Enterprise M8000/M9000 servers.

1.4 Component Mounting Conditions

■ CPUMs can be added in units of two modules.

■ Dual inline memory module (DIMMs) can be added in units of 16 modules.

■ If you add an IOU, a CMU must be mounted for the slot with the same slot

number.

■ IOU Onboard Device Card_A (IOUA) can be mounted in PCIe Slot #0, #2, #4, and

#6 in the IOU.

■ External I/O Expansion Unit connection cards can be mounted in PCIe Slot #1, #3,

#5, and #7 in the IOU.

1.5 Optional Products

The following products are the main options available for the SPARC Enterprise
M8000/M9000 servers.

■ Power Supply Options

■ External I/O Expansion Unit

■ SPARC Enterprise M9000 Server (Expansion Cabinet) Option

For information about other optional products, visit our website.

1-24 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

1.5.1 Power Supply Options

The power cabinet and the rack-mountable dual power feed option for the SPARC
Enterprise M8000 server are offered as power supply options.

The power cabinet enables dual power feed or three-phase power feed.

The rack-mountable dual power feed option for the SPARC Enterprise M8000 server
receives power from two external AC power sources that are independent of each
other, and duplicates the input power system.

To use a single-phase dual power feed configuration for the SPARC Enterprise
M8000 server, mount the rack-mountable dual power feed option in the rack space
itself. This requires a rack space with a height of 6 RUs in the cabinet. For the SPARC
Enterprise M9000 server, you must add the power cabinet.

For three-phase power feed in either server, an additional power cabinet is required.
Install one power cabinet for each SPARC Enterprise M8000/M9000 server.

For details, see the SPARC Enterprise M8000/M9000 Servers Site Planning Guide.

Note – A three-phase power feed option can be installed only at the factory before

shipment. A single-phase power feed cannot be changed to a three-phase power
feed, or vice versa, after shipment from the factory.

TABLE 1-6 lists specifications of the power cabinet.

TABLE 1-6 Specifications of the Power Cabinet and M8000/M9000 Dual Power Feed Option

Item

Outside dimensions Width [mm] 489

Depth [mm] 1244

Height [mm] 1800

Weight [kg] 350

Input power:
Single-phase power
input

Voltage [V] AC200 to 240 10%

Number of phases Single phase

Frequency [Hz] 50/60 +2%, -4%

Rack-mountable Dual

Power Feed options Power Cabinet

317

1003

278(6U)

75

Note – For specifications of the three-phase power feed option, see the SPARC

Enterprise M8000/M9000 Servers Site Planning Guide .

Chapter 1 System Overview 1-25

1.5.2 External I/O Expansion Unit

The External I/O Expansion Unit is an optional product used to add PCI slots. The
External I/O Expansion Unit has a height of four RUs (rack units), about 18 cm, in a
19-inch rack.

The External I/O Expansion Unit can accommodate up to two I/O Boats by using
either six PCIe slots or six PCI-X slots.

■ PCIe slots in each I/O Boat: short size to long size (to 312 mm)

■ PCI-X slots in each I/O Boat: short size to long size (to 312 mm)

Also, active addition and replacement is enabled for all slots in the External I/O
Expansion Unit.

For details, see the External I/O Expansion Unit Installation and Service Manual .

FIGURE 1-11 External I/O Expansion Unit

1.5.3 SPARC Enterprise M9000 Server (Expansion Cabinet) Option

A SPARC Enterprise M9000 server (base cabinet) configuration can contain up to 32
CPU Modules (64 cores for SPARC64 VI processors, 128 cores for SPARC64 VII
processors), up to 1 TB of memory, and up to 224 PCI slots. A configuration
containing more components than described above would require the expansion
cabinet option of the SPARC Enterprise M9000 server.

1-26 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

A configuration with the SPARC Enterprise M9000 server (expansion cabinet) can
contain up to 64 CPU modules (128 cores for SPARC64 VI processors, 256 cores for
SPARC64 VII processors), up to 2 TB of memory, and up to 288 PCI slots.

For information about connecting the SPARC Enterprise M9000 server (expansion
cabinet) and the SPARC Enterprise M9000 server (base cabinet), see the SPARC

Enterprise M8000/M9000 Servers Installation Guide.

1.6 Software Features

The SPARC Enterprise M8000/M9000 servers use XSCF for system administration
and monitoring.

The Solaris OS can be installed as the operating environment used in a domain.

For details, see Chapter 3.

Chapter 1 System Overview 1-27

1-28 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

CHAPTER

2

System Features

This chapter explains the following technical aspects, including features and
structures.

■ Section 2.1, “Hardware Configuration” on page 2-1

■ Section 2.2, “Partitioning” on page 2-7

■ Section 2.3, “Resource Management” on page 2-12

■ Section 2.4, “RAS” on page 2-14

2.1 Hardware Configuration

This section explains the hardware configuration, which includes the following
items:

■ CPU

■ Memory Subsystem

■ I/O Subsystem

■ System Bus

■ System Control

2.1.1 CPU

The SPARC Enterprise M8000/M9000 servers use the SPARC64 VI/SPARC64 VII
CPU, a proprietary high-performance multi-core processor. On-chip L2 cache
memory minimizes memory latency.

An instruction retry function has been implemented so that operation can be
continued by retrying an instruction for which an error has been detected.

2-1

The SPARC Enterprise M8000 server, SPARC Enterprise M9000 server, and the
SPARC Enterprise M9000 server with expansion cabinet take advantage of system
scalability by supporting up to 16, 32, or up to 64 CPU modules, respectively.

CPU modules running at different clock frequencies can be used in a single system.

The latest CPUs can therefore be installed when improved processing performance is
required.

2.1.1.1 SPARC64 VI and SPARC64 VII Processors and CPU Operational Modes

Note – This section applies only to SPARC Enterprise M8000/M9000 servers that

run or will run SPARC64 VII processors.

The SPARC Enterprise M8000/M9000 servers support system boards that contain
SPARC64 VI processors, SPARC64 VII processors, or a mix of the two processor
types.

Note – The SPARC64 VII processors are supported only on SPARC Enterprise

M8000/M9000 servers that run certain versions of XCP firmware (beginning with
XCP 1070) and Solaris software. For specific information about these minimum
software and firmware requirements, see the latest version of the Product Notes (no
earlier than the XCP 1070 edition) for your server.

2-2 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

FIGURE 2-1 shows an example of a mixed configuration of SPARC64 VI and SPARC64

VII processors.

FIGURE 2-1 CPUs on CPU/Memory Board Unit (CMU) and Domain Configuration

A mix of SPARC64 VI and SPARC64 VII processors can be mounted on a single
CMU, as shown in CMU#2 and CMU#3 in

FIGURE 2-1. And a single domain can be

configured with a mix of these SPARC64 processors, as shown in Domain 2 in

FIGURE 2-1.

Chapter 2 System Features 2-3

CPU Operational Modes

A SPARC Enterprise M8000/M9000 server domain runs in one of the following CPU
operational modes:

■ SPARC64 VI Compatible Mode – All processors in the domain – which can be

SPARC64 VI processors, SPARC64 VII processors, or any combination of them –
behave like and are treated by the OS as SPARC64 VI processors. The new
capabilities of SPARC64 VII processors are not available in this mode. Domains 1
and 2 in

■ SPARC64 VII Enhanced Mode – All boards in the domain must contain only

SPARC64 VII processors. In this mode, the server utilizes the new features of
these processors. Domain 0 in

DR operations work normally on domains running in SPARC64 VI Compatible
Mode. You can use DR to add, delete or move boards with either or both processor
types, which are all treated as if they are SPARC64 VI processors.

DR also operates normally on domains running in SPARC64 VII Enhanced Mode,
with one exception: You cannot use DR to add or move into the domain a system
board that contains any SPARC64 VI processors. To add a SPARC64 VI processor you
must power off the domain, change it to SPARC64 VI Compatible Mode, then reboot
the domain.

For the settings of the CPU operational mode, see the SPARC Enterprise

M3000/M4000/M5000/M8000/M9000 Servers XSCF User’s Guide or the SPARC
Enterprise M3000/M4000/M5000/M8000/M9000 Servers XSCF Reference Manual.

FIGURE 2-1 correspond to this mode.

FIGURE 2-1 corresponds to this mode.

There are restrictions on the DR operation depending on whether the Solaris OS
operates in the SPARC64 VII enhanced mode or in the SPARC64 VI compatible
mode. For DR operation, see the SPARC Enterprise M4000/M5000/M8000/M9000
Servers Dynamic Reconfiguration (DR) User’s Guide.

Note – If SPARC64 VI processors are intended to be added to a domain which

consists only of SPARC64 VII processors, we strongly suggest setting the SPARC64
VI compatible mode in advance. Refer to the SPARC Enterprise
M3000/M4000/M5000/M8000/M9000 Servers XSCF User’s Guide or man pages for
more information on the setdomainmode command.

2-4 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

2.1.2 Memory Subsystem

The memory subsystem controls memory access and cache memory. The server uses
DDR-II DIMM memory.

Each CMU has thirty-two memory slots.

Also, the SPARC Enterprise M8000 server, SPARC Enterprise M9000 server, and
SPARC Enterprise M9000 server with expansion cabinet can mount up to 128, 256, or
512 DIMMs, respectively.

The memory subsystems use up to eight-way interleaving, providing higher-speed
memory access.

Memory mirror mode is supported for every pair of memory buses in a CMU. This
enables continued operation using the other non-defective bus if an error occurs in
one bus. Memory mirror mode can be set up by the system administrator.

2.1.3 I/O Subsystem

The I/O subsystem controls data transfer between the main unit and I/O devices.
These servers use PCIe as the interconnect bus for I/O devices.

Each IOU contains eight-lane (x8) PCIe slots. Also, eight-lane PCIe slots or 133-MHz
64-bit PCI-X slots can be in a mounted through an External I/O Expansion Unit.

The SPARC Enterprise M8000 server, SPARC Enterprise M9000 server, and the
SPARC Enterprise M9000 with expansion cabinet can mount up to 32, 64, or 128
PCIe-compatible cards, respectively.

PCI-Express slots or PCI-X slots can be added by mounting an External I/O
Expansion Unit through a PCI-Express slot.

2.1.4 System Bus

The CMU containing a CPU and memory subsystem and each component in an IOU
containing an I/O subsystem are used for high-throughput data transfer between all
components through a crossbar switch. The crossbar switch has duplicated bus
routes. If one crossbar switch has an error, the system can be restarted to isolate the
faulty switch, enabling the high-end servers to continue operation.

FIGURE 2-2 shows data transfer in the system.

Chapter 2 System Features 2-5

FIGURE 2-2 Main Component Connections

2-6 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

Note – The SC is the system controller that controls CPUs and memory and handles

communication with the XB.

2.1.5 System Control

System control of this server refers to the system control contained within the
XSCFU that runs the XSCF and every component controlled by the XSCF.

As long as input power is being supplied to the server, the XSCF constantly
monitors the server even if all domains are powered off.

The following functions are provided to increase system availability:

■ Configuration management and monitoring

■ Cooling unit (FAN Unit) monitoring

■ Domain status monitoring

■ Power-on and power-off of peripheral devices

■ Complete control and monitoring of the server through abnormality monitoring

■ Remote partitioning for domain configuration and management

■ Server management and monitoring functions by the user through an external network

connection

■ Notifying the system administrator of fault information on the server

■ Remote console input-output

2.2 Partitioning

A single SPARC Enterprise M8000/M9000 server cabinet can be divided into
multiple independent systems for operation. This dividing function is called
partitioning.

This section describes features of partitioning and system configurations that can be
implemented through partitioning.

2.2.1 Features

The individual systems resulting from partitioning can be built in the SPARC
Enterprise M8000/M9000 servers. These individual, divided systems are called
domains. Domains are sometimes called partitions.

Chapter 2 System Features 2-7

Partitioning enables arbitrary assignment of resources in the server. Partitioning also
enables flexible domain configurations to be used according to the job load or
processing amount.

An independent operating system can run in a domain. Each domain is protected by
hardware so that it is not affected by other domains. For example, a software-based
problem, such as an OS panic, in one domain does not directly affect jobs in the
other domains. Furthermore, the operating system in each domain can be reset and
shut down independently.

2.2.2 Domain Hardware Requirements

The basic hardware resources making up a domain are a CMU and IOU mounted in
the high-end servers or a physical system board (PSB) consisting of a CMU.

A PSB can be logically divided into one part (no division) or four parts. The physical
unit configuration of each divided part of a PSB is called an extended system board
(XSB).

A PSB that is logically divided into one part (no division) is called a Uni-XSB, and a
PSB that is logically divided into four parts is called a Quad-XSB.

A domain can be configured with any combination of these XSBs. The XSCF is used
to configure a domain and specify the PSB division type.

Note – Although a CMU with two CPUMs can be configured into Quad-XSB mode

on an M8000/M9000 server, the server generates a "configuration error" message for
those XSBs that do not have a CPUM and memory.

2-8 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

FIGURE 2-3 shows the partitioning division types.

FIGURE 2-3 Partition Division Types

■ Uni-XSB types

■ Quad-XSB types

Chapter 2 System Features 2-9

2.2.3 Domain Configuration

Any XSBs in the server can be combined to configure a domain, regardless of
whether the divided XSB is the Uni-XSBs or Quad-XSBs.

These XSBs can be used in any combination for a flexible domain configuration.
Also, the quantity of resources for one XSB can be adjusted according to the division
type of a PSB. Thus, a domain can be configured based on the quantity of resources
required for job operations.

XSCF user interfaces are used to configure a domain. Each configured domain is
managed by the XSCF.

The maximum number of domains that can be configured in the servers depends on
the system. Up to 16 domains can be configured in SPARC Enterprise M8000 servers,
and up to 24 domains can be configured in SPARC Enterprise M9000 servers.

To configure a domain, an LSB number must first be assigned so that a logical
system board (LSB) can function as an LSB of the XSB.

This LSB number is referenced by the Solaris OS, and it must be a unique number in
the domain. However, if one XSB is shared by multiple domains, a common LSB
number need not be defined in the domains. An arbitrary LSB number can be
assigned for this setting in each domain.

Domain configuration settings are made for each domain. A domain can be
configured by specifying an XSB together with this LSB number.

Up to 16 XSBs can be configured in a single domain.

The following as well as the quantity of resources must be considered by the user
who is specifying the domain configuration and division type:

■ The Uni-XSB type is suitable in the configuration of a domain requiring a large

quantity of resources. Also, an XSB of the Uni-XSB type is separated by the
physical configuration units of a CMU and IOU. Thus, if a hardware error occurs
in a CPU or memory, hardware can easily be replaced without affecting other
domains. However, a resource quantity decrease due to an error may be in the
range specified by the PSB.

■ Quad-XSB type is suitable in the configuration of a small-scale domain, and

optimized for flexible resource management. However, since domains are
logically separated in a PSB, an error in the hardware shared within the PSB may
affect other domains.

In addition, resources of a configured domain can be added to and deleted from
individual XSBs, and they can be moved between domains.

2-10 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

FIGURE 2-4 shows the domain configuration.

FIGURE 2-4 Domain Configuration

Chapter 2 System Features 2-11

2.3 Resource Management

This section explains the following functions that support dynamic reconfiguration
of domain resources during system operation:

■ Dynamic Reconfiguration

■ PCI Hot-plug

■ Capacity on Demand

■ Zones

2.3.1 Dynamic Reconfiguration

Dynamic reconfiguration (DR) enables hardware resources on system boards to be
added and removed dynamically without stopping system operation. DR thus
enables optimal relocation of system resources. Also, if a failure occurs, DR can place
the system in a state that enables active replacement of the faulty component.

Using the DR function enables additions or distributions of resources as required for
job expansions or new jobs, and it can be used for the following purposes.

■ Effective use of system resources

By reserving some resources, the reserved resources can be added according to
changes in the work load occurring daily, monthly, or annually. This enables
flexible resource allocations on the system that needs to operate 24 hours a day,
every day of the year in accordance with changes in the amount of data and the
work load.

■ Active replacement of system resources

If a failure occurs in a CPU for a domain that has been configured with system
resources of multiple system boards, the DR function enables the faulty CPU to be
isolated dynamically without stopping the system. The replacement CPU can be
configured dynamically in the original domain.

For details on Dynamic Reconfiguration, see the SPARC Enterprise

M4000/M5000/M8000/M9000 Servers Dynamic Reconfiguration (DR) User’s Guide.

2-12 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

2.3.2 PCI Hot-plug

The PCI hot-plug function enables PCI cards to be added or removed under the
Solaris OS without a system reboot.

Examples of uses for the PCI hot-plug function are as follows:

■ Replacing or removing a faulty PCI card or one that will probably become faulty,

during system operation

■ Adding a PCI card during system operation

For details on the PCI hot-plug function, see the SPARC Enterprise M8000/M9000
Servers Service Manual.

2.3.3 Capacity on Demand

Capacity on Demand (COD) is an optional service that allows the user to purchase
spare processing resources (CPUs) for the servers. The spare resources are provided
in the form of one or more CPUs on COD boards that are installed on your server.
However, to access these CPUs, you must first purchase the COD right-to-use (RTU)
licenses for them.

The right-to-use license for CPUs specifies the number of CPUs that can be used in
the entire system. The system administrator decides the system boards and domains
to which the Right to Use is to be assigned.

For details on RTU assignment, see Section 3.2.2.6, “Resource Management” on

page 3-5.

For details on COD, see the SPARC Enterprise M3000/M4000/M5000/M8000/M9000

Servers Administration Guide .

Note – RTU means a license applicable to each CPU. To use CPUs with the extra

number of CPU RTUs purchased beforehand, the user needs to purchase additional
RTUs processors on each system board. The right-to-use license for CPUs specifies
the number of CPUs that can be used in the entire system. The system administrator
decides the system boards and domains to which the Right to Use is to be assigned.

2.3.4 Zones

The Solaris 10 OS has a function called Zones that divides the processing resources
and allocates them to applications.

Chapter 2 System Features 2-13

In a domain, resources can be divided into sections called containers, and the
processing sections are allocated to each application. The processing resources are
managed independently in each container. If a problem occurs in a container, the
container can be isolated so that it does not affect other containers. It provides
flexible resource allocation that enables optimal resource management with
consideration given to the processing load.

2.4 RAS

RAS is an acronym for functions related to Reliability, Availability, and
Serviceability.

RAS for SPARC Enterprise M8000/M9000 servers minimizes system downtime by
providing for error checking at appropriate locations and by providing centralized
monitoring and control of error checking.

Also SPARC Enterprise M8000/M9000 servers can be configured with clustering
software or centralized management software to enhance the RAS function.

Any scheduled system halt, such as a periodic maintenance or system configuration
change can also be performed without affecting operating resources. This can
improve service uptime significantly.

2.4.1 Reliability

To improve quality and gain high reliability, you must select appropriate
components considering the lifetime of the products and response at the time of
error occurrence.

Reliability is equally important to both hardware and software.

Furthermore, software errors are not only triggered by program errors, but also by
hardware errors.

SPARC Enterprise M8000/M9000 servers provide the following functions to realize
high reliability.

■ Monitoring by the XSCF to periodically check whether software such as the

Solaris OS is running in domains (host watchdog monitoring).

■ Memory patrol is periodically performed to detect memory software errors and

stuck faults, even in memory areas not normally used, to prevent use of faulty
memory and thereby prevent system failures caused by faulty memory from
occurring.

2-14 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

■ Since ECC protects functional data in all routes including a computing unit, a

register, cache memory, and a system bus, all 1-bit errors can be automatically
corrected by hardware to ensure data integrity.

2.4.2 Availability

Availability is characterized by how easily a server fails and how quickly the user
can be recovered from the failure. The amount of time the system is usable is
represented as a percentage.

Hardware and software faults in the system cannot be completely eliminated. To
provide high availability, the system must include mechanisms that enable
continuous system operation even if a failure occurs in hardware, such as
components and devices, or in software, such as the operating system, or application
software.

SPARC Enterprise M8000/M9000 servers provide the functions listed below to
obtain high availability. Higher availability can also be obtained by combining the
server with clustering software or management software.

■ Supporting redundant configurations and active (hot) replacement of Power

Supply Units and FAN Units

■ Supporting redundant configuration of hard disk drive, mirroring by software

and active replacement

■ Extended range of automatic correction of temporary faults in memory, system

buses, and LSI internal data

■ Supporting an enhanced retry function and degradation function for detected

faults

■ Shortening the downtime by using automatic system reboot

■ Shortening the time taken for system startup

■ XSCF collection of fault information, and preventive maintenance using different

types of warnings

■ Supporting the Chipkill function in the memory subsystem, which enables single-

bit error correction to continue processing in response to continuous burst read
errors caused by failures of a memory device

■ Supporting the memory mirroring function enables normal data processing

through the other memory bus, thereby preventing system failures in response to
an error at the bus or device connected to memory bus

■ Memory patrol function has no influence on the workload of software operation

because it is implemented in hardware

Chapter 2 System Features 2-15

2.4.3 Serviceability

Serviceability is characterized by how easily a server fault can be diagnosed, and
how quickly the server can be recovered from the fault or how easily the fault can be
corrected.

To achieve high serviceability rates, it must be possible to identify the causes of
component or device failure. To facilitate recovery from failure, the system must
determine the cause of the failure and isolate the faulty component for replacement.
The system must also notify the system administrator and/or service engineer of the
event and situation in an easy-to-understand format that prevents
misunderstandings.

SPARC Enterprise M8000/M9000 servers provide the following solution to realize
high serviceability:

■ Status LEDs mounted on the operator panel, indicating the main replaceable

components and the components to which active replacement is applicable

■ Remote recognition of the device operating status and remote maintenance using

the XSC

■ LED blinking function for indicating the maintenance target (CHECK-LED, which

is also called a locator)

■ Notes and cautions marked on different types of labels provided for the system

administrator and service engineers

■ Automatic notification for reporting different types of faults to the system

administrator and service engineers

■ Centralized systematic monitoring, such as supporting SNMP, of a complex

system from a data center

2-16 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

CHAPTER

3

About Software

This chapter explains the following software functions.

■ Section 3.1, “Solaris OS Functions” on page 3-1

■ Section 3.2, “XSCF Firmware Function” on page 3-2

3.1 Solaris OS Functions

The Solaris OS has the following features:

■ Solaris reliability that has been built over the years

■ Affinity that fully brings out the hardware performance of the SPARC

architecture.

■ A variety of products from ISVs (application software and middleware)

■ Resource optimization using the partitioning and DR functions

■ Dynamic addition/change of IO device using PCI hot plug

■ Resource management with Solaris zones using Solaris container technology

■ Advanced system management in cooperation with XSCF

For details of the Solaris OS, see the manual on the following URL.

http://docs.sun.com

Irrespective of the capabilities of the software suite, the Solaris OS has the following
functions for communicating with the SPARC Enterprise server hardware:

■ Domain Management

■ PCI Hot-plug

3-1

3.1.1 Domain Management

In the SPARC Enterprise M8000/M9000 servers, a physical system board (PSB) can
be logically divided into one part (no division) or four parts by a partitioning
function unique to the system.

A PSB that is logically divided into one part (no division) is called a Uni-XSB, and a
PSB that is logically divided into four parts is called a Quad-XSB.

The physical unit configuration of each divided part of a PSB is called an extended
system board (XSB).

In the SPARC Enterprise system, a domain can be configured with any combination
of these XSBs.

3.1.2 PCI Hot-plug

SPARC Enterprise M8000/M9000 servers support insertion and removal of PCI cards
for specific PCI-Express and PCI-X hot-plug controllers. Before removing the PCI
card, be sure to cancel the settings and isolate the card by using the Solaris OS
cfgadm(1M) command, and make sure that the card is physically removable.

For details of PCI hot-plug, see the SPARC Enterprise
M3000/M4000/M5000/M8000/M9000 Servers Administration Guide.

3.2 XSCF Firmware Function

The XSCF firmware is a System Control Facility including a dedicated processor that
is independent from the processors in the server. This section describes XSCF
firmware features and provides an overview of XSCF firmware functions.

3.2.1 XSCF Features

The XSCF is firmware that is preinstalled, and operates on the XSCFU as standard
equipment. As long as input power is being supplied to the server, the XSCF
constantly monitors and manages the server even if the power to domains is turned
off. In addition, the XSCF provides a user interface from which users can operate
and manage the server.

3-2 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

The XSCFU has a serial port and LAN port as external interfaces. A terminal such as
a personal computer or workstation can be connected to the XSCF through a serial
connection or Ethernet connection.

The servers can be operated and managed from the command line-based XSCF Shell
or browser-based XSCF Web pages provided by the XSCF.

Only the XSCF Shell can be used through the serial connection. Both the XSCF Shell
and XSCF Web pages can be used through the Ethernet connection.

The XSCFU supports a redundant configuration (duplicate configuration) for high
reliability.

The XSCF that is currently in control of the server is called the active XSCFU, and
the other XSCF is called the standby XSCF or standby XSCFU since it serves as the
backup XSCF to the active one.

The active XSCF and standby XSCF monitor each other to implement a failover
mechanism to switch between the active XSCF or standby XSCF when one of them
detects and error in the other.

For details on functions provided by the XSCF, see Section 3.2.2, “XSCF Functional

Overview” on page 3-4, and the SPARC Enterprise

M3000/M4000/M5000/M8000/M9000 Servers XSCF User’s Guide.

3.2.1.1 Command Line-based User Interface (XSCF Shell)

The XSCF Shell is a command line-based user interface that can be used from a
terminal, such as a personal computer or workstation, connected to the XSCF
through a serial connection or Ethernet connection.

With the serial connection, the terminal is connected directly to the server to use
shell commands provided by the XSCF. Also, the console redirection function of the
XSCF enables the terminal to be used as an operating system console.

With the Ethernet connection, the terminal is connected to the XSCF via Secure Shell
(SHH) or telnet to use shell commands provided by the XSCF.

The following are the main operations that can be performed with the XSCF Shell:

■ Display the server configuration or status and various related settings

■ Display the domain configuration or status and various related settings

■ Start or shut down a domain

■ Make settings for various network services

■ Make settings for various security functions

■ Make various settings for the remote maintenance service function

Chapter 3 About Software 3-3

3.2.1.2 Browser-Based User Interface (XSCF Web)

XSCF WEb is a browser-based user interface that can be used from a terminal, such
as a personal computer or workstation, connected to the server through an Ethernet
connection.

However, the XSCF Web pages cannot be used through a serial connection. If the
browser function of a terminal is used for a connection to the XSCF, BUI operations
can be performed.

3.2.2 XSCF Functional Overview

This section provides an overview of the main functions supported by the XSCF.

For details on each function, see the SPARC Enterprise
M3000/M4000/M5000/M8000/M9000 Servers XSCF User’s Guide.

3.2.2.1 System Management

The main tasks of the XSCF are control and monitoring of the entire SPARC
Enterprise system, such as configuration management and monitoring of the
server’s cooling components (FAN units), domain status monitoring, power-on and
power-off of peripheral units, and error monitoring. Also, the XSCF provides a
partitioning function for domain configuration and management.

The XSCF constantly monitors the server status so that the system can operate stably.

When any error is detected in the system, the system status monitoring mechanism
immediately collects error information about the hardware (hardware log) and
analyzes it to identify the error location and check the error status. The XSCF
displays the status, and it degrades the relevant component or domain as necessary
or it resets the system, thereby preventing the error from occurring again.

The XSCF provides high reliability, high availability, and high serviceability for the
entire system.

3.2.2.2 Security Management

The XSCF manages user accounts for the XSCF. The operating range in the XSCF
Shell and XSCF Web pages can be limited based on user account types and settings.
Moreover, the XSCF provides an IP address filtering function for permitting access to
the XSCF and an encryption function using SSH and SSL. Operator errors and
unauthorized access during system operation are recorded in a log. The system
administrator can use these functions to investigate the cause of a system problem.

3-4 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

3.2.2.3 System Status Management

The XSCF provides functions as XSCF operations for displaying the system
configuration status, creating and changing a domain configuration definition, and
starting and stopping domains. Also, the XSCF provides the DR function, which
assists in dynamically changing a system board configuration during domain
operation. Thus, domain resources can be optimized for job operations. Moreover,
the XSCF in linkage with the Solaris OS manages CPU, memory, and I/O resources.

3.2.2.4 Error Detection and Management

The XSCF constantly monitors the system status so that the system can operate
stably. When any error is detected in the system, the XSCF immediately collects error
information about the hardware (hardware log) and analyzes it to identify the error
location. To continue operation, the XSCF degrades the relevant component or
domain as necessary according to error conditions or it resets the system, thereby
preventing the problem from occurring again. The user can take prompt action for
problems since easy-to-understand and accurate information on hardware errors and
fault locations are thus provided to the user.

3.2.2.5 Remote System Control and Monitoring

The XSCF provides functions for monitoring the server through an Ethernet
connection so that the user can remotely manage the server. Moreover, a function for
reporting error information to the system administrator and a remote console input­output function are supported. System availability is thus increased.

3.2.2.6 Resource Management

The XSCF manages hardware resources on configured domains and system boards.
Resource management provides a dynamic reconfiguration function which enables
dynamic reconfiguration of a domain. In addition, COD is provided to realize
resource management of CPUs that are purchased by license.

Dynamic Reconfiguration (DR)

The XSCF assists in dynamically changing a system board configuration during
system operation. The XSCF can be used for dynamic reconfiguration of domains.

For details on DR, see the SPARC Enterprise M4000/M5000/M8000/M9000 Servers
Dynamic Reconfiguration (DR) User’s Guide.

Chapter 3 About Software 3-5

Capacity on Demand (COD)

To use COD, RTUs must be purchased. Then, resources such as CPUs must be
configured according to the number of purchased RTUs so that they can be used as
needed. The licenses that are defined are allocated to individual resources when
such resources are required for use because of the start of a domain or another
trigger.

For details, see the SPARC Enterprise M3000/M4000/M5000/M8000/M9000 Servers

Administration Guide

3.2.2.7 Airflow Indicator

The Airflow indicator confirms the amount of airflow emitted while the SPARC
Enterprise M8000/M9000 servers are up and running.

The Airflow indicator indicates the volume of air exhausted from the server. The
values do not include the peripheral devices.

To display the amount of exhaust air, use the showenvironment air command.

CODE EXAMPLE 4

XSCF> showenvironment air
Air Flow:5810CMH

Note – Airflow monitoring measurement values are for reference only.

For details of the showenvironment(8) command, refer to the man page. For
installation details of the SPARC Enterprise M8000/M9000 servers, see the SPARC

Enterprise M8000/M9000 Servers Site Planning Guide and the SPARC Enterprise
M8000/M9000 Servers Installation Guide.

You can also obtain the exhaust air data using the SNMP agent function. To obtain
the data of exhaust air using the SNMP agent function, install the latest XSCF
extension MIB definition file to the SNMP manager. For details on the XSCF
extension MIB definition file, see the SPARC Enterprise
M3000/M4000/M5000/M8000/M9000 Servers XSCF User’s Guide.

3-6 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009

Index

A

Airflow Indicator, 3-6
Availability, 2-15

C

Components

CPU Module, 1-20
CPU/Memory Unit, 1-21

F

Features

high-end server, 1-5
Partitioning, 2-7
Software, 3-1
System, 2-1
XSCF, 3-2

H

Hardware Configuration

CPU, 2-1
I/O Subsystem, 2-5
Memory Subsystem, 2-5
System Bus, 2-5
System Control, 2-7

M

M8000 appearance, 1-2
M9000 appearance

base cabinet only, 1-3
with an expansion cabinet, 1-4

N

Names of components

M8000 Front View, 1-12
M8000 Rear View, 1-12
M9000 (Base cabinet only) Front View, 1-14
M9000 (Base cabinet only) Rear View, 1-14
M9000 (With am Expansion Cabinet) Rear

View, 1-16

M9000 (With an Expansion Cabinet) Front

View, 1-16

O

Operator Panel

LED, 1-17
Switch, 1-19

P

Physical unit, 2-8
power cabinet, 1-12, 1-14, 1-16

Q

Quad-XSB, 2-8

R

Reliability, 2-14
Resource Management

Capacity on Demand (COD), 2-13
PCI hot-plug, 2-13
Zone, 2-13

S

Serviceability, 2-16

Index-1

Software

Solaris Operating System, 3-1
XSCF Firmware, 3-2

Specifications

System, 1-8

System

Specifications, 1-8

U

Uni-XSB, 2-8

X

XSCF Firmware, 3-2
XSCF Shell, 3-3
XSCF Web, 3-4

Index-2 SPARC Enterprise M8000/M9000 Servers Overview Guide • August 2009