克隆dpdk git 存储库并构建helloworld应用程序后，出现以下错误：
$ ./examples/helloworld/build/helloworld
EAL: Detected 4 lcore(s)
EAL: Detected 1 NUMA nodes
EAL: Multi-process socket /run/user/1000/dpdk/rte/mp_socket
EAL: Selected IOVA mode 'VA'
EAL: No available hugepages reported in hugepages-1048576kB
EAL: Probing VFIO support...
EAL: VFIO support initialized
EAL: Couldn't get fd on hugepage file
EAL: error allocating rte services array
EAL: FATAL: rte_service_init() failed
EAL: rte_service_init() failed
PANIC in main():
Cannot init EAL
5: [./examples/helloworld/build/helloworld(+0x11de) [0x56175faac1de]]
4: [/lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf3) [0x7f31f60fe0b3]]
3: [./examples/helloworld/build/helloworld(+0x111c) [0x56175faac11c]]
2: [/lib/x86_64-linux-gnu/librte_eal.so.20.0(__rte_panic+0xc5) [0x7f31f62d537e]]
1: [/lib/x86_64-linux-gnu/librte_eal.so.20.0(rte_dump_stack+0x32) [0x7f31f62ecc52]]
Aborted (core dumped)
检查了大页支持，看起来不错：
$ cat /proc/meminfo | grep -i huge
AnonHugePages: 0 kB
ShmemHugePages: 0 kB
FileHugePages: 0 kB
HugePages_Total: 256
HugePages_Free: 255
HugePages_Rsvd: 0
HugePages_Surp: 0
Hugepagesize: 2048 kB
Hugetlb: 524288 kB
$ mount | grep huge
cgroup on /sys/fs/cgroup/hugetlb type cgroup (rw,nosuid,nodev,noexec,relatime,hugetlb)
hugetlbfs on /dev/hugepages type hugetlbfs (rw,relatime,pagesize=2M)
$ cat /proc/filesystems | grep huge
nodev hugetlbfs
$ cat /proc/sys/vm/nr_hugepages
256
我在相关问题中看到了解决方法；使用以下选项运行它--no-huge，该选项有效：
$ ./examples/helloworld/build/helloworld --no-huge
EAL: Detected 4 lcore(s)
EAL: Detected 1 NUMA nodes
EAL: Static memory layout is selected, amount of reserved memory can be adjusted with -m or --socket-mem
EAL: Multi-process socket /run/user/1000/dpdk/rte/mp_socket
EAL: Selected IOVA mode 'VA'
EAL: Probing VFIO support...
EAL: VFIO support initialized
EAL: PCI device 0000:02:01.0 on NUMA socket -1
EAL: Invalid NUMA socket, default to 0
EAL: probe driver: 8086:100f net_e1000_em
EAL: PCI device 0000:03:00.0 on NUMA socket -1
EAL: Invalid NUMA socket, default to 0
EAL: probe driver: 15ad:7b0 net_vmxnet3
hello from core 1
hello from core 2
hello from core 3
hello from core 0
但这是一个有限的解决方案。
TL;DR 使用sudo
按照 @VipinVarghese 的建议运行--log-level=eal,8显示这是一个权限问题：
$ ./examples/helloworld/build/helloworld --log-level=eal,8\nEAL: Detected lcore 0 as core 0 on socket 0\nEAL: Detected lcore 1 as core 0 on socket 0\nEAL: Detected lcore 2 as core 0 on socket 0\nEAL: Detected lcore 3 as core 0 on socket 0\nEAL: Support maximum 128 logical core(s) by configuration.\nEAL: Detected 4 lcore(s)\nEAL: Detected 1 NUMA nodes\nEAL: open shared lib /usr/lib/x86_64-linux-gnu/dpdk/pmds-20.0/librte_pmd_qede.so\nEAL: Registered [vdev] bus.\nEAL: Registered [pci] bus.\nEAL: Registered [eth] device class.\nEAL: open shared lib /usr/lib/x86_64-linux-gnu/dpdk/pmds-20.0/librte_pmd_aesni_mb.so\n...\nEAL: Ask a virtual area of 0x61000 bytes\nEAL: Virtual area found at 0xd00600000 (size = 0x61000)\nEAL: Memseg list allocated: 0x800kB at socket 0\nEAL: Ask a virtual area of 0x400000000 bytes\nEAL: Virtual area found at 0xd00800000 (size = 0x400000000)\nEAL: TSC frequency is ~2590000 KHz\nEAL: Master lcore 0 is ready (tid=7fc11ed01d00;cpuset=[0])\nEAL: lcore 2 is ready (tid=7fc116ffd700;cpuset=[2])\nEAL: lcore 3 is ready (tid=7fc1167fc700;cpuset=[3])\nEAL: lcore 1 is ready (tid=7fc1177fe700;cpuset=[1])\nEAL: Trying to obtain current memory policy.\nEAL: Setting policy MPOL_PREFERRED for socket 0\nEAL: get_seg_fd(): open failed: Permission denied\nEAL: Couldn\'t get fd on hugepage file\nEAL: attempted to allocate 1 segments, but only 0 were allocated\nEAL: Restoring previous memory policy: 0\nEAL: error allocating rte services array\nEAL: FATAL: rte_service_init() failed\nEAL: rte_service_init() failed\nPANIC in main():\nCannot init EAL\n5: [./examples/helloworld/build/helloworld(+0x11de) [0x56459e5391de]]\n4: [/lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf3) [0x7fc11eed00b3]]\n3: [./examples/helloworld/build/helloworld(+0x111c) [0x56459e53911c]]\n2: [/lib/x86_64-linux-gnu/librte_eal.so.20.0(__rte_panic+0xc5) [0x7fc11f0a737e]]\n1: [/lib/x86_64-linux-gnu/librte_eal.so.20.0(rte_dump_stack+0x32) [0x7fc11f0bec52]]\nAborted (core dumped)\n尝试解决权限问题（EAL：get_seg_fd（）：打开失败：权限被拒绝），但只有当我以root身份运行它时才有效：
\n$ sudo ./examples/helloworld/build/helloworld\nEAL: Detected 4 lcore(s)\nEAL: Detected 1 NUMA nodes\nEAL: Multi-process socket /var/run/dpdk/rte/mp_socket\nEAL: Selected IOVA mode \'PA\'\nEAL: No available hugepages reported in hugepages-1048576kB\nEAL: Probing VFIO support...\nEAL: VFIO support initialized\nEAL: PCI device 0000:02:01.0 on NUMA socket -1\nEAL: Invalid NUMA socket, default to 0\nEAL: probe driver: 8086:100f net_e1000_em\nEAL: PCI device 0000:03:00.0 on NUMA socket -1\nEAL: Invalid NUMA socket, default to 0\nEAL: probe driver: 15ad:7b0 net_vmxnet3\nhello from core 1\nhello from core 2\nhello from core 3\nhello from core 0\n事实证明，这是正确的方法，尽管文档似乎认为这是显而易见的。“6.2. 运行示例应用程序”部分没有提及所需的 root 权限，摘录如下：
\n\n\n将 DPDK 应用程序二进制文件复制到您的目标，然后按如下方式运行应用程序（假设平台每个处理器插槽有四个内存通道，并且核心 0-3 存在并用于运行应用程序）：
\n./dpdk-helloworld -l 0-3 -n 4
\n
不过，这一点在文档后面提到，请参阅“ 8.2. 在没有 Root 权限的情况下运行 DPDK 应用程序”，其中有明确的说明：
\n\n\n以下说明将允许使用较旧的\nLinux 内核版本以非 root 身份运行 DPDK。但是，从版本 4.0 开始，内核不允许非特权进程从页面映射文件读取物理地址信息，从而使这些进程无法使用需要物理地址的硬件设备
\n
常见问题解答中也有提示：
\n\n\n\n
\n- \xe2\x80\x9cEAL: map_all_hugepages(): open failed: Permission returned 无法初始化内存\xe2\x80\x9d 是什么意思？这很可能是由于测试应用程序未使用 sudo 运行来将用户提升为超级用户。或者，应用程序也可以以常规用户身份运行。\n 有关详细信息，请参阅 DPDK 入门\n指南。
\n
还有一封涉及该主题的电子邮件：
\n2016-07-07 16:47, Jez Higgins:\n> Is it possible to get DPDK up and running as non-root - if so, can\n> anyone guide me to what I\'m missing? Or should I be giving this up as a\n> bad job?\n\nYou can try the --no-huge option.\nBut most of drivers won\'t work without hugepage currently.\nA rework of the memory allocation is needed to make it work better.\n那是四年前的事了。也许已经有一个不需要sudoor的解决方案--no-huge？如果是这样，欢迎其他答案。现在，我就这么做。