Dot Hill SANnet II 200 FC Array Technical Product Description Guide
Copyright 2003 by Dot Hill Systems Corp. All Rights Reserved
Copyright 2003 Dot Hill Systems Corp., 6305 El Camino Real, Carlsbad, California 92009, USA. All Rights Reserved. Sun Microsystems, Inc. and Dot Hill Systems Corp. may have intellectual property rights relating to technology embodied in this product or document. In particular, and without limitation, these intellectual property rights may include one or more of the U.S. patents listed at http://www.sun.com/patents and one or more additional patents or pending patent applications in the U.S. and other countries. This product or document is distributed under licenses restricting its use, copying distribution, and decompilation. No part of this product or document may be reproduced in any form by any means without prior written authorization of Sun and its licensors, if any 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. DOCUMENTATION IS PROVIDED AS IS AND ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE OR NONINFRINGEMENT, ARE DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD TO BE LEGALLY INVALID. THIS PUBLICATION COULD INCLUDE TECHNICAL INACCURACIES OR TYPOGRAPHICAL ERRORS. CHANGES ARE PERIODICALLY ADDED TO THE INFORMATION HEREIN; THESE CHANGES WILL BE INCORPORATED IN NEW EDITIONS OF THE PUBLICATION. SUN MICROSYSTEMS, INC. AND DOT HILL SYSTEMS CORPORATION MAY MAKE IMPROVEMENTS AND/OR CHANGES IN THE PRODUCT(S) AND/OR THE PROGRAM(S) DESCRIBED IN THIS PUBLICATION AT ANY TIME. Last update: 5/15/2003, T. Uhler

Table of Contents

INTRODUCTION..... 4 KEY FEATURES.... 4 ARCHITECTURE FUNDAMENTALS.... 5 MANAGEMENT INTERFACES.... 7 RELIABILITY, AVAILABILITY AND SERVICEABILITY... 8 PERFORMANCE.... 8 SCALABILITY..... 9 ARCHITECTURE.... 10 ENCLOSURE MODULES.... 10 RAID CONTROLLER I/O MODULES.... 10 DISK DRIVES..... 12 POWER AND COOLING MODULES... 13 EXPANSION ARRAY I/O MODULES.... 13 BATTERY MODULES.... 14 FEATURES.... 15 CONTROLLER OPTIMIZATION.... 15 CONTROLLER REDUNDANCY.... 15 CACHE PROTECTION..... 16 WRITE CACHING..... 17 LOGICAL DRIVES/DRIVE REBUILDING.... 18 DISK REDUNDANCY..... 18 SPARE DISKS..... 18 MANAGEMENT..... 19 CONFIGURATION..... 19 MONITORING..... 20 EVENT LOGS..... 20 IN-BAND & OUT-OF-BAND MANAGEMENT.... 21 DETAILED SPECIFICATIONS.... 24 GLOSSARY.... 28

Introduction

Introducing the Dot Hill SANnet II 200 FC array, the flagship product of the Dot Hill family of storage products. The SANnet II 200 FC array supports high-performance 2-Gb Fibre Channel interface technology throughout its architecture, from disk drives and ports through the midplane and through host ports and hosts. Each Dot Hill SANnet II 200 FC array holds twelve 1-inch high, low profile disk drives in a 2U high (3.5-inches) package. The array is available with dual redundant RAID controllers, a single RAID controller, or without controllers for use as an expansion unit. An expansion unit can also be used as a stand-alone JBOD storage system or as a host-based RAID array when used with volume management software supporting software RAID.
FIGURE 1: Front View of SANnet II 200 FC Array (RAID array, Expansion Unit/JBOD)
The Dot Hill SANnet II 200 FC array is positioned at the entry-level and midrange market segment. Primary target markets include small and medium-sized businesses, Linux and Windows environments, Web applications, and ruggedized environments, including government, ISPs and telecommunications markets. The Dot Hill SANnet II 200 FC array meets the requirements of a wide range of applications providing a powerful set of flexible and easy-to-use tools. With the Dot Hill SANnet II 200 FC array, customers can pay for what they need today and can easily scale in performance and capacity as their business grows.
FIGURE 2: Dot Hill SANnet II 200 FC Array (rear view)
The Dot Hill SANnet II 200 FC array is Telcordia NEBS Level 3-certified (the highest level attainable), and it also passes rigorous MIL-STD-810 tests. This means that the array is ultraruggedized and ideally suited for telecommunication; industrial; military/defense; and air, land and sea applications.

Key Features

As highlighted above, the Dot Hill SANnet II 200 FC array array is an ultra-compact, superrugged storage system that meets entry-level and midrange requirements. It also provides
affordable, enterprise-class performance and availability features, management functionality and configuration flexibility. Here are a few highlights:
Six 2-Gb FC ports per RAID controller or twelve 2-Gb FC ports per RAID array in a dual RAID controller configuration. Up to eight servers can be directly attached -- no external switch required -- to a dual RAID controller array, providing an incredible raw bandwidth of up to 16-Gb/sec. An extremely space-efficient design provides up to 12 disks and redundant or single RAID controllers in just 2U of rack space. Up to two SANnet II 200 FC array storage expansion units can be attached to a single RAID array, for a total raw storage capacity of over 5.2TB (using thirty-six 146-GB drives). Unified graphical user interface (GUI) provides intuitive configuration, management and reporting for every Dot Hill SANnet II FC series array in your environment. RAID controller support for a broad range of RAID levels: 0, 1, 0+1, 1+0, 3, 5, 3+0, 5+0 and up to 1,024 LUNs, thus assuring extremely flexible performance and protection. Dynamically expand capacity and performance by adding disks without interrupting storage operations or attached servers. Automated read and write cache management with user selectable write-through or writeback cache policies and optimization for sequential or random access.

Architecture Fundamentals
Dot Hill SANnet II 200 FC arrays are modular storage systems that are ideally suited for the following wide variety of server platforms: Volume, Entry-Level Servers Workgroup, Departmental and Midrange Servers Enterprise Servers NEBS-certified Servers Servers that Require MIL-STD Peripherals/Subsystems
The Dot Hill SANnet II 200 FC array can be installed in racks and rack cabinets. In addition to supporting typical entry-level and midrange environments, these rugged systems are NEBS Level 3-certified for use in telecommunications and ISP infrastructures; plus they are MIL-STD-810F-certified for use in military applications as well. The modular architecture consists of a number of self-contained base enclosures, expansion enclosures and disks. Each base and expansion enclosure occupies 2U of rack space and supports up to 12 disks. Base enclosures include one or two controllers while expansion enclosures contain no controllers. A base enclosure can support more than 12 disks by adding one or two expansion enclosures. Once expansion enclosures are added, the collection of enclosures and disks becomes one fully
integrated array effectively the equivalent of a base enclosure supporting 24 or 36 disks rather than multiple independent enclosures. The expansion of base units is optional.
Dot Hill SANnet II 200 FC Array Features/Functions/Benefits

Feature

2-Gb FC architecture Up to 12 FC ports Dual hot-swap/redundant power supplies and fans 1,024 LUNs RAID support with hotswap/global hot-spare drives Dual RAID controller configurations Expansion arrays Industry-standard rack/system cabinet mounting

Technical Function

Up to 16 Gb/sec raw bandwidth (eight host channels) For host and expansion capability If one fails, the other keeps the array running smoothly; dynamic replacement of failed unit does not disrupt production I/O Separate data sets Quick, easy, dynamic failed drive replacement while array is active High-availability RAID (hot swap/redundant controllers with mirrored cache) Daisy-chain to a RAID controller array Center post or four post compatibility

Benefit

Very fast access and transfer of information Up to eight direct-attached server and up to two expansion units Easy serviceability and enhanced system availability Supports many data sets according to server needs Can be serviced without interruption Access to data is not affected by controller failover Saves money; provides a cost effective, transaction-intensive configuration Provides flexible cabinet and rack installation

The smallest possible Dot Hill SANnet II 200 FC array configuration consists of a single base enclosure containing a number of fully integrated field replaceable units (FRUs). FRUs include RAID controllers, disk drives, battery cache modules, I/O modules and power/cooling units. The exact number and combination of FRUs included within each base or expansion enclosure varies by array configuration. The rackmountable 2U-high Dot Hill SANnet II 200 FC array supports 2-Gb Fibre Channel both internally to the drives and externally to the host ports. Configuration management and enclosure event reporting are enabled through an in-band FC or out-of-band 10/100 BASE-T Ethernet port and a DB9 serial port. Dot Hills host-based SANscape software is used for management and event monitoring. This software can also launch from a Web browser. Each 2-Gb FC controller has 1 GB of battery-backed data cache with intelligent caching algorithms and supports support RAID levels 0, 1, 0+1, 1+0, 3, 5, 3+0, and 5+0; up to 1,024 LUNs; and 256 command tag queues (CTQs). In BOTH single and dual controller configurations the maximum number of addressable LUNs is 1,024. Dual RAID controllers in active-active, symmetric failover configurations allow fail-safe, continuous online protection.
With two RAID controllers installed, they are configured for redundancy and mirrored write cache so if either controller fails or is removed, the remaining controller takes over the workload (failover), allowing for fail-safe, continuous, online protection. Each RAID controller can support up to four direct-attached host I/O ports when in a nonredundant path mode. In dual controller configurations, the maximum number of direct-attached host I/O ports is eight. Both the RAID array and expansion array support up to twelve 1-inch high (low-profile) 2-GB FC disk drives. A maximum configuration supports up to 36 disk drives (one RAID array plus two expansion drive arrays). Each drive array is connected to each other via optional external FC cables. The array includes dual hot-swap/redundant load-sharing/load-balancing power and cooling units (100 to 240VAC or -48 or -60VDC). Each has separate power inputs and contains dual, spindlesynchronized, high-velocity (52 CFM) fans with detection circuitry to monitor degraded performance. Fan rotation sensors are used to watch for degraded cooling performance, thus providing superior over-temperature protection. Each RAID controller I/O module FRU includes one SES event monitoring circuit. With dual redundant RAID controllers, the SES logic communicates with one another over dual I2C busses. This circuit monitors all internal +12 and +5 DC voltage outputs per power and cooling unit. Seven temperature sensors and two fan speed sensors from each unit are monitored by the event monitoring integrated circuit. This circuit controls front and rear panel display LEDs and buzzer alarm.

Base Unit with Redundant Controllers
Controller I/O Modules Disk Drives Power and Cooling Modules Battery Backup Modules Hot-swappable Hot-swappable Hot-swappable Hot-swappable
Base Unit with Single Controller
Hot-serviceable Hot-swappable Hot-swappable Hot-swappable
Expansion Unit (no controllers)
Not applicable Hot-swappable Hot-swappable Not applicable

Performance

Dot Hill SANnet II 200 FC array arrays provide extremely high levels of performance, and all within an ultra-compact package. The use of 2Gb fibre channel technology throughout for disks and servers results in performance that meets or exceeds todays fastest storage arrays. Cache memories of up to 2GB per array (dual RAID controller configuration) with support for 15,000RPM disks and flexible choices of hardware-based RAID level protection ensure optimum performance.

Scalability

Room for 12 disks within an enclosure that occupies just 2U of rack space provides excellent capacity for many environments, including and in particular those requiring small footprints. A choice of 36GB, 73GB and 146GB disks permits users to balance the number of disks and storage capacity needed. When even more storage capacity is required, expansion enclosures can be easily added to expand the number of disks up to 24 or 36, providing up to 5.25TB of total raw storage capacity in just 6U of rack space.

Architecture

Dot Hill SANnet II 200 FC arrays use modular design principles. Essentially, each array is a collection of independent modules that operate cooperatively, providing all the necessary array functions.

Enclosure Modules

The primary building block of any Dot Hill SANnet II 200 FC array is its enclosure. It consists of a compact ruggedized chassis with internal mid-plane. The mid-plane interconnects the rearfacing Raid Controller IOM FRUs and connects to the redundant fibre channel loops of the disk drives. The mid-plane provides the internal enclosure connections for the disks. The enclosure securely holds and interconnects other FRUs to create a functional storage system.
FIGURE 3: Dot Hill SANnet II 200 FC Array (front view)
The enclosure itself is a FRU with no serviceable components. If the chassis or an internal midplane were damaged, all of the other FRUs could be removed and inserted into a replacement enclosure in minutes. There are no critical active components within the chassis or on the internal midplane, so the chance of a component failure within an enclosure is very low. The base and expansion enclosures of Dot Hill SANnet II 200 FC arrays appear similar, and they are interchangeable. It is possible to easily convert an expansion enclosure to a base RAID array or vice versa.

Each host/drive loop includes multiple components. Each I/O board contains FCAL loops and port bypass circuits that are associated with three components: a channel on the RAID controller, the SFP-pluggable port residing within the I/O board, and a connection to the opposite I/O board. This architecture provides a data path for both RAID controller to either the top or bottom SFPpluggable port on a given channel. Plugging an SFP into a port enables external connections to that port. Plugging and unplugging SFPs into ports is easy. The configuration of a single RAID controller configuration is slightly different. The connection to the lower I/O board and the redundant disk drive remain the same. However there are not host or expansion SFP connections on the lower I/O board.

Disk Drives

The Dot Hill SANnet II 200 FC array supports a variety of disks available in three different capacities. Current choices include 36GB, 73GB and 146GB disk drives. The 73GB and 146GB disks are available in speeds of 10,000RPM, and the 36GB drive is available in 15,000RPM speeds. Disks FRUs are hot-swappable or hot-serviceable depending their logical configuration i.e., depending on whether the disks are configured to provide redundant RAID protection or not. The disks are not slot dependent. This allows them to be removed, stored and replaced into the system in random order without affecting stored information or system configuration. Disks are mounted into a rugged sliding tray and held securely in place by a front-mounted handle with locking thumbscrew.
FIGURE 5: Disk Drives (front view; bezel removed)
The FC-AL architecture connecting the disk drives to the SFP ports differs from the host/drive channels. In the disk drive FC architecture, channel 2 from both controllers appears on the upper I/O board and channel 3 from both controllers appears on the lower I/O board. The components residing on the disk drive loops are: Channel 2 or 3 (depending upon I/O board being reviewed) from one controller Channel 2 or 3 from the second controller Two SFPs Disk drive loop A for channel 2 or disk drive loop B for channel 3 The SCSI Enclosure Services (SES) logic
Avoid operating a Dot Hill SANnet II 200 FC array for an extended period of time with a disk removed to maintain optimum cooling. If a disk is being removed permanently or for an indefinite period of time, installation of an air management module should be put in its place.
Power and Cooling Modules
The Dot Hill SANnet II 200 FC array features a redundant pair of combination power and cooling modules. Two fully redundant 420-Watt power supplies feature load-sharing and load-balancing capabilities. Each AC power and cooling unit has auto-ranging capability from 90VAC to 264VAC and 47 to 63 Hz. With these redundant power supplies, one maintains electrical power to the system if the other fails. A single power and cooling unit can spin up, maintain, and sustain power for a fully loaded Dot Hill SANnet II 200 FC array unit.

Controller Redundancy

Dot Hill SANnet II 200 FC arrays are available with single or redundant controllers. When two controllers are present, they can operate as a redundant pair or single independent raid controllers. Redundant controllers can be set to function in active/active (recommended) or active/standby pairs. Unlike other storage systems, redundant controllers behave as one virtual system consisting of primary and secondary controllers. Configuration, management and monitoring are performed using the primary controller only. The secondary controller automatically synchronizes its configuration to the primary controller to ensure their configuration remains identical. If an active controller detects the other controller of a redundant pair is malfunctioning or has failed, it immediately disables the faulty controller and transparently resumes its workload. This temporary process, called failover, occurs instantly and without interuption to server or array operations.
The surviing controller of a failover process always becomes the primary controller. Replacing the faulty controller will result in an automatic failback process, where the array restores a redundant controller configuration. The new controller will become the secondary controller. A particular logical drive must be assigned to either the primary or secondary controller. The controller a logical drive is assigned to performs all necessary functions for that set of disks until a controller failover occurs. One logical drive cannot be assigned to both controllers, but logical drives can be distributed among the controllers to balance controller workloads. It is necessary to connect ethernet management interfaces to both redundant controllers. For example, if one controller is connected to a management network, the second controller should be also be connected. Failure to do this may interupt management access if a controller fail over occurs. However the serial RS-232 interface are ORed together, therefore a single serial connection from either Raid IOM is all that is required even during a failover scenario. Since each fibre interface only supports a single loop ID, two host adapters are necessary for the active-to-active redundant controller operation. Using two host adapters in each server ensures continued operation even when a data path fails. In active-to-active mode, the connection to each host adapter should be considered a data path connecting the host to either the primary or the secondary controller. One adapter should be configured to serve the primary controller, and the other adapter to serve the secondary controller. Each target ID on the host channels should be assigned either a primary ID or a secondary ID. If one controller fails, the existing controller can inherit ID from its counterpart and activate the one standby channel to serve host I/Os.

Write Caching

Dot Hill SANnet II 200 FC arrays provide important safeguards for stored information. One option that has an effect on how information is protected is user-selectable write-through (safest) or write-back (fastest) caching. Neither write-cache option is superior in every environment, so it is important to understand what each option does before choosing. With write-through caching selected, all information received by a Dot Hill SANnet II 200 FC array is written to its disks before the array confirms the successful completion of the write operation. Information is always written to disks when using write-though caching so write information never remains within the controllers cache, but write performance is limited by the speed of the disks. Write-back caching changes write behavior to enhance performance without compromising protection. It allows an array to confirm successful completion of write operations when information reaches cache rather than disks. Controllers contain battery backups that protect the content of cache memories for up to 72 hours. When redundant controllers are present and operating in active/active mode, write-back cache contents are continually synchronized between controllers for added protection. Cache operates at speeds orders of magnitude faster than disks, so write-back caching often provides significant performance improvement. Choosing write-cache modes is often based on the number of controllers present within a Dot Hill SANnet II 200 FC array. When using an array with a single controller, write-through caching protects against potential data loss that could occur if the controller failed while using write-back caching. A controller in a dual controller configuration does not represent a single point-offailure, so write-back caching often provides the best results.
Logical Drives/Drive Rebuilding
A logical drive is a set of drives grouped together to operate under a particular RAID level. Each array is capable of supporting as many as eight logical drives, and a logical drive can be further divided into a maximum of 32 partitions. The logical drives can have the same or different RAID levels. The total number of partitions cannot exceed 128 partitions per array. If you want to assign 128 partitions to 128 LUNs in an array, you need to have a minimum of four logical drives with 32 partitions each. Spare disks are destined to become part of a logical drive rebuilding process. Dot Hill SANnet II 200 FC array arrays provide several options for detecting the need to rebuild a logical drive. For example, an array may wait until a disk fails completely before rebuilding a logical drive or detect a malfunctioning disk and rebuild the logical drive before the disk fails completely. Several options exist for choosing logical drive rebuilding preferences. When a disk fails without warning, the controller first examines whether there is a local spare disk assigned to this logical drive. If yes, it automatically starts to rebuild the data of the failed disk to it. If there is no local spare available, the controller next searches for a global spare to rebuild the logical drive. If no valid spare disks are available, the logical drive rebuilding waits until a spare disk becomes available, generally after the replacement of the failed disk.

Disk Redundancy

As with most arrays, disk redundancy is provided by the RAID features supported by Dot Hill SANnet II 200 FC arrays. Configuring a set of disks into a logical drive operating under a mirrored or parity-protected RAID level ensures information will not be lost in the event of a disk failure. Moreover, taking advantage of the spare disk capabilities of Dot Hill SANnet II 200 FC array arrays further enhances disk redundancy.

Spare Disks

A Dot Hill SANnet II 200 FC array disk can be assigned as a data disk or a spare disk. When configured as a spare, it can serve as a local spare to one specified logical drive or as a global spare available to all logical drives. More than one spare disk can exist for a particular logical drive and even combinations of local and global disks. It is a good practice to ensure every logical drive is protected by at least one spare disk, even if many logical drives are sharing spare disks.

Management

Configuration
Dot Hills SANscape software is a Java technology-based software program that combines storage configuration, maintenance, and monitoring tools into a single, easy-to-use application. SANscape software provides centralized administration of Dot Hill SANnet II 200 FC array storage systems across existing local and wide area networks. It greatly simplifies storage management and reduces administration costs.
SANscapes graphical interface (GUI) uses intuitive controls and graphics to present configuration options, maintenance features, and status information for storage systems and servers. A color-coded design provides feedback and clear status information for each component. Critical conditions that require immediate attention are always easily identified and simple to locate. Configuration features and controls are well marked and operate smoothly. SANscape is also very easy to learn through its use of familiar interface elements. SANscape provides complete monitoring of SANnet II FC RAID controllers, disk drives, etc. From a single console, system administrators can view and make changes to storage systems. In the event of a status change, SANscape sends real-time, proactive alerts to the system administrator via its console display, e-mail, or through an alphanumeric pager, allowing users to monitor the system remotely. Storage setup and management is easy with SANscape. Custom configuration options allow network administrators to configure storage volumes, RAID levels, cache modes, stripe sizes, and other storage parameters to meet particular server and application requirements. SANscape also allows dynamic array firmware upgrades when there are dual redundant controllers configured. With SANscape's unsurpassed ease of use and attention to detail, even the most ambitious storage installations are simple to manage. SANscape features include the following: GUI based management and monitoring Phone home alert support (email alerts) Defines the types of message traps sent, the timing of messages sent, forward encrypted messages, and receives messages, which functions as an email-viewing program. Operates in background mode continuously on the computer where it is installed and also has a controlling agent (a controlling agent is the only agent which talks to a specific array).

FIGURE 12: Event Log Window
In-Band & Out-of-Band Management
SANscapes out-of-band storage management capability enables you to monitor and manage arrays over the network using TCP/IP. Unlike in-band storage management (the standard method of storage management for storage), which requires the SANscape Agent to be running on the server that is physically attached to the storage, out-of-band storage management does not require the SANscape Agent to be running on the server that is physically attached to the storage.
With out-of-band storage management, you do not need to load extra software on the server, and you have the flexibility to monitor and manage storage from anywhere on the network.
FIGURE 13: In-Band Management
FIGURE 14: Out-of-Band Management

Firmware Updates

For a fast and easy download of new versions of controller firmware, disk drive firmware and SES firmware, use one of the following tools: SANscape CLI (with an in-band connection, for Solaris and Windows hosts) SANscape program (with an in-band connection, for Solaris and Windows hosts) Firmware application (for controller firmware download only from a Windows host with an out-of-band serial port connection)
You can also use a Windows terminal emulation session with ZMODEM capabilities to access the firmware application. The following firmware upgrade features apply to controller firmware: Redundant Controller Rolling Firmware Upgrade: When a download is performed on a dualcontroller system, firmware is flashed onto both controllers without interrupting host I/Os. When the download process is complete, the primary controller will reset and let the secondary controller take over the service temporarily. When the primary controller comes back on-line, the secondary controller will hand over the workload and then reset itself for the new firmware to take effect. The rolling upgrade is automatically performed by controller firmware, and the users intervention is not necessary. Automatically Synchronized Controller Firmware Versions: A controller that replaces a failed unit in a dual-controller system is often running a newer release of firmware version. To maintain compatibility, the surviving primary controller will automatically update the firmware running on the replacement secondary controller to the firmware version of the primary controller. Upgrading Firmware Using the Serial Port Connections (from Windows hosts): The firmware can be downloaded to the RAID controller by using an ANSI/VT100- compatible emulation program. The emulation program must support the ZMODEM file transfer protocol. Emulation programs such as HyperTerminal, Telix, and PROCOMM Plus can perform the firmware upgrade.

Detailed Specifications

Drives Form Factor Interface Supported Drives Number of Ports Maximum Cable Length Maximum Point to Point Length
Dual-ported Fibre Channel 3.5 in., low profile 2 Gbit Fibre Channel 36 GB, 15,000 rpm; 73 GB, 10,000 rpm; 146 GB, 10,000 rpm Up to eight server ports and four storage expansion ports, (with dual RAID controllers) 250 m
36 GB, 15,000 rpm Disk Drives 73 GB, 10,000 rpm Disk Drives 146 GB, 10,000 rpm Disk Drives
436 GB maximum storage capacity (raw, in single 2U array)
876 GB maximum storage capacity (raw, in single 2U array)
1.72 TB maximum storage capacity (raw, in single 2U array)
RAID Levels Number of LUNS Number of Local Hot Spares Number of Global Hot Spares
0, 1, 0+1, 1+0, 3, 5, 3+0, and 5+0 Up to 1,024 Up to 20 (RAID set and disk quantity dependent)
Up to 20 (RAID set and disk quantity dependent)
Cache Size (read and write) Cache Battery Backup Cache Write Default Cache Selectable Parameters

1 GB per controller

Up to 72 hours Write Back (write through -- user configurable) 32 K block size (optimized for random file transfer) 128 K block size (optimized for sequential file transfer)

Operating System Support

Solaris[tm] Operating Environments 8, 9 Microsoft Windows NT 4.0 Microsoft Windows 2000 server Red Hat Linux distribution v7.3 HP-UX 11.0 and 11i IBM-AIX 4.3.3 and 5.1L (32 and 64 bit) Dot Hill SANscape
Management Software Tools
Dot Hill SANscape Alert Dot Hill SANscape CLI Dot Hill SANpath
Fibre Channel Configuration Options
Fibre Channel arbitrated public and private loop Point-to-point Switched fabric

Serviceability

Non-disruptive controller firmware upgrades, via SSCS Hot-swap RAID controllers (with dual RAID controllers) Up to twelve hot-swap disk drives Two hot-swap and redundant power/cooling supplies
AC Input Voltage 100 to 240 VAC, single phase
Power Requirement Current Per Input DC Input Voltage Power Requirement Current Per Input
90 to 132 VAC, 180 to 264 VAC (47 to 63 Hz) 100 to 240 VAC, 50 to 60 Hz, 5.0-7.1 A
-48 or -60 VDC, 18 A -36 to -75 VDC -48 or -60 VDC, 18 A
Operating Temperature Humidity Altitude Shock Vibration Noise Non-Operating Temperature Humidity Altitude Shock Vibration -40C to 65C (-40F to 149F) 0% to 90% relative to 27C, noncondensing -30 m to 12,192 m (-100 to 40,000 ft.) 15.0 G, 11-ms, half-sine 1.0 G, 5-500 Hz, swept-sine 5C to 40C (41F to 104F) 10% to 90% relative to 38C, noncondensing -30 m to 3048 m (-100 to 10,000 ft.) 5.0 G, 11-ms, half-sine 0.2 G, 5-500 Hz, swept-sine LWAD* = 6.6 Bels
*Note: LWAD (1 Bel = 10dB) Declared noise emissions in accordance with ISO 9296, measured at 23C
Meets or exceeds the following requirements: UL listed UL 60950:2000, CSA-C22.2 No. 60950-00, EN 60950:2000, IEC 60950, TUV, CB Scheme, GOST-R Mark, S-Mark, FCC Part 15 Class B, CISPR 22 55022:1998 Class B, ICES-003 VCCI Class B, EN AS/NZS 3548:1996, BSMI CNS 13438 Class B, S Mark IEC 61000-3-2:2000, IEC1000-3-3:1995/A1:2001 CSIPR 24 EN 55024 NEBS Level 3 (GR-63-CORE; GR-1089-CORE), MIL-STD-810F, ETSI EN 300 386

Safety

Emission Harmonics Immunity Other
Height Width Depth Weight
8.8 cm (3.5 in.) (2.0 U) 44.7 cm (17.6 in.) 53.3 cm (21.0 in.) 22.7 kg (50 lb.)

Glossary

active-active controllers A pair of components, such as storage controllers in a failure-tolerant RAID array that share a task or set of tasks when both are functioning normally. When one component of the pair fails, the other takes the entire load. Dual active controllers (also called dual-active controllers) are connected to the same set of devices and provide a combination of higher I/O performance and greater failure tolerance than a single controller. American National Standards Institute A process where data is automatically reconstructed after a drive failure and written to a standby (spare) drive. An automatic rebuild will also occur when a new drive is installed manually in place of a failed drive. If the rebuild process is interrupted by a reset, use the Rebuild command on the Array Administration menu to restart the rebuilding process. The background rate is the percentage of available array controller CPU time assigned to array administration activities, such as rebuilding failed drives, checking parity, and initialization. If the background rate is set to 100%, the array administration activities have a higher priority than any other array activity. At 0%, the array administration activity is done only if there is no other activity on the array controller. A measure of the capacity of a communication channel, usually specified in MB/second. Memory on the RAID controller card, which permits intermediate storage of, read and write data without physically reading/writing from/to the disk, which can increase overall performance under certain conditions. Allows data to be stored in a pre-designated area of a disk or RAM (random access memory). Caching is used to speed up the operation of RAID arrays, disk drives, computers and servers, or other peripheral devices. Channel Any path used for the transfer of data and control information between storage devices and a storage controller or I/O adapter. Also refers to one Fibre bus on a disk array controller. Each disk array controller provides at least one channel. International Special Committee on Radio Interference Command line interface. Inside the same drive array enclosure, a single contiguous drive channel supporting 12 drives concurrently Software device address that identifies the controller/LUN, such as cXtYdZs0, where X is the host bus adapter, Y is the controller, and Z is the LUN. s0 slice number is used by the system, not by RAID Manager. Two or more drives configured as a Drive Group (see next). A physical set of drives configured as an array. Drive groups are defined during configuration. An enclosure containing a group of drives, power supplies, cooling fans, I/O cards, and mid-planes (no RAID controller/controllers); generally, an external drive array that is used to daisy chain to an existing hardware based RAID configuration. A mode of operation for failure-tolerant arrays in which a component has failed and its function has been assumed by a redundant component. Allows disk write commands to be safely acknowledged to the host before the data is actually written to the disk media. This can be enabled/disabled through the storage management software. The capacity to cope with internal hardware problems without interrupting the array's data availability, often by using backup systems brought online when a failure is detected. Many arrays provide fault tolerance by using RAID architecture to give protection against loss of data when a single disk drive fails. Using RAID 1 (mirroring), RAID 3 or 5 (striping with parity), or RAID 6 or 1+0 (mirroring and striping) techniques, the array controller can reconstruct data from a failed drive and write it to a standby or replacement drive. A logical drive that provides protection of data in the event of a single drive failure by employing RAID 1, 3, 5, or 6 (also known as RAID 1+0). Fibre Channel-Arbitrated Loop. FC-AL is implemented as either a loop. A loop can contain up to 126 nodes. A cost-effective 2/1-gigabit communications link deployed across a wide range of hardware. Fibre channel adapters of a host computer, server, or workstation. An Arbitrated Loop Hub is a wiring concentrator. "Arbitrated" means that all nodes communicating over

ANSI automatic rebuild

background rate

bandwidth cache

caching

CH channel

CISPR CLI concatenated channel device name
disk array drive group expansion drive array
failover fast write fault tolerance
fault tolerant logical drive FC-AL Fibre channel Fibre channel HBAs Fibre hubs
this Fibre loop are sharing a 100MBps segment. Whenever more devices are added to a single segment, the bandwidth available to each node is further divided. A loop configuration allows different devices in the loop to be configured in a token ring style. With a Fibre Hub, a Fibre loop can be re-arranged in a star-like configuration for the Hub itself contains port bypass circuitry that forms an internal loop inside. Bypass circuits can automatically reconfigure the loop once a device is removed or added without disrupting the physical connection to other devices. FRU full-duplex GB GBIC groups Field-Replaceable Unit Data transmission in both directions at the same time. See also half-duplex and simplex. Gigabyte. 1,000,000,000 (one billion) bytes. Gigabit Interface Converter. A hot-swappable input/output device that plugs into a Gigabit Ethernet port or Fibre Channel. A group is a new data object that allows multiple servers to be contained under a single category, are similar in concept to domains, and allow you to organize servers within configuration service. Instead of a linear tree of all the managed servers, the configuration service operator can organize the servers into like sets or groups. In the case where many servers are present, groups allow more icons to appear at the same time in the main configuration service window without scrolling. Groups are not required. You can configure configuration service for no groups and fifteen servers, for example, or for one group with ten servers underneath, with an additional five at the top level. Configuration service allows any combination. The number of groups permitted and the number of servers within a group is limited only by available array memory. If a server is a member of a group and a user deletes that group from the group list box, configuration service reassigns the servers in that group to the no group category. Configuration service automatically remaps the tree in the main window. Refers to an interface, such as Fibre, that can transmit data in only one direction at a time. See also fullduplex and simplex. Host Bus Adapter A card that connects a peripheral device to the computer system's I/O bus. The ability to remove, replace, or add a device while current I/O processes continue. A drive in a RAID 1 or RAID 5 configuration that is held in reserve to replace any other drive that fails. After a reconstruction, the hot-spare drive is returned to the standby status. The ability to remove, replace or add a device while power is still applied but all I/O processes are suspended. The ability of a field-replaceable unit (FRU) to be removed and replaced while the array remains powered on and operational. Identifier number International Electrotechnical Commission The process of writing a specific pattern to all data blocks on all drives in a logical drive. This process overwrites and destroys existing data on the disks and the logical drive. Initialization is required to make the entire logical drive consistent at the onset. Initialization ensures that any parity checks performed in the future will execute correctly. Input/output operations per second. A measure of I/O performance, this is usually used to quote random I/O performance. See throughput. Just a Bunch Of Disks. JBOD refers to a group of drives without an embedded RAID controller; generally, such a group is used without RAID formatting, with a host-based hardware RAID controller, or with RAID formatting from host software (with no hardware-base RAID controller) Local Area Network Logical drive A section of disk storage space, also referred to as a LUN, that is presented to the host operating environment as a single physical drive. A logical drive may be located on one or more physical drives. Each array controller can manage one to eight logical drives Logical unit number. A LUN is a set of physical drives in a RAID configuration which are seen by the operating system as one virtual drive. The ability to change the virtual LUN as presented to the server from storage. This enables such benefits as the ability of a server to boot from the SAN without requiring of a local disk drive. Each server requires LUN 0 to boot. The characteristic that enables an administrator to dynamically map an HBA to a specified LUN. This provides an individual server or multiple servers access to an individual drive or to multiple drives, and prohibits unwanted server access to the same drives. Megabyte. 1,000,000 bytes or characters of data. Data written to one disk drive is simultaneously written to another disk drive. If one disk fails, the other

S S A N n t t I I F C 0 ANne e I I U

SPECIFICATION SHEET SPECIFICATION SHEET
Powerful, rack-dense, scalable, super-rugged Fibre Channel RAID disk array.
Adapts to your unique requirements. Highly flexible arrays with hundreds of possible configurations that can be cost-matched to most any application workload and data critical requirement. In addition, the SANnet II FC provides the option to seamlessly connect SANnet II SATA array expansion trays to your FC environment to create a simple, easily managed, tiered storage architecture. 8 FC ports enable connectivity of up to 8 directattached servers can eliminate the need for costly external switches and reducing management overhead. Packs 3.6TB into a fully hot-swap redundant, multiport, multi-LUN, highly serviceable 2U enclosure. RAID arrays can be quickly scaled to over 32TB of raw capacity. Our efficient storage design allows you to store over 116TB in a single 42U rack. Highly ruggedized array meets full NEBS Level 3 certification and complies with MIL-STD-810F specifications.

The powerful 2Gb SANnet II FC array provides a modular, building-block approach and high port counts to help reduce costs. Up to four dual-path or eight single path servers can be connected to a dual controller tray without using costly switches and extra cabling. With its highly intuitive management interface, this array is extremely easy to deploy, configure, manage, and monitor. With affordable, enterprise-class features and functionality, the SANnet II FC array leads the industry with dual hot-swap power and cooling, hot-swap redundant RAID controllers with mirrored cache, hot-swap disk drives, global and local hot sparing, dynamic LUN expansion, dynamic capacity expansion, non-disruptive firmware code loading, and remote status monitoring.

Adaptable.
SANnet II FC Specifications

GENERAL

Product Family Product Type Chassis Configuration Storage Architecture Supported Hosts Total Capacity Total Disks Mounting Options Max Number of Chassis Max Capacity per Chassis
SANnet II RAID, JBOD 2U, 12 drives SAN or DAS Up to 64 Up to 32.4TB with 300GB FC drives Up to 108 FC; or up to 72 mixed SATA & FC Rack mount 9 (1 RAID and 8 JBOD) 3.6TB (300GB FC drives) 6TB (500GB SATA drives)
ENVIRONMENTAL - OPERATING
Temperature Humidity Altitude Shock Vibration Noise Heat

5C to 40C (41F to 104F) 10% to 90% 27C (81F) non-condensing -30m to 3048m (-100ft to 10,000ft) 5.0G, 11ms, half-sine 0.2G, 5-500Hz, swept-sine Less than LwAd 6.7B (65 dBA) 1200 BTU/hour

ENVIRONMENTAL NON-OPERATING
Temperature Humidity Altitude Shock Vibration

Host Connection Interface Type External Ports
4/8 Ports - Fibre Channel 2 Gbit Fibre Channel 4 per expansion JBOD
--40C to 65C (--40F to 149F) 0% TO 90% 38C (100F) non-condensing -30m to 12,192m (-100ft to 40,000 ft) 15.0G, 11ms, half-sine 1.0G, 5-500Hz, swept-sine

HIGH-AVAILABILITY FEATURES
Redundant Hot-Swap Controllers Redundant Hot-Swap Disks Redundant Hot-Swap Fans Redundant Hot-Swap Power Dual Power Cords Multiple Hot Standby Spare Automatic Failover Alternate Pathing Yes Yes Yes Yes Yes Yes Yes Yes

DRIVES

Max Number of Drives Drive Options
108 FC 73GB, 146GB or 300GB at 10,000 RPM FC 36GB, 73GB or 146GB at 15,000 RPM SATA 250GB or 500GB at 7,200 RPM

Levels Supported RAID Type Cache Memory Cache Backup Arrays per System Partitions per Array Volumes per System Mirrored Cache Battery Cache Backup Flash Cache Backup
0, 1, 3, 5, 10, 30, 50 or JBOD Hardware 1GB per controller Battery, 72 hours 1 to to to 1024 Yes Yes Yes

REGULATORY

Safety Emissions

Harmonics and Flicker Immunity Other Country Approvals

MANAGEMENT

Interface Types Protocols Supported Management Consoles Management Software
Serial, Ethernet, FC SMI-S 1.02, SNMP, API JAVA, GUI, CLI, API Dot Hill SANscape with MPIO support
UL listed, cUL, CSA-C22.2 EN 60950:2000, IEC 60950, GS, S-Mark FCC Part 15 Class B, ICES-003, EN 300-386, EN 55022 Class B, VCCI Class B, AS/NZS 3548, Class B, BSMI Class B EN 61000-3, EN 61000-3-3 EN 300-386, EN 55024 NEBS Level 3 (GR-63; GR-1089) MIL-STD-810F, ETSI EN USA, European Union (EU), Canada, Argentina, Taiwan, Japan, Australia 2 Years Yes, via SMI-S, SNMP, CLI, API Yes Yes Yes Yes

SUPPORT

ELECTRICAL AC INPUT

Voltage Current Power

100-240 VAC @ 50/60Hz, single phase 10A maximum per input 360W typical
Standard Hardware Warranty Environmental Monitoring Phone-home Capability Remote Diagnostics Non-disruptive Updates Non-disruptive Volume Expansion

PHYSICAL

ELECTRICAL DC INPUT

-36 to -72 VDC, -48v nominal 20A maximum per input 360W typical
Height Depth Width Chassis Weight Chassis w/Drives Weight
8.75cm (3.45 inches) 53.3cm (21.0 inches) 44.7cm (17.6 inches) 27.2kg (60lbs.) 34.0kg (75lbs.)
Corporate Headquarters: 2200 Faraday Avenue, Suite 100 Carlsbad, CA 92008 USA 800-872-2783 760-931-5500 Fax: 760-931-5527
Europe: Marssteden TD Enschede THE NETHERLANDS 31-53-428-4980
Asia-Pacific: Chiyoda Trade Ctr., Bldg. 4F 2-3-3 Uchi-Kanda, Chiyoda-Ku Tokyo 101-0047 JAPAN 81-3-3251-1690
2006 Copyright Dot Hill Systems Corporation. All rights reserved. Dot Hill Systems Corp., Dot Hill and the Dot Hill logo are trademarks of Dot Hill Systems Corp. Product names mentioned herein are trademarks and/or registered trademarks of their respective owners. Specifications and features may change without notice. 1-12-06