netserver on SUT in out-of-the-box configuration
采用开箱即用配置的 SUT上的netserver
For the netserver scalability tests, those values range from 2.770 to 1.623.
对于netserver可伸缩性测试，这些值的范围从2.770到1.623。
Figure 6. netperf and netserver (bidirectional), out of the box with numactl.
图6. netperf和netserver(双向)，开箱即用配置加上numactl。
Table 1. Scaling computations for netserver, netperf, and bidirectional tests
表1.netserver、netperf和双向测试的变化计算值
Table 2. netserver, netperf, and bidirectional scaling computations, out of the box with numactl.
表2. netserver、netperf和双向测试(开箱即用配置加上numactl)的变化计算值。
Table 1 shows the scaling computations averaged for the netserver, netperf, and bidirectional tests.
表1给出netserver、netperf和双向测试的平均变化计算值。
The number of SUT netserver instances and remote netperf instances were increased accordingly for each test.
对于每个测试，相应地增加SUTnetserver实例和远程netperf实例的数量。
It's a basic client-server model benchmark and contains two corresponding executables, netperf and netserver.
它是一个基本的客户机-服务器模型基准，包含两个对应的可执行文件netperf和netserver。
For the netserver scalability tests, those values range from 1.647 for smaller message sizes to 1.944 for larger message sizes.
对于netserver可伸缩性测试，这些值的范围从 1.647（比较小的消息大小）到 1.944（比较大的消息大小）。
Restated, there were two benchmark instances, one netperf and one netserver, per Ethernet adapter, and only one Ethernet adapter per node was used.
再次重申，每个以太网适配器有两个基准实例(一个netserver和一个netperf)，每个节点只使用一个以太网适配器。
The netserver, netperf, and bidirectional scalability tests were run and data were collected in the same way as in the out-of-the-box configuration.
按照与开箱即用配置相同的方式，执行netserver、netperf和双向可伸缩性测试并收集数据。
Each corresponding remote instance of netperf or netserver ran on its own Ethernet adapter to ensure the fullest possible traffic to and from the SUT.
对应的netperf或netserver远程实例在它自己的以太网适配器上运行，以确保尽可能完整地测试与SUT之间的通信流。
In this case though, only the first system board Ethernet adapter of any node was utilized and by one instance of netperf along with one instance of netserver.
但是，在这种测试中，只使用任何节点的第一个系统板载以太网适配器，而且只使用一个netserver实例和一个netperf实例。
Each instance of netserver listened on a dedicated port and IP address; each Ethernet adapter's IP address was on a separate subnet to ensure dedicated traffic.
每个netserver实例监听一个专用端口和IP地址；每个以太网适配器的IP地址属于单独的子网以确保专用的通信流。
The remote drivers ran corresponding instances of netperf to provide stream traffic in a one-to-one mapping of remote netperf instances to SUT netserver instances.
远程驱动程序运行对应的netperf实例，从而按照远程 netperf 实例到SUTnetserver 实例的一对一映射提供流通信。
The first of the netserver scalability tests utilized a single instance of netserver on each of the two system board Ethernet adapters on the first node of the SUT.
第一个netserver可伸缩性测试在SUT的第一个节点的两个系统板载以太网适配器上各使用一个netserver实例。
Next, netperf scalability tests were run just like the netserver scalability tests, except that netperf was run on the SUT while netserver was run on the remote systems.
接下来，按照与netserver可伸缩性测试相同的方式执行netperf可伸缩性测试，惟一的差异是netperf在SUT上运行，netserver在远程系统上运行。
The netserver scalability tests were run and data were collected in the same way as in the out-of-the-box configuration except that only one Ethernet adapter per node was used.
按照与开箱即用配置相同的方式，执行netserver可伸缩性测试并收集数据，但是每个节点上只使用一个以太网适配器。
Figure 14 shows a comparison of the netserver scalability tests when using 2 adapters (1 on each of the first 2 nodes) and 4 adapters (1 on each of all 4 nodes) with and without bonding.
图14对比了在启用和禁用绑定的情况下netserver可伸缩性测试的结果，测试使用2个适配器(前2个节点上各使用一个适配器)和4个适配器(所有4个节点上各使用一个适配器)。
Figure 1 shows the network stream throughput and CPU utilization for the netserver scalability test runs while using the system board Ethernet adapters on 1, 2, and 4 nodes of the SUT.
图1显示netserver可伸缩性测试的网络流吞吐量和系统cpu利用率，分别使用SUT中1、2和4个节点上的系统板载以太网适配器。
Figure 7 shows the network stream throughput and CPU utilization for the netserver scalability test runs while using the system board Ethernet adapters on 1, 2, and 4 nodes of the SUT.
图7显示netserver可伸缩性测试的网络流吞吐量和系统cpu利用率，分别使用SUT中1、2和4个节点上的系统板载以太网适配器。
The simple TCP_STREAM test times the transfer of data from the netperf system to the netserver system to measure how fast one system can send data and how fast the other can receive it.
简单的TCP_STREAM测试从netperf系统到netserver系统的数据传输时间，以此度量一个系统发送数据和另一个系统接收数据的速度。
Similar to the out-of-the-box tests, the scaling computations were made and averaged for the netserver, netperf, and bidirectional tests from 1 to 2 nodes, 2 to 4 nodes, and 1 to 8 nodes.
与开箱即用测试一样，在从1个节点扩展到2个节点、2个节点到4个节点和1个节点到4个节点的情况下，分别计算netserver、netperf和双向测试的平均变化值。
Figure 4 shows the network stream throughput and CPU utilization for the netserver scalability test runs while utilizing the system board Ethernet adapters on 1, 2, and 4 nodes of the SUT.
图4显示netserver可伸缩性测试的网络流吞吐量和系统cpu利用率，分别使用SUT中1、2和4个节点上的系统板载以太网适配器。
Figure 10 shows the network stream throughput and CPU utilization for the netserver scalability test runs while utilizing the system board Ethernet adapters on 1, 2, and 4 nodes of the SUT.
图10显示netserver可伸缩性测试的网络流吞吐量和系统cpu利用率，分别使用SUT中1、2和4个节点上的系统板载以太网适配器。
The second netserver scalability test used all four system board Ethernet adapters on the first two nodes and the third test used all eight system board Ethernet adapters on all four nodes.
第二个netserver可伸缩性测试使用前2个节点上的所有4个系统板载以太网适配器，第三个测试使用所有4个节点上的所有8个系统板载以太网适配器。
The second netserver scalability test used all four system board Ethernet adapters on the first two nodes and the third test used all eight system board Ethernet adapters on all four nodes.
第二个netserver可伸缩性测试使用前2个节点上的所有4个系统板载以太网适配器，第三个测试使用所有4个节点上的所有8个系统板载以太网适配器。
应用推荐