计算优化虚拟机大小Compute optimized virtual machine sizes

计算优化 VM 大小具有较高的 CPU 与内存之比。Compute optimized VM sizes have a high CPU-to-memory ratio. 这些大小适用于中等流量的 Web 服务器、网络设备、批处理和应用程序服务器。These sizes are good for medium traffic web servers, network appliances, batch processes, and application servers. 本文提供了有关 vCPU、数据磁盘和 NIC 的数量的信息。This article provides information about the number of vCPUs, data disks, and NICs. 它还介绍了此分组中每个大小的存储吞吐量和网络带宽。It also includes information about storage throughput and network bandwidth for each size in this grouping.

Fsv2 系列基于 Intel® Xeon® Platinum 8168 处理器。The Fsv2-series is based on the Intel® Xeon® Platinum 8168 processor. 它具有稳定的 3.4 GHz 的全核 Turbo 时钟速度和最大为 3.7 GHz 的单核 Turbo 频率。It features a sustained all core Turbo clock speed of 3.4 GHz and a maximum single-core turbo frequency of 3.7 GHz. Intel 可扩展处理器上提供了全新的 Intel® AVX-512 指令。Intel® AVX-512 instructions are new on Intel Scalable Processors. 对于单精度和双精度浮点运算,这些指令可为向量处理工作负荷提供高达 2 倍的性能提升。These instructions provide up to a 2X performance boost to vector processing workloads on both single and double precision floating point operations. 换而言之,对于任何计算工作负荷,它们的处理速度相当快。In other words, they're really fast for any computational workload.

凭借较低的每小时定价,Fsv2 系列在基于每个 vCPU 的 Azure 计算单位 (ACU) 的 Azure 产品组合中具有最高性价比。At a lower per-hour list price, the Fsv2-series is the best value in price-performance in the Azure portfolio based on the Azure Compute Unit (ACU) per vCPU.

Fsv2 系列 1Fsv2-series 1

ACU:195 - 210ACU: 195 - 210

高级存储:支持Premium Storage: Supported

高级存储缓存:支持Premium Storage caching: Supported

大小Size vCPUvCPUs 内存:GiBMemory: GiB 临时存储 (SSD) GiBTemp storage (SSD) GiB 最大数据磁盘数Max data disks 最大缓存吞吐量和临时存储吞吐量:IOPS/Mbps(以 GiB 为单位的缓存大小)Max cached and temp storage throughput: IOPS / MBps (cache size in GiB) 最大非缓存磁盘吞吐量:IOPS/MbpsMax uncached disk throughput: IOPS / MBps 最大 NIC 数/预期网络带宽 (Mbps)Max NICs / Expected network bandwidth (Mbps)
Standard_F2s_v2Standard_F2s_v2 22 44 1616 44 4000 / 31 (32)4000 / 31 (32) 3200 / 473200 / 47 2 / 8752 / 875
Standard_F4s_v2Standard_F4s_v2 44 88 3232 88 8000 / 63 (64)8000 / 63 (64) 6400 / 956400 / 95 2 / 17502 / 1750
Standard_F8s_v2Standard_F8s_v2 88 1616 6464 1616 16000 / 127 (128)16000 / 127 (128) 12800 / 19012800 / 190 4 / 35004 / 3500
Standard_F16s_v2Standard_F16s_v2 1616 3232 128128 3232 32000 / 255 (256)32000 / 255 (256) 25600 / 38025600 / 380 4 / 70004 / 7000
Standard_F32s_v2Standard_F32s_v2 3232 6464 256256 3232 64000 / 512 (512)64000 / 512 (512) 51200 / 75051200 / 750 8 / 140008 / 14000
Standard_F48s_v2Standard_F48s_v2 4848 9696 384384 3232 96000/768 (768)96000 / 768 (768) 76800/110076800 / 1100 8/210008 / 21000
Standard_F64s_v2Standard_F64s_v2 6464 128128 512512 3232 128000 / 1024 (1024)128000 / 1024 (1024) 80000 / 110080000 / 1100 8 / 280008 / 28000
Standard_F72s_v22, 3Standard_F72s_v22, 3 7272 144144 576576 3232 144000 / 1152 (1520)144000 / 1152 (1520) 80000 / 110080000 / 1100 8 / 300008 / 30000

1 Fsv2 系列 VM 采用了 Intel® 超线程技术。1 Fsv2-series VMs feature Intel® Hyper-Threading Technology.

2 使用超过 64 个 vCPU 需要以下受支持的来宾操作系统之一:2 The use of more than 64 vCPU require one of these supported guest operating systems:

  • Windows Server 2016 或更高版本Windows Server 2016 or later

  • Ubuntu 16.04 LTS 或更高版本,带 Azure 优化内核(4.15 内核或更高版本)Ubuntu 16.04 LTS or later, with Azure tuned kernel (4.15 kernel or later)

  • SLES 12 SP2 或更高版本SLES 12 SP2 or later

  • CentOS 版本 6.7 到 6.10,安装了 Microsoft 提供的 LIS 程序包 4.3.1(或更高版本)CentOS version 6.7 through 6.10, with Microsoft-provided LIS package 4.3.1 (or later) installed

  • CentOS 版本 7.3,安装了 Microsoft 提供的 LIS 程序包 4.2.1(或更高版本)CentOS version 7.3, with Microsoft-provided LIS package 4.2.1 (or later) installed

  • CentOS 版本 7.6 或更高版本CentOS version 7.6 or later

  • Debian 9,带有向后移植内核 Debian 10 或更高版本Debian 9 with the backports kernel, Debian 10 or later

  • 带有 4.14 内核或更高版本的 CoreOSCoreOS with a 4.14 kernel or later

3 实例与专用于单个客户的硬件隔离。3 Instance is isolated to hardware dedicated to a single customer.

大小表定义Size table definitions

  • 存储容量的单位为 GiB 或 1024^3 字节。Storage capacity is shown in units of GiB or 1024^3 bytes. 比较以 GB(1000^3 字节)为单位的磁盘与以 GiB(1024^3 字节)为单位的磁盘时,请记住以 GiB 为单位的容量数显得更小。When you compare disks measured in GB (1000^3 bytes) to disks measured in GiB (1024^3) remember that capacity numbers given in GiB may appear smaller. 例如,1023 GiB = 1098.4 GB。For example, 1023 GiB = 1098.4 GB.

  • 磁盘吞吐量的单位为每秒输入/输出操作数 (IOPS) 和 Mbps,其中 Mbps = 10^6 字节/秒。Disk throughput is measured in input/output operations per second (IOPS) and MBps where MBps = 10^6 bytes/sec.

  • 数据磁盘可以在缓存或非缓存模式下运行。Data disks can operate in cached or uncached modes. 对于缓存数据磁盘操作,主机缓存模式设置为 ReadOnlyReadWriteFor cached data disk operation, the host cache mode is set to ReadOnly or ReadWrite. 对于非缓存数据磁盘操作,主机缓存模式设置为 NoneFor uncached data disk operation, the host cache mode is set to None.

  • 若要获得 VM 的最佳性能,应将数据磁盘数限制为每 vCPU 2 个磁盘。If you want to get the best performance for your VMs, you should limit the number of data disks to two disks per vCPU.

  • 预期的网络带宽是指跨所有 NIC 为每个 VM 类型分配的最大聚合带宽,适用于所有目标。Expected network bandwidth is the maximum aggregated bandwidth allocated per VM type across all NICs, for all destinations. 有关详细信息,请参阅虚拟机网络带宽For more information, see Virtual machine network bandwidth.

    无法保证上限。Upper limits aren't guaranteed. 限值用于在为目标应用程序选择适当的 VM 类型时提供指导。Limits offer guidance for selecting the right VM type for the intended application. 实际的网络性能将取决于多种因素,包括网络拥塞、应用程序负载和网络设置。Actual network performance will depend on several factors including network congestion, application loads, and network settings. 有关如何优化网络吞吐量的信息,请参阅为 Azure 虚拟机优化网络吞吐量For information on optimizing network throughput, see Optimize network throughput for Azure virtual machines. 若要在 Linux 或 Windows 中达到预期的网络性能,可能需要选择特定版本,或者需要优化 VM。To achieve the expected network performance on Linux or Windows, you may need to select a specific version or optimize your VM. 有关详细信息,请参阅带宽/吞吐量测试 (NTTTCP)For more information, see Bandwidth/Throughput testing (NTTTCP).

其他大小Other sizes

后续步骤Next steps

了解有关 Azure 计算单元 (ACU) 如何帮助跨 Azure SKU 比较计算性能的详细信息。Learn more about how Azure compute units (ACU) can help you compare compute performance across Azure SKUs.