Re: [PATCH] ethdev: fix device init without socket-local memory

2024-07-22 Thread Bruce Richardson
On Sun, Jul 21, 2024 at 11:56:08PM +0100, Ferruh Yigit wrote: > On 7/19/2024 5:10 PM, Bruce Richardson wrote: > > On Fri, Jul 19, 2024 at 04:31:11PM +0100, Ferruh Yigit wrote: > >> On 7/19/2024 2:22 PM, Bruce Richardson wrote: > >>> On Fri, Jul 19, 2024 at 12:10:24PM +0100, Ferruh Yigit wrote: > >>

Re: [PATCH] ethdev: fix device init without socket-local memory

2024-07-21 Thread Ferruh Yigit
On 7/19/2024 5:10 PM, Bruce Richardson wrote: > On Fri, Jul 19, 2024 at 04:31:11PM +0100, Ferruh Yigit wrote: >> On 7/19/2024 2:22 PM, Bruce Richardson wrote: >>> On Fri, Jul 19, 2024 at 12:10:24PM +0100, Ferruh Yigit wrote: One option can be adding a warning log to the fallback case, saying t

Re: [PATCH] ethdev: fix device init without socket-local memory

2024-07-19 Thread Bruce Richardson
On Fri, Jul 19, 2024 at 04:31:11PM +0100, Ferruh Yigit wrote: > On 7/19/2024 2:22 PM, Bruce Richardson wrote: > > On Fri, Jul 19, 2024 at 12:10:24PM +0100, Ferruh Yigit wrote: > >> One option can be adding a warning log to the fallback case, saying that > >> memory allocated from non-local socket a

Re: [PATCH] ethdev: fix device init without socket-local memory

2024-07-19 Thread Ferruh Yigit
On 7/19/2024 2:22 PM, Bruce Richardson wrote: > On Fri, Jul 19, 2024 at 12:10:24PM +0100, Ferruh Yigit wrote: >> On 7/19/2024 10:57 AM, Bruce Richardson wrote: >>> On Fri, Jul 19, 2024 at 09:59:50AM +0100, Ferruh Yigit wrote: On 7/11/2024 1:35 PM, Bruce Richardson wrote: > When allocating

Re: [PATCH] ethdev: fix device init without socket-local memory

2024-07-19 Thread Bruce Richardson
On Fri, Jul 19, 2024 at 12:10:24PM +0100, Ferruh Yigit wrote: > On 7/19/2024 10:57 AM, Bruce Richardson wrote: > > On Fri, Jul 19, 2024 at 09:59:50AM +0100, Ferruh Yigit wrote: > >> On 7/11/2024 1:35 PM, Bruce Richardson wrote: > >>> When allocating memory for an ethdev, the rte_malloc_socket call

Re: [PATCH] ethdev: fix device init without socket-local memory

2024-07-19 Thread Ferruh Yigit
On 7/19/2024 10:57 AM, Bruce Richardson wrote: > On Fri, Jul 19, 2024 at 09:59:50AM +0100, Ferruh Yigit wrote: >> On 7/11/2024 1:35 PM, Bruce Richardson wrote: >>> When allocating memory for an ethdev, the rte_malloc_socket call used >>> only allocates memory on the NUMA node/socket local to the de

Re: [PATCH] ethdev: fix device init without socket-local memory

2024-07-19 Thread Bruce Richardson
On Fri, Jul 19, 2024 at 09:59:50AM +0100, Ferruh Yigit wrote: > On 7/11/2024 1:35 PM, Bruce Richardson wrote: > > When allocating memory for an ethdev, the rte_malloc_socket call used > > only allocates memory on the NUMA node/socket local to the device. This > > means that even if the user wanted

Re: [PATCH] ethdev: fix device init without socket-local memory

2024-07-19 Thread Bruce Richardson
On Fri, Jul 19, 2024 at 09:59:50AM +0100, Ferruh Yigit wrote: > On 7/11/2024 1:35 PM, Bruce Richardson wrote: > > When allocating memory for an ethdev, the rte_malloc_socket call used > > only allocates memory on the NUMA node/socket local to the device. This > > means that even if the user wanted

Re: [PATCH] ethdev: fix device init without socket-local memory

2024-07-19 Thread Ferruh Yigit
On 7/11/2024 1:35 PM, Bruce Richardson wrote: > When allocating memory for an ethdev, the rte_malloc_socket call used > only allocates memory on the NUMA node/socket local to the device. This > means that even if the user wanted to, they could never use a remote NIC > without also having memory on

[PATCH] ethdev: fix device init without socket-local memory

2024-07-11 Thread Bruce Richardson
When allocating memory for an ethdev, the rte_malloc_socket call used only allocates memory on the NUMA node/socket local to the device. This means that even if the user wanted to, they could never use a remote NIC without also having memory on that NIC's socket. For example, if we change examples