Click Here For New Huawei Blade Server Page
Featuring high energy efficiency, outstanding performance, high scalability and virtualization performance, E series blade server is an ideal choice for customers' growing business by consolidating computing, switching, storage, IOs and management subsystems into one single chassis.
The FusionServer E9000 converged-architecture blade server enables convergence of computing, storage, networking, and management.
It provides a powerful platform for high-end carrier or enterprise applications, and is ideal for data centers, virtualization, mission-critical services, and high-performance computing.
Provides 16 slots in a 12U chassis that includes redundant Power Supply Units (PSUs), heat-dissipation modules, management modules, and switch modules.
The Huawei E9000 server can be installed in a standard 19-inch rack at a depth of at least 1m. It is available with AC or DC power setups to suit data center requirements
 |
 |
Hightlight
Specification
|
Form Factor |
12U |
|
Blade |
16 half-width slots or 8 full-width slots Supports flexible configurations of full-width and half-width nodes |
|
Switch Modules |
4 slots for Huawei CX series switch modules provide a midplane switching capability of 15.6 Tbit/s CX110 GE switch module: 12 x GE + 4 x 10 GE uplink, 32 x GE downlink CX111 GE switch module: 12 x GE + 4 x 10 GE uplink, 32 x GE downlink CX116 GE pass-through module: 32 x GE uplink, 32 x GE downlink CX210 8G FC switch module: 8 x 8G FC uplink, 16 x 8G FC downlink CX220 16G FC Switch Module: 8 x 16G FC uplink, 16 x 16G FC downlink CX310 10 GE switch module: 16 x 10 GE uplink, 32 x 10 GE downlink CX311 10 GE/FCoE converged switch module: 16 x 10 GE + 8 x 8G FC uplink, 32 x 10 GE downlink CX317 10 GE pass through module: 32 x 10 GE uplink, 32 x 10 GE downlink CX318 10 GE pass through module: 32 x 10 GE uplink, 32 x 10 GE downlink CX611 InfiniBand switch module (QDR 40 Gbit/s, FDR 56 Gbit/s): 18 x QDR/FDR uplink, 16 x QDR/FDR downlink CX710 40 GE switch module: 8 x 40 GE uplink, 16 x 40 GE downlink CX912 multi-plane switch module; supports FC ports: 16 x 10 GE + 8 x 8G FC uplink, 32 x 10 GE + 16 x 8G FC downlink CX915 multi-plane switch module: 4 x 10 GE + 12 x GE + 8 x 8G FC uplink, 32 x GE + 16 x 8G FC downlink |
|
PSU |
AC/DC PSU: maximum six 3,000W/2,000W AC or six 2,500W DC hot-swappable PSUs in N+N or N+M redundancy mode |
|
Fan Modules |
Provides 14 hot-swappable fan modules in N+1 redundancy mode |
|
Management |
|
|
Power Supply |
110V/220V AC or –48V DC |
|
Operating Temperature |
5°C to 40°C |
|
Dimensions |
Height: 530 mm (20.87 in.) Width: 442 mm (17.40 in.) Depth: 840 mm (33.07 in.) |
| Model | Picture | Width | brief introduction |
| CH121 |  |
half width 2-socket | E5-2600 V3/V4 family contain up to two 22-core processors to power each compute node, 24 DDR4 DIMMs, providing a maximum memory capacity of 1.5 TB |
| CH140 |  |
Two 2-socket, twin compute nodes in a half-width slot | Supports the full series of Intel® Xeon® E5-2600 V3/V4 processors to deliver up to 2 x 22-core of computing capacity; a half-width slot supports two small slots in two layers for installing two independent 2-socket compute node |
| CH220 |  |
Full-width 2-socket I/O Expansion Compute Node | E5-2600 v3/v4 series delivers up to two 22-core processors on each node, Six standard PCIe card expansion slots for various PCIe configuration modes provide the best possible PCIe expansion capability on a single compute node |
| CH221 |  |
Full-width 2-socket I/O Expansion Compute Node | Supports the full series of Intel® Xeon® E5-2600 series quad-core, six-core, and eight-core processors to deliver up to 2*eight-core 2.9 GHz of computing power. Provides 24 DIMMs at 1.5 times the usual height. These apply mainstream granules and double the memory capacity to up to 768 GB DDR3 (providing the highest cost-efficiency for large-memory applications). Provides 4 PCIe x8 full-height half-length slots for installing 4 GPUs or PCIe SSDs, providing the best possible PCIe expansion capability on a single compute node |
| CH222 |  |
Full-width 2-socket Storage Expansion compute node | The CH222 provides superior computing performance and a large storage capacity. Featuring Intel® Xeon® E5-2600 series processors (up to 135 W) and support for up to 24 DIMM slots, 15 x 2.5" SAS/SATA HDD or SDD hard disks, and a 1 GB RAID cache, the CH222 is suitable for big-data analysis and processing applications that require large storage capacity and high computing performance, such as videos, searches, and biological sciences. |
| CH225 |  |
Full-width 2-socket All-flash Storage Expansion compute node | Supports up to 12 x 2.5-inch NVMe SSDs and 2 x 2.5-inch SAS/SATA HDDs or SSDs, delivering up to 9,600,000 IOPS. Delivers industry-leading NVMe storage capacity per node, Supports the full series and all specifications of Intel® Xeon® E5-2600 V3/V4 processors. Provides 2 x 22-core processors to deliver superior computing capability |
| CH226 | |
Full-width 2-socket Storage Expansion compute node | Intel® Xeon® E5-2600 V3/V4 processors to deliver up to 2 x 22-core of computing capacity, 24 DDR4 DIMMs, Supports 6 x 3.5 in. SAS/SATA HDDs and 2 x 2.5 in. SAS/SATA HDDs or SSDs, which provide the highest storage capacity on a single node |
| CH240 | |
Full-width 4-socket compute node | Supports Intel® Xeon® E5-4600 series processors, with up to 8 cores each, a 20 MB L3 cache, 8 GT/s QPI, hyper-threading, and Turbo acceleration technology. Provides 48 DIMMs at 1.5 times the usual height. These apply mainstream granules and provide the memory capacity of up to 1.5 TB DDR3 (providing the highest cost-efficiency for large-memory applications). Supports up to 8 x 2.5" SAS/SATA HDDs or SSDs, or SSDs (twice as many hard disks as competitors' 4-socket blade servers). |
| CH242 | |
Full-width 4-socket compute node | Supports new-generation Intel® Xeon® E7-4800 v2 series 8-core, 10-core, 12-core, and 15-core high-performance processors based on the Brickland platform, and provides outstanding computing performance with up to four 15-core 2.8 GHz processors. 4-socket compute node installed in a full-width slot, supports up to a maximum of 32 DDR3 DIMMs at 1.5 times the usual height that apply to mainstream granules, addressing large-memory-capacity applications at low cost. Supports a maximum of eight 2.5-inch SAS HDDs, SATA HDDs, or SSDs, and provides a maximum of 3 PCIe slots for standard PCIe cards. |
|
Key Competitiveness |
Key feature |
HP C7000 G8 |
IBM FlexSystem |
Cisco UCS G3 |
Huawei E9000 |
|
Engineering capability |
heat dissipation for front ,rear slots and power supply |
1200W/100W |
1200W/100W |
1200W/100W |
1400W/280W |
|
Computing capability |
Computing density |
32 |
56 |
16 |
64 |
|
Memory capacity |
Memory capacity per chassis (mainstream granules) |
8.2T |
10.8T |
6.14T |
12.3T |
|
Storage capability |
2.5" disk quantity per slot |
12 |
12 |
12 |
15 |
|
Computing and storage converged |
External SAN |
Internal SAN |
External SAN |
External SAN Internal DS |
|
|
network |
Backplane Bandwidth |
6.144Tbps |
7.168Tbps |
1.28Tbps |
15.6Tbps |
|
10GE/FCoE/8G FC/IB switch |
Y |
Y |
Y |
Y |
|
|
40GE |
Y |
N |
Y |
Y |
|
|
RoCE |
N |
Y |
N |
Y |
|
|
16G FC |
N |
Y |
N |
N |
|
|
PCIe expansion |
PCIe resources expansion |
N |
2*PCIe 8x+2*PCIe 16x |
N |
4*PCIe 8x or 2*PCIe 16x |
|
Running environment |
Ambient temperature |
5°C~35°C |
5°C~40°C |
5°C~35°C |
5°C~40°C |
|
HUAWEI E9000 |
DELL M1000e |
IBM FlexSystem |
SuperMicro SuperBlade |
|
|
Quantity of CPUs/Chassis |
64 |
32 |
32 |
40 |
|
Single node maintenance |
Yes |
Yes |
No |
No |
|
Quantity of memory channel |
8 |
6 |
6 |
8 |
|
HUAWEI E9000 |
DELL M1000e |
IBM FlexSystem |
|
|
Quantity of HDDs per slot |
15 |
7 |
12 |
|
Quantity of HDDs per chassis |
120 |
56 |
84 |
|
HUAWEI E9000 |
DELL M1000e |
IBM FlexSystem |
HP C7000 |
|
|
Backplane bandwidth |
15.6T |
8.96T |
6.27T |
7.168T |
|
Quantity of 10GE |
128 |
48 |
88 |
64 |
Huawei FusionServer E9000 (E9000 for short) is a new-generation blade server designed for cloud computing and big data applications based on comprehensive analysis of HP's C7000 (launched in 2007), Cisco's UCS5108 (launched in 2009) and VCE Vblock (launched in 2010).
| Huawei Advantage | Customer Benefits | Competitor' defense and Huawei's HTB Strategy |
| No. 1 computing density in the industry. Number of processors in a 1U chassis: ● Huawei E9000: 5.3/U ● HP C7000: 3.2/U ● HP C3000: 2.7/U |
E9000 provides high computing density and performance. | Competitors' defense: HP C7000 servers are transformed from CPU stacking to CPU+GPU heterogeneous computing. Huawei HTB strategy: ● The number of GPU nodes occupies only 20% in HC cluster. Heterogeneous computing has limited application. ● The E9000 server (configured with CH220 IO nodes) supports CPU+GPU. |
| No. 1 storage density in the industry. Number of 2.5" hard disks in a 1U chassis: ● Huawei E9000: 12/U ● HP C7000: 9.6/U ● HP C3000: 8/U |
High storage density ensures high concurrent read and write performance. The concurrent read and write performance is determined by PCIe bandwidth or hard disk IOPS upper limit. | Competitors' defense: HP D2200sb DAS nodes can be combined with adjacent blades, while Vendor H CH222 nodes cannot. Huawei's HTB strategy: A D2200sb combined with two adjacent blades provides up to 12 hard disks. However, the D2200sb cannot be combined with E7 4-socket blades. A 2-socket blade of E9000 provides 15 hard disks, and a 4-socket blade provides 8 hard disks. Vendor H's C7000 servers do not support PCIe SSD cards, while E9000 storage nodes (except CH140 and CH240) support PCIe SSD cards. |
| No. 1 switching capability in the industry. Design bandwidth of the backplane: ● Huawei E9000: 15.6 Tbit/s ●HP C7000 platinum: 6.144 Tbit/s |
The E9000 backplane supports 100GE and IB EDR, maximizing return on investment (ROI). | Competitors' defense: The E9000 provides four switch slots, while the HP C7000 provides 8 switch slots. Huawei's HTB strategy: The E9000 provides multi-plane switch modules. Two switch planes are created in a slot. The E9000 supports hybrid networking of Ethernet +FC SAN, IB, and FCoE modules. Except IB, all E9000 switch modules support layer3 switching, while Vendor H's servers support only layer 2 switching. |
| No. 1 engineering capability in the industry. Power supply and heat dissipation capability of a full-width slot: ● Huawei E9000:1400 W/40°C ●HP C7000:1200 W/35°C |
This feature improves system reliability and availability and reduces the PUE of data centers. | Competitors' defense: The temperature of 77% data centers is set to 18°C to 21°C. It is seldom for servers to operate at 40°C. In addition, the servers operating at 40°C consume more power. The E9000 servers do not support three-phase power. Huawei's HTB strategy: ● According to statistics, 7% power consumption is generated to reduce the temperature by 1°C. Nowadays, the cooling devices account for more than 40% of the devices in data centers. Overcooling causes waste of energy. If the data center temperature increases by 5°C in the world, the total carbon dioxide emission will be reduced by 1.7 million tons and electricity of 24.3 billion degrees will be saved. The E9000 servers use intelligent power management fan modules and orthogonal air duct design, which consumes 5% less power at the same CPU load. ● The E9000 servers support three-phase power supply converted by PDUs. |
| Claimed Advantage | Customer Benefits | Competitor' defense and Huawei's HTB Strategy |
| 10U chassis ● HP C7000: 4 C7000s in a cabinet ● Huawei E9000: 3 E9000s in a cabinet |
The high-density design saves floor space. | ● The power distribution for a cabinet in 95% data centers is 6 kW to 10 kW, which supports one high-end blade or two to three low-end blades. ● A 42U cabinet can hold three 12U E9000 servers, leaving 6U space for other devices. |
| Supports 8 interconnected switch modules. ● HP C7000: provides 8 slots for switch modules ● Huawei E9000: provides 4 slots for switch modules |
The C7000 servers support a wide variety of switch modules, allowing flexible networking. | ● According Gartner statistics, data center converged networking will be the mainstream networking mode in the near future. ● The E9000 servers support FCoE networking as well as multi-plane networking, offering flexible configuration and deployment. |
| Compatible with the blade servers of the same vendor. ● HP C7000: supports x86/AMD/work station/Unix blades/NAS gateway/blade tape drive/SAS switch modules ● Huawei E9000: supports only x86 blades. |
High compatibility help maximize ROI of customers. | x86 servers account for 90% in the server market. The market share of non-x86 servers is decreasing. ● The E9000 CH220/221 nodes support work stations. ● The demand for blade tape drivers is less than 1%. If required, the E9000 server can meet customer requirements by using an external tape drive. The use of SAS switch modules and JBOD causes the similar cost as the IP SAN but offers poorer reliability than IP SAN. If NAS gateway blades are used, the servers must have WSS installed on compute blades and connect to vendor H's SAN storage. This configuration causes high costs and low reliability. Customers can achieve the same purpose by using an external storage |
| Provides an LCD on the front panel. ● HP C7000: LCD ● Huawei E9000: touchscreen |
The LCD helps maintenance personnel learn about the server status in real time. | The Huawei E9000 server provides a touchscreen. |
| Implements unified management. ● HP C7000: OneView ● Huawei E9000: eSight |
OneView implements unified management of computing, storage, and network resources, simplifying management and increasing O&M efficiency. | ●Huawei eSight implements unified management of servers. ● Huawei eSight and E9000 internal management modules support stateless computing, implement plug-and-play of E9000 servers in site deployment, equipment migration, and parts replacement. |
| Provides high power efficiency and optimal heat dissipation. ● Huawei E9000: 1400 W/40°C ● HP C7000: 1200 W/35°C |
This feature helps reduce power costs | ●If HP C7000 servers use common blades with high power-consuming CPUs, at least 4 to 12 memory modules must be configured. ● The E9000 servers support 1400 W full-width and 700 W half-width nodes, E5-2600 v2 and E7-4800/8800 v2 series processors, and K1/K2/K2000/K4000 /Intel Phi PCIe cards. |
Huawei FusionServer E9000 (E9000 for short) is a new-generation blade server designed for cloud computing and big data applications based on comprehensive analysis of HPE's C7000 (launched in 2007), Cisco's UCS5108 (launched in 2009) and VCE Vblock (launched in 2010).
| Huawei Advantage | Customer Benefits | Competitor' defense and Huawei's HTB Strategy |
| No. 1 computing density in the industry. Number of processors in a 1U chassis: ● E9000: 5.3/U ● UCS: 2.7/U |
E9000 provides high computing density and performance. | Competitors' defense: The CH140 compute node of E9000 provides only 8 memory slots and can be configured with a maximum of 24 memory modules. It offers poor memory performance. Huawei's HTB strategy: ● The memory performance is determined by the communication bandwidth between the memory and the CPU. The memory bandwidth is determined by the maximum number of memory channels and memory frequency. The IvyBridge EP platform supports up to 8 memory channels. The CH140 provides 8-channel memory and supports memory modules of the highest frequency. It provides high read and write performance. ● The top two drawbacks of USC servers in clusters are long delay and poor CPU performance. |
| No. 1 storage density in the industry. Number of 2.5" hard disks in a 1U chassis: ● E9000: 12/U ● UCS: 2.7/U |
High storage density allows large local storage space and high concurrent read and write performance. The concurrent read and write performance is determined by PCIe bandwidth or hard disk IOPS upper limit. | Competitors' defense: The CH222 storage nodes of E9000 cannot provide shared storage resources to other blades. Huawei's HTB strategy: The CH222 running Vendor H DSware software can group the local 15 hard disks as a virtual storage resource pool to support more servers. It implements the SAN storage functions. The DSware computing and storage convergence architecture allows a cabinet to provide 1000 Gbit/s (SAN 128 Gbit/s) concurrent bandwidth and 96 Gbit/s SSD (SAN 12 Gbit/s SAS) throughput. |
| No. 1 switching capability in the industry. Design bandwidth of the backplane: ● E9000: 15.6 Tbit/s ● UCS: 1.28 Tbit/s |
The E9000 backplane supports 100GE and IB EDR, maximizing return on investment (ROI). | Competitors' defense: The multi-plane networking of E9000 causes complicated deployment and management. The UCS single switching plane implements convergence of services and management as well as convergence of switching and FC SAN, simplifying deployment. Huawei's HTB strategy: The UCS servers build a unified computing, storage, and management network based on FCoE Fabric Interconnect. However, the networking does not support IB interconnection. The E9000 servers support multi-plane networking as well as FCoE networking. Vendor H eSight implements unified management of servers. |
| No. 1 engineering capability in the industry. Power supply and heat dissipation capability of a full-width slot: ● E9000: 1400 W/40°C ● UCS: 1200 W/35°C |
This feature improves system reliability and availability and reduces the PUE of data centers. | Competitors' defense: The temperature of 77% data centers is set to 18°C to 21°C. It is seldom for servers to operate at 40°C. In addition, the servers operating at 40°C consume more power. Huawei's HTB strategy: ● According to statistics, 7% power consumption is generated to reduce the temperature by 1°C. Nowadays, the cooling devices account for more than 40% of the devices in data centers. Overcooling causes waste of energy. If the data center temperature increases by 5°C in the world, the total carbon dioxide emission will be reduced by 1.7 million tons and electricity of 24.3 billion degrees will be saved. The E9000 servers use intelligent power management fan modules and orthogonal air duct design, which consumes 5% less power at the same CPU load. ● A fire was caught due to poor heat dissipation of UCS servers. |
| Claimed Advantage | Customer Benefits | Competitor' defense and Huawei's HTB Strategy |
| Unified computing Provides stateless computing Configuration drift among blade and rack servers | Plug-and-play servers reduce deployment time. | ● The E9000 servers support stateless computing and allow plug-and-play of blades in initial deployment, system migration, and parts replacement. ● The UCS5108 servers offer poor resource expansion. The E9000 servers can be configured with CH222 storage nodes and CH220/221 I/O expansion nodes, which offer more advantages in big data and VDI applications. |
| Unified network Use UCS 6200 FI series FCoE switches to unify LAN /SAN and management planes. Use FEX 2200 series I/O cards to replace switch modules | Unified network simplifies networking and costs. One set of FI switch performs switching and management of a maximum of 160 blade and rack servers. The subsequent expansion cost is low. | ● The networking mode restricts the UCS5108 servers in convergence and virtualization applications. ● The UCS5108 servers do not support IB interconnection, and the chassis does not support evolution to 100GE. ● The UCS servers use private network protocols. ● The E9000 servers offer lower expansion costs than the UCS5108 servers. E9000 servers, CX310 switches, and external FCoE switches with an uplink convergence ratio (blades to external switches) of 1:4 to a unified LAN+SAN network. |
| Unified management The FI built-in UCS Manager implements unified management of servers, LAN, and SAN. The cost-efficient FEX cards implement management and I/O connection of subracks and FI switches. One set of FI can manage up to 160 blade and rack servers. | Unified management reduces O&M costs. | Huawei eSight implements unified management of servers, LAN, and SAN device |
Huawei E9000 base with 6 compute nodes and 10GE uplinks
| No. | Part Number | Model | Description | Unit Qty. | Qty. | Note |
| E9000 Basic Package: 6 CH121v3 10G Nodes with 16*10G Uplink Switch Module | ||||||
| 1 | E9000 | 1 | ||||
| 1.1 | Chassis Basic Configuration | |||||
| 02301029 | IT1K21E9000 | 12U standard integrative module with Delivery Accessory | 1 | 1 | ||
| 03054675 | IT1DSMMA0000 | MM910,Shelf Management Module A | 2 | 2 | ||
| 03030QEJ | IT0E01FAN000 | OSCA Fan Box | 14 | 14 | ||
| 02310LKL | IT1MPOWERM00 | 3000W platinum AC power supply unit | 6 | 6 | ||
| 1.2 | Switch Module | |||||
| 03054849 | IT1DXCUB00 | CX310,16*10GE Converged Switch Module | 2 | 2 | 16 x 10GE uplink to switch OUTSIDE E9000 Chassis; 32 x 10GE downlink to compute nodes within E9000; e.g: CH121v3 in this case. | |
| 1.3 | Optional Equipments | |||||
| 21240817 | EGUIDER05 | 4U Static Rail Kit | 1 | 1 | ||
| CH121 V3_Site1 | ||||||
| 2 | E9000 | 6 | ||||
| 2.1 | Blade Basic Configuration | |||||
| 2.1.1 | Blade MotherBoard | |||||
| 03056132 | IT11SGCA05 | Grantley EP Compute Node,CH121 V3 | 1 | 6 | ||
| 2.1.2 | Haswell EP CPU | |||||
| 41020498 | EHSE52620 | Intel Xeon E5-2620 v3(2.4GHz/6-core/15MB/85W) Processor | 2 | 12 | ||
| 2.1.3 | DDR4 Memory | |||||
| 06200201 | N21DDR432 | DDR4 RDIMM Memory,32GB,2133MT/s,2Rank(2G*4bit),1.2V,ECC | 4 | 24 | ||
| 2.1.4 | Hard Disk(include Front Panel) | |||||
| 02311HAL | N900S1210W2 | HDD,900GB,SAS 12Gb/s,10K rpm,128MB or above,2.5inch(2.5inch Drive Bay) | 2 | 12 | ||
| 2.1.5 | RAID Card and Other Accessories | |||||
| 03021FTX | BC0MESMCE600 | RU120 SAS/SATA RAID Card,RAID0,1,10,1E,0 Cache(LSI2308) | 1 | 6 | ||
| 2.1.6 | Network Mezz Card | |||||
| 03022YMY | IT11MXEM | MZ310,2*10G Mezzanine Card | 1 | 6 | Network Adapter On Compute Node; 2 Port 10G connect to switch module internally, e.g: CX310 in this case | |
Huawei E9000 base with 8 compute nodes, 10GE uplink and 8G Fibre Channel connections
| No. | Part Number | Model | Description | Unit Qty. | Qty. | Note |
| E9000 6 Compute Node with 10G Ethernet uplink and 8G SAN Package | ||||||
| 1 | E9000 | 1 | ||||
| 1.1 | Chassis Basic Configuration | |||||
| 02301029 | IT1K21E9000 | 12U standard integrative module with Delivery Accessory | 1 | 1 | ||
| 03054675 | IT1DSMMA0000 | MM910,Shelf Management Module A | 2 | 2 | ||
| 03030QEJ | IT0E01FAN000 | OSCA Fan Box | 14 | 14 | ||
| 02310LKL | IT1MPOWERM00 | 3000W platinum AC power supply unit | 6 | 6 | ||
| 1.2 | Switch Module | |||||
| 03056858 | IT11XCUA08 | CX912,16*10GE Port,8*8G FC Port(4-Uplink Port Activate,Brocade),Multi-Plane Switch Module | 2 | 2 | 16 x 10GE uplink to switch OUTSIDE E9000 Chassis; 32 x 10GE downlink to compute nodes within E9000; e.g: CH121v3 in this case. 8*8G FC Port connects to OUTSIDE SAN Storage;can be extended to 16*8G FC with license. |
|
| 05330492 | BC0LICENSE02 | FCSwitch-Brocade-ISL Trunking License License | 2 | 2 | ||
| 05330493 | BC0LICENSE01 | FCSwitch-Brocade-Full Fabric License | 2 | 2 | ||
| 1.3 | Optional Equipments | |||||
| 21240817 | EGUIDER05 | 4U Static Rail Kit | 1 | 1 | ||
| CH121 V3_Site1 | ||||||
| 2 | E9000 | 6 | ||||
| 2.1 | Blade Basic Configuration | |||||
| 2.1.1 | Blade MotherBoard | |||||
| 03056132 | IT11SGCA05 | Grantley EP Compute Node,CH121 V3 | 1 | 6 | ||
| 2.1.2 | Haswell EP CPU | |||||
| 41020498 | EHSE52620 | Intel Xeon E5-2620 v3(2.4GHz/6-core/15MB/85W) Processor | 2 | 12 | ||
| 2.1.3 | DDR4 Memory | |||||
| 06200201 | N21DDR432 | DDR4 RDIMM Memory,32GB,2133MT/s,2Rank(2G*4bit),1.2V,ECC | 4 | 24 | ||
| 2.1.4 | Hard Disk(include Front Panel) | |||||
| 02311HAL | N900S1210W2 | HDD,900GB,SAS 12Gb/s,10K rpm,128MB or above,2.5inch(2.5inch Drive Bay) | 2 | 12 | ||
| 2.1.5 | RAID Card and Other Accessories | |||||
| 03021FTX | BC0MESMCE600 | RU120 SAS/SATA RAID Card,RAID0,1,10,1E,0 Cache(LSI2308) | 1 | 6 | ||
| 2.1.6 | Network Mezz Card | |||||
| 03022XBT | IT11MXEL | MZ912-2*10GE,2*8G FC Mezzanine Card | 1 | 6 | Network/SAN Adapter On Compute Node; 2 Port 10G connect to switch module internally, e.g: CX912 in this case 2*8G FC Connects internal SAN switch, in this case, CX912 |
|
