On Tue, 2 Jul 2024 18:17:08 +0800 (GMT+08:00) 洪全 <hongq...@iie.ac.cn> wrote:
> Dear DPDK community, > > > I am encountering an issue when attempting to run a 32-bit DPDK application > on Linux. Specifically, I am facing a "Cannot allocate memory" error during > initialization. While I can mitigate this issue by using the `--no-huge` > option, it adversely affects the performance of my application. > > > Here is the error output I receive: > > > ``` > sudo ./app -l 0-1 --proc-type=primary --file-prefix=pmd1 > --vdev=net_tap001,iface=tap001 --no-pci > EAL: Detected CPU lcores: 2 > EAL: Detected NUMA nodes: 1 > EAL: Detected shared linkage of DPDK > EAL: Multi-process socket /var/run/dpdk/pmd1/mp_socket > EAL: Selected IOVA mode 'PA' > EAL: Cannot get a virtual area: Cannot allocate memory > EAL: Cannot allocate VA space for memseg list, retrying with different page > size > EAL: Cannot allocate VA space on socket 0 > EAL: FATAL: Cannot init memory > EAL: Cannot init memory > app: main.c:284: main: Assertion `(ret = rte_eal_init(argc, (char **) argv)) > >= 0' failed. > Aborted > ``` > > > When debugging with `--log-level=eal,8`, the relevant portion of the output > indicates attempts to allocate memory: > > > ``` > EAL: Attempting to preallocate 2048M on socket 0 > EAL: Ask a virtual area of 0xc000 bytes > EAL: Virtual area found at 0xeb077000 (size = 0xc000) > EAL: Memseg list allocated at socket 0, page size 0x800kB > EAL: Ask a virtual area of 0x80000000 bytes > EAL: Cannot mmap((nil), 0x80200000, 0x0, 0x22, -1, 0x0): Cannot allocate > memory > EAL: Cannot get a virtual area: Cannot allocate memory > EAL: Cannot allocate VA space for memseg list, retrying with different page > size > EAL: Cannot allocate VA space on socket 0 > EAL: FATAL: Cannot init memory > EAL: Cannot init memory > app: main.c:284: main: Assertion `(ret = rte_eal_init(argc, (char **) argv)) > >= 0' failed. > Aborted > ``` > > > System information: > - Hugepages configured: `echo 1024 > > /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages` > - Hugepages mounted: `mount -t hugetlbfs hugetlbfs /dev/hugepages` > - NUMA node information: `numactl --hardware` > - available: 1 nodes (0) > - node 0 cpus: 0 1 > - node 0 size: 7896 MB > - node 0 free: 3915 MB > - node distances: > - node 0: 10 > > > DPDK version: 22.03 > Distribution: Ubuntu 22.04 > Kernel information: Linux hq-virtual-machine 6.5.0-35-generic > #35~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue May 7 09:00:52 UTC 2 x86_64 x86_64 > x86_64 GNU/Linux > > > I believe the issue stems from the attempt to preallocate 2048M on socket 0, > but using `-m` or `--socket-mem` options did not resolve the problem. > > > Could you please provide guidance on how to properly configure DPDK to avoid > this memory allocation issue while maximizing performance? What CPU architecture? Traditionally on 32 bit x86 has 3GB for userspace and 1GB is the shadow kernel. Some other architecture may do the same thing. In userspace, you then have some memory for programs code, data and stack. The DPDK EAL init then tries to map all of available huge pages (2G) and fails to find enough contiguous virtual address space to fit. Try smaller amount of huge pages.
