Re: [PATCH RFC 1/1] genirq: Make threaded handler use irq affinity for managed interrupt

[John Garry]

On 03/01/2020 11:29, Ming Lei wrote:
> On Fri, Jan 03, 2020 at 10:41:48AM +0000, John Garry wrote:
> > On 03/01/2020 00:46, Ming Lei wrote:
> > > > > > d the
> > > > > > DMA API more than an architecture-specific problem.
> > > > > >
> > > > > > Given that we have so far very little data, I'd hold off any conclusion.
> > > > > We can start to collect latency data of dma unmapping vs nvme_irq()
> > > > > on both x86 and arm64.
> > > > >
> > > > > I will see if I can get a such box for collecting the latency data.
> > > > To reiterate what I mentioned before about IOMMU DMA unmap on x86, a key
> > > > difference is that by default it uses the non-strict (lazy) mode unmap, i.e.
> > > > we unmap in batches. ARM64 uses general default, which is strict mode, i.e.
> > > > every unmap results in an IOTLB fluch.
> > > >
> > > > In my setup, if I switch to lazy unmap (set iommu.strict=0 on cmdline), then
> > > > no lockup.
> > > >
> > > > Are any special IOMMU setups being used for x86, like enabling strict mode?
> > > > I don't know...
> > > BTW, I have run the test on one 224-core ARM64 with one 32-hw_queue NVMe, the
> > > softlock issue can be triggered in one minute.
> > >
> > > nvme_irq() often takes ~5us to complete on this machine, then there is really
> > > risk of cpu lockup when IOPS is > 200K.
> >
> > Do you have a typical nvme_irq() completion time for a mid-range x86 server?
>
> ~1us.

Eh, so ~ x5 faster on x86 machine?! Seems some real issue here.

> It is done via bcc script, and ebpf itself may introduce some overhead.

Can you share the script/instructions? I would like to test on my 
machine. I assume you tested on an ThunderX2.

> > > The soft lockup can be triggered too if 'iommu.strict=0' is passed in,
> > > just takes a bit longer by starting more IO jobs.
> > >
> > > In above test, I submit IO to one single NVMe drive from 4 CPU cores via 8 or
> > > 12 jobs(iommu.strict=0), meantime make the nvme interrupt handled just in one
> > > dedicated CPU core.
> >
> > Well a problem with so many CPUs is that it does not scale (well) with MQ
> > devices, like NVMe.
> >
> > As CPU count goes up, device queue count doesn't and we get more contention.
>
> The problem is worse on ARM64 system, in which there are more CPU cores,
> and each single CPU core is often slower than x86's. Meantime each
> hardware interrupt has to be handled on single CPU target.

Agreed

> Also the storage device(such as NVMe) itself should be same for both
> from performance viewpoint.
>
> > > Is there lock contention among iommu dma map and unmap callback?
> >
> > There would be the IOVA management, but that would be common to x86. Each
> > CPU keeps an IOVA cache, and there is a central pool of cached IOVAs, so
> > that reduces any contention, unless the caches are exhausted.
> >
> > I think most contention/bottleneck is at the SMMU HW interface, which has a
> > single queue interface.
>
> Not sure if it is related with single queue interface, given my test just
> uses single hw queue by pushing several CPU cores to submit IO and
> handling the single queue's interrupt on one dedicated CPU core.

ok, but in my testing I was not limiting to a group of CPUs mapped to a 
single queue, and in this case I saw heavy SMMU driver loading [0].

thanks,
John

[0] 
https://lore.kernel.org/linux-iommu/20190821151749.23743-1-will@xxxxxxxxxx/T/#m4f20e9237797944e63f566ae9e02507794f25fb1