> Subject: Re: [PATCH v3] genirq/matrix: Choose CPU for managed IRQs based
> on how many of them are allocated
>
> On Sat, 3 Nov 2018, Thomas Gleixner wrote:
> > On Fri, 2 Nov 2018, Long Li wrote:
> > > /**
> > > * irq_matrix_assign_system - Assign system wide entry in the matrix
> > > * @m:
> Subject: Re: [PATCH v3] genirq/matrix: Choose CPU for managed IRQs based
> on how many of them are allocated
>
> On Sat, 3 Nov 2018, Thomas Gleixner wrote:
> > On Fri, 2 Nov 2018, Long Li wrote:
> > > /**
> > > * irq_matrix_assign_system - Assign system wide entry in the matrix
> > > * @m:
On Sat, 3 Nov 2018, Thomas Gleixner wrote:
> On Fri, 2 Nov 2018, Long Li wrote:
> > /**
> > * irq_matrix_assign_system - Assign system wide entry in the matrix
> > * @m: Matrix pointer
> > @@ -269,7 +291,7 @@ int irq_matrix_alloc_managed(struct irq_matrix *m,
> > const struct
On Sat, 3 Nov 2018, Thomas Gleixner wrote:
> On Fri, 2 Nov 2018, Long Li wrote:
> > /**
> > * irq_matrix_assign_system - Assign system wide entry in the matrix
> > * @m: Matrix pointer
> > @@ -269,7 +291,7 @@ int irq_matrix_alloc_managed(struct irq_matrix *m,
> > const struct
Long,
On Fri, 2 Nov 2018, Long Li wrote:
> /**
> * irq_matrix_assign_system - Assign system wide entry in the matrix
> * @m: Matrix pointer
> @@ -269,7 +291,7 @@ int irq_matrix_alloc_managed(struct irq_matrix *m, const
> struct cpumask *msk,
> if (cpumask_empty(msk))
>
Long,
On Fri, 2 Nov 2018, Long Li wrote:
> /**
> * irq_matrix_assign_system - Assign system wide entry in the matrix
> * @m: Matrix pointer
> @@ -269,7 +291,7 @@ int irq_matrix_alloc_managed(struct irq_matrix *m, const
> struct cpumask *msk,
> if (cpumask_empty(msk))
>
From: Long Li
On a large system with multiple devices of the same class (e.g. NVMe disks,
using managed IRQs), the kernel tends to concentrate their IRQs on several
CPUs.
The issue is that when NVMe calls irq_matrix_alloc_managed(), the assigned
CPU tends to be the first several CPUs in the
From: Long Li
On a large system with multiple devices of the same class (e.g. NVMe disks,
using managed IRQs), the kernel tends to concentrate their IRQs on several
CPUs.
The issue is that when NVMe calls irq_matrix_alloc_managed(), the assigned
CPU tends to be the first several CPUs in the
8 matches
Mail list logo