在RHEL的各个版本中对网卡特性的支持情况

https://access.redhat.com/articles/1390483

Network Adapter Feature Support in RHEL

Updated 2015年六月23日20:26 - 

English 

The following tables list network features that are supported in some of the most commonly used Red Hat Enterprise Linux network drivers. The cells display the version of Red Hat Enterprise Linux where a feature was enabled for a particular driver and the feature's full support or tech preview1 status, or they display an "x" if the feature is not supported by the listed driver. Fully supported items list only the update release of RHEL where the feature was enabled. Tech preview items include "(TP)" in the cell. When a feature transitions from tech preview to fully supported status, the "(TP)" will be removed and the fully supported update release will be listed instead.

Red Hat Enterprise Linux 7

VendorDriverDriver IntroducedSR-IOV2Time Stamping Capabilities3Hardware Offload for Network Overlays4Busy Poll Sockets5Byte Queue Limits6
Broadcomtg37.0x7.0 - HW/SWxx7.0
Chelsiocxgb37.0xxxxx
 cxgb4/cxgb4vf7.07.0 (TP)xxxx
Ciscoenic7.07.0 (TP)xx7.1x
 usnic7.1 (TP)xxxxx
Emulexbe2net7.07.0x7.17.0x
 ocrdma7.0xxxxx
Intele1000e7.0x7.0 - HW/SWxx7.0
 igb/igbvf7.07.07.0 - HW/SWxx7.0
 ixgbe/ixgbevf7.07.07.0 - HW/SWx7.07.0
 i40e/i40evf7.0 (TP)7.0 (TP)7.0 - HW/SWxx7.0
Mellanoxmlx4_en7.07.0 (TP)7.0 - HW7.07.07.0
 mlx4_ib7.07.0 (TP)xxxx
 mlx57.0xxxxx
Myricommyri10e7.0xxx7.0x
Qlogicbna7.0xxxxx
 bnx27.0xxxx7.0
 bnx2x7.07.07.0 - SW7.07.07.0
 qlge7.0xxxxx
 qlcnic7.07.0 (TP)xxxx
Solarflaresfc7.0x7.0 - HWxx7.0

Legend
7.x = The update release of RHEL 7 where the feature was introduced
TP = Feature is in tech preview (not for use in production environments)
x = feature not present

Red Hat Enterprise Linux 6

VendorDriverDriver IntroducedSR-IOV7Time Stamping Capabilities8Busy Poll Sockets5
Broadcomtg36.0x6.5 - HW/SWx
Chelsiocxgb36.0xxx
 cxgb4/cxgb4vf6.06.4 (TP)xx
Ciscoenic6.06.3 (TP)xx
 usnic6.6xxx
Emulexbe2net6.06.4x6.6
 ocrdma6.5xxx
Intele1000e6.0x6.5 - HW/SWx
 igb/igbvf6.06.06.5 - HW/SWx
 ixgbe/ixgbevf6.06.06.4 - HW/SW6.6
 i40e/i40evf6.6 (TP)6.6 (TP)6.6 - HW/SWx
Mellanoxmlx4_en6.06.5 (TP)6.5 - HW6.6
 mlx4_ib6.06.5 (TP)xx
 mlx56.6xxx
Myricommyri10e6.0xxx
Qlogicbna6.1xxx
 bnx26.0xxx
 bnx2x6.06.56.5 - SW6.6
 qlge6.0xxx
 qlcnic6.16.5 (TP)xx
Solarflaresfc6.0x6.5 - HWx

Legend
6.x = The update release of RHEL 6 where the feature was introduced
TP = Feature is in tech preview (not for use in production environments)
x = feature not present


  1. Tech preview items may not work entirely as expected and should not be used in production environments. For more information on Red Hat technology previews, see https://access.redhat.com/support/offerings/techpreview/

  2. See the SR-IOV section of the RHEL 7 Virtualization Deployment and Administration Guide for more information. 

  3. See the PTP section of the RHEL 7 System Administrators Guide for more information. 

  4. An overlay network is simply a computer network which is built on top of another network. Overlay networking technologies, such as virtual extensible LAN (VXLAN) and network virtualization using generic routing (NVGRE), allow dynamic provisioning of network segments for elastic computing environments. The added flexibility comes at a cost, due to the additional processing overhead for encapsulation and de-encapsulation of packets. This consumes both CPU resources and degrades network performance, especially for high speed connections. By introducing hardware offloading capabilities that can be found in some of today’s modern NICs, the added overhead for packet processing can be offloaded to the NIC hardware, resulting in improved CPU utilization and higher throughput. 

  5. Busy poll sockets (a.k.a. low-latency sockets) are a software implementation that reduces networking latency and jitter within the kernel. This implementation makes it easy for applications to poll for new packets directly in the network driver which speeds up packets moving into the network stack. Applications that are sensitive to unpredictable latency benefit from the top-down, busy-wait polling method that replaces interrupts for incoming packets. 

  6. Byte queue limits provide a configurable limit to how much packet data can accumulate in the transmission queue of a network device. The purpose of the limit is to reduce latency caused by excessive queuing in hardware (buffer bloat) without lowering overall throughput. 

  7. See the SR-IOV section of the RHEL 6 Virtualization Administration Guide for more information. 

  8. See the PTP section of the RHEL 6 Deployment Guide for more information. 

### 如何在Linux系统中添加网卡 #### 配置新网卡的方法 对于希望向Linux系统中添加新的网卡并完成其配置的情况,在RHEL 5/6/7环境中,可以通过编辑位于`/etc/sysconfig/network-scripts/`目录下的相应接口配置文件来实现永久性的网络设置更改[^1]。 当准备为新增加的物理或虚拟网卡创建配置时,通常会新建一个名为`ifcfg-<interface_name>`的文件,其中`<interface_name>`代表具体的网卡名(例如eth0, ens33)。下面是一个针对静态IP设定的例子: ```bash vi /etc/sysconfig/network-scripts/ifcfg-ens34 ``` 在此文件内应指定如下参数以定义该网卡的行为特性: - `TYPE=Ethernet`: 表明这是一个以太网类型的设备。 - `DEVICE=ens34`: 设定此配置对应于哪个实际存在的网卡设备名称。 - `ONBOOT=yes`: 确认开机自启状态下自动激活这张网卡。 - `BOOTPROTO=static`: 使用固定分配而非DHCP协议获取地址信息。 - `IPADDR=<your_ip_address>`: 输入期望赋予给这个网卡的具体IPv4地址。 - `NETMASK=<subnet_mask>`: 提供子网掩码用于计算所在局域网范围。 - `GATEWAY=<gateway_ip>`: 如果适用的话,则指派通往外部路由的第一跳地址。 - `DNS1=<dns_server_ip>`: 设置首选域名解析服务的位置以便能够访问互联网资源[^2]。 保存上述修改之后,为了使这些改动生效,可以执行以下命令重启整个网络服务从而加载最新的配置数据[^3]: ```bash service network restart ``` 或者更现代的方式是在较新版发行版里采用systemctl工具来进行相同的操作: ```bash systemctl restart NetworkManager.service ``` 这样就完成了对额外网卡的基础配置过程。需要注意的是不同版本之间可能存在细微差异,因此建议参照具体使用的Linux发行版官方文档获得最准确指导。
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值