Hi Konstantin,

> I think we introduce a race window here.
> If secondary process would do first mmap() before rte_config.mem_config-
> >mem_cfg_addr was properly set by primary process, then it will try to do
> second mmap() with wrong address.
> I think we need to do second mmap() straight after
> rte_eal_mcfg_wait_complete(), or even just inside it.

Acknowledged, will respin.

Best regards,
Anatoly Burakov
DPDK SW Engineer



Reply via email to