Use alloc_pages_node() allocate memory for vring queue with proper
NUMA affinity.
Reported-by: kernel test robot <[email protected]>
Suggested-by: Jiang Liu <[email protected]>
Signed-off-by: Shile Zhang <[email protected]>
---
Changelog
v1 -> v2:
- fixed compile warning reported by LKP.
---
drivers/virtio/virtio_ring.c | 10 ++++++----
1 file changed, 6 insertions(+), 4 deletions(-)
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 58b96baa8d48..d38fd6872c8c 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -276,9 +276,11 @@ static void *vring_alloc_queue(struct virtio_device *vdev, size_t size,
return dma_alloc_coherent(vdev->dev.parent, size,
dma_handle, flag);
} else {
- void *queue = alloc_pages_exact(PAGE_ALIGN(size), flag);
-
- if (queue) {
+ void *queue = NULL;
+ struct page *page = alloc_pages_node(dev_to_node(vdev->dev.parent),
+ flag, get_order(size));
+ if (page) {
+ queue = page_address(page);
phys_addr_t phys_addr = virt_to_phys(queue);
*dma_handle = (dma_addr_t)phys_addr;
@@ -308,7 +310,7 @@ static void vring_free_queue(struct virtio_device *vdev, size_t size,
if (vring_use_dma_api(vdev))
dma_free_coherent(vdev->dev.parent, size, queue, dma_handle);
else
- free_pages_exact(queue, PAGE_ALIGN(size));
+ free_pages((unsigned long)queue, get_order(size));
}
/*
--
2.24.0.rc2
On Tue, Jul 21, 2020 at 03:00:13PM +0800, Shile Zhang wrote:
> Use alloc_pages_node() allocate memory for vring queue with proper
> NUMA affinity.
>
> Reported-by: kernel test robot <[email protected]>
> Suggested-by: Jiang Liu <[email protected]>
> Signed-off-by: Shile Zhang <[email protected]>
Do you observe any performance gains from this patch?
I also wonder why isn't the probe code run on the correct numa node?
That would fix a wide class of issues like this without need to tweak
drivers.
Bjorn, what do you think? Was this considered?
> ---
> Changelog
> v1 -> v2:
> - fixed compile warning reported by LKP.
> ---
> drivers/virtio/virtio_ring.c | 10 ++++++----
> 1 file changed, 6 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
> index 58b96baa8d48..d38fd6872c8c 100644
> --- a/drivers/virtio/virtio_ring.c
> +++ b/drivers/virtio/virtio_ring.c
> @@ -276,9 +276,11 @@ static void *vring_alloc_queue(struct virtio_device *vdev, size_t size,
> return dma_alloc_coherent(vdev->dev.parent, size,
> dma_handle, flag);
> } else {
> - void *queue = alloc_pages_exact(PAGE_ALIGN(size), flag);
> -
> - if (queue) {
> + void *queue = NULL;
> + struct page *page = alloc_pages_node(dev_to_node(vdev->dev.parent),
> + flag, get_order(size));
> + if (page) {
> + queue = page_address(page);
> phys_addr_t phys_addr = virt_to_phys(queue);
> *dma_handle = (dma_addr_t)phys_addr;
>
> @@ -308,7 +310,7 @@ static void vring_free_queue(struct virtio_device *vdev, size_t size,
> if (vring_use_dma_api(vdev))
> dma_free_coherent(vdev->dev.parent, size, queue, dma_handle);
> else
> - free_pages_exact(queue, PAGE_ALIGN(size));
> + free_pages((unsigned long)queue, get_order(size));
> }
>
> /*
> --
> 2.24.0.rc2
On 2020/7/21 16:18, Michael S. Tsirkin wrote:
> On Tue, Jul 21, 2020 at 03:00:13PM +0800, Shile Zhang wrote:
>> Use alloc_pages_node() allocate memory for vring queue with proper
>> NUMA affinity.
>>
>> Reported-by: kernel test robot <[email protected]>
>> Suggested-by: Jiang Liu <[email protected]>
>> Signed-off-by: Shile Zhang <[email protected]>
>
> Do you observe any performance gains from this patch?
Thanks for your comments!
Yes, the bandwidth can boost more than doubled (from 30Gbps to 80GBps)
with this changes in my test env (8 numa nodes), with netperf test.
>
> I also wonder why isn't the probe code run on the correct numa node?
> That would fix a wide class of issues like this without need to tweak
> drivers.
Good point, I'll check this, thanks!
>
> Bjorn, what do you think? Was this considered?
>
>> ---
>> Changelog
>> v1 -> v2:
>> - fixed compile warning reported by LKP.
>> ---
>> drivers/virtio/virtio_ring.c | 10 ++++++----
>> 1 file changed, 6 insertions(+), 4 deletions(-)
>>
>> diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
>> index 58b96baa8d48..d38fd6872c8c 100644
>> --- a/drivers/virtio/virtio_ring.c
>> +++ b/drivers/virtio/virtio_ring.c
>> @@ -276,9 +276,11 @@ static void *vring_alloc_queue(struct virtio_device *vdev, size_t size,
>> return dma_alloc_coherent(vdev->dev.parent, size,
>> dma_handle, flag);
>> } else {
>> - void *queue = alloc_pages_exact(PAGE_ALIGN(size), flag);
>> -
>> - if (queue) {
>> + void *queue = NULL;
>> + struct page *page = alloc_pages_node(dev_to_node(vdev->dev.parent),
>> + flag, get_order(size));
>> + if (page) {
>> + queue = page_address(page);
>> phys_addr_t phys_addr = virt_to_phys(queue);
>> *dma_handle = (dma_addr_t)phys_addr;
>>
>> @@ -308,7 +310,7 @@ static void vring_free_queue(struct virtio_device *vdev, size_t size,
>> if (vring_use_dma_api(vdev))
>> dma_free_coherent(vdev->dev.parent, size, queue, dma_handle);
>> else
>> - free_pages_exact(queue, PAGE_ALIGN(size));
>> + free_pages((unsigned long)queue, get_order(size));
>> }
>>
>> /*
>> --
>> 2.24.0.rc2
On 2020/7/21 19:28, Shile Zhang wrote:
>
>
> On 2020/7/21 16:18, Michael S. Tsirkin wrote:
>> On Tue, Jul 21, 2020 at 03:00:13PM +0800, Shile Zhang wrote:
>>> Use alloc_pages_node() allocate memory for vring queue with proper
>>> NUMA affinity.
>>>
>>> Reported-by: kernel test robot <[email protected]>
>>> Suggested-by: Jiang Liu <[email protected]>
>>> Signed-off-by: Shile Zhang <[email protected]>
>>
>> Do you observe any performance gains from this patch?
>
> Thanks for your comments!
> Yes, the bandwidth can boost more than doubled (from 30Gbps to 80GBps)
> with this changes in my test env (8 numa nodes), with netperf test.
>
>>
>> I also wonder why isn't the probe code run on the correct numa node?
>> That would fix a wide class of issues like this without need to tweak
>> drivers.
>
> Good point, I'll check this, thanks!
Sorry, I have no idea about how the probe code to grab the appropriate
NUMA node.
>
>>
>> Bjorn, what do you think? Was this considered?
Hi Bjorn, Could you please give any comments about this issue?
Thanks!
>>
>>> ---
>>> Changelog
>>> v1 -> v2:
>>> - fixed compile warning reported by LKP.
>>> ---
>>> drivers/virtio/virtio_ring.c | 10 ++++++----
>>> 1 file changed, 6 insertions(+), 4 deletions(-)
>>>
>>> diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
>>> index 58b96baa8d48..d38fd6872c8c 100644
>>> --- a/drivers/virtio/virtio_ring.c
>>> +++ b/drivers/virtio/virtio_ring.c
>>> @@ -276,9 +276,11 @@ static void *vring_alloc_queue(struct
>>> virtio_device *vdev, size_t size,
>>> return dma_alloc_coherent(vdev->dev.parent, size,
>>> dma_handle, flag);
>>> } else {
>>> - void *queue = alloc_pages_exact(PAGE_ALIGN(size), flag);
>>> -
>>> - if (queue) {
>>> + void *queue = NULL;
>>> + struct page *page =
>>> alloc_pages_node(dev_to_node(vdev->dev.parent),
>>> + flag, get_order(size));
>>> + if (page) {
>>> + queue = page_address(page);
>>> phys_addr_t phys_addr = virt_to_phys(queue);
>>> *dma_handle = (dma_addr_t)phys_addr;
>>> @@ -308,7 +310,7 @@ static void vring_free_queue(struct virtio_device
>>> *vdev, size_t size,
>>> if (vring_use_dma_api(vdev))
>>> dma_free_coherent(vdev->dev.parent, size, queue, dma_handle);
>>> else
>>> - free_pages_exact(queue, PAGE_ALIGN(size));
>>> + free_pages((unsigned long)queue, get_order(size));
>>> }
>>> /*
>>> --
>>> 2.24.0.rc2
Hi Michael & Bjorn,
Sorry for the ping,
but how about this patch/issue? any comments/suggestions?
Thanks!
On 2020/7/27 21:10, Shile Zhang wrote:
>
>
> On 2020/7/21 19:28, Shile Zhang wrote:
>>
>>
>> On 2020/7/21 16:18, Michael S. Tsirkin wrote:
>>> On Tue, Jul 21, 2020 at 03:00:13PM +0800, Shile Zhang wrote:
>>>> Use alloc_pages_node() allocate memory for vring queue with proper
>>>> NUMA affinity.
>>>>
>>>> Reported-by: kernel test robot <[email protected]>
>>>> Suggested-by: Jiang Liu <[email protected]>
>>>> Signed-off-by: Shile Zhang <[email protected]>
>>>
>>> Do you observe any performance gains from this patch?
>>
>> Thanks for your comments!
>> Yes, the bandwidth can boost more than doubled (from 30Gbps to 80GBps)
>> with this changes in my test env (8 numa nodes), with netperf test.
>>
>>>
>>> I also wonder why isn't the probe code run on the correct numa node?
>>> That would fix a wide class of issues like this without need to tweak
>>> drivers.
>>
>> Good point, I'll check this, thanks!
>
> Sorry, I have no idea about how the probe code to grab the appropriate
> NUMA node.
>
>>
>>>
>>> Bjorn, what do you think? Was this considered?
>
> Hi Bjorn, Could you please give any comments about this issue?
> Thanks!
>
>>>
>>>> ---
>>>> Changelog
>>>> v1 -> v2:
>>>> - fixed compile warning reported by LKP.
>>>> ---
>>>> drivers/virtio/virtio_ring.c | 10 ++++++----
>>>> 1 file changed, 6 insertions(+), 4 deletions(-)
>>>>
>>>> diff --git a/drivers/virtio/virtio_ring.c
>>>> b/drivers/virtio/virtio_ring.c
>>>> index 58b96baa8d48..d38fd6872c8c 100644
>>>> --- a/drivers/virtio/virtio_ring.c
>>>> +++ b/drivers/virtio/virtio_ring.c
>>>> @@ -276,9 +276,11 @@ static void *vring_alloc_queue(struct
>>>> virtio_device *vdev, size_t size,
>>>> return dma_alloc_coherent(vdev->dev.parent, size,
>>>> dma_handle, flag);
>>>> } else {
>>>> - void *queue = alloc_pages_exact(PAGE_ALIGN(size), flag);
>>>> -
>>>> - if (queue) {
>>>> + void *queue = NULL;
>>>> + struct page *page =
>>>> alloc_pages_node(dev_to_node(vdev->dev.parent),
>>>> + flag, get_order(size));
>>>> + if (page) {
>>>> + queue = page_address(page);
>>>> phys_addr_t phys_addr = virt_to_phys(queue);
>>>> *dma_handle = (dma_addr_t)phys_addr;
>>>> @@ -308,7 +310,7 @@ static void vring_free_queue(struct
>>>> virtio_device *vdev, size_t size,
>>>> if (vring_use_dma_api(vdev))
>>>> dma_free_coherent(vdev->dev.parent, size, queue, dma_handle);
>>>> else
>>>> - free_pages_exact(queue, PAGE_ALIGN(size));
>>>> + free_pages((unsigned long)queue, get_order(size));
>>>> }
>>>> /*
>>>> --
>>>> 2.24.0.rc2