Cisco Cisco UCS C3260 Rack Server Ficha De Dados

I/O Virtualization

Features

Benefits

Multi-mode I/O Virtualization Operations

• Supports two modes of operations of virtualized environments:

- Direct assignment of part of the port resources to different guest operating systems using the PCI SIG SR-IOV standard (Also

known as native mode or pass through mode)

- Central management of the networking resources by hypervisor (Also known as software switch acceleration mode)

• A hybrid model, where some of the VMs are assigned a dedicated share of the port and the rest are serviced by an hypervisor is

also supported

Virtual Machine Device Queues (VMDq)

• Offloads data-sorting from the Hypervisor to silicon, improving data throughput and CPU usage

• QoS feature for Tx data by providing round-robin servicing and preventing head-of-line blocking

• Sorting based on MAC addresses and VLAN tags

Next Generation VMDq

• Enhanced QoS feature by providing weighted round-robin servicing for the Tx data

• Provides loopback functionality; data transfers between the virtual machines within the same physical server do not go out to

the wire and back in, improving throughput and CPU usage

• Supports replication of multicast and broadcast data

64 transmit (Tx) and receive (Rx) queue pairs per port

• Supports VMware* NetQueue and Microsoft* VMQ

• MAC/VLAN filtering for pool selection and either DCB or RSS for the queue in pool selection

Flexible Port Partitioning: 64 Virtual Functions per port

• Virtual Functions (VFs) appear as Ethernet Controllers in Linux OSes that can be assigned to VMs, Kernel processes or teamed

using the Linux* Bonding Drivers

Support for PCI-SIG SR-IOV specification

• Up to 64 Virtual Functions per Port

Rx/Tx Round-Robin scheduling

• Assigns time slices in equal portions in circular order for Rx/Tx for balanced bandwidth allocation

Traffic Isolation

• Processes or VM can be assigned a dedicated VF with VLAN support

Traffic Steering

• Offloads sorting and classifying traffic in to VF or queues

VM to VM Packet forwarding (Packet Loopback)

• On-chip VM-VM traffic allows PCIe* speed switching between VM

Multicast and Broadcast Packet Replication

• Multicast and broadcast packets can be sent to a single queue or be replicated across a across multiple queue pools

Per-pool settings, statistics, off loads, and jumbo support

• Each Queue Pair or Pool has its own statistics, off-loads and Jumbo support options

Dynamic Transmit and Receive Queues

• Queues can be enabled or disabled dynamically

Independent Function Level Reset (FLR) for Physical and Virtual

Functions

• VF resets only the part of the logic dedicated to specific VF and does not influence the shared port

IEEE 802.1Q Virtual Local Area Network (VLAN) support with

VLAN tag insertion, stripping and packet filtering for up to

4096 VLAN tags

• Adding (for transmits) and ping (for receives) of VLAN tags

• Filtering packets belonging to certain VLANs

IEEE 802.1Q advanced packet filtering

• Lower processor usage

L2 Ethernet MAC Address Filters (unicast and Multicast)

• Enables up to 128 MAC address to be assigned to queue pools and virtual functions for controller based traffic steering

L2 VLAN Filters

• Enables up to 64 VLANs to be assigned to queue pools and virtual functions for controller based traffic steering

Mirroring rules

• Ability to reflect network traffic to a given VM or VLAN based on up to four mirroring types

Stateless Offloads and Performance Features

Features

Benefits

TCP/UDP, IPv4 checksum offloads (Rx/ Tx/Large-send);

Extended Tx descriptors for more offload capabilities

• Improved CPU usage

• Checksum and segmentation capability extended to new standard packet type

IPv6 support for IP/TCP and IP/UDP receive checksum offload

• Improved CPU usage

Tx TCP Segmentation Offload (TSO-IPv4, IPv6)

• Large TCP I/O is segmented into smaller packets to increase throughput and reduce CPU overhead

• Compatible with large-send offload

Interrupt throttling control

• Limits maximum interrupt rate and improves CPU usage

Legacy and Message Signal Interrupt (MSI) Modes

• Enables Interrupt mapping

Message Signal Interrupt Extension (MSI-X)

• Dynamic allocation of up to 64 vectors per port

Intelligent interrupt generation

• Enhanced software device driver performance

Receive Side Scaling (RSS) for Windows environment

Scalable I/O for Linux environments (IPv4, IPv6, TCP/UDP)

• Up to 32 flows per port

• Improves the system performance related to handling of network data on multiprocessor systems

Receive Side Coalescing (RSC)

• Merge multiple received frames from the same TCP/IP connection into a single structure

128 Tx and Rx Queues (per port)

• Queues provide QoS for virtualization, DCB, RSS, L2 Ethertype, FCoE Redirection, L3/4 5-tuple filters, Flow Director and TCp

SYN filters

Rate Control Traffic per Traffic Class/Transmit Queue

• In order to guarantee each pool with adequate bandwidth, a per-pool bandwidth control mechanism is used

FCoE Tx / Rx CRC Offload

• Offloads receive FC CRC integrity check while tracking the CRC bytes and FC padding bytes

Large FC Receive

• Large FC receive includes two types of offloads that can save a data copy by posting the received FC payload directly to the

kernel storage cache or the user application space