RE: [EXT] Re: [PATCH net] octeontx2-pf: Set maximum queue size to 16K
From: Ratheesh Kannoth <rkannoth@marvell.com>
Date: 2023-08-07 02:51:50
Also in:
lkml
From: Ratheesh Kannoth <rkannoth@marvell.com>
Date: 2023-08-07 02:51:50
Also in:
lkml
From: Jakub Kicinski <kuba@kernel.org> Sent: Saturday, August 5, 2023 2:05 AM To: Alexander Lobakin <aleksander.lobakin@intel.com> Subject: Re: [EXT] Re: [PATCH net] octeontx2-pf: Set maximum queue size to 16K IDK if I agree with you here :S Tuning this in the driver relies on the assumption that the HW / driver is the thing that matters. I'd think that the workload, platform (CPU) and config (e.g. is IOMMU enabled?) will matter at least as much. While driver developers will end up tuning to whatever servers they have, random single config and most likely.. iperf. IMO it's much better to re-purpose "pool_size" and treat it as the ring size, because that's what most drivers end up putting there. Defer tuning of the effective ring size to the core and user input (via the "it will be added any minute now" netlink API for configuring page pools)... So capping the recycle ring to 32k instead of returning the error seems like an okay solution for now.
Either of the solutions looks Okay to me. Let me push a patch with Jacub's proposal for now. -Ratheesh.