mirror of https://gitee.com/openkylin/linux.git
ixgbe: Make use of cpumask_local_spread to improve RSS locality
This patch is meant to address locality issues present in the ixgbe driver when it is loaded on a system supporting multiple NUMA nodes and more CPUs then the device can map in a 1:1 fashion. Instead of just arbitrarily mapping itself to CPUs 0-62 it would make much more sense to map itself to the local CPUs first, and then map itself to any remaining CPUs that might be used. The first effect of this is that queue 0 should always be allocated on the local CPU/NUMA node. This is important as it is the default destination if a packet doesn't match any existing flow director filter or RSS rule and as such having it local should help to reduce QPI cross-talk in the event of an unrecognized traffic type. In addition this should increase the likelihood of the RSS queues being allocated and used on CPUs local to the device while the ATR/Flow Director queues would be able to route traffic directly to the CPU that is likely to be processing it. Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This commit is contained in:
parent
0e100440e2
commit
780e354dcd
|
@ -832,9 +832,9 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
|
|||
int xdp_count, int xdp_idx,
|
||||
int rxr_count, int rxr_idx)
|
||||
{
|
||||
int node = dev_to_node(&adapter->pdev->dev);
|
||||
struct ixgbe_q_vector *q_vector;
|
||||
struct ixgbe_ring *ring;
|
||||
int node = NUMA_NO_NODE;
|
||||
int cpu = -1;
|
||||
int ring_count;
|
||||
u8 tcs = adapter->hw_tcs;
|
||||
|
@ -845,10 +845,8 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
|
|||
if ((tcs <= 1) && !(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) {
|
||||
u16 rss_i = adapter->ring_feature[RING_F_RSS].indices;
|
||||
if (rss_i > 1 && adapter->atr_sample_rate) {
|
||||
if (cpu_online(v_idx)) {
|
||||
cpu = v_idx;
|
||||
node = cpu_to_node(cpu);
|
||||
}
|
||||
cpu = cpumask_local_spread(v_idx, node);
|
||||
node = cpu_to_node(cpu);
|
||||
}
|
||||
}
|
||||
|
||||
|
|
Loading…
Reference in New Issue