Virtualization - Feb 2023 - virtio-fs: adding support for multi-queue

On Wed, Feb 08, 2023 at 09:33:33AM +0100, Peter-Jan Gootzen
wrote:
> 
> 
> On 07/02/2023 22:57, Vivek Goyal wrote:
> > On Tue, Feb 07, 2023 at 04:32:02PM -0500, Stefan Hajnoczi wrote:
> > > On Tue, Feb 07, 2023 at 02:53:58PM -0500, Vivek Goyal wrote:
> > > > On Tue, Feb 07, 2023 at 02:45:39PM -0500, Stefan Hajnoczi
wrote:
> > > > > On Tue, Feb 07, 2023 at 11:14:46AM +0100, Peter-Jan
Gootzen wrote:
> > > > > > Hi,
> > > > > > 
> > > > 
> > > > [cc German]
> > > > 
> > > > > > For my MSc thesis project in collaboration with
IBM
> > > > > > (https://github.com/IBM/dpu-virtio-fs) we are
looking to improve the
> > > > > > performance of the virtio-fs driver in high
throughput scenarios. We think
> > > > > > the main bottleneck is the fact that the virtio-fs
driver does not support
> > > > > > multi-queue (while the spec does). A big factor in
this is that our setup on
> > > > > > the virtio-fs device-side (a DPU) does not easily
allow multiple cores to
> > > > > > tend to a single virtio queue.
> > > > 
> > > > This is an interesting limitation in DPU.
> > > 
> > > Virtqueues are single-consumer queues anyway. Sharing them
between
> > > multiple threads would be expensive. I think using multiqueue is
natural
> > > and not specific to DPUs.
> > 
> > Can we create multiple threads (a thread pool) on DPU and let these
> > threads process requests in parallel (While there is only one virt
> > queue).
> > 
> > So this is what we had done in virtiofsd. One thread is dedicated to
> > pull the requests from virt queue and then pass the request to thread
> > pool to process it. And that seems to help with performance in
> > certain cases.
> > 
> > Is that possible on DPU? That itself can give a nice performance
> > boost for certain workloads without having to implement multiqueue
> > actually.
> > 
> > Just curious. I am not opposed to the idea of multiqueue. I am
> > just curious about the kind of performance gain (if any) it can
> > provide. And will this be helpful for rust virtiofsd running on
> > host as well?
> > 
> > Thanks
> > Vivek
> > 
> There is technically nothing preventing us from consuming a single queue on
> multiple cores, however our current Virtio implementation (DPU-side) is set
> up with the assumption that you should never want to do that (concurrency
> mayham around the Virtqueues and the DMAs). So instead of putting all the
> work into reworking the implementation to support that and still incur the
> big overhead, we see it more fitting to amend the virtio-fs driver with
> multi-queue support.
> 
> 
> > Is it just a theory at this point of time or have you implemented
> > it and seeing significant performance benefit with multiqueue?
> 
> It is a theory, but we are currently seeing that using the single request
> queue, the single core attending to that queue on the DPU is reasonably
> close to being fully saturated.
> 
> > And will this be helpful for rust virtiofsd running on
> > host as well?
> 
> I figure this would be dependent on the workload and the users-needs.
> Having many cores concurrently pulling on their own virtq and then
> immediately process the request locally would of course improve
performance.
> But we are offloading all this work to the DPU, for providing
> high-throughput cloud services.
I think Vivek is getting at whether your code processes requests
sequentially or in parallel. A single thread processing the virtqueue
that hands off requests to worker threads or uses io_uring to perform
I/O asynchronously will perform differently from a single thread that
processes requests sequentially in a blocking fashion. Multiqueue is not
necessary for parallelism, but the single queue might become a
bottleneck.
> > Sounds good. Assigning vqs round-robin is the strategy that virtio-net
> > and virtio-blk use. virtio-blk could be an interesting example as
it's
> > similar to virtiofs. The Linux multiqueue block layer and core virtio
> > irq allocation handle CPU affinity in the case of virtio-blk.
> 
> The virtio-blk use the queue assigned by the mq block layer and virtio-net
> the queue assigned from the net core layer correct?
Yes.
> If I interpret you correct, the round-robin strategy is done by assigning
> cores to queues round-robin, not per requests dynamically round-robin?
Yes, virtqueues are assigned to CPUs statically.
> This is what I remembered as well, but can't find it clearly in the
source
> right now, do you have references to the source for this?
virtio_blk.ko uses an irq_affinity descriptor to tell virtio_find_vqs()
to spread MSI interrupts across CPUs:
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/block/virtio_blk.c#n609

The core blk-mq code has the blk_mq_virtio_map_queues() function to map
block layer queues to virtqueues:
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/block/blk-mq-virtio.c#n24

virtio_net.ko manually sets virtqueue affinity:
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/net/virtio_net.c#n2283

virtio_net.ko tells the core net subsystem about queues using
netif_set_real_num_tx_queues() and then skbs are mapped to queues by
common code:
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/net/core/dev.c#n4079

Stefan
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 488 bytes
Desc: not available
URL:
<http://lists.linuxfoundation.org/pipermail/virtualization/attachments/20230208/0b66186d/attachment.sig>

On 08/02/2023 11:43, Stefan Hajnoczi wrote:
> On Wed, Feb 08, 2023 at 09:33:33AM +0100, Peter-Jan Gootzen wrote:
>>
>>
>> On 07/02/2023 22:57, Vivek Goyal wrote:
>>> On Tue, Feb 07, 2023 at 04:32:02PM -0500, Stefan Hajnoczi wrote:
>>>> On Tue, Feb 07, 2023 at 02:53:58PM -0500, Vivek Goyal wrote:
>>>>> On Tue, Feb 07, 2023 at 02:45:39PM -0500, Stefan Hajnoczi
wrote:
>>>>>> On Tue, Feb 07, 2023 at 11:14:46AM +0100, Peter-Jan
Gootzen wrote:
>>>>>>> Hi,
>>>>>>>
>>>>>
>>>>> [cc German]
>>>>>
>>>>>>> For my MSc thesis project in collaboration with IBM
>>>>>>> (https://github.com/IBM/dpu-virtio-fs) we are
looking to improve the
>>>>>>> performance of the virtio-fs driver in high
throughput scenarios. We think
>>>>>>> the main bottleneck is the fact that the virtio-fs
driver does not support
>>>>>>> multi-queue (while the spec does). A big factor in
this is that our setup on
>>>>>>> the virtio-fs device-side (a DPU) does not easily
allow multiple cores to
>>>>>>> tend to a single virtio queue.
>>>>>
>>>>> This is an interesting limitation in DPU.
>>>>
>>>> Virtqueues are single-consumer queues anyway. Sharing them
between
>>>> multiple threads would be expensive. I think using multiqueue
is natural
>>>> and not specific to DPUs.
>>>
>>> Can we create multiple threads (a thread pool) on DPU and let these
>>> threads process requests in parallel (While there is only one virt
>>> queue).
>>>
>>> So this is what we had done in virtiofsd. One thread is dedicated
to
>>> pull the requests from virt queue and then pass the request to
thread
>>> pool to process it. And that seems to help with performance in
>>> certain cases.
>>>
>>> Is that possible on DPU? That itself can give a nice performance
>>> boost for certain workloads without having to implement multiqueue
>>> actually.
>>>
>>> Just curious. I am not opposed to the idea of multiqueue. I am
>>> just curious about the kind of performance gain (if any) it can
>>> provide. And will this be helpful for rust virtiofsd running on
>>> host as well?
>>>
>>> Thanks
>>> Vivek
>>>
>> There is technically nothing preventing us from consuming a single
queue on
>> multiple cores, however our current Virtio implementation (DPU-side) is
set
>> up with the assumption that you should never want to do that
(concurrency
>> mayham around the Virtqueues and the DMAs). So instead of putting all
the
>> work into reworking the implementation to support that and still incur
the
>> big overhead, we see it more fitting to amend the virtio-fs driver with
>> multi-queue support.
>>
>>
>>> Is it just a theory at this point of time or have you implemented
>>> it and seeing significant performance benefit with multiqueue?
>>
>> It is a theory, but we are currently seeing that using the single
request
>> queue, the single core attending to that queue on the DPU is reasonably
>> close to being fully saturated.
>>
>>> And will this be helpful for rust virtiofsd running on
>>> host as well?
>>
>> I figure this would be dependent on the workload and the users-needs.
>> Having many cores concurrently pulling on their own virtq and then
>> immediately process the request locally would of course improve
performance.
>> But we are offloading all this work to the DPU, for providing
>> high-throughput cloud services.
> 
> I think Vivek is getting at whether your code processes requests
> sequentially or in parallel. A single thread processing the virtqueue
> that hands off requests to worker threads or uses io_uring to perform
> I/O asynchronously will perform differently from a single thread that
> processes requests sequentially in a blocking fashion. Multiqueue is not
> necessary for parallelism, but the single queue might become a
> bottleneck.
Requests are handled non-blocking with remote IO on the DPU. Our current 
architecture is as follows:
T1: Tends to the Virtq, parses FUSE to remote IO and fires off the 
asynchronous remote IO.
T2: Polls for completion on the remote IO and parses it back to FUSE, 
puts the FUSE buffers in a completion queue of T1.
T1: Handles the Virtio completion and DMA of the requests in the CQ.

Thread 1 is busy polling on its two queues (Virtq and CQ) with equal 
priority, thread 2 is busy polling as well. This setup is not really 
optimal, but we are working within the constraints of both our DPU and 
remote IO stack.
Currently we are able to get with sequential single job 4k throughput:
Write: 246MiB/s
Read: 20MiB/s
We are not sure yet where the bottleneck is for reads, we hope to be 
able to match it to the write speed. For writes the two main bottlenecks 
we see are: the single Virtq (so limited parallelism on the DPU and 
remote-side) and that virtio-fs IO is constrained to the page size of 4k 
(NFS for example, who we are trying to replace, sees huge performance 
gains with larger block sizes).
>> This is what I remembered as well, but can't find it clearly in the
source
>> right now, do you have references to the source for this?
> 
> virtio_blk.ko uses an irq_affinity descriptor to tell virtio_find_vqs()
> to spread MSI interrupts across CPUs:
>
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/block/virtio_blk.c#n609
> 
> The core blk-mq code has the blk_mq_virtio_map_queues() function to map
> block layer queues to virtqueues:
>
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/block/blk-mq-virtio.c#n24
> 
> virtio_net.ko manually sets virtqueue affinity:
>
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/net/virtio_net.c#n2283
> 
> virtio_net.ko tells the core net subsystem about queues using
> netif_set_real_num_tx_queues() and then skbs are mapped to queues by
> common code:
>
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/net/core/dev.c#n4079
Thanks for the pointers. :)

Thanks,
Peter-Jan