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

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20200104120349.GA3810@ming.t460p>
Date:   Sat, 4 Jan 2020 20:03:49 +0800
From:   Ming Lei <ming.lei@...hat.com>
To:     John Garry <john.garry@...wei.com>
Cc:     Marc Zyngier <maz@...nel.org>,
        "tglx@...utronix.de" <tglx@...utronix.de>,
        "chenxiang (M)" <chenxiang66@...ilicon.com>,
        "bigeasy@...utronix.de" <bigeasy@...utronix.de>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
        "hare@...e.com" <hare@...e.com>, "hch@....de" <hch@....de>,
        "axboe@...nel.dk" <axboe@...nel.dk>,
        "bvanassche@....org" <bvanassche@....org>,
        "peterz@...radead.org" <peterz@...radead.org>,
        "mingo@...hat.com" <mingo@...hat.com>,
        Zhang Yi <yi.zhang@...hat.com>
Subject: Re: [PATCH RFC 1/1] genirq: Make threaded handler use irq affinity
 for managed interrupt

On Fri, Jan 03, 2020 at 11:50:51AM +0000, John Garry wrote:
> 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.

It should have been done easier by bpftrace than bcc, however it has bug in case
of too many cpu cores on arm64.

So I uses a modified hardirqs.py to do that, you can collect the latency
histogram via funclatency too.



Thanks,
Ming

View attachment "hardirqs.py" of type "text/plain" (5436 bytes)