82599_10 Datasheet, PDF (3/4 Pages) Intel Corporation – Transforming the data center through a reliable and unified 10GbE network

Features
10 Gigabit MAC Advanced Features
Auto-negotiation support as defined in IEEE 802.3ap clause 73
IEEE 802.3*-compliant flow-control support with software-
controllable pause times and threshold values
Integrated LinkSec security engines (IEEE 802.1ae): AES-GCM
128bit; Encryption + Authentication; One SC x 2 SA per port.
Replay Protection with Zero Window
Integrated IPsec security engines: AES GCM 128 bit; AH or ESP
encapsulation; IPv4 and IPv6 (no option or extended headers)
Time Sync (IEEE 1588, 802.1as)
Benefits
• Provides automatic configuration between 1000BASE-KX, 10GBASE-KX4, and
10GBASE-KR modes
• Improves performance and reliability
• Frame loss reduced from receive overruns
• Control over the transmissions of pause frames through software or hardware triggering
• Provides end-to-end Layer 2 data protection between the host and the destination.
• It provides encryption and authentication at every hop along the network (i.e., servers,
switches and clients)
• Provides end-to-end Layer 3 data protection between the host and the destination
• It offloads the encryption engine to provide line rate throughput in an IPsec environment
• Lets networked Ethernet equipment synchronize internal clocks according to a network
master clock
• Endpoint can then acquire an accurate estimate of the master time by compensating for
link latency
LAN Performance Features
Tx/Rx IP, TCP, and UDP checksum offloading (IPv4, IPv6)
capabilities (IPv4, IPv6)
Tx TCP segmentation offload (IPv4, IPv6)
IPv6 offloading
TSO Interleaving for Reduced Latency
TCP Receive Side Coalescing (RSC) for up to 32 flows/port
MSI-X support
Mechanism available for reducing interrupts generated
from Tx/Rx operations
Low latency interrupts
Receive Side Scaling for Windows environments and
Scalable I/O for Linux* environments (IPv4, IPv6, TCP/UDP)
Intel® Ethernet Flow Director
Supports advanced filters that direct receive packets by
their flows to different queues
Optimized queues: 128 Transmit (Tx) and Receive (Rx)
Header split and replication in receive
IEEE 802.1q virtual local area network (VLAN) support with
VLAN tag insertion, stripping and packet filtering for up to
4096 VLAN tags
Double VLAN
• Lower processor utilization
• Checksum and segmentation capability extended to new standard packet type
• Increased throughput and lower processor utilization
• Checksum and segmentation capability extended to new standard packet type
• Lowers CPU utilization by reducing overhead
• Minimizes the overhead of interrupts
• Allows load balancing of interrupt handling between different cores/CPUs
• Maximizes system performance and throughput
• Provides the ability to toggle between interrupt aggregation and non-aggregation mode
based on the type of data being transferred
• Multiple Rx queues
• Enables tight control on routing a flow in the platform. Matches flows and CPU cores for
flow affinity
• Supports multiple parameters for flexible flow classification and load balancing
• Network packet handling without waiting or buffer overflow
• Efficient packet prioritization
• Helps the driver to focus on the relevant part of the packet without the
need to parse it
• Ability to create multiple VLAN segments
• Used for systems where the switches add an additional tag containing switching information
Virtualization Features
Virtual Machine Data Queue² (VMDq)
Virtual Machine Direct Connect (VMDc)
Packet Loopback
• Allows the efficient routing of packets to the correct target virtual machine in a virtualized
environment using multiple hardware queues
• Enables direct I/O connectivity to the virtual machines bypassing the virtual switch in the VMM
• Enables VM migration capability across two physical servers
• Based on industry-standard PCI-SIG SR-IOV
• Enables the I/O silicon to route the data packets between the VMs within the same server
instead of having to go out on the wire and come back to the same server
• Lowers CPU utilization and improves latency
Unified Networking Features
Enhanced Transmission Selection (draft IEEE 802.1az)
Priority Flow Control (draft IEEE 802.1Qbb)
FCoE Transmit Segmentation
• Resource allocation per virtual link to provide differentiation among different traffic types
(LAN, SAN, and IPC)
• Enables finer grain control of traffic for virtual links associated with Priority group. Enables
“no-drop” behavior on Ethernet for critical storage traffic
• Transmit segmentation enables the FCoE initiator to transmit multiple FCoE packets up to a
complete FC sequence with a single header in host memory (single instruction), thus reducing
CPU overhead
3