Hello Min, On Wed, Dec 21, 2022 at 11:49 AM David Marchand <david.march...@redhat.com> wrote: > > Trying to allocate memory on the first detected numa node has less > chance to find some memory actually available rather than on the main > lcore numa node (especially when the DPDK application is started only > on one numa node). > > Signed-off-by: David Marchand <david.march...@redhat.com>
I see a failure in the loongarch CI. Running binary with argv[]:'/home/zhoumin/dpdk/build/app/test/dpdk-test' '--file-prefix=eal_flags_c_opt_autotest' '--proc-type=secondary' '--lcores' '0-1,2@(5-7),(3-5)@(0,2),(0,6),7' Error - process did not run ok with valid corelist value Test Failed The logs don't give the full picture (though it is not LoongArch CI fault). I tried to read back on past mail exchanges about the loongarch server, but I did not find the info. I suspect cores 5 to 7 belong to different numa nodes, can you confirm? I'll post a new revision to account for this case. -- David Marchand
