Re: Error in rte_eal_init() when multiple PODs over single node of K8 cluster

[Bruce Richardson <bruce.richardson@intel.com>]

On Mon, Apr 01, 2024 at 07:38:10AM +0000, Avijit  Pandey wrote:
>    Hello Bruce,
> 
> 
>    Thank you for your mail!
> 
> 
>    I have attached the complete log that we observed.
> 
> 
>    Upon your suggestion, we experimented with the --in-memory option and
>    it worked!  Since this option enables both --no-shconf and
>    --huge-unlink. We also tried each option separately. The test ran fine
>    with the --no-shconf option, but it failed when only the --huge-unlink
>    option was added.
> 
>    Now when --no-shconf option also worked, we also need some
>    understanding whether it will impact multi-queue performance and if
>    there are any other costs associated with using this flag.
> 
The no-shconf should have no performance impacts, the flag only adjusts
whether the basic DPDK configuration information (generally only used at
init time), giving details of hugepage mappings etc, is stored in shared
memory or in memory local to the process. Using the former allows sharing
among multiple processes, but could lead to name conflicts between
processes unless --file-prefix EAL argument is also used. Using the latter,
local memory, disables multi-process support, but is probably safer and
easier if MP support is unnecessary.

/Bruce