iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

sfc: default config to 1 channel/core in local NUMA node only

Browse Source 
Handling channels from CPUs in different NUMA node can penalize
performance, so better configure only one channel per core in the same
NUMA node than the NIC, and not per each core in the system.

Fallback to all other online cores if there are not online CPUs in local
NUMA node.

Signed-off-by: Íñigo Huguet <ihuguet@redhat.com>
Acked-by: Martin Habets <habetsm.xilinx@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This commit is contained in:
Íñigo Huguet 2022-02-28 14:22:53 +01:00 committed by Jakub Kicinski
parent ef739f1dd3
commit c265b569a4
1 changed files with 34 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

51
drivers/net/ethernet/sfc/efx_channels.c
View File

@ -78,31 +78,48 @@ static const struct efx_channel_type efx_default_channel_type = {
* INTERRUPTS
*************/
static unsigned int efx_wanted_parallelism(struct efx_nic *efx)
static unsigned int count_online_cores(struct efx_nic *efx, bool local_node)
{
cpumask_var_t thread_mask;
cpumask_var_t filter_mask;
unsigned int count;
int cpu;
if (unlikely(!zalloc_cpumask_var(&filter_mask, GFP_KERNEL))) {
netif_warn(efx, probe, efx->net_dev,
"RSS disabled due to allocation failure\n");
return 1;
}
cpumask_copy(filter_mask, cpu_online_mask);
if (local_node) {
int numa_node = pcibus_to_node(efx->pci_dev->bus);
cpumask_and(filter_mask, filter_mask, cpumask_of_node(numa_node));
}
count = 0;
for_each_cpu(cpu, filter_mask) {
++count;
cpumask_andnot(filter_mask, filter_mask, topology_sibling_cpumask(cpu));
}
free_cpumask_var(filter_mask);
return count;
}
static unsigned int efx_wanted_parallelism(struct efx_nic *efx)
{
unsigned int count;
if (rss_cpus) {
count = rss_cpus;
} else {
if (unlikely(!zalloc_cpumask_var(&thread_mask, GFP_KERNEL))) {
netif_warn(efx, probe, efx->net_dev,
"RSS disabled due to allocation failure\n");
return 1;
}
count = count_online_cores(efx, true);
count = 0;
for_each_online_cpu(cpu) {
if (!cpumask_test_cpu(cpu, thread_mask)) {
++count;
cpumask_or(thread_mask, thread_mask,
topology_sibling_cpumask(cpu));
}
}
free_cpumask_var(thread_mask);
/* If no online CPUs in local node, fallback to any online CPUs */
if (count == 0)
count = count_online_cores(efx, false);
}
if (count > EFX_MAX_RX_QUEUES) {