QoS Support for High Performance Scientific Grid Applications
- 格式:pdf
- 大小:451.91 KB
- 文档页数:10
Mellanox ConnectX-4 AdaptersProduct GuideConnectX-4 from Mellanox is a family of high-performance and low-latency Ethernet and InfiniBand adapters. The ConnectX-4 Lx EN adapters are available in 40 Gb and 25 Gb Ethernet speeds and the ConnectX-4 Virtual Protocol Interconnect (VPI) adapters support either InfiniBand or Ethernet.These adapters address virtualized infrastructure challenges, delivering best-in-class performance to various demanding markets and applications. Providing true hardware-based I/O isolation with unmatched scalability and efficiency, achieving the most cost-effective and flexible solution for Web 2.0, Cloud, data analytics, database, and storage platforms.The following figure shows the Mellanox ConnectX-4 2x100GbE/EDR IB QSFP28 VPI Adapter (the standard heat sink has been removed in this photo).Figure 1. Mellanox ConnectX-4 2x100GbE/EDR IB QSFP28 VPI Adapter (heatsink removed)Did you know?Virtual Protocol Interconnect (VPI) enables standard networking, clustering, storage, and management protocols to seamlessly operate over any converged network by leveraging a consolidated software stack. Each port can operate on InfiniBand, Ethernet, or Data Center Bridging (DCB) fabrics, and supports Ethernet over InfiniBand (EoIB) as well as RDMA over Converged Ethernet (RoCE). VPI simplifies I/O system design and makes it easier for IT managers to deploy infrastructure that meets the challenges of a dynamic data center.Click here to check for updatesFigure 2. ThinkSystem Mellanox ConnectX-4 Lx 10/25GbE SFP28 2-port OCP Ethernet Adapter Supported transceivers and cablesThis section lists the supported transceivers and cables:25 Gb Ethernet adapters25 Gb Ethernet adaptersThe following table lists the supported transceivers.Table 3. TransceiversPart number Feature code Description10Gb Transceivers46C34475053SFP+ SR Transceiver4TC7A78615BNDR ThinkSystem Accelink 10G SR SFP+ Ethernet transceiver4TC7A90142BWG5SFP+ 10G LR Transceiver PRC only (for China only)25Gb Transceivers4M27A67041BFH2Lenovo 25Gb SR SFP28 Ethernet Transceiver7G17A03537AV1B Lenovo Dual Rate 10G/25G SR SFP28 Transceiver4TC7A88638BYBJ ThinkSystem Finisar Dual Rate 10G/25G SR SFP28 TransceiverThe following table lists the supported cables.Table 4. Supported DAC cables - 25 Gb EthernetPart number Feature code Description25 GbE SFP28 DAC cables7Z57A03557AV1W Lenovo 1m Passive 25G SFP28 DAC Cable7Z57A03558AV1X Lenovo 3m Passive 25G SFP28 DAC Cable7Z57A03559AV1Y Lenovo 5m Passive 25G SFP28 DAC CableLC-LC OM3 Fiber Optic Cables (these cables require a transceiver)00MN499ASR5Lenovo 0.5m LC-LC OM3 MMF Cable00MN502ASR6Lenovo 1m LC-LC OM3 MMF Cable00MN505ASR7Lenovo 3m LC-LC OM3 MMF Cable00MN508ASR8Lenovo 5m LC-LC OM3 MMF Cable00MN511ASR9Lenovo 10m LC-LC OM3 MMF Cable00MN514ASRA Lenovo 15m LC-LC OM3 MMF Cable00MN517ASRB Lenovo 25m LC-LC OM3 MMF Cable00MN520ASRC Lenovo 30m LC-LC OM3 MMF Cable25Gb transceivers: When installed in this 25Gb Ethernet adapter, 25Gb transceivers are designed to operate at either 25 Gb/s or 10 Gb/s speeds as listed in the description of the transceiver, however the speed also depends on the negotiation with the connected switch. In most configurations, this negotiation is automatic, however in some configurations you may have to manually set the link speed or FEC mode.In addition, the 25Gb adapters also can share a connection to a 100 Gb switch using a 4:1 breakout cable. Supported breakout cables (fiber optic and AOC) are listed in the following table.Table 5. Breakout cables for connectivity to a 100Gb switchPart number Feature code DescriptionMTP-4xLC OM3 MMF Breakout Cable00FM412A5UA Lenovo 1m MPO-4xLC OM3 MMF Breakout Cable00FM413A5UB Lenovo 3m MPO-4xLC OM3 MMF Breakout Cable00FM414A5UC Lenovo 5m MPO-4xLC OM3 MMF Breakout Cable100G Breakout OM4 MPO Cables (these cables require a transceiver)7Z57A03573AV2B Lenovo 1m MPO to 4x LC Breakout OM4 MMF Cable7Z57A03574AV2C Lenovo 3m MPO to 4x LC Breakout OM4 MMF Cable7Z57A03575AV2D Lenovo 5m MPO to 4x LC Breakout OM4 MMF CableQSFP28 100Gb Ethernet Breakout Active Optical Cables7Z57A03552AV1S Lenovo 5m 100G to 4x25G Breakout Active Optical Cable7Z57A03554AV1U Lenovo 15m 100G to 4x25G Breakout Active Optical CableQSFP28 100G-to-4x25G Ethernet Breakout Cables7Z57A03564AV22Lenovo 1m 100G QSFP28 to 4x25G SFP28 Breakout DAC Cable 4Z57A85043BS32Lenovo 1.5m 100G to 4x25G Breakout SFP28 Breakout DAC Cable 4Z57A85044BS33Lenovo 2m 100G to 4x25G Breakout SFP28 Breakout DAC Cable 7Z57A03565AV23Lenovo 3m 100G QSFP28 to 4x25G SFP28 Breakout DAC Cable 7Z57A03566AV24Lenovo 5m 100G QSFP28 to 4x25G SFP28 Breakout DAC CableIn addition, the 25Gb adapters also support the following 10 GbE AOC/DAC cables.Table 6. Supported optical transceivers and DAC cables - 10 Gb EthernetPart number Feature code DescriptionSFP+ 10Gb Active Optical Cables00YL634ATYX Lenovo 1m SFP+ to SFP+ Active Optical Cable00YL637ATYY Lenovo 3m SFP+ to SFP+ Active Optical Cable00YL640ATYZ Lenovo 5m SFP+ to SFP+ Active Optical Cable00YL643ATZ0Lenovo 7m SFP+ to SFP+ Active Optical Cable00YL646ATZ1Lenovo 15m SFP+ to SFP+ Active Optical Cable00YL649ATZ2Lenovo 20m SFP+ to SFP+ Active Optical Cable10Gb SFP+ Passive DAC cables00D6288A3RG0.5m Passive DAC SFP+ Cable90Y9427A1PH1m Passive DAC SFP+ Cable00AY764A51N 1.5m Passive DAC SFP+ Cable00AY765A51P2m Passive DAC SFP+ Cable90Y9430A1PJ3m Passive DAC SFP+ Cable90Y9433A1PK5m Passive DAC SFP+ Cable00D6151A3RH7m Passive DAC SFP+ Cable10Gb SFP+ Active DAC cables00VX111AT2R Lenovo 1m Active DAC SFP+ Cables00VX114AT2S Lenovo 3m Active DAC SFP+ Cables00VX117AT2T Lenovo 5m Active DAC SFP+ CablesThe following figure shows the Mellanox ConnectX-4 Lx ML2 1x25GbE SFP28 Adapter.Figure 3. Mellanox ConnectX-4 Lx 10/25GbE SFP28 1-port ML2 Adapter (heatsink removed)FeaturesThe ConnectX-4 family of adapters offer a number of performance features, including the following: ConnectX-4 Lx Ethernet adaptersThe ConnectX-4 Lx adapters discussed in this product guide offer a high performance Ethernetadapter solution for Ethernet speeds up to 40 Gb/s, enabling seamless networking, clustering, or storage. The Lx adapters reduce application runtime, and offer the flexibility and scalability to make infrastructure run as efficiently and productively as possible.ConnectX-4 100 Gb Ethernet / EDR InfiniBandConnectX-4 with Virtual Protocol Interconnect (VPI) offers the highest throughput VPI adapter,supporting EDR 100Gb/s InfiniBand and 100Gb/s Ethernet and enabling any standard networking, clustering, or storage to operate seamlessly over any converged network leveraging a consolidated software stack.I/O VirtualizationFigure 4. Mellanox ConnectX-4 Lx 1x40GbE QSFP+ Adapter (heatsink removed) Technical specificationsPCIe 3.0 host interface:ConnectX-4 Lx Ethernet adapters: PCIe 3.0 x8 interfaceConnectX-4 EDR InfiniBand / 100 Gb Ethernet adapter: PCIe 3.0 x16 interface Support for MSI/MSI-X mechanismsExternal connectors:25 Gb PCIe and ML2 adapters: SFP2840 Gb and 100 Gb adapters: QSFP28Server support - ThinkSystemThe following tables list the ThinkSystem servers that are compatible. Table 7. Server support - ThinkSystem (Part 1 of 3)PartNumber Description Edge1S IntelV2AMD V3Intel V3ConnectX-4 Lx 25 Gb Ethernet adapters01GR250Mellanox ConnectX-4 Lx 10/25GbESFP28 2-port PCIe EthernetAdapterN N N N N N N N N N N N N N N N N N N4XC7A08249ThinkSystem Mellanox ConnectX-4Lx 10/25GbE SFP28 2-port PCIeEthernet AdapterY N N N N N N N N N N N N N N N N N N4XC7A08246ThinkSystem Mellanox ConnectX-4Lx 10/25GbE SFP28 2-port OCPEthernet AdapterN N N N N N N N N N N N N N N N N N N7ZT7A00507ThinkSystem Mellanox ConnectX-4Lx 10/25GbE SFP28 2-Port ML2Ethernet Adapter N N N N N N N N N N N N N N N N N N N SE35(7Z46/7D1X)SE35V2(7DA9)SE36V2(7DAM)SE45(7D8T)SE455V3(7DBY)ST5V2(7D8K/7D8J)ST25V2(7D8G/7D8F)SR25V2(7D7R/7D7Q)SR635V3(7D9H/7D9G)SR655V3(7D9F/7D9E)SR645V3(7D9D/7D9C)SR665V3(7D9B/7D9A)SR675V3(7D9Q/7D9R)ST65V3(7D7B/7D7A)SR63V3(7D72/7D73)SR65V3(7D75/7D76)SR85V3(7D97/7D96)SR86V3(7D94/7D93)SR95V3(7DC5/7DC4)PartNumber Description Dense V32S Intel V2AMD V1Dense V24SV28SConnectX-4 Lx 25 Gb Ethernet adapters01GR250Mellanox ConnectX-4 Lx10/25GbE SFP28 2-port PCIeEthernet AdapterN N N N N N N N N N N N N N N N N N N Y4XC7A08249ThinkSystem MellanoxConnectX-4 Lx 10/25GbESFP28 2-port PCIe EthernetAdapterN N N N N Y Y N Y Y N Y Y Y N N N N N N4XC7A08246ThinkSystem MellanoxConnectX-4 Lx 10/25GbESFP28 2-port OCP EthernetAdapterN N N N N Y Y N Y Y N Y Y N N N N N N N7ZT7A00507ThinkSystem MellanoxConnectX-4 Lx 10/25GbESFP28 2-Port ML2 EthernetAdapter N N N N N N N N N N N N N N N N N N N Y SD665V3(7D9P)SD665-NV3(7DAZ)SD65V3(7D7M)SD65-IV3(7D7L)ST65V2(7Z75/7Z74)SR63V2(7Z7/7Z71)SR65V2(7Z72/7Z73)SR67V2(7Z22/7Z23)SR635(7Y98/7Y99)SR655(7Y/7Z1)SR655ClientOSSR645(7D2Y/7D2X)SR665(7D2W/7D2V)SD63V2(7D1K)SD65V2(7D1M)SD65-NV2(7D1N)SN55V2(7Z69)SR85V2(7D31/7D32)SR86V2(7Z59/7Z6)SR95(7X11/7X12)PartNumber Description4S V11S Intel V12S Intel V1Dense V1ConnectX-4 Lx 25 Gb Ethernet adapters01GR250Mellanox ConnectX-4 Lx 10/25GbESFP28 2-port PCIe EthernetAdapterY Y Y N N N Y Y N N N N Y Y N N N N N4XC7A08249ThinkSystem Mellanox ConnectX-4Lx 10/25GbE SFP28 2-port PCIeEthernet AdapterN N N N N N N N N N N N N N N N N N N4XC7A08246ThinkSystem Mellanox ConnectX-4Lx 10/25GbE SFP28 2-port OCPEthernet AdapterN N N N N N N N N N N N N N N N N N N7ZT7A00507ThinkSystem Mellanox ConnectX-4Lx 10/25GbE SFP28 2-Port ML2Ethernet AdapterY Y Y N N N N N N N N N Y Y N N N N N SR85(7X18/7X19)SR85P(7D2F/2D2G)SR86(7X69/7X7)ST5(7Y48/7Y5)ST25(7Y45/7Y46)SR15(7Y54)SR25(7Y52/7Y51)ST55(7X9/7X1)SR53(7X7/7X8)SR55(7X3/7X4)SR57(7Y2/7Y3)SR59(7X98/7X99)SR63(7X1/7X2)SR65(7X5/7X6)SR67(7Y36/7Y37)SD53(7X21)SD65(7X58)SN55(7X16)SN85(7X15)Server support - System xThe following tables list the System x and dense servers that are compatible.Support for System x and dense servers with Xeon E5 v4 and E3 v5 processorsTable 10. Support for System x and dense servers with Xeon E5 v4 and E3 v5 processorsPartnumber DescriptionConnectX-4 Lx Ethernet adapters01GR250Mellanox ConnectX-4 Lx 10/25GbE SFP28 2-port PCIeAdapterN N Y Y Y Y N N00MN990Mellanox ConnectX-4 Lx 10/25GbE SFP28 1-port ML2AdapterN N Y Y Y Y N N7ZT7A00507Mellanox ConnectX-4 Lx 10/25GbE SFP28 2-Port ML2AdapterN N N N N N N N 00MM950Mellanox ConnectX-4 Lx 1x40GbE QSFP+ Adapter N N Y Y Y Y N N ConnectX-4 VPI InfiniBand adapters7XC7A05524Mellanox ConnectX 4 PCIe FDR 1 Port QSFP VPI Adapter N N N N N N N N 7ZT7A00500Mellanox ConnectX-4 PCIe FDR 2-Port QSFP VPI Adapter N N N N N N N N00MM960Mellanox ConnectX-4 2x100GbE/EDR IB QSFP28 VPI Adapter N N Y Y Y Y N N x325M6(3943)x325M6(3633)x355M5(8869)x365M5(8871)x385X6/x395X6(6241,E7v4)nx36M5(5465,E5-26v4)sd35(5493)nx36M5WCT(5467,v4)Support for System x and dense servers with Intel E5 v3 and E3 v3 processors Table 11. Support for servers with Intel Xeon v3 processorsPart number DescriptionConnectX-4 Lx Ethernet adapters01GR250Mellanox ConnectX-4 Lx 10/25GbE SFP28 2-port PCIe Adapter N N N Y Y Y Y 00MN990Mellanox ConnectX-4 Lx 10/25GbE SFP28 1-port ML2 Adapter N N N Y Y Y Y 7ZT7A00507Mellanox ConnectX-4 Lx 10/25GbE SFP28 2-Port ML2 Adapter N N N N N N N 00MM950Mellanox ConnectX-4 Lx 1x40GbE QSFP+ AdapterN N N Y Y Y Y ConnectX-4 VPI InfiniBand adapters7ZT7A00500ThinkSystem Mellanox ConnectX-4 PCIe FDR 2-Port QSFP VPIAdapter N N N N N N N 00MM960Mellanox ConnectX-4 2x100GbE/EDR IB QSFP28 VPI AdapterNNNYYYYx 3100 M 5 (5457)x 3250 M 5 (5458)x 3500 M 5 (5464)x 3550 M 5 (5463)x 3650 M 5 (5462)x 3850 X 6/x 3950 X 6 (6241, E 7 v 3)n x 360 M 5 (5465)Support for System x servers with Intel Xeon v2 processors Table 12. Support for servers with Intel Xeon v2 processorsPart number DescriptionConnectX-4 Lx Ethernet adapters01GR250Mellanox ConnectX-4 Lx 10/25GbE SFP28 2-port PCIe AdapterN N N N N N N Y 00MN990Mellanox ConnectX-4 Lx 10/25GbE SFP28 1-port ML2AdapterN N N N N N N Y 7ZT7A00507Mellanox ConnectX-4 Lx 10/25GbE SFP28 2-Port ML2Adapter N N N N N N N N 00MM950Mellanox ConnectX-4 Lx 1x40GbE QSFP+ AdapterN N N N N N N Y ConnectX-4 VPI InfiniBand adapters7ZT7A00500ThinkSystem Mellanox ConnectX-4 PCIe FDR 2-Port QSFPVPI Adapter N N N N N N N N 00MM960Mellanox ConnectX-4 2x100GbE/EDR IB QSFP28 VPI AdapterNNNNNNNY The following figure shows the Mellanox ConnectX-4 Lx 2x25GbE SFP28 Adapter.x 3300 M 4 (7382)x 3500 M 4 (7383, E 5-2600 v 2)x 3550 M 4 (7914, E 5-2600 v 2)x 3630 M 4 (7158, E 5-2400 v 2)x 3650 M 4 (7915, E 5-2600 v 2)x 3650 M 4 B D (5466)x 3750 M 4 (8753)x 3850 X 6/x 3950 X 6 (6241, E 7 v 2)Figure 5. Mellanox ConnectX-4 Lx 10/25GbE SFP28 2-port PCIe Ethernet Adapter (heatsink removed) Operating system supportThe Mellanox ConnectX-4 adapters support the following operating systems:Mellanox ConnectX-4 Lx 10/25GbE SFP28 2-port PCIe Ethernet Adapter, 01GR250ThinkSystem Mellanox ConnectX-4 Lx 10/25GbE 2-port PCIe Ethernet Adapter, 4XC7A08249ThinkSystem Mellanox ConnectX-4 Lx 10/25GbE SFP28 2-port OCP Ethernet Adapter, 4XC7A08246 Mellanox ConnectX-4 Lx 10/25GbE SFP28 1-port ML2 Adapter, 00MN990ThinkSystem Mellanox ConnectX-4 Lx 10/25GbE SFP28 2-Port ML2 Ethernet Adapter, 7ZT7A00507 Mellanox ConnectX-4 Lx 1x40GbE QSFP+ Adapter, 00MM950ThinkSystem Mellanox ConnectX-4 PCIe FDR 1-Port QSFP VPI Adapter, 7XC7A05524ThinkSystem Mellanox ConnectX-4 PCIe FDR 2-Port QSFP VPI Adapter, 7ZT7A00500Mellanox ConnectX-4 2x100GbE/EDR IB QSFP28 VPI Adapter, 00MM960Table 13. Operating system support for Mellanox ConnectX-4 Lx 2x25GbE PCIe Adapter, 01GR250 (Part 1of 2)Operating systemsMicrosoft Windows Server 2012N N N N N N N N N N N N N N N N Y Y Microsoft Windows Server 2012 R2N N N N N N N N N Y Y Y Y Y Y Y Y Y Microsoft Windows Server 2016Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Microsoft Windows Server 2019Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N Y Microsoft Windows Server 2022Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N N Microsoft Windows Server version 1709N N N N N N N N N Y Y Y Y Y Y Y Y Y Microsoft Windows Server version 1803N N N N N N N N N Y Y Y Y Y Y N N N Red Hat Enterprise Linux 6.10N N N N N N N N N Y Y Y Y Y Y Y Y Y Red Hat Enterprise Linux 6.9N N N N N N N N N Y Y Y Y Y Y Y Y Y Red Hat Enterprise Linux 7.3N N N N N N N N N Y Y Y Y N Y Y Y Y Red Hat Enterprise Linux 7.4N N N N N N N N N Y Y Y Y Y Y Y Y Y Red Hat Enterprise Linux 7.5Y N N N N N N N N Y Y Y Y Y Y Y Y Y Red Hat Enterprise Linux 7.6N Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Red Hat Enterprise Linux 7.7Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Red Hat Enterprise Linux 7.8Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Red Hat Enterprise Linux 7.9Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Red Hat Enterprise Linux 8.0Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N Y Red Hat Enterprise Linux 8.1Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N Y Red Hat Enterprise Linux 8.2Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N Y Red Hat Enterprise Linux 8.3Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N Y Red Hat Enterprise Linux 8.4Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N N Red Hat Enterprise Linux 8.5Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N N Red Hat Enterprise Linux 8.6Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N N Red Hat Enterprise Linux 8.7Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N N Red Hat Enterprise Linux 8.8Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N N Red Hat Enterprise Linux 8.9Y Y Y Y Y Y Y Y Y N N N N N N N N N Red Hat Enterprise Linux 9.0Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N N Red Hat Enterprise Linux 9.1Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N N Red Hat Enterprise Linux 9.2Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N N Red Hat Enterprise Linux 9.3Y Y Y Y Y Y Y Y Y N N N N N N N N N SUSE Linux Enterprise Server 11 SP4N N N N N N N N N Y Y Y Y Y Y YYY S R 250S D 530 (X e o n G e n 2)S R 630 (X e o n G e n 2)S R 650 (X e o n G e n 2)S R 850 (X e o n G e n 2)S R 850P (X e o n G e n 2)S R 860 (X e o n G e n 2)S R 950 (X e o n G e n 2)S T 550 (X e o n G e n 2)S D 530 (X e o n G e n 1)S R 630 (X e o n G e n 1)S R 650 (X e o n G e n 1)S R 850 (X e o n G e n 1)S R 860 (X e o n G e n 1)S R 950 (X e o n G e n 1)S T 550 (X e o n G e n 1)x 3850/3950 X 6 (6241, E 7 v 3)x 3850/3950 X 6 (6241, E 7 v 4)11SUSE Linux Enterprise Server 12 SP2N N N N N N N N N Y Y Y Y N Y Y Y Y SUSE Linux Enterprise Server 12 SP3Y N N N N Y N N N Y Y Y Y Y Y Y Y Y SUSE Linux Enterprise Server 12 SP4N Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y SUSE Linux Enterprise Server 12 SP5Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y SUSE Linux Enterprise Server 15Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y SUSE Linux Enterprise Server 15 SP1Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y SUSE Linux Enterprise Server 15 SP2Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y SUSE Linux Enterprise Server 15 SP3Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N N SUSE Linux Enterprise Server 15 SP4Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N N SUSE Linux Enterprise Server 15 SP5Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N N Ubuntu 22.04 LTSY Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N N VMware vSphere Hypervisor (ESXi) 5.5N N N N N N N N N N N N N N N N Y N VMware vSphere Hypervisor (ESXi) 6.0 U3N N N N N N N N N Y Y Y Y Y Y Y Y Y VMware vSphere Hypervisor (ESXi) 6.5N N N N N N N N N Y Y Y Y N Y Y N Y VMware vSphere Hypervisor (ESXi) 6.5 U1N N N N N N N N N Y Y Y Y Y Y Y N Y VMware vSphere Hypervisor (ESXi) 6.5 U2Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N Y VMware vSphere Hypervisor (ESXi) 6.5 U3Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N Y VMware vSphere Hypervisor (ESXi) 6.7Y N N N N N N N N Y Y Y Y Y Y Y N Y VMware vSphere Hypervisor (ESXi) 6.7 U1N Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N Y VMware vSphere Hypervisor (ESXi) 6.7 U2Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N Y VMware vSphere Hypervisor (ESXi) 6.7 U3Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N Y VMware vSphere Hypervisor (ESXi) 7.0Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N N VMware vSphere Hypervisor (ESXi) 7.0 U1Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N N VMware vSphere Hypervisor (ESXi) 7.0 U2Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N N VMware vSphere Hypervisor (ESXi) 7.0 U3Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N N VMware vSphere Hypervisor (ESXi) 8.0Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N N VMware vSphere Hypervisor (ESXi) 8.0 U1Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y N N VMware vSphere Hypervisor (ESXi) 8.0 U2Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y YNN Operating systems[in box driver support only]S R 250S D 530 (X e o n G e n 2)S R 630 (X e o n G e n 2)S R 650 (X e o n G e n 2)S R 850 (X e o n G e n 2)S R 850P (X e o n G e n 2)S R 860 (X e o n G e n 2)S R 950 (X e o n G e n 2)S T 550 (X e o n G e n 2)S D 530 (X e o n G e n 1)S R 630 (X e o n G e n 1)S R 650 (X e o n G e n 1)S R 850 (X e o n G e n 1)S R 860 (X e o n G e n 1)S R 950 (X e o n G e n 1)S T 550 (X e o n G e n 1)x 3850/3950 X 6 (6241, E 7 v 3)x 3850/3950 X 6 (6241, E 7 v 4)1Table 14. Operating system support for Mellanox ConnectX-4 Lx 2x25GbE PCIe Adapter, 01GR250 (Part 2of 2)Operating systemsMicrosoft Windows Server 2012Y N Y Y Y Microsoft Windows Server 2012 R2Y N Y Y Y Microsoft Windows Server 2016Y Y Y Y Y Microsoft Windows Server 2019N N Y N Y Microsoft Windows Server 2022N N N N N Microsoft Windows Server version 1709Y Y Y Y Y Microsoft Windows Server version 1803N N Y N Y Red Hat Enterprise Linux 6.10Y Y Y Y Y Red Hat Enterprise Linux 6.9Y Y Y Y Y Red Hat Enterprise Linux 7.3Y Y Y Y Y Red Hat Enterprise Linux 7.4Y Y Y Y Y Red Hat Enterprise Linux 7.5Y Y Y Y Y Red Hat Enterprise Linux 7.6Y Y Y Y Y Red Hat Enterprise Linux 7.7Y Y Y Y Y Red Hat Enterprise Linux 7.8Y Y Y Y Y Red Hat Enterprise Linux 7.9Y Y Y Y Y Red Hat Enterprise Linux 8.0N N N N N Red Hat Enterprise Linux 8.1N N N N N Red Hat Enterprise Linux 8.2N N N N N Red Hat Enterprise Linux 8.3N N N N N Red Hat Enterprise Linux 8.4N N N N N Red Hat Enterprise Linux 8.5N N N N N Red Hat Enterprise Linux 8.6N N N N N Red Hat Enterprise Linux 8.7N N N N N Red Hat Enterprise Linux 8.8N N N N N Red Hat Enterprise Linux 8.9N N N N N Red Hat Enterprise Linux 9.0N N N N N Red Hat Enterprise Linux 9.1N N N N N Red Hat Enterprise Linux 9.2N N N N N Red Hat Enterprise Linux 9.3N N N N N SUSE Linux Enterprise Server 11 SP4Y N Y Y Y SUSE Linux Enterprise Server 12 SP2Y Y Y Y Y SUSE Linux Enterprise Server 12 SP3Y Y Y Y Y SUSE Linux Enterprise Server 12 SP4Y Y Y Y Y SUSE Linux Enterprise Server 12 SP5Y Y Y Y Yn x 360 M 5 (5465)x 3550 M 5 (5463)x 3550 M 5 (8869)x 3650 M 5 (5462)x 3650 M 5 (8871)SUSE Linux Enterprise Server 15Y N Y N Y SUSE Linux Enterprise Server 15 SP1Y N Y N Y SUSE Linux Enterprise Server 15 SP2Y N Y N Y SUSE Linux Enterprise Server 15 SP3N N N N N SUSE Linux Enterprise Server 15 SP4N N N N N SUSE Linux Enterprise Server 15 SP5N N N N N Ubuntu 22.04 LTSN N N N N VMware vSphere Hypervisor (ESXi) 5.5Y N Y Y Y VMware vSphere Hypervisor (ESXi) 6.0 U3Y N Y Y Y VMware vSphere Hypervisor (ESXi) 6.5Y Y Y Y Y VMware vSphere Hypervisor (ESXi) 6.5 U1Y Y Y Y Y VMware vSphere Hypervisor (ESXi) 6.5 U2Y Y Y Y Y VMware vSphere Hypervisor (ESXi) 6.5 U3Y Y Y Y Y VMware vSphere Hypervisor (ESXi) 6.7Y N Y N Y VMware vSphere Hypervisor (ESXi) 6.7 U1Y N Y N Y VMware vSphere Hypervisor (ESXi) 6.7 U2Y N Y N Y VMware vSphere Hypervisor (ESXi) 6.7 U3Y N Y N Y VMware vSphere Hypervisor (ESXi) 7.0N N N N N VMware vSphere Hypervisor (ESXi) 7.0 U1N N N N N VMware vSphere Hypervisor (ESXi) 7.0 U2N N N N N VMware vSphere Hypervisor (ESXi) 7.0 U3N N N N N VMware vSphere Hypervisor (ESXi) 8.0N N N N N VMware vSphere Hypervisor (ESXi) 8.0 U1N N N N N VMware vSphere Hypervisor (ESXi) 8.0 U2N N N N NOperating systemsTable 15. Operating system support for ThinkSystem Mellanox ConnectX-4 Lx 10/25GbE SFP28 2-port PCIe Ethernet Adapter, 4XC7A08249Operating systems Microsoft Windows 10N N N N N N Y N Microsoft Windows 11N N N N N N Y N Microsoft Windows Server 2016Y Y Y Y Y Y Y Y Microsoft Windows Server 2019Y Y Y Y Y Y Y Y Microsoft Windows Server 2022Y Y Y YYYYY Red Hat Enterprise Linux 7.6Y N N N Y Y Y Y Red Hat Enterprise Linux 7.7Y N N N Y Y Y Y n x 360 M 5 (5465)x 3550 M 5 (5463)x 3550 M 5 (8869)x 3650 M 5 (5462)x 3650 M 5 (8871)S E 350S D 630 V 2S R 630 V 2S R 650 V 2S R 635S R 645S R 655S R 665211111111Red Hat Enterprise Linux 7.8Y N N N Y Y Y Y Red Hat Enterprise Linux 7.9Y Y Y Y Y Y Y Y Red Hat Enterprise Linux 8.0N N N N Y NY NRed Hat Enterprise Linux 8.1Y N N N Y Y Y Y Red Hat Enterprise Linux 8.2Y Y Y Y Y Y Y Y Red Hat Enterprise Linux 8.3Y Y Y Y Y Y Y Y Red Hat Enterprise Linux 8.4Y Y Y Y Y Y Y Y Red Hat Enterprise Linux 8.5Y Y Y Y Y Y Y Y Red Hat Enterprise Linux 8.6Y Y Y Y Y Y Y Y Red Hat Enterprise Linux 8.7Y Y Y Y Y Y Y Y Red Hat Enterprise Linux 8.8Y Y Y Y Y Y Y Y Red Hat Enterprise Linux 8.9N Y Y Y Y Y Y Y Red Hat Enterprise Linux 9.0Y Y Y Y Y Y Y Y Red Hat Enterprise Linux 9.1Y Y Y Y Y Y Y Y Red Hat Enterprise Linux 9.2Y Y Y Y Y Y Y Y Red Hat Enterprise Linux 9.3N Y Y Y Y Y Y Y SUSE Linux Enterprise Server 12 SP4N N N N Y N Y N SUSE Linux Enterprise Server 12 SP5N Y Y Y Y Y Y Y SUSE Linux Enterprise Server 15Y N N N N N N N SUSE Linux Enterprise Server 15 SP1Y N N N Y Y Y Y SUSE Linux Enterprise Server 15 SP2Y Y Y Y Y Y Y Y SUSE Linux Enterprise Server 15 SP3Y Y Y Y Y Y Y Y SUSE Linux Enterprise Server 15 SP4Y Y Y Y Y Y Y Y SUSE Linux Enterprise Server 15 SP5Y Y Y Y Y Y Y Y Ubuntu 18.04.5 LTS N Y Y Y N N N N Ubuntu 18.04.6 LTS Y N N N N N N N Ubuntu 20.04 LTS N N Y Y N N N N Ubuntu 20.04.5 LTS Y N N N N N N N Ubuntu 22.04 LTSY Y Y Y Y Y Y Y VMware vSphere Hypervisor (ESXi) 6.5 U2Y N N N N N N N VMware vSphere Hypervisor (ESXi) 6.7 U2Y N N N N N N N VMware vSphere Hypervisor (ESXi) 6.7 U3Y Y Y YYY Y Y VMware vSphere Hypervisor (ESXi) 7.0Y N N N Y Y Y Y VMware vSphere Hypervisor (ESXi) 7.0 U1Y N N N Y Y Y Y VMware vSphere Hypervisor (ESXi) 7.0 U2Y Y Y Y Y Y Y Y VMware vSphere Hypervisor (ESXi) 7.0 U3Y Y Y Y Y Y Y Y VMware vSphere Hypervisor (ESXi) 8.0Y Y Y Y Y Y Y Y VMware vSphere Hypervisor (ESXi) 8.0 U1Y Y Y Y Y Y Y Y VMware vSphere Hypervisor (ESXi) 8.0 U2Y Y Y YYYYYOperating systems S E 350S D 630 V 2S R 630 V 2S R 650 V 2S R 635S R 645S R 655S R 6651111111111111111111111111111111。
Hillstone AX-Series:Application Delivery Controller (ADC)AX1000 / AX1000S/ AX2000 / AX2000S / AX4060 / AX4060S / vADCHillstone AX Series Application Delivery Controllers (ADCs) are the next generation of enterprise-class application delivery optimization products. The Hillstone ADC supports a full range of load balancing functions, including link load balancing (LLB), server load balancing (SLB) and global server load balancing (GSLB). In addition, the AX Series supports health checks for applications, servers and links, first-level network attack protection, SSL offload, application and dataacceleration via caching, and more. The Hillstone ADC can greatly improve the availability and scalability of core applications and business platforms, and effectively improve the operational efficiency of enterprise data centers. Together with Hillstone security products such as next-generation firewalls, the Hillstone ADC can provide end-to-end application delivery and security capabilities for your applications and business operations.Hillstone’s ADC fully supports IPv6, high-performance clustering and carrier-grade high availability. It is widely used in server load balancing; traffic distribution and business continuity acrossmultiple data centers; link optimization across multiple ISPs; CDN traffic management; and other application optimization and acceleration scenarios. The Hillstone ADC provides industry-leadingsolutions for government, finance, network operators, education, healthcare and other sectors.High-performance Server Load Balancing Hillstone’s AX Series provides server load balancing with high-capacity concurrent and new session processing capabilities. It intelligently adjusts traffic distribution based upon the health status of server nodes, and automatically completes switching to ensure the best user experience as well as application high availability. Hillstone’s ADC utilizes Layer4 to Layer 7 load balancing algorithms and load balancing based on domain names. Intelligent application identification based on characteristics, behavior and other information allows fine-tuning of performance and throughput to support employee productivity. It also supports application-layer content switching and rewrite to improve the availability of both servers and applications.Intelligent, Efficient and Dynamic Link Load Balancing Hillstone’s AX Series ADC offers enterprise-class link load balancing technology. It features an innovative adaptive link selection control algorithm that can detect link connectivity, bandwidth utilization, delay, packet loss and jitter in real time, and adjust the traffic forwarding rules based uponthe actual link quality and performance. Using an intelligent closed loop, the best route can be selected in real time so that problems such as unbalanced link utilization, single point of failure, poor cross-ISP access, wastage of link resources, and other performance problems are eliminated. The Hillstone ADC supports multiple link load balancing modes such as ECMP, ISP routing, dynamic link switching, and application routing to ensure optimal link access and support employee productivity. High-performance SSL Offload for Secured ApplicationsFinance, healthcare, e-commerce and other applicationsare commonly secured via SSL encryption, which adds workload to servers that can impact performance andlimit scalability. Hillstone’s ADC supports SSL hardware acceleration technology that provides industry-leading 2048-bit SSL processing performance. By offloading SSL traffic to the Hillstone ADC’s dedicated SSL processing resources, the server workload is significantly reduced resulting in improved server performance and scalability.Full-featured IPv6In addition to IPv6 support, the Hillstone ADC supports IPv6 application layer transformation technology to help IPv4 websites and networks seamlessly upgrade to or interoperate with IPv6. Through intelligent link processing technology, the addressing problem can be solved efficiently. The Hillstone ADC standard configuration comes with a 1T hard drive and supports log storage for the IPv6 application layer transformation.End-to-end Security ProtectionTogether with Hillstone Networks’ next-generation firewalls, CloudEdge, CloudHive and other security products, the Hillstone ADC can provide end-to-end security protection capabilities from network access to data centers.Product HighlightsServer Load Balancing• L4 and L7 server load balancing• HTTP content switching based on URL, HTTP header, cookie• HTTP content rewriting• Redirection for HTTP requests• Supports IPv6• Supports HTTP2.0• Supports WebSocket protocol• Supports fastHTTP modeServer Health Checks• Predefined and custom health checks for ICMP, TCP, UDP, HTTP, HTTPS, SMTP, POP3, IMAP, DNS, FTP protocols and third-party objects• Supports email exchange protocol / RADIUS protocol health checks• Support server resource health checkServer Session Persistence• Source IP based session persistence• Session persistence for encrypted cookie• Supports sharing session peersistence table across VMsApplication Acceleration• HTTP caching (jpg, doc, ppt, xls, html, css, js, pdf, swf, mp3, avi, flv, mp4)• TCP connection multiplexing• HTTP compression (doc, ppt, xls, html, css, js) SSL Inspection• Software SSL offload; supported versions include SSLv2, SSLv3, TLS 1.0, TLS1.1, TLS1.2• Hardware SSL offload• Predefined or customized encryption algorithms with priorities• SSL connection multiplexing• Supports SSL proxy• Works in conjunction with sBDS and NIPS to identify encrypted traffic Link Load Balancing• Supports IP address library and ISP address librarywith automatic update• Policy routing supports domain name andgeographic location routingGlobal Server Load Balancing• Supports DNS proxy• DNS proxy blacklist and whitelist• Inbound SmartDNS• SmartDNS supports IP address library and ISPaddress library with automatic updatesSystem Management• System management via WebUI, Console, Telnetand SSH• Role-based authorization of administrators,auditors and operators• Access control on the administrator address forremote management• Supports WebUI administrators to bind to trustdomain, and certificate authentication for adminis-trators• Configuration for password complexity andminimum length restrictions• Supports SNTP, and synchronization of systemtime from multiple NTP servers• Supports multiple configuration files and configu-ration file backup and recovery• Supports hping, tcpdump and curl operation andmaintenance toolsApplication Identification• Application identification based on applicationcharacteristics, behavior and related information• Multi-dimensional application definitions• Thousands of application signatures• Application signature database updated inreal-timeLog and Monitoring• Supports a variety of log types, including eventlogs, network logs, configuration logs, NAT logs,SLB logs, health check logs, etc.• Log storage in both local device and server• Email alarms and log alarms• Real-time WebUI display of system resourceutilization and hardware status• Monitoring and graphical display of the SLB status• Device status monitoring on mobile devices viaCloudView• Supports forwarding SLB log, health check binarylog to HSADeployment and Network Configuration• Deployment via one-arm reverse proxy, routing,transparent, or DSR• Supports static routing, ISP routing, policy routing,and RIP dynamic routing protocol, and supportsimport of ISP information• HA / AP mode• Supports configuration, session, health checks,PKI synchronization• Policy control• VSYS• Supports AWS, Azure and Alibaba Cloud (manualdeployment only)• Support LMS centralized authorization• Supports VMware / KVM / Xen / Hyper-Vvirtualization deployment• QoS• Session limiting• Supports anti-DDoS• Supports centralized management• Supports programmable script aRulesDNS Server• Supports A, AAAA, NS, CNAME, PTR, MX, TXT, SRV• Recursive forwarding• DNS transparent proxyFeaturesASIC 360,0001 TB 64 GB2 × USB Port, 1 ×MGT, 1 × HA, 1 × Serial 2 × USB Port, 1 ×MGT, 1 × HA, 1 × Serial hot-swappable hot-swappable hot-swappable Frequency 50/60 Hz 50/60 Hz 50/60 Hz Average Power 350W 550W 550W Height2U2U2UDimension (W×D×H)(430 x 500 x 88 mm)16.9 x 19.7 x 3.5 in (430 x 500 x 88 mm)(550 x 440 x 88mm)21.7 x 17.3 x 3.5 in (550 x 440 x 88mm)(550 x 440 x 88mm)21.7 x 17.3 x 3.5 in (550 x 440 x 88mm)Net Weight 28.7 lb (13 kg)52.9 lb (24 kg)52.9 lb (24 kg)Gross Weight37.5 lb (17 kg)63.9 lb (29 kg)63.9 lb (29 kg)Operating Temperature 32-104 °F (0-40 °C)32-104 °F (0-40 °C)32-104 °F (0-40 °C)Allowed Relative Humiditynon-condensing5 ~ 85%,non-condensingnon-condensing5 ~ 90%,non-condensingnon-condensing5 ~ 90%,non-condensingL4 Throughput (SRIOV)10 Gbps30 GbpsL4 Throughput (VMXNet3) 2 Gbps 2 GbpsL7 HTTP Throughput (SRIOV)7.5 Gbps22 GbpsL7 HTTP Throughput (VMXNet3) 2 Gbps 2 GbpsL4 Connections/s200,000600,000L7 HTTP Connections/s150,000450,000Concurrent Connections 3 Million8 MillionECDHE RSA 2K SSL (TPS) (1)4,00014,000ECDHE RSA 2K SSL Throughput (2)800 Mbps 3 Gbps Module OptionsModule IOC-AX-4GE-B IOC-AX-4SFP IOC-AX-8GE-B IOC-AX-8SFP IOC-AX-4GE4SFP I/O Ports 4 × SFP Ports8 × SFP PortsDimension1U (Occupies 1 generic slot)1U (Occupies 1 generic slot)Weight0.33 lb (0.15 kg)0.55 lb (0.25 kg)Module IOC-AX-2SFP+IOC-AX-4SFP+IOC-AX-4GE-B-H IOC-AX-4SFP-H IOC-AX-8GE-B-H I/O Ports 4 × SFP+ Ports 4 × SFP PortsDimension1U (Occupies 1 generic slot)1U (Occupies 1 generic slot)Weight0.44 lb (0.2 kg)0.33 lb (0.15 kg)Module IOC-AX-8SFP-H IOC-AX-4GE4SFP-H IOC-AX-2SFP+-H IOC-AX-4SFP+-H IOC-AX-2QSFP+-H I/O Ports 4 × GE and 4 × SFP Ports 4 × SFP+ PortsDimension1U (Occupies 1 generic slot)1U (Occupies 1 generic slot)Weight0.55 lb (0.25 kg)0.44 lb (0.2 kg)NOTES:(1) In the test, Transaction Per TCP Connection uses Maximum Possible;(2) The RSA key length is 2048Bit, and the encryption suite is AES256-SHA256.。
LASYSTEMS - Brusselsesteenweg 208 - 1730 Asse - BelgiumPhone: +32-2-4531312 - Fax: +32-2-4531763E-mail:***************** Tp-link TL-WPA281 (TL-WPA281)AV200 N, Fast Ethernet, 802.11d/g/n, PowerPlug, RJ-45, 128-bit AES, 6W, WhitePrice details: PDF generated on: 17 April, 2013Price excl. VAT: 38.94 €Eco fees: 0.04 €VAT 21 %: 8.19 €Product details:Product code: TL-WPA281EAN: 6935364031299Manufacturer: TP-LINK47.17 €* VAT included300Mbps AV200 Wireless N Powerline ExtenderHighlights:- 300Mbps Wireless N Rate-Extend Wireless Coverage;- HomePlug AV standard compliant, high-speed data transfer rates of up to 200Mbps;- Super small design with a new exterior, blends indiscreetly in front of any power outlet;- No new wires, Easy Plug and Play operation, No configuration required.What This Product DoesTP-LINK Wireless N Powerline Extender TL-WPA281 extends the Internet connection to every room connected to a home's circuitry. All devices in the room have two options to get access to TL-WPA281, whether through wireless or using an Ethernet cable. With 200Mbps Powerline link rate and 300Mbps wireless N rate, it is ideal for bandwidth consuming or latency sensitive applications like video streaming, online gaming and Internet calls. With TL-WPA281, Internet can now truly be available everywhere in your home or office.Up to 200Mbps, 300 MetersWith advanced HomePlug AV technology, TL-WPA281 provides users with stable, high-speed data transfer rates of up to 300Mbps on a circuit length of up to 300 meters. Together with its built-in Qos and powerful AES encryption, the TL-WPA281 is a great choice for a whole home solution to connect all network compatible devices--from computers and game consoles, to set-top boxes for IPTV, printers and NAS.300Mbps Wireless N Rate-Extend Your Wireless CoverageWith wireless speeds of up to 300Mbps, users can effortlessly extend their networks via their home's existing electrical circuitry and broadcast a wireless signal to another area of their home or office.Multiple HD Video StreamsWith 200Mbps powerline and 300Mbps wireless speeds, the TL-PA281 is ideal for lag-sensitive applications.Pair Button for Easy Network SecuritySimply by pushing the Pair button on the adapters, users can set up a hassle-free Powerline network within minutes, complete with 128-bit AES encryption for network security and data protection.- Plug the adapter into the power outlet;- Connect the device via the network cable to the adapter;- Press the encryption buttons-and you're done!WPS One-Button SecurityCompatible with Wi-Fi Protected Setup (WPS), TL-WPA281 features WPS One-Button Security Setup that allows users to almost instantly setup their security simply by pressing the "WPS" button on the adapter, automatically establishing a WPA2 secure connection, which is more secure than WEP encryptions. Not only is this faster than normal security setups but more convenient in that you don't need to remember a password!Support QoS for Advanced Multiple-media OptimizationThe device's Quality of Service (QoS) function prioritizes the bandwidth requirements of data traffic. Users can choose which type of traffic they will use -- Internet, Online Game, Audio, Video or VoIP and the QoS functions will guarantee clear, instant reproduction of that application, even when other applications are running on the network at the same time.Features:- HomePlug AV standard compliant, high-speed data transfer rate of up to 200Mbps, ideal for HD video or 3D video streaming and online gaming;- 300Mbps wireless N rate;- Mains Filter for better powerline communication performance;- No new wires, use existing electrical wiring;- Up to 300 meter range over a home's electrical circuit for better performance through walls or across floors;- Plug and Play, no new wires or configuration required;- Easily connect and secure your network with push button security (“Pair'' button, “WPS'' button);- Built-in QoS assures the quality of bandwidth sensitive applications such as voice, video and online games;- Supports IGMP managed multicast IP transmission, optimizes IPTV streaming.Main specifications:Ports & interfacesConnectivity technology:Wired/WirelessHost interface:PowerPlugInterface:Ethernet/WLANInternal:NEthernet LAN (RJ-45) ports quantity: 1Connector(s):RJ-45, EU, US, UKBandwidthData transfer rate (max):300 Mbit/sSupported data transfer rates:10/100 Mbit/sNetworkingChipset:-Ethernet LAN connection:YCabling technology:10/100BaseT(X)Networking standards:IEEE 802.11b, IEEE 802.11n, IEEE 802.3, IEEE 802.3uModulation:OFDMFrequency band: 2.4 GHzMaximum operating distance:300 mCopper ethernet cabling technology:100BASE-T, 100BASE-TX, 10BASE-TWireless LAN featuresWireless LAN connection:YWireless LAN type:802.11b, 802.11g, 802.11nWLAN data transfer rates supported:11, 54, 150 Mbit/sTechnical detailsColour of product:WhiteCompliance industry standards:IEEE 802.3, IEEE 802.3u, IEEE 802.11b/g/nPlug and Play:YOperating temperature range (T-T):32 - 104 °FEthernet LAN data transfer rates:10, 100 Mbit/sEnergy managementPower consumption (typical): 6 WOperating system/softwareWindows operating systems supported:YMac operating systems supported:YLinux operating systems supported:YWeight & dimensionsWidth:58 mmDepth:40 mmHeight:105 mmIllumination/AlarmsLED indicators:LAN, Power, WLANPower LED:YCertificatesRoHS compliance:YCertification:CE, FCCSystem requirementsMac compatibility:YSecuritySecurity algorithms supported:128-bit AES, WEP, WPA, WPA-PSK, WPA2, WPA2-PSK, WPS Operational conditionsOperating temperature range (T-T):0 - 40 °CStorage temperature range (T-T):-40 - 70 °COperating relative humidity range:10 - 90 %Storage relative humidity range: 5 - 90 %Packaging contentCables included:LAN (RJ-45)Manual:YQuick start guide:YOther featuresCompatible operating systems:Windows 2000Windows XPWindows 2003Windows VistaWindows7MacLinuxNetworking features:Fast EthernetWireless technology:Wi-Fi*PLEASE NOTE: Every effort has been made to ensure the accuracy of all information contained herein. Lasystems makes no warranty expressed or implied with respect to accuracy of the information, including price, editorials or specifications. Lasystems or its suppliers shall not be liable for incidental, consequential or special damages arising from, or as a result of, any electronic transmission or the accuracy of the information contained herin, even if Lasystems has been advised of the possibility of such damages. Product and manufacturer names are used only for the purpose of identification.。
Application Note 306 –QoS Setup ProcedureTransition Networks, Inc.10900 Red Circle DriveTransition Networks Inc. offers networking connectivity solutions that make networks perform better, faster and more reliably while helping companies leverage their existingQoS Set-up Guide This application note describes how to set-up QoS on Transition Networks ION modules that support Layer-2 switch QoS functions of priority classification, queuing and remarking.1. Port Priority Queues:Each port contains 4 different classes of output priority queues.The packets will be transmitted from these queues in the weighted round-robin fashionwith the weights of 8:4:2:1 for the class queues 3, 2, 1 and 0.2. Classification:Incoming Packets to a port can be classified based on L2 CoS (IEEE 802.1p) or L3 IPDiffServ (IPv4/IPv6) priority field or port default priority. Section-5 details howport/L2/L3 classification can be configured per port.IEEE priority re-mapping:When a packet is classified by L2 CoS priority, it will be re-mapped to another L2priority value as defined in the per-port priority re-mapping table in Figure-3.IP priority re-mapping :When a packet is classified by IP priority, it will be re-mapped by the global IP remappingtable in Figure-2. The re-mapped 2 bit priority value would be used for 2purposes:1) These 2 bit class values would directly map to the output queue of the egress port2) Egress priority re-marking of the frame. When the packet is eligible for remarking,it would bescaled-up to 3-bits, by borrowing the least significant bit of the port defaultpriority.Application Note 306 –QoS Setup ProcedureTransition Networks, Inc.10900 Red Circle DriveTransition Networks Inc. offers networking connectivity solutions that make networks perform better, faster and more reliably while helping companies leverage their existing3. Queuing:Once the incoming packet is classified/re-mapped based on port/L2/L3 priority, the packet would be queued to the egress port queue based on the global system queue remapping table.3.1) L2 priorityPacket classified by port L2 default or frame L2 priority will be queued based on the “IEEE Priority Class”re-mapping table in Figure-1.3.2) IP priorityPacket classified by IP priority will be queued based on the “IP Traffic Class”remapping table in Figure-2.4. Classification and Queuing configuration options:The following classification/queuing options are available and this is configured per port.4.1) port default priorityThis can be enabled per port by disabling “IEEE Priority Class”and “IP Traffic Class”.All the frames would be assigned to the port default priority. In the following example,port default priority has been set to “4”.4.2) IEEE priority onlyThis can be configured per port by enabling “IEEE Priority Class”and disabling “IP Traffic Class”. All untagged frames(including IP) would be assigned to the port default priority.4.3) IP priority onlyThis can be configured per port by enabling “IP Traffic Class”and disabling “IEEE Priority Class”. Tagged and non-IP frames would be assigned to the port default priority.Application Note 306 –QoS Setup ProcedureTransition Networks, Inc.10900 Red Circle DriveTransition Networks Inc. offers networking connectivity solutions that make networks perform better, faster and more reliably while helping companies leverage their existing4.4) IP and IEEE priority with the precedence of IPThis can be configured per port by enabling both “IEEE Priority Class”and “IP TrafficClass”and “Priority Precedence”set to “Use IP”.Note: The Tagged IP packet would get queued to one of the egress port priority queues asper the global IP-remapping table. However, the remapped IEEE priority value will beused for re-marking the packet.4.5) IP and IEEE priority with the precedence of IEEEThis can be configured per port by enabling both “IEEE Priority Class”and “IP TrafficClass”and “Priority Precedence”set to “Use IEEE.”Note: Tagged IP packet would get queued on the egress port as per the global IEEE remapping table.Option (4) and (5) differs only in which how a packet gets queued. The frame re-markingpriority would work in the same way for both options.5. Priority Override:The initial re-mapped priority value can be further over-ridden by VLAN or per frame SA/DA.Application Note 306 –QoS Setup ProcedureTransition Networks, Inc.10900 Red Circle DriveTransition Networks Inc. offers networking connectivity solutions that make networks perform better, faster and more reliably while helping companies leverage their existingThe following one or more overrides can be enabled per port. Should more than one override match, the following order of priority is applied (i.e., DA would override all other)1) VID Priority Override2) SA Priority Override3) DA Priority OverrideThe higher order 2 bits of the VID/MAC priority will be used as the queue re-mapped priority.6.1) VID Priority OverrideThis requires the VLAN entry to be configured with the desired priority in the VLAN database.Application Note 306 –QoS Setup ProcedureTransition Networks, Inc.10900 Red Circle DriveTransition Networks Inc. offers networking connectivity solutions that make networks perform better, faster and more reliably while helping companies leverage their existingIn the above example, the VLAN 100 packets egress on port with the priority marked/remarked to priority “7”. The higher 2 bits of the VID priority (0x7) will be used as the queue priority. Hence, the packets will get queued to the output queue “3”6.2) SA/DA Priority OverridePriority override for SA/DA must be added to the MAC table as a static entry with the desired priority.Application Note 306 –QoS Setup ProcedureTransition Networks, Inc.10900 Red Circle DriveTransition Networks Inc. offers networking connectivity solutions that make networks perform better, faster and more reliably while helping companies leverage their existing7. Remarking:Packet IEEE priority could be re-marked with the value assigned during the ingress classification/priority override. This would require proper VLAN configuration with the egress port defined as “memEgressTag ”in the VLAN DB. Please refer to the VLAN configuration application note (App Note 302) for VLAN configuration details.Application Note 306 –QoS Setup ProcedureTransition Networks, Inc.10900 Red Circle DriveTransition Networks Inc. offers networking connectivity solutions that make networks perform better, faster and more reliably while helping companies leverage their existing8. Appendix –Figures Figure (1) –“IEEE Priority Class”–System level queue priority remapping table.Application Note 306 –QoS Setup ProcedureTransition Networks, Inc. 10900 Red Circle Drive Transition Networks Inc. offers networking connectivity solutions that make networks perform better, faster and more reliably while helping companies leverage their existingFigure(2) –“IP Traffic Class”–System Level IP Traffic class remapping tableApplication Note 306 –QoS Setup ProcedureTransition Networks, Inc. 10900 Red Circle Drive Transition Networks Inc. offers networking connectivity solutions that make networks perform better, faster and more reliably while helping companies leverage their existingFigure(3) –“User Priority”–Port level IEEE priority remapping table。
Data SheetCisco Catalyst 6500 Series Supervisor Engine 2TProduct OverviewThe Cisco® Catalyst® 6500 Supervisor Engine 2T (Figure 1) is the newest addition to the family of supervisor engines. The Supervisor Engine 2T is designed to deliver higher performance, better scalability, and enhanced hardware-enabled features. Supervisor Engine 2T integrates a high-performance 2-Terabit crossbar switch fabric that enables 80 Gbps switching capacity per slot on all Cisco Catalyst 6500 E-Series Chassis. The forwarding engine on Supervisor Engine 2T is capable of delivering high-performance forwarding for Layer 2 and Layer 3 services. Supervisor Engine 2T delivers many new hardware-enabled innovations in the areas of security, quality of service (QoS), virtualization, and manageability. The rich feature set of Supervisor Engine 2T enhances applications such as traditional IP forwarding, Layer 2 and Layer 3 Multiprotocol Label Switching (MPLS) VPNs, and VPLS. The Cisco Catalyst 6500 with Supervisor Engine 2T and all the features and the technical advancements establish product leadership in borderless networks as well as data center deployments.Figure 1. Supervisor Engine 2TFeatures and BenefitsSupervisor Engine 2T delivers scalable performance, intelligence, and a broad set of features to address the needs of Borderless Networks, data centers, and service provider networks. Some of the primary features for Supervisor Engine 2T include:●Platform scalability: Delivering up to 80 Gbps per slot of switching capacity on E-Series chassis; 2-Terabitaggregate bandwidth capacity using the 6513-E chassis, scaling to 4-Terabit capacity with VSS. Support for up to 1056 ports of 1Gbps and 352 ports of 10Gbps systems deployed with VSS. Providing 1Gbps/10Gbps and 40Gbps interface support to address future customer bandwidth growth requirements.●Security: Support for Cisco TrustSec, CTS, providing MacSec encryption and Role-Based ACL. Providingcontrol plane policing to address denial of service attacks.●Virtualization: Native support for VPLS, as well as enhancements such as VPN-aware NAT, VPN statistics,and VPN netflow as important features needed for deployment of network virtualization.●Netflow application monitoring: Supervisor Engine 2T supports enhanced application monitoring such asFlexible and Sampled Netflow for intelligent and scalable application monitoring.Primary Supervisor Engine 2T ComponentsPolicy Feature Card 4Supervisor Engine 2T features the integrated Policy Feature Card 4 (PFC4), which improves performance and scalability and provides new and enhanced hardware features. The PFC4 is equipped with a high-performance ASIC complex that enables hardware acceleration for existing and new software features. The PFC4 supports Layer 2 and Layer 3 forwarding, QoS, Netflow and Access Control List (ACLs) and multicast packet replication and processes security policies such as access control lists (ACLs) operations all simultaneously enabled with no performance impact. The PFC4 supports all of these operations for both IPv4 and IPv6.PFC4 also provides enhanced performance and scalability and supports many new innovations such as native VPLS, flexible NetFlow, egress NetFlow, Cisco TrustSec, distributed policers, control plane policing, and comprehensive IPv6 features.Multilayer Switch Feature Card 5Supervisor Engine 2T features the Multilayer Switch Feature Card 5 (MSFC5), providing high-performance, multilayer switching and routing intelligence. Equipped with a high-performance processor, the MSFC5 runs both Layer 2 protocols and Layer 3 protocols on the dual-core CPU complex. These include routing protocol support, Layer 2 protocols (for example, Spanning Tree Protocol and VLAN Trunking Protocol), and security services.The MSFC5 builds the Cisco Express Forwarding information base (FIB) table in software and then downloads this table to the hardware application-specific-integrated circuits (ASICs) on the PFC4 and Distributed Forwarding Card 4 (DFC4), if present on a module, which make the forwarding decisions for IP unicast and multicast traffic.Features and Benefits detailsThis section provides details of scalability and performance capabilities of Supervisor Engine 2T and functions supported.Tables 1 through 4 show the scalability, virtualization and security features for Supervisor Engine 2T.Table 1. ScalabilityName VS-S2T-10G VS-S2T-10G-XLIPv4 routing In hardwareUp to 720 Mpps**In hardwareUp to 720 Mpps**IPv6 routing In hardwareUp to 390 Mpps**In hardwareUp to 390 Mpps**L2 bridging In hardwareUp to 720 Mpps**In hardwareUp to 720 Mpps**MPLS MPLS in hardware to enable use of Layer 3 VPNs and EoMPLStunneling. Up to 8192 VRFs with a total of up to 256K*forwarding entries per system. MPLS in hardware to enable use of Layer 3 VPNs and EoMPLS tunneling. Up to 8192 VRFs with a total of up to 1024K forwarding entries per system.VLAN 4K 4KBridge domains 16k 16kVPLS In hardware (Up to 390 Mpps**) In hardware (Up to 390 Mpps**) GRE In hardware (Up to 390 Mpps**) In hardware (Up to 390 Mpps**) NAT Hardware assisted Hardware assistedMAC entries 128k 128kRoutes 256K(IPv4)128K (IPv6) 1024K (IPv4) 512K (IPv6)Name VS-S2T-10G VS-S2T-10G-XL Netflow entries 512K 1024KMulticast routes 128K (IPv4)128K (IPv6) 128K (IPv4) 128K (IPv6)* 1K=1024.** Requires fully populated 6513-E chassis with DFC4/DFC4XLTable 2. QoS Features and ScalabilityFeature VS-S2T-10G VS-S2T-10G-XLLayer-3 classification and marking access control entries (ACEs) 64K shared for QOS / Security 256K shared for QOS/Security Aggregate traffic rate-limiting policers 16348 16348Flow-based rate-limiting method; number of rates Per source address, destinationaddress, or full flow; 64 rates Per source address, destination address, or full flow; 64 ratesLayer 2 rate limiters 20 ingress/6 egress 20 ingress/6 egressMAC ACLs featuring per-port/per VLAN granularity Yes YesDistributed policers Yes YesShared uFlow policers Yes YesEgress uFlow policers Yes YesPacket or byte policers Yes YesPer port per VLAN Yes YesTable 3. Security Features and ScalabilityFeature VS-S2T-10G VS-S2T-10G-XLPort security Yes YesIEEE 802.1x and 802.1x extensions Yes YesVLAN and router ACLs and port ACLs Yes Yes1:1 mask ratio to ACE values Yes YesSecurity ACL entries 64K shared for QOS / Security 256K shared for QOS/Security CPU rate limiters (DoS protection) 57 57uRPF check (IPv4/IPv6) Up to 16 Up to 16Number of interfaces with unique ACL 16k 16kRPF interfaces 16 16Private VLANs Yes YesMAC ACLs on IP Yes YesLogical interfaces 128k 128kEtherChannel hash 8 bits 8 bitsCisco TrustSec support (including L2 encryption) Yes YesCPU HW rate limiters by PPS or BPS Yes YesCoPP for multicast L2 and L3 support L2 and L3 supportCoPP for exceptions (MTU, TTL) Yes YesCoPP exceptions Netflow support Yes YesACL labels 16K 16KPort ACL 8K 8KACL dry run Yes YesHitless ACL changes Yes YesTable 4. MPLS and Virtualization FeaturesFeature VS-S2T-10G VS-S2T-10G-XLVSS Yes YesLabel imposition/disposition (MPLS-PE), swapping (MPLS-P) Yes YesLabel Distribution Protocol (LDP) Yes YesMPLS VPN Yes YesVRF Lite Yes YesQoS mechanisms using experimental (EXP) bits Yes YesMPLS-RSVP-TE Yes YesYes YesMPLS differentiated services (diffserv)-aware traffic engineering(MPLS-DS-TE)MPLS traceroute Yes YesEoMPLS Yes YesEoMPLS tunnels 16k 16kNative VPLS in HW Yes YesNative L2 over multipoint GRE Yes YesVRF-aware operational contexts Yes YesVPN Netflow support Yes YesVPN aware NAT Yes YesVRF-lite scalability VLAN reuse per sub-interface VLAN reuse per sub-interfacePer VPN interface statistics Yes YesPlatform Support and CompatibilityTable 5 lists product specifications.Table 5. Product SpecificationsProduct SpecificationsChassis compatibility ●E-Series only: Cisco Catalyst 6503-E, 6504-E, 6506-E, 6509-E, 6509-V-E, 6513E Switch fabric ●2.08 Tbps Crossbar Switch Fabric with 26 Fabric ChannelsLine-card compatibility ●WS-X6908-10G-2T, WS-X6908-10G-2TXL●WS-X6824-SFP-2T, WS-X6824-SFP-2TXL●WS-X6848-SFP-2T, WS-X6848-SFP-2TXL●WS-X6848-TX-2T, WS-X6848-TX-2TXL● WS-X6816-10T-2T, WS-X6816-10T-2TXL●WS-X6816-10G-2T, WS-X6816-10G-2TXL●WS-X6904-40G-2T, WS-X6904-40G-2TXL●WS-X6704-10GE with CFC●WS-X6724-SFP with CFC●WS-X6748-SFP with CFC●WS-X6748-GE-TX with CFC●WS-X6148A-RJ-45, WS-X6148A-45AF, WS-X6148-FE-SFP, WS-X6148A-GE-TX, WS-X6148A-GE-45AF, WS-X6148E-GE-45ATWith a DFC4 or DFC4XL upgrade (WS-F6k-DFC4-A, WS-F6k-DFC4-AXL)●WS-X6704-10GE●WS-X6724-SFP●WS-X6748-SFP●WS-X6748-GE-TXWith a DFC4 or DFC4XL upgrade (WS-F6k-DFC4-E, WS-F6k-DFC4-EXL)●WS-X6716-10G-3C, WS-X6716-10G-3CXL●WS-X6716-10T-3C, WS-X6716-10T-3CXLFan tray and power supply supported ●1400W for 6503-E●2700W for 6504-E●3000W AC or DC all other chassis●4000W AC or DC all other chassis●6000W AC or DC all other chassis●8700W AC all other chassisSlot requirements Occupies the Supervisor slots as follows:●3-slot E-chassis: slots 1 and 2●4-slot E-chassis: slots 1 and 2●6-slot E-chassis: slots 5 and 6●9-slot V-E chassis: slots 5 and 6●9-slot E-chassis: slots 5 and 6●13-slot E-chassis: slots 7 and 8Software compatibility ●12.2(50)SY and future releasesOptics and SFP options ●X2-10GB-LR,● X2-10GB-SR●X2-10GB-CX4,●X2-10GB-ER,●X2-10GB-LX4,●X2-10GB-LRM●X2-10GB-ZR●X2-10GB-DWDM●CVR-X2-SFP10G - OneX Adapter●SFP-H10GB-CU1M1 - 1 Meter Passive Cable●SFP-H10GB-CU3M1 -3 Meter Passive Cable●SFP-H10GB-CU5M1 - 5 Meter Passive Cable●SFP-10G-SRService Modules ●ACE 20, ACE 30, NAM-1, NAM-2, NAM-3, FWSM, ASA-SM, WiSM-1, WiSM-2SW packages ●IP BASE●IP Services●Advanced IP Services●Advanced Enterprise ServicesConnectivity management processor (CMP) ●Integrated Connectivity Management Processor for improved Out-of-Band Management DRAM ●2GB for Lite and XL (4GB upgrade with 2GB memory upgrade (2+2)NVRAM ●4 MBCompact Flash ●1GBUSB ●USB base console and file system - Support for Host and DeviceManagement LED ●Blue Beacon LEDUplink ports ●3 x GE SFP Ports●2 x 10G X2 Ports●1 x 10/100/1000 Management PortConsole ports ●One console port (RJ-45)Reliability and availability ●FSU (Fast software upgrade)●SSO+NSF (Stateful Switchover + Nonstop Forwarding)●OIR (Online insertion and removal) Hot Swap of power supplies, modules, fan trays andSupervisorsMIBs ●MPLS LDP MIB, MPLS Label Switch Router (LSR) MIB, MPLS-TE MIB, MPLS VPNMIB; see software release notes for additional information●Check the following MIB finder for more info:/public/sw-center/netmgmt/cmtk/mibs.shtmlNetwork management ●Cisco WorksPhysical specifications ●(H x W x D): 1.73 x 14.4 x 16 in (4.4 x 36.6 x 40.6 cm)●Weight: 12.0 lbsPower consumption ●Lite: 435W MAX●XL: 450W MAXECC ●ECC Protection SupportEnvironmental conditions ●Operating temperature: 32 to 104°F (0 to 40°C)●Storage temperature: -40 to 167°F (-40 to 75°C)●Relative humidity: 10 to 90 percent, noncondensing**Check software release for availability.Product SpecificationsTable 6 lists specifications and compliance information.Table 6. Product Specifications and ComplianceProduct SpecificationsRegulatory ComplianceSafety ●UL 60950-1●CAN/CSA-C22.2 No. 60950-1●EN 60950-1●IEC 60950-1●AS/NZS 60950-1●GB4943EMC: emissions ●47CFR Part 15 (CFR 47) Class A●AS/NZS CISPR22 Class A●CISPR2 2 Class A●EN55022 Class A●ICES003 Class A●VCCI Class A●EN61000-3-2●EN61000-3-3●KN22 Class A●CNS13438 Class AEMC: immunity ●EN50082-1●EN61000-6-1●EN55024●CISPR24●EN300386●KN 61000-4 SeriesNEBS criteria levels ●SR-3580 NEBS level 3 GR-63-CORE, issue 3; GR-1089 CORE, issue 4 Verizon NEBS compliance ●Telecommunications Carrier Group (TCG) ChecklistQwest NEBS requirements ●Telecommunications Carrier Group (TCG) ChecklistATT NEBS requirements ●ATT TP76200 level 3 and TCG ChecklistETSI ●ETS 300 019-2-1, Class 1.2 Storage●ETS 300 019-2-2, Class 2.3 Transportation●ETS 300 019-2-3, Class 3.2 Stationary UseOrdering InformationTo place an order, visit the Cisco Ordering Home Page. Tables 7 and 8 give ordering and part number information. Table 7. Supervisor Engine and Memory Part NumberPart Number DescriptionVS-S2T-10G Cisco Catalyst 6500 Series Supervisor Engine 2TVS-S2T-10G-XL Cisco Catalyst 6500 Series Supervisor Engine 2T XLVS-S2T-10G= Cisco Catalyst 6500 Series Supervisor Engine 2T SpareVS-S2T-10G-XL= Cisco Catalyst 6500 Series Supervisor Engine 2T XL SpareVS-F6K-PFC4XL= Cisco Catalyst 6500 Series Supervisor PFC 4 XL SpareMEM-SUP2T-2GB Cisco Catalyst 6500 2GB Memory for Supervisor Engine 2TMEM-SUP2T-2GB= Cisco Catalyst 6500 2GB Memory for Supervisor Engine 2T SpareMEM-C6K-CPTFL1GB Cisco Catalyst 6500 Compact Flash Memory 1GBMEM-C6k-CPTFL1GB= Cisco Catalyst 6500 Compact Flash Memory 1GB SpareMEM-C6K-CPTFL2GB Cisco Catalyst 6500 Compact Flash Memory 2GBMEM-C6k-CPTFL2GB= Cisco Catalyst 6500 Compact Flash Memory 2GB SpareTable 8. Software Part NumbersSoftware Part Number DescriptionS2TAEK9-12250SY Cisco CAT6000-VS-S2T IOS ADV ENT SERV FULL ENCRYPTS2TAEK9N-12250SY Cisco CAT6000-VS-S2T IOS ADVANCED ENTERPRISE SERVICES NPES2TAIK9-12250SY Cisco CAT6000-VS-S2T IOS ADVANCED IP SERVICES FULL ENCRYPTS2TAIK9N-12250S Cisco CAT6000-VS-S2T IOS ADVANCED IP SERVICES LAN ONLY NPES2TIBK9-12250SY Cisco CAT6000-VS-S2T IOS IP BASE LAN ONLY FULL ENCRYPTS2TIBK9N-12250SY Cisco CAT6000-VS-S2T IOS IP BASE LAN ONLY NPES2TISK9-12250SY Cisco CAT6000-VS-S2T IOS IP SERV LAN ONLY FULL ENCRYPTS2TISK9N-12250SY Cisco CAT6000-VS-S2T IOS IP SERV LAN ONLY NPES2TIB-12250SY Cisco CAT6000-VS-S2T IOS IP BASES2TIS-12250SY Cisco CAT6000-VS-S2T IOS IP SERVCisco and Partner ServicesEnable the innovative, secure, intelligent edge in the Borderless Network Architecture using personalized services from Cisco and our partners. Through a discovery process that begins with understanding your business objectives, we help you integrate the new Cisco Catalyst 6500-C4 System into your architecture and incorporate network services onto that platform. Sharing knowledge and leading practices, we support your success every step of the way as you deploy, absorb, manage, and scale new technology. Choose from a flexible suite of support services designed to meet your business needs and help you maintain high-quality network performance while controlling operational costs. For additional information about Cisco services, visit /go/services.Warranty Coverage and Technical Service OptionsThe Cisco Catalyst 6500 C4 System comes with a Cisco 90-day hardware warranty. Adding a contract for a technical service offering such as Cisco SMARTnet® Service to your device coverage provides access to the Cisco Technical Assistance Center (TAC) and can provide a variety of hardware replacement options to meet critical business needs, updates for licensed OS software, and registered access to the extensive knowledge base and support tools.For more information about Cisco warranties, go to /go/warranty.For information about Cisco Technical Services, go to /go/ts.Table 9 shows the Cisco technical services available for the Cisco Catalyst 6500 C4 System.Table 9. Cisco Technical Services for Cisco Catalyst 6500 C4 SystemTechnical ServicesCisco SMARTnet Service●Around-the-clock, global access to the Cisco Technical Assistance Center (TAC)●Unrestricted access to the extensive resources, communities, and tools●Next-business-day, 8x5x4, 24x7x4, and 24x7x2 advance hardware replacement2 and onsite parts replacement and installation available●Ongoing operating system software updates within the licensed feature set1●Proactive diagnostics and real-time alerts on Smart Call Home enabled devicesCisco Focused Technical Support ServicesThree levels of premium, high-touch services are available:●Cisco High-Touch Operations Management Service●Cisco High-Touch Technical Support Service●Cisco High-Touch Engineering ServiceValid Cisco SMARTnet or SP Base contracts on all network equipment are required.Footnotes:1. Cisco operating system updates include the following: maintenance releases, minor updates, and major updates within the licensed feature set.2. Advance hardware replacement is available in various service-level combinations. For example, 8x5xNBD indicates that shipment will be initiated during the standard 8-hour business day, 5 days a week (the generally accepted business days within the relevant region), with next business day (NBD) delivery. Where NBD is not available, same day ship is provided. Restrictions apply; please review the appropriate service descriptions for details.For More InformationFor more information about Cisco Catalyst 6500 Series switch, visit/en/US/products/hw/switches/ps708/index.html.。
功能一览集中策略控制-一个集中的、覆盖整个网络的策略数据库消除了在路由选择和交换环境中为实现QoS的配置、修改和部署而一个设备一个设备地进行管理的必要。
易于使用的策略配置-QPM简化了通信流分类和端对端QoS供应的配置,同时可以提供基于规则的策略有效性验证。
为关键商业应用提供差别服务-根据应用定义定义不同的服务等级,可通过内容级的应用识别功能得到加强。
<BR>语音QoS支持-确保高质量语音和视频服务的性能。
全面的QoS功能支持-提供广泛的可以利用智能QoS功能的拥塞管理、拥塞避免和通信流整形服务。
自动化策略部署-确保在Cisco设备上部署可控的和可靠的QoS策略。
QoS策略管理器的优点QoS的目标是通过提供专用带宽、控制抖动和延迟、管理拥塞和提高通信流效率来提供一致、可预测的网络服务。
作为增强智能网络的一部分,QoS对整个企业来说都是非常重要的。
通过实现应用性能需求到QoS策略的转换过程的自动化,QPM可以确保关键商业应用、语音和多媒体通信流的可靠性能,它们都在争夺非关键性通信流。
QPM提供的关键益处包括能够支持整个网络范围内的基于内容的差别服务,自动化的QoS配置和部署,以及确保园区网到WAN的策略控制。
提供整个网络范围内的差别服务根据应用通信流的相对重要性提供网络资源是最有效的提供QoS的方式。
分组分类是一个关键功能,它允许为通过某一网络单元或特定接口的适当的数据分组提供QoS服务。
使用QPM,一个管理员可以快速构建基于规则的能够对应用通信流进行识别并将其划分为不同服务等级的QoS策略。
被分类以后,可以根据适当的IP优先级或差别服务代码点(DSCP)对这些数据分组作出标记。
QPM支持粒度等级良好的通信流分类,包括TCP/用户数据报协议(UDP)端口和IP地址。
通过Cisco IOS软件中网络应用识别(NBAR)的增强分类功能,QPM还可以支持Cisco内容组网。
NBAR支持通过应用签名、分组中的特殊内容(包括Web URL)以及动态协议的捕获来进行分类。
cisco871w路由器QoS配置步骤cisco 871w路由器QoS配置步骤在Cisco网络设备上使用服务质量(QoS),可以为某些类型的网络流量提供固定的带宽和优先级。
笔者会向大家介绍如何通过我们的设置模板,轻松的为Cisco路由器和交换机配置QoS.网络管理员可以通过QoS为某类网络流量指定所需的带宽和优先级。
首先我们要理解带宽和优先级之间的区别。
当我们在网络设备(路由器和交换机)上指定了某类数据流的优先级和带宽,那么这些数据就会在其它数据传输之前进行传输,同时网络设备也会通过加大该类数据的发送量的方式来提高其传输带宽。
正如我之前所说的,配置QoS是一件复杂的工作。
根据QoS的不同,使用QoS的方式也多种多样。
我们曾介绍过如何利用Cisco IOS AutoQoS对路由器进行自动配置,为VoIP数据流提供足够的带宽和优先级。
配置QoS下面我们就来看看在Cisco 871W路由器上配置QoS的具体步骤。
第1步:定义传输类型你必须告诉路由器,哪种数据流需要进行QoS管理。
你可以通过访问控制列表(ACL)或者基于网络应用程序识别(NBAR)的方式来进行定义。
其中ACL是为路由器设定不同传输数据类型的传统方式。
而NBAR则是让路由器识别流经路由器的各种数据的类别,比如HTTP数据是HTTP类别,Skype是Skype类别。
但是路由器可识别的应用程序协议数量是有限的,这依赖于路由器内部存储的一个程序协议列表。
虽然路由器无法识别全部应用程序,但是路由器厂商在每次IOS 升级时,会在列表中加入更多的程序。
另外,你也可以自己定义程序识别列表。
第2步:创建类映射(class-map)类映射就是将不同类型的数据流进行分组。
比如,你可以创建一个叫做"VoIP traffic"的类映射,然后将各种VoIP协议归入该类。
第3步:创建策略映射(policy-map)策略映射可以与类映射匹配,确定某类数据流的带宽和/或优先级。
cisco qos限速的方法步骤详解思科cisco路由交换是所有设备中小编觉得最难的。
不少网友都不知道Cisco交换机下,该如何进行QOS限速配置。
其实步骤并不难,下面店铺给大家介绍一下具体操作办法,供大家参考!cisco qos 限速实例1:思科交换机上QOS限速问题用于交换机上对专线用户的带宽进行控制,交换机平时都是10/100/1000、三种速率的,对于其它的速率需要进行QOS进行限速,也可以对一些端口进行限制,做策略,对一些端口进行限制。
一、网络说明user1_PC1接在Cisco3560 F0/1上,速率为1M;ip_add 192.168.1.1/24user2_PC2接在Cisco3560 F0/2上,速率为2M;ip_add 192.168.2.1/24Cisco3560的G0/1为出口,或级联端口。
二、详细配置过程注:每个接口每个方向只支持一个策略;一个策略可以用于多个接口。
因此所有PC的下载速率的限制都应该定义在同一个策略(在本例子当中为policy-map user-down),而PC不同速率的区分是在Class-map分别定义。
1、在交换机上启动QOSSwitch(config)#mls qos //在交换机上启动QOS2、分别定义PC1(192.168.1.1)和PC2(192.168.2.1)访问控制列表Switch(config)#access-list 1 permit 192.168.1.0 0.0.0.255 //控制pc1上行流量Switch(config)#access-list 101 permit any 192.168.1.0 0.0.0.255 //控制pc1下行流量Switch(config)#access-list 2 permit 192.168.1.2 0 0.0.0.255 //控制pc2上行流量Switch(config)#access-list 102 permit any 192.168.2.1 0.0.0.255 //控制pc2下行流量3、定义类,并和上面定义的访问控制列表绑定Switch(config)# class-map user1-up //定义PC1上行的类,并绑定访问列表1Switch(config-cmap)# match access-group 1Switch(config-cmap)# exitSwitch(config)# class-map user2-upSwitch(config-cmap)# match access-group 2 //定义PC2上行的类,并绑定访问列表2Switch(config-cmap)# exitSwitch(config)# class-map user1-downSwitch(config-cmap)# match access-group 101 //定义PC1下行的类,并绑定访问列表101Switch(config-cmap)# exitSwitch(config)# class-map user2-downSwitch(config-cmap)# match access-group 102 //定义PC2下行的类,并绑定访问列表102Switch(config-cmap)# exit4、定义策略,把上面定义的类绑定到该策略Switch(config)# policy-map user1-up //定义PC1上行的速率为1M,超过的丢弃Switch(config-pmap)# class user1-upSwitch(config-pmap-c)# trust dscpSwitch(config-pmap-c)# police 1000000 1000000 exceed-action dropSwitch(config)# policy-map user2-up //定义PC2上行的速率为2M ,超过丢弃Switch(config-pmap)# class user2-upSwitch(config-pmap-c)# trust dscpSwitch(config-pmap-c)# police 2000000 2000000 exceed-action dropSwitch(config)# policy-map user-downSwitch(config-pmap)# class user1-downSwitch(config-pmap-c)# trust dscpSwitch(config-pmap-c)# police 1000000 1000000 exceed-action dropSwitch(config-pmap-c)# exitSwitch(config-pmap)# class user2-downSwitch(config-pmap-c)# trust dscpSwitch(config-pmap-c)# police 2000000 2000000 exceed-action dropSwitch(config-pmap-c)# exit5、在接口上运用策略Switch(config)# interface f0/1Switch(config-if)# service-policy input user1-upSwitch(config)# interface f0/2Switch(config-if)# service-policy input user2-upSwitch(config)# interface g0/1Switch(config-if)# service-policy input user-down实例2:限制BT下载的QOS配置实例一、找出BT程序开放的连接端口,默认为6881至6889.二、将局域网内经常拉BT的IP统计出来,建立扩展访问列表如下:Extended IP access list btdownloadpermit tcp any host 192.168.1.120 range 6881 6889permit tcp any host 192.168.1.135 range 6881 6889permit tcp any host 192.168.1.146 range 6881 6889permit tcp any host 192.168.1.159 range 6881 6889permit tcp any host 192.168.1.211 range 6881 6889permit tcp any host 192.168.1.223 range 6881 6889三、建立class-map class_btCisco(config)#class-map class_btCisco(config-cmap)#match access-group name btdownload四、建立policy-map qos_bt 进行速率限制Cisco(config)#policy-map qos_btCisco(config-pmap)#class class_btCisco(config-pmap-c)#police 5000000 8000 exceed-action drop五、QOS配置完毕了,不过在将QOS应用到端口前,要搞清楚一个概念,QOS机制不能与flowcontrol(流控制)功能共存在同一个端口上。
如何设置QoS来限制各个电脑的速度QoS(Quality of Service)是一种网络技术,可用于限制各个设备的带宽使用,以确保网络的稳定性和流畅性。
如果您的家庭网络存在速度缓慢的问题,您可以通过设置QoS来限制各个电脑的速度,以确保每个设备获得足够的带宽。
以下是如何设置QoS来限制各个电脑的速度的基本步骤:步骤一:登录路由器的Web管理界面首先,您需要登录路由器的Web管理界面。
在浏览器中输入路由器的IP地址,例如192.168.1.1,并输入用户名和密码进行登录。
步骤二:启用QoS功能在路由器的Web管理界面上,找到QoS设置选项,并启用QoS功能。
这将为您提供设置每个设备带宽限制的选项。
步骤三:为每个设备设置带宽限制在QoS设置页面上,为每个设备设置带宽限制。
您可以手动输入每个设备的MAC地址,并分配所需的最大带宽限制。
例如,如果您有三台设备需要连接到网络,您可以为每台设备分配不同的带宽限制,以确保每个设备都获得足够的带宽。
步骤四:设置更高级别的QoS配置(可选)如果您的路由器支持更高级别的QoS配置,您还可以设置更精细的带宽限制。
例如,您可以设置每个设备的优先级,以确保关键任务获得足够的带宽。
此外,您还可以设置不同应用程序的带宽限制,以确保网络流畅性。
步骤五:保存设置并重新启动路由器完成所有设置后,不要忘记保存设置并重新启动路由器,以确保设置生效。
请注意,每个路由器的QoS设置过程略有不同。
因此,如果您遇到问题或需要更多帮助,请参考您的路由器制造商的文档或支持服务。
总之,设置QoS是一种很好的方法,可以限制各个电脑的速度,以确保网络的稳定性和流畅性。
如果您遇到任何问题,请参考本文提供的步骤或者咨询您的路由器制造商的文档或支持服务。
QoS Support for High-Performance Scientific Grid Applications Rashid Al-Ali,1,2Gregor von Laszewski,1Kaizar Amin,1,3Mihael Hategan,1Omer Rana,2David Walker,2and Nestor Zaluzec11Argonne National Laboratory,U.S.A.2CardiffUniversity,UK.3University of North Texas,U.S.A.AbstractThe Grid approach provides the ability to access and use distributed resources as part of virtual organiza-tions.The emerging Grid infrastructure gives rise to a class of scientific applications and services to support collaborative and distributed resource-sharing require-ments as part of teleimmersion,visualization,and sim-ulation services.Because such applications operate in a collaborative mode,data must be stored and delivered in timely manner to meet deadlines.Hence,this class of applications has stringent real-time constraints and quality-of-service(QoS)requirements.A QoS manage-ment approach is required to orchestrate and guarantee the interaction between such applications and services. In this paper we discuss the design and prototype im-plementation of a QoS system and show how we enable Grid applications to become QoS compliant.We vali-date this approach through a case study of nanomate-rials.Our approach,enhances the current Open Grid Services Architecture.We demonstrate the usefulness of the approach on a nano materials application.1IntroductionAdvanced commercial and scientific applications of-ten require high-performance,high-end resources that are both expensive and scarce.Based on the Grid ap-proach[1]the emerging Grid infrastructure[2]is mak-ing these resources available to service providers and users,but effective use of such resources requires mech-anisms to manage sophisticated Grid environments. Consequently,considerable effort has gone into secu-rity issues,resource scheduling,and complex execu-tion frameworks.Although the Grid community has collectively made considerable progress,only recently has consideration been given to a fundamental prob-lem prevailing in service-oriented architectures:provid-ing deterministic quality-of-service(QoS)assurances to service consumers.Providing nontrivial QoS is one of the primary goals of the Grid approach.Nevertheless, most Grid environments operate on a best-effort basis, sharing the Grid resources among its users with equal priority.A considerable degradation in performance and efficiency must be addressed when a large number of requests are issued for shared Grid resources.To address this problem,we concentrate on ways to increase the collective efficency a term refered to by von Laszewski as the efficiency of scientists collaboratively using these resources.One practical solution is to intro-duce QoS mechanisms that enable service providers to partition their services based on quality criteria such as priority,fairness,and economic gain.In other words,a QoS-aware Grid infrastructure can offer deterministic QoS assurances based on a particular criterion,rather than on a best-effort service.Consider the following scenario[3].A group of scientists want to conduct a collaborative simulation experiment for a specific period of time using high-end resources,such as an electron microscope,acces-sible through a Grid infrastructure.The experiment requires access to resources suitable forfine-grained, real-time computation and requires a specific network bandwidth to connect the sites during the experiment. After the experiment is concluded,the data must be moved to a large-capacity,shared data-store,allowing access to the data by groups of scientists not located at the electron microscope site.Clearly,this scenario has a number of requirements that a non-Grid-based resource management or scheduling system cannot ful-fill.Motivated by such a scenario,we propose a com-prehensive QoS management architecture in service-oriented Grids,called Grid Quality of Service Manage-ment(G-QoSm).We validate our proposed architec-ture with a proof-of-concept prototype implementation and show its effectiveness in a scientific application in-volving nanomaterials.The paper is structured as follows.In Section2 we provide an overview of quality of service in net-working and distributed computing.In Section3weoutline the general requirements of a Grid QoS man-agement system and give an overview of existing Grid QoS systems.In Section4we present G-QoSm and its major components.In Section5we discuss a typ-ical high-performance Grid application and outline its QoS requirements.In Section7we discuss performance results based on executing applications with QoS sup-port.We conclude the paper with a summary of future work.2Quality-of-Service:Background and TerminologyQuality of service has been explored in various con-texts[4,5].Two types of QoS can be distinguished: quantitative and qualitative characteristics of the Grid infrastructure.Qualitative characteristics refer to ele-ments such as service reliability and user satisfaction regarding service.Quantitative characteristics refer to elements such as networks,CPUs,or storage.For ex-ample,the following are quantitative parameters for network QoS:Delay,the time it takes a packet to travel from sender to receiver.Delay jitter,the variation in the delay of packets taking the same route.Through-put,the rate at which packets go through the network (i.e.,bandwidth).Packet-loss rate’,the rate at which packets are dropped,lost,or corrupted.Together,these four parameters form the network QoS measurement matrix.CPU,or compute,QoS can be divided into shared and exclusive categories[6].In shared systems,in which more than one user-level application shares the CPU,the application can specify a percentage of the CPU.In exclusive systems,in which usually one user-level application has exclusive access to one or more CPUs,the application can specify the number of CPUs as the QoS parameter.Storage QoS is related to device such as memory and disks.In this context,QoS is specified by bandwidth and space.Bandwidth is the rate of data transfer be-tween the storage devices to the application.Space is the amount of storage space that the application can use for writing data.Usually,applications specify two QoS requirements: the characteristics of the resource and the period the resource is required.Reservation involves giving the application the confidence,or assurance,that the re-source allocation will succeed with the required level of QoS when needed.The reservation can be immediate or in advance,and the duration of the reservation can be definite(for a defined period of time)or indefinite (for a specified start time and unlimited duration).3QoS in Grid ComputingThe Grid approach can be seen as a global-scale distributed-computing infrastructure with coordinated resource sharing[1,2].The fundamental Grid prob-lem that many researchers have been investigating is resource management,specifying how Grid middleware can provide resource coordination for client application transparently.One of the most successful middleware projects that provides such coordination is the Globus Alliance[7].The availability of Grid middleware tools, such as the Globus Toolkit,facilitates persistent access to Grid services.The use of Grid middleware has ex-panded from scientific applications to business-oriented disciplines while envisioning a service-oriented archi-tecture to build sophisticated Grid applications with complex Grid resources requirements.In most Grid settings,Grid applications submit their requirements to Grid resource management ser-vices that schedule jobs as resources become available. Some classes of applications cannot wait for resources to become available,however.For these applications, it must be possible to reserve Grid resources and ser-vices at a particular time(in advance or on-demand). In addition,other features are highly desirable,indeed required,if the Grid resource management service is to be able to handle complex scientific and business ap-plications.We review these requirements in the next subsection and then briefly discuss how well current QoS systems meet these requirements.3.1RequirementsA Grid resource management system should adhere to the following requirements that relate to QoS issues.Advance Resource Reservation.The system should support mechanisms for advance,immediate,or ‘on-demand’resource reservation.Advance reservation is particularly important when dealing with scarce re-sources,as is often the case with high-performance and high-end scientific applications in Grids.Reservation Policy.The system should support a mechanism that facilitates Grid resource owners enforc-ing their policies governing when,how,and who can use their resource,while decoupling reservation and policy entities,in order to improve reservationflexibility[8]. Agreement Protocol.The system should assure the clients of their advance reservation status,and the resource quality they expect during the service session. Such assurance can be contained in an agreement pro-tocol,such as Service Level Agreements(SLAs).Security.The system should prevent malicious users penetrating,or altering,data repositories that hold in-formation about reservations,policies and agreement protocols.In addition to a secure channel between the clients and applications and the Grid resources,a proper security infrastructure is required. Simplicity.The QoS enhancement should have a reasonably simple design that requires minimal over-heads in terms of computation,infrastructure,storage and message complexity.Scalability.The approach should be scalable to a large number of entities,since the Grid is a global-scale infrastructure,and there will be dynamic resources and users joining the Grid.3.2Current QoS SystemsQoS in Grids is actively being researched.However, the only substantial system developed within the Grid community(to our knowledge)is the General-purpose Architecture for Reservation and Allocation(GARA). GARA[9]provides programmers a convenient access to end-to-end QoS.It provides advance reservations, with uniform treatment to various types of resources such as network,compute,and disk.GARA’s reser-vation is a promise that the client or application ini-tiating the reservation will receive a specific quality of service from the resource manager.GARA also pro-vides an application programming interface to manip-ulate reservation requests,such as create,modify,bind, and cancel.GARA uses the Dynamic Soft Real-time (DSRT)scheduler[10]as the underlying compute re-source manager,and it uses Cisco routers to deliver network QoS.Although GARA has gained popularity in the Grid community,it has certain limitations in coping with current application requirements and technologies:•Most current applications employ the emerging new technology of the Web services and the Open Grid Service Architecture(OGSA)[11].Unfortu-nately,GARA is not OGSA-enabled,and OGSA-enabled applications cannot therefore leverage GARA services.•Grid applications require the simultaneous allo-cation of various resources.This process is per-formed by the resource manager that contacts the required resources and possibly reserves the re-sources for future allocation.An agreement pro-tocol should exist to inform the application about the resources negotiated for allocation and the level of quality the application expects.This infor-mation is usually encapsulated in a ServiceLevelFigure1.The G-QoSm architecture with anOGSA-enabled QoS service.Agreement.GARA does not support the concept of an agreement protocol and cannot distinguish whether an application requires a CPU and a net-work resource.The application has to perform two separate calls to GARA and,on success,receives two different handlers.It is the application’s re-sponsibility to manage these handlers when claim-ing the resources.•QoS monitoring and adaptation during the active QoS session is one of the most important and suc-cessful mechanisms to provide a quality guarantee.GARA is not tooled with adaptive functions[12].The most significant limitation,however,is that GARA is at this time no longer actively being devel-oped.4Grid QoS ManagementGrid Quality of Service Management(G-QoSm)is an evolving approach to support QoS management in computational Grids in the context of the Open Grid Service Architecture(OGSA)[13,14].G-QoSm con-sists of three main operational phases:establishment, activity,and termination.During the establishment phase,a client’s application states the desired service and QoS specification.G-QoSm then undertakes a ser-vice discovery,based on the specified QoS properties, and negotiates an agreement offer for the client’s ap-plication.During the activity phase,additional activ-ities,including QoS monitoring,adaptation,account-ing and possibly renegotiation,may take place.Dur-ing the termination phase,the QoS session is ended,through resource reservation expiration,agreement vi-olation,or service completion;resources are then freed for use by other clients.Our framework supports these three phases through interaction among components, as depicted in Figure1.In the next section we de-scribe these interactions and highlight service provision for Grid applications.4.1QoS Grid ServiceThe basic building block of our architecture is the QoS Grid service(QGS),an OGSA-enabled Grid ser-vice providing QoS functionalities such as negotiation and reservation.Each QoS-enabled resource is accessed through a QGS.Since QGS is a Grid service,it pub-lishes itself to a QoS registry service.In addition to the QoS functionalities,it supports two types of resource allocation strategy:resource domain,which provides compute,network, and disk QoS withfine-grained specifications,andtime domain,where the whole Grid node,in which the QGS resides,can be reserved for a defined period of time.This functionality is enabled by ensuring that all re-quests must be issued through the QGS.Further,the QGS interacts with a number of modules to deliver QoS guarantees.These modules are the QoS Handler, reservation manager,allocation manager,and the QoS registry service(see Figure1).Currently,G-QoSm sup-ports compute resource-based QoS;we have begun in-tegrating network and disk support.QoS Handler Access to Grid services is enabled through the Java CoG Kit,which provides a convenient abstraction to Grid services for Globus Toolkit versions 2and3.The Java CoG Kit introduced the concept of task handlers,which allow us to build QoS-enhanced abstractions for computational tasks(see Section4.2). Hence,we have introduced a QoS Handler as a link with the Java CoG Kit Core.The QoS Handler im-plements the required QoS action,encapsulated in the Java CoG Kit Task object,such as QoS negotiation re-quest or QoS job submission.We have enhanced the Task object with QoS-related parameters dependent on the Task action required;for example,in the case of a negotiation request,parameters include start time,end time,resource type,and specifications.Once the Task object has been specified,the QoS Handler is,for ex-ample,delegated,on behalf of the client or application, to negotiate QoS requests.In this case the QoS Han-dler is seen as the client,from the QGS point of view.This is a useful approach especially when the appli-cation requires more than one Grid resource.All the application needs is to instantiate the required number of QoS Handler objects,submit the Task object to the handlers,and let the handlers negotiate QoS requests with the QGS to return an agreement.Furthermore,in a QoS-enabled job submission through the interactive mode,the QoS Handler listens for notifications of job status,with the notification implemented by the QGS as an OGSA notification.We plan to align ourselves with the GGF Grid Resource Agreement and Alloca-tion Protocol(GRAAP)Working Group[15]that is defining a WS-Agreement protocol meant to address machine-to-machine negotiations.Reservation Manager.The reservation manager is based around a data structure that supports reserva-tions for quantifiable resources;resources associated with defined capacities.The reservation manager is decoupled from the underlying resources and does not have direct interaction with them.However,it ob-tains resource characteristics,and policies governing resource usage,from the policy manager.The policy manager,on the other hand,is responsible for validat-ing reservation requests by applying domain-specific rules,established by the resource owners,on when, how,and by whom the resource can be used.In brief, when the reservation manager receives a reservation request from the QGS,it contacts the policy manager for validation and then performs admission control to check the availability of the requested resource.Upon success,it returns a positive reply to the QGS,which allows the QGS to propose a negotiable service agree-ment offer.Allocation Manager.The Allocation Manager’s primary role is to interact with underlying resource managers for resource allocation and deallocation and to inquire about the status of the resources.It has in-terfaces with various resource managers,namely,the Dynamic Soft Real Time Scheduler(DSRT)[10]and Network Resource Manager(NRM);we are also inves-tigating Nest as the disk storage resource manager[16]. When the allocation manager receives resource alloca-tion request from the QGS,it forwards the request to the designated underlying resource manager.The Al-location Manager interacts with adaptive services to enforce adaptation strategies;for details,see[12]. QoS Registry Service.Since the framework oper-ates in the OGSA architecture,the QGS and other Grid services in the OGSI container should be pub-lished in some registry service so they can be knownby others.Service publishing,in this discussion,does not mean simply publishing a service name,URL,and basic description.For example,for QGS,it includes in-formation on what QoS-enabled service it offers,what allocation strategies it employs,and what classes of network QoS it offers(e.g.,best effort,controlled load, or guaranteed).For other Grid services,service pub-lishing includes information about QoS properties such as performance characteristics and service execution re-quirements.To date,we have used an extended version of the Universal Description Discovery and Integration as part of our QoS registry service.The UDDIe[17] is a Web services registry system,which provides ser-vice providers a means to publish their services with QoS properties and,hence,to search for these services based on the QoS properties.4.2Java CoG Kit CoreThe Java CoG Kit Core(cog-core)[18]compo-nent offers a technology-and architecture-independent abstraction layer that provides true interoperability across multiple Grid implementations.Cog-core pro-vides convenient APIs for Grid applications to access the underlying Grid technology.Furthermore,cog-core offers several useful abstractions reusable as part of a Quality of Service framework including Grid tasks and their corresponding handlers.Task.The Java CoG Kit defines a Task as an atomic unit of execution.A task is not limited to executing a job.Instead,it abstracts the generic Grid functional-ity,including authentication,remote job execution,file transfer request,or information query.It has a unique identity,a security context,a specification,and a ser-vice contact.The task identity helps in uniquely representing the task across the Grid.The security context represents the abstract security credentials of the task.This ab-straction makes it possible to integrate a variety of dif-ferent own security context as part of the Grid infras-tructure.Hence,the security context in cog-core of-fers a common construct that can be extended by the different implementations to satisfy the corresponding back-end requirement.The specification represents the actual attributes or parameters required for the execu-tion of the Grid-centric task.The generalized speci-fication can be extended for common Grid tasks such as remote job execution,file transfer,and information query.The service contact associated with a task sym-bolizes the Grid resource required to execute it.Handlers.The Task Handler provides a simple in-terface to handle interaction with a generic Grid task. It categorizes the tasks and providing the appropri-ate functionality.For example,the task handler will handle a remote job execution task differently from a file transfer request task.This approach does not im-pose any restrictions on the implementation of the task handler as long as its working is transparent to the end user.This module is back-end-specific and has a sepa-rate implementation for each abstraction it supports.4.3Application IntegrationWe have prototyped an implementation to demon-strate the ease of use and effectiveness of a Grid ap-plication using QoS functions.To enable other Grid applications to use the QoS-enabled framework,one needs to conduct the following simple steps:(a)create a task object based on cog-core,(b)depending on the type of the required QoS function,set up the necessary objects for security,job specification,and service con-tact,(c)instantiate a QoS Handler,and(d)Associate the created task with the QoS Handler,and submit the task.Figure2shows a Java code fragment demonstrat-ing how applications can generate QoS negotiation re-quest,QoS job submission,and task submission to a QoS handler,respectively.The concept of abstracting the QoS services and in-teracting with the QGS by creating a task(i.e.,QoS function)and submitting it to a QoS Handler has a great advantage when dealing with multiple distributed Grid resources:it makes the design and specification of abstract QoS-based brokers easier.5Application Case Study:Nanoscale StructuresTo validate our QoS approach,we applied our refer-ence implementation and prototyped a Grid computing environment for the analysis of a nanoscale structures application.This application involves a new experi-mental technique,position-resolved diffraction,being developed as part of Argonne National Laboratory’s advanced analytical electron microscope program[19]. With this technique,a focused electron probe is sequen-tially scanned across a two-dimensionalfield of view of a thin specimen.At each point on the specimen a two-dimensional electron diffraction pattern is acquired and stored.Analysis of the spatial variation in the electron diffraction pattern of each measured point allows the/***QoS:Prepare Negotiation Task***/ private void prepareQosNegotiationTask(){ //create a QoS service,andsetup QoS attributes Task task=new QosTaskImpl(‘‘myTask’’,QoS.NEGOTIATION);this.task.setAttribute(‘‘startTime’’,startTime); this.task.setAttribute(‘‘endTime’’,endTime);this.task.setAttribute(‘‘allocStrategy’’,strategy); this.task.setAttribute(‘‘cpu_capacity’’,cpuCapacity); //create a Globus version of the security context SecurityContextImpl securityContext=new GlobusSecurityContextImpl();//selects the default credentialssecurityContext.setCredential(null);//associate the security context with the tasktask.setSecurityContext(securityContext);//create a contact for the Grid resourceContact contact=new Contact(‘‘myGridNode’’);//create a service contactServiceContact service=new ServiceContactImpl(qosServiceURL);//associate the service contact with the contact contact.setServiceContact(‘‘QGSurl’’,service);//associate the contact with the tasktask.setContact(contact);}/***QoS:Prepare Job Submission Task***/private void prepareQosJobSubmissionTask(){//create a QoS JobSumbission TaskTask task=new TaskImpl(‘‘myTask’’,QoS.JOBSUBMISSION);this.task.setAttribute(‘‘agreementToken’’,token);//create a remote job specificationJobSpecification spec=new JobSpecificationImpl();//set all the job related parametersspec.setExecutable(‘‘/bin/myExecutable’’);spec.setRedirected(false);spec.setStdOutput(‘‘QosOutput’’);//associate the specification with the tasktask.setSpecification(spec);//create a Globus version of the security context SecurityContextImpl securityContext=new GlobusSecurityContextImpl();securityContext.setCredential(null);task.setSecurityContext(securityContext);Contact contact=new Contact(‘‘myQoScontact’’); ServiceContact service=new ServiceContactImpl(qosServiceURL);contact.setServiceContact(‘‘QGSurl’’,service);task.setContact(contact);}/***QoS:Task Submission to QoS Handler***/private void QosTaskSubmission(Task task){TaskHandler handler=new QoSTaskHandlerImpl();//submit the task to the handlerhandler.submit(task);}Figure2.A sample code fragment for QoS negotiation,and task submission to QoS han-dlerFigure3.Asynchronous processes define aworkflow steered by the scientist to supportthe problem-solving process with the help ofabstract Grid tasks.researcher to study subtle changes resulting from mi-crostructural differences,such as ferro-and electromag-netic domain formation and motion,at unprecedented spatial scales.As much as one terabyte of data can be taken during such an experiment.The analysis of this data requires a resource-rich Grid infrastructure to accommodate real-time constraints.Results need to be archived,remote compute resources need to be re-served and made available during an experiment,and the data needs to be moved to the compute resources where they will be analyzed.Moreover,results need to be gathered and presented in a form that is meaningful to the scientist.The need for aflexible infrastructure is demon-strated through a simpleflow diagram depicted in Fig-ure3.The elementary logic of the instrument con-trol can be expressed as a sequence of processes that depend on each other:(a)Data acquisition:gathers time-delayed images from the electron microscope.(b) Backup:backs up the incoming data.(c)Data analy-sis:performs scientific calculations on the time delayed images.(d)Result display:gathers the results from the data analysis,in a form easy to interpret,to enable further judgments for steering the experiment.The nanostructures application presents one of many scientific use patterns that occur in high-end in-strument scenarios.The pattern includes a high vol-ume of interaction during an experiment that must be dealt with in an adaptive andflexible way.Unexpected and unpredicted experiment conditions must be con-sidered,and the instrument operator’s interface to theGrid must be as simple as possible while at the same time providing neededflexibility to interactively mod-ify the experiment setup.The Java CoG Kit provides a convenient abstraction for formulating these tasks while reusing the patterns forfile transfer,job execution,and job management. At the same time it hides much of the complexity, which the Grid application developer may not want to see.To provide the necessaryflexibility,we plan to develop graphical components for the Java CoG Kit and integrate them in a problem-solving environment that targets the use of a scientific instrument.Through this interface,the scientist will be able to interact eas-ily with the experiment resources and decide when, what,and where data gathered during the course of the experiment is backed up.Imagefilters and moni-tors,plugged dynamically into the workflow for image analysis,help to validate the correctness and useful-ness of the running experiment.Since the sample in the instrument may require specialized and individ-ualfilters,the experiment operator must be given a methodology that allows their easy creation and adap-tation.Because of the focus on the experiment itself, the use of the Grid should be through abstractions as much as possible.Based on the application descrip-tion,we derive the following requirements for QoS:(a) Network requirements to transfer the time-delayed im-ages from the electron microscope as part of the data acquisition process.(b)Disk storage to cache quickly incoming data during the acquisition process and the availability of large storage for a backup process.(c) Computation power to process the scientific calcula-tions on the time-delayed images in real time,as new images become available in the data analysis process.(d)Collect results produced by the data analysis pro-cess and transfer them to a display,where the scientist can interpret outcomes and further steer the experi-ment.6Case Scenarios and RequirementsIn this section,we use case scenarios to illustrate how the QoSm framework can also benefit scientists in other disciplines.Collaborative Real-Time Experiments.A group of scientists located in different domains are collaborat-ing on a nanoscale structure experiment.Each scien-tist participates in the experiment by providing local data augmentation and then transferring that data to a high-performance computing resource for collaborative data analysis.The scientists at corresponding domains establish a guaranteed network bandwidth to conduct data transfer;similarly,the scientists at the data analy-sis location establish resource guarantees,not only for the data transfer but also for computing power with adequate resources to perform the data analysis and produce results in a specific time,when all scientist are online to interact with or steer the experiment. Ad Hoc Real-Time Experiments Needing Com-puting Power.Several scientists decide to conduct an experiment to verify certainfindings.The decision is made on an ad hoc basis,that is,without prior ar-rangement.The experiment must be conducted in a Grid infrastructure,with enough computing resources to perform the desired experiment in a reasonable time and fulfill the scientists ad hoc requirements.Here, the scientists require some commitment from the Grid middleware that the resources needed for the experi-ment are indeed available at this time.The scientists therefore submit a QoS negotiation request to a QoS manager.The QoS manager gives such a commitment if the resources are available at the specific time;if the resources are not available,the QoS manager proposes a new available time,which the scientist may accept or reject.Experiments with Deadline Constraints.A team of scientists has a deadline for delivering experi-ment results.The scientists therefore contact the QoS manager in advance to negotiate a QoS agreement to guarantee resource availability during the experiment.These three scenarios have the following common elements:(a)The need for Grid resources with par-ticular capabilities(b)The need for resources to be available for a predefined period of time(c)The need for an agreement to indicate the commitment level of resource availabilityWith these elements in mind,we have engineered the G-QoSm framework to fulfill resource requests with QoS specifications,perform advance reservations of re-sources,generate QoS agreements,and execute services based on prenegotiated QoS agreements.In the rest of the paper,we focus on the third elementthe commit-ment level of resource availabilityas we discuss the im-plementation of G-QoSm and provide initial experience results.7Implementation and ResultsOur testbed contained Grid computing resources in-cluding two Linux-based computers with a1.8GHz Pentium processor and256MB of memory for the ser-vice consumer,and a Pentium processor1.2GHz and 512MB of memory for the service provider.Deployed。