Although the widely acknowledged Ethernet speed upgrading path was 10G-40G-100G, web-scale data centers and cloud based services need servers with above 10GbE capability and cost sensitive for nearer-term deployment. It indicates that the latest path for server connection will be 10G-25G-100G with potential for future upgrading to 400G. But why 25G? Because moving from 10G to 40G is a big jump and it turns out that the incremental cost of 25G silicon over 10G is not that great. This new 25 Gigabit Ethernet standard will require improved cables and transceiver modules capable of handling this additional bandwidth. It is just under this circumstance that QSFP28 and SFP28 for 25 Gigabit Ethernet are promoted.
25 Gigabit Ethernet (25GbE) has passed the first hurdle in the IEEE standards body with a successful Call for Interest (CFI) in July, 2014. It is a proposed standard for Ethernet connectivity that will benefit cloud and enterprise data center environments. 25GbE leverages technology defined for 100 Gigabit Ethernet implemented as four 25-Gbit/s lanes (IEEE 802.3bj) running on four fibers or copper pairs.
The value of 25GbE technology is clear in comparison to the existing 40GbE standard. Obviously, 25GbE technology provides greater port density and a lower cost per unit of bandwidth for rack server connectivity. For applications that demand substantially higher throughputs to the endpoint, there exists 50GbE—using only two lanes instead of four—as a superior alternative to 40GbE in both link performance and physical lane efficiency.
The proposed 25GbE standard delivers 2.5 times more performance per SerDes lane using twinax copper wire than that available over existing 10G and 40G connections. A 50GbE link using two switch/NIC SerDes lanes running at 25 Gb/s each delivers 25% more bandwidth than a 40GbE link while needing just half the number (four) of twinax copper pairs. Therefore, a 25GbE link using a single switch/NIC SerDes lane provides 2.5 times the bandwidth of a 10GbE link over the same number of twinax copper pairs are used in today’s SFP+ direct-attach copper (DAC) cables.
Maybe the most outstanding benefit of 25GbE technology to data-center operators is maximizing bandwidth and port density within the space constraints of a small 1U front panel. It also leverages single-lane 25Gb/s physical layer technology developed to support 100GbE.
QSFP28 is used for 4x25GE and SFP28 is used for a single 25GE port. SFP28 module, based on the SFP+ form-factor, supports the emerging 25G Ethernet standard. It enables error-free transmission of 25Gb/s over 100m of OM4 multi-mode fiber and a new generation of high-density 25 Gigabit Ethernet switches and network interface cards, facilitating server connectivity in data centers, and a conventional and cost-effective upgrade path for enterprises deploying 10 Gigabit Ethernet links today in the ubiquitous SFP+ form factor. The QSFP28 (25G quad small form-factor pluggable) transceiver and interconnect cable is a high-density, high-speed product solution designed for applications in the data center and networking markets. The interconnect offers four channels of high-speed signals with data rates ranging from 25 Gbps up to potentially 40 Gbps, and will meet 100 Gbps Ethernet (4x25 Gbps) and 100 Gbps 4X InfiniBand Enhanced Data Rate (EDR) requirements. The following shows a QSFP28-SR4 module and a 10GBASE-SR SFP+ module (MA-SFP-10GB-SR).
The dominant next-generation server connection speed is going to be 25G as it providing a cost competitive longer reach option for mainstream customers. FS.COM has already introduced cost-effective QSFP28 modules, QSFP28 to QSFP28 cable as well as SFP28 cable. With advanced OEM technology and strict cost control, we can help you save more than 30%~50% off on the cost of the QSFP28 modules.
※コメント投稿者のブログIDはブログ作成者のみに通知されます