H3C UniServer R4900 G7 U Series Air-Cooled and Cold Plate-Based Liquid-Cooled Server User Guide-5W100

HomeSupportServersH3C UniServer R4900 G7Technical DocumentsInstall & UpgradeInstallation GuidesH3C UniServer R4900 G7 U Series Air-Cooled and Cold Plate-Based Liquid-Cooled Server User Guide-5W100
02-Appendix A Specifications and support information

Component specifications

For the server-compatible components and detailed information, visit the Compatibility Matrix by Server Model at http://www.h3c.com/en/home/qr/default.htm?id=66.


Operating temperature specifications

 

NOTE:

The cooling capability of the server depends on the power density of devices within the cabinet, the cooling capability of the cabinet, and the spacing between the server and other devices.

 

Table 1 shows the operating temperature specifications of the server.

Table 1 Operating temperature requirements without liquid-cooled module

Drive configuration

Maximum temperature

Remarks

30°C (86°F)

35°C (95°F)

40°C (104°F)

8LFF

When a full-length GPU (such as a rear L20) is installed, processors rated at 550 W or higher are not supported.

When a full-length GPU (such as a rear L20) is installed, processors rated at 550 W or higher are not supported.

The following are not supported:

·     All rear drives (including AIC and PCIe M.2)

·     Rear supercapacitor

·     OCP network adapters above 25G

·     MRDIMMs

·     Intelligent network adapters

·     GPUs

·     96 GB and larger DIMMs

·     Delta DPS-1600AB-13 R 1600W Platinum AC power supply

·     Processors rated at 550 W or higher

Fan speed is not limited.

12LFF

When a full-length GPU (such as a rear L20) is installed, processors rated at 400 W or higher are not supported.

·     Delta DPS-1600AB-13 R 1600W Platinum AC power supplies are not supported.

·     Full-length GPUs (such as the L20) are not supported.

8LFF

When a full-length GPU (such as a rear L20) is installed, processors rated at 400 W or higher are not supported.

·     Full-length GPUs (such as the L20) are not supported.

Fan speed is limited to 80%.

12LFF

Full-length GPUs (such as the L20) are not supported.

·     Delta DPS-1600AB-13 R 1600W Platinum AC power supplies are not supported.

·     MR DIMMs are not supported.

·     Full-length GPUs (such as the L20) are not supported.

·     When a single fan fails (for fans with dual rotors, this applies to the failure of one rotor), the declared operating temperature is reduced by 5°C (41°F), and the maximum supported operating temperature must not exceed 35°C (95°F). The performance of DIMMs, MR DIMMs, GPUs with capacities of 64G or higher might decrease.

·     When GPUs and HDDs are installed, the fans will not be speed-limited.

·     When MRDIMMs and DIMMs of 96 GB or larger are installed, memory filler modules must be installed in the slots without DIMMs.

 

Table 2 Operating temperature requirements with liquid-cooled module

Drive configuration

Maximum temperature

Remarks

30°C (86°F)

35°C (95°F)

40°C (104°F)

8LFF

Supports all configurations

When a fanless OCP air baffle is used, OCP network adapters rated above 25G are not supported.

The following are not supported:

·     All rear drives (including AIC and PCIe M.2)

·     Rear supercapacitor

·     OCP network adapters above 25G

·     MRDIMMs

·     Intelligent network adapters

·     GPUs

·     96 GB and larger DIMMs

·     Delta DPS-1600AB-13 R 1600W Platinum AC power supply

Fan speed is not limited.

12LFF

Supports all configurations

·     Full-length GPUs (such as the L20) are not supported.

·     When a fanless OCP air baffle is used, OCP network adapters rated above 25G are not supported.

8LFF

Supports all configurations

Full-length GPUs (such as the L20) are not supported.

Fan speed is limited to 80%.

12LFF

Full-length GPUs such as the L20 are not supported

·     MR DIMMs are not supported.

·     When a fanless OCP air baffle is used, OCP network adapters rated above 25G are not supported.

·     GPUs (such as the L20) are not supported.

·     When a single fan fails (for fans with dual rotors, this applies to the failure of one rotor), the declared operating temperature is reduced by 5°C (41°F), and the maximum supported operating temperature must not exceed 35°C (95°F). The performance of DIMMs, MR DIMMs, GPUs with capacities of 64G or higher might decrease.

·     When GPUs and HDDs are installed, the fans will not be speed-limited.

·     When MRDIMMs and DIMMs of 96 GB or larger are installed, memory filler modules must be installed in the slots without DIMMs.

 


Technical support

If you encounter any complicated problems during daily maintenance or troubleshooting, contact H3C Support.

Obtaining the most recent firmware or software

To obtain the most recent firmware or software, access https://www.h3c.com/en/BizPortal/DownLoadAccessory/en_DownLoadAccessoryFilt.aspx.

Product security and compatibility

For information about the product security and compatibility, see the compliance and safety mannual for the server.

Collecting information

To facilitate troubleshooting, collect the following server information before contacting Technical Support:

·     Log information and sensor information.

¡     Log information , including the following:

-     Event log, operation log, and SDS log on HDM.

-     Diagnosis information in iFIST.

¡     Sensor information on HDM.

·     Product serial number.

·     Product model and name.

·     Error information screenshots and description.

·     Hardware change records, including adding, replacing, or re-installing hardware components.

·     Third-party software.

·     Operating system type and version.

Preparing maintenance tools

To facilitate troubleshooting, prepare the following tools: For more information about these tools, see "Installation tools."

·     T-25, T-15, and T-10 Torx screwdrivers.

·     T30 Torx screwdriver.

·     Flat-head screwdriver and Phillips screwdriver.

·     Cage nut insertion/extraction tool.

·     Diagonal pliers.

·     Multimeter.

·     Interface cable (such as an Ethernet cable or optical fiber).

·     Monitor (such as PC).

·     ESD wrist strap, antistatic gloves, and antistatic clothing.


Product recycling

New H3C Technologies Co., Ltd. provides product recycling services for its customers to ensure that hardware at the end of its life is recycled. Vendors with product recycling qualification are contracted to New H3C to process the recycled hardware in an environmentally responsible way.

For product recycling services, contact New H3C at

·     Tel: 400-810-0504

·     E-mail: [email protected]

·     Website: http://www.h3c.com


Glossary

Table 3 Glossary

Item

Description

B

BIOS

The Basic Input Output System (BIOS) is a collection of programs stored on a ROM chip on the server motherboard. It includes critical components such as the Basic Input Output Program, Power-On Self-Test (POST), and system startup programs. The BIOS provides the most fundamental and direct hardware settings and controls for the computer.

C

CPLD

Complex Programmable Logic Device (CPLD) is a type of digital integrated circuit that can construct logic functions according to requirements.

G

 

GPU

A GPU is one of the most important components of a server. It is used to convert digital signals from the server into analog signals, which are then displayed on a monitor. Additionally, a GPU has image processing capabilities and can assist CPUs in tasks, thereby enhancing the overall operational speed of the server.

H

HDM

Hardware Device Management (HDM) is a control unit used for server management. Through HDM, you can simplify the server configuration process, view server component information, monitor server operation status, and remotely control the server, among other functions.

Hot swapping

Hot swapping capability refers to the ability to remove or install a component in a server while the server is running, without the need to power down the server. This operation does not disrupt the running system and avoids any impact on its operation.

K

KVM device

A Keyboard, Video, Mouse (KVM) device is a physical device that allows you to monitor and manage multiple servers using a single set of keyboard, display, and mouse.

N

Network adapter

A network adapter is a network component that operates at the data link layer. It not only establishes a physical connection and electrical signal matching between the LAN transmission media but also provides functions such as frame transmission and reception, frame encapsulation and decapsulation, medium access control, data encoding and decoding, and data caching.

NVMe VROC module

Used to activate and achieve the RAID capabilities of NVMe drives in conjunction with the VMD technology.

R

RAID

Redundant Array of Independent Disks (RAID) is a technology used for combining multiple independent physical drives in different ways to create a disk array, providing higher storage performance and data security than a single drive.

Redundancy

Redundancy means that when a component, such as a fan, fails, the system can automatically utilize a backup component to replace the failed one.

T

Temperature sensor

A temperature sensor is used to detect the temperature at a specific location and transmits temperature information to the server system.

U

U

The IEC 60297-1 standard specifies the units of vertical height measurement for racks and enclosures in the form of "U" or "RU" (rack unit), where 1 U or 1 RU is equivalent to 44.45 millimeters.

UniBay drive backplane

A UniBay drive backplane is a backplane that supports SAS/SATA/NVMe drives.

UniSystem

UniSystem is a software program developed by H3C for server management. It allows for quick and flexible server configurations and intelligent guidance for users. With FIST, users can even develop their own tools. It is an intelligent and scalable server management tool.

V

VMD

The VMD technology provides hot-swapping capability, drive management, and fault tolerance features for NVMe drives, making them reliable, available, and serviceable.

 


Acronyms

Table 4 Acronyms

Item

Full name

B

BIOS

Basic Input Output System

C

CMA

Cable Management Arm

CPLD

Complex Programmable Logic Device

CPU

Central Processing Unit

D

DCPMM

Data Center Persistent Memory Module

DDR

Double Data Rate

DIMM

Dual Inline Memory Module

DRAM

Dynamic Random Access Memory

DVD

Digital Versatile Disc

G

GPU

Graphics Processing Unit

H

HBA

Host Bus Adapter

HDD

Hard Disk Drive

HDM

Hardware Device Management

I

IDC

Internet Data Center

K

KVM

Keyboard, Video, Mouse

L

LRDIMM

Load Reduced Dual Inline Memory Module

N

NCSI

Network Controller Sideband Interface

NVMe

Non-Volatile Memory Express

P

PCIe

Peripheral Component Interconnect Express

POST

Power-on Self Test

R

RAID

Redundant Array of Independent Disks

RDIMM

Registered Dual Inline Memory Module

S

SAS

Serial Attached Small Computer System Interface

SATA

Serial ATA

SD

Secure Digital

SDS

Secure Diagnosis System

SFF

Small Form Factor

sLOM

small form factor Local Area Network on Motherboard

SSD

Solid State Drive

T

TCM

Trusted Cryptography Module

TDP

Thermal Design Power

TPM

Trusted Platform Module

U

UID

Unit Identification

UPI

Ultra Path Interconnect

UPS

Uninterruptible Power Supply

USB

Universal Serial Bus

V

VROC

Virtual RAID on CPU

VMD

Volume Management Device

 

  • Cloud & AI
  • InterConnect
  • Intelligent Computing
  • Intelligent Storage
  • Security
  • SMB Products
  • Intelligent Terminal Products
  • Product Support Services
  • Technical Service Solutions
All Services
  • Resource Center
  • Policy
  • Online Help
  • Technical Blogs
All Support
  • Become A Partner
  • Partner Policy & Program
  • Global Learning
  • Partner Sales Resources
  • Partner Business Management
  • Service Business
All Partners
  • Profile
  • News & Events
  • Online Exhibition Center
  • Contact Us
All About Us