On Fri, 8 Sep 2023 14:31:22 +0000 (UTC) Don Trotter <[email protected]> wrote:
> On Thursday, September 7, 2023 at 09:26:34 PM CDT, jiangheng (G) > <[email protected]> wrote: > > > > Hi > > I've had the same error. It may be caused by this parameter: > > https://github.com/DPDK/dpdk/blob/v22.11/config/rte_config.h#L33C9-L33C33 > > If you use 2MB hugepages, the max memory size is 2MB * 8192 = 16GB. This > error will occur when you allocate more than 16GB of memory per numa. > > > > But should not have this error if you use 512 MB of memory, can you show > RTE_MAX_MEMSEG_PER_LIST in your dpdk? > > Check whether the other sizes hugepage is used, Theoretically, this error > indicates that the rte_eal_init init fails and the program should exit. > My initial statement was that the log was seen "from EAL during EAL > init", but that is not right. The call to rte_eal_init() is successful. Later > I allocate the memory, using rte_mempool_create("node_pool", (128 * 1024 * > 1024 - 1), 256, 256, 0, NULL, NULL, NULL, NULL, rte_socket_id(), 0). That is > when I see the message. And the call to allocate the memory is successful, > and I am processing packets and allocating nodes just fine. Here is the > information from rte_config.h. > $ grep RTE_MAX_MEM > ./cn98xx-release-output/build/dpdk/config/rte_config.h#define > RTE_MAX_MEMSEG_LISTS 128#define RTE_MAX_MEMSEG_PER_LIST 8192#define > RTE_MAX_MEM_MB_PER_LIST 32768#define RTE_MAX_MEMSEG_PER_TYPE 32768#define > RTE_MAX_MEM_MB_PER_TYPE 65536#define RTE_MAX_MEMZONE 2560 > > > > 发件人: Don Trotter <[email protected]> > 发送时间: 2023年9月8日 5:33 > 收件人: Stephen Hemminger <[email protected]> > 抄送: [email protected] > 主题: Re: EAL: eal_memalloc_alloc_seg_bulk(): couldn't find suitable memseg_list > > > > On Thursday, September 7, 2023 at 03:21:12 PM CDT, Stephen Hemminger > <[email protected]> wrote: > > > > > > On Thu, 7 Sep 2023 19:58:35 +0000 (UTC) > > > Don Trotter <[email protected]> wrote: > > > To clarify, the log message when my application called > >rte_mempool_create() to create the "node_pool", and the call succeeded. > > Thanks,Don Trotter > > On Thursday, September 7, 2023 at 01:54:08 PM CDT, Don Trotter > ><[email protected]> wrote: > > > > Hi, > > I have recently started using DPDK. I am working on a project on OcteonTX2 > > with DPDK 11.23.01. I am seeing this message from EAL during EAL init, but > > everything is working. > > EAL: eal_memalloc_alloc_seg_bulk(): couldn't find suitable memseg_list > > The system has 96GB of memory. These 2 pools get created and everything > > works fine. > > mempool <mbuf_pool>@0x13fed3e00 flags=10 socket_id=0 pool=0x1140300000 > > iova=0x13fed3e00 nb_mem_chunks=1 size=65535 populated_size=65535 > > header_size=128 elt_size=10200 trailer_size=40 total_obj_size=10368 > > private_data_size=128 ops_index=0 ops_name: <cn9k_mempool_ops> avg > > bytes/object=10368.558602 > > mempool <node_pool>@0x1575d8180 flags=10 socket_id=-1 pool=0x19ffffd00 > > iova=0x1575d8180 nb_mem_chunks=2 size=134217727 populated_size=134217727 > > header_size=128 elt_size=256 trailer_size=0 total_obj_size=384 > > private_data_size=0 ops_index=3 ops_name: <ring_mp_mc> avg > > bytes/object=384.000094 > > You read that right. I’ve got 128*1024*1024 256 byte buffers created for > > data. > > I also see there is still heap left, although pretty low after. > > Heap id:0 Heap name:socket_0 Heap_size:55834574848, > > Free_size:2403644544, Alloc_size:53430930304, > > Greatest_free_size:536870016, Alloc_count:293, Free_count:5, > > Linux free stats. > > tmp# free -h -w total used free shared > > buffers cache availableMem: 95Gi 88Gi 6.5Gi > > 444Mi 0B 470Mi 599MiSwap: 0B > > 0B 0B > > Is there anything wrong with that EAL log? Is there a lurking problem? > > Thanks,Don Trotter > > > > > > > > Did you setup hugepages? > How many and what size? > Is this a NUMA system? > > Also 11.23.01 seems like a weird release number. > The DPDK release numbering scheme is year followed by month. I.e. 22.11 was > released in November of 2022 > > > > > > # cat /sys/kernel/mm/hugepages/hugepages-524288kB/nr_hugepages > > 176 > > > > Yes it is a NUMA system. > > > > You are correct sir. The SDK is SDK11.23.01 (2023-01) and DPDK is 22.11. > > > > Thanks, Don Trotter > > > > You may need to add hugepages on each NUMA node.
