Re: [PATCH 3/4 net-next] net: mana: add a function to spread IRQs per CPUs

[Souradeep Chakrabarti]

On Tue, Jan 09, 2024 at 08:20:31PM +0000, Haiyang Zhang wrote:
> 
> 
> > -----Original Message-----
> > From: Michael Kelley <mhklinux@xxxxxxxxxxx>
> > Sent: Tuesday, January 9, 2024 2:23 PM
> > To: Souradeep Chakrabarti <schakrabarti@xxxxxxxxxxxxxxxxxxx>; KY Srinivasan
> > <kys@xxxxxxxxxxxxx>; Haiyang Zhang <haiyangz@xxxxxxxxxxxxx>;
> > wei.liu@xxxxxxxxxx; Dexuan Cui <decui@xxxxxxxxxxxxx>;
> > davem@xxxxxxxxxxxxx; edumazet@xxxxxxxxxx; kuba@xxxxxxxxxx;
> > pabeni@xxxxxxxxxx; Long Li <longli@xxxxxxxxxxxxx>; yury.norov@xxxxxxxxx;
> > leon@xxxxxxxxxx; cai.huoqing@xxxxxxxxx; ssengar@xxxxxxxxxxxxxxxxxxx;
> > vkuznets@xxxxxxxxxx; tglx@xxxxxxxxxxxxx; linux-hyperv@xxxxxxxxxxxxxxx;
> > netdev@xxxxxxxxxxxxxxx; linux-kernel@xxxxxxxxxxxxxxx; linux-
> > rdma@xxxxxxxxxxxxxxx
> > Cc: Souradeep Chakrabarti <schakrabarti@xxxxxxxxxxxxx>; Paul Rosswurm
> > <paulros@xxxxxxxxxxxxx>
> > Subject: RE: [PATCH 3/4 net-next] net: mana: add a function to spread IRQs per
> > CPUs
> > 
> > [Some people who received this message don't often get email from
> > mhklinux@xxxxxxxxxxx. Learn why this is important at
> > https://aka.ms/LearnAboutSenderIdentification ]
> > 
> > From: Souradeep Chakrabarti <schakrabarti@xxxxxxxxxxxxxxxxxxx> Sent:
> > Tuesday, January 9, 2024 2:51 AM
> > >
> > > From: Yury Norov <yury.norov@xxxxxxxxx>
> > >
> > > Souradeep investigated that the driver performs faster if IRQs are
> > > spread on CPUs with the following heuristics:
> > >
> > > 1. No more than one IRQ per CPU, if possible;
> > > 2. NUMA locality is the second priority;
> > > 3. Sibling dislocality is the last priority.
> > >
> > > Let's consider this topology:
> > >
> > > Node            0               1
> > > Core        0       1       2       3
> > > CPU       0   1   2   3   4   5   6   7
> > >
> > > The most performant IRQ distribution based on the above topology
> > > and heuristics may look like this:
> > >
> > > IRQ     Nodes   Cores   CPUs
> > > 0       1       0       0-1
> > > 1       1       1       2-3
> > > 2       1       0       0-1
> > > 3       1       1       2-3
> > > 4       2       2       4-5
> > > 5       2       3       6-7
> > > 6       2       2       4-5
> > > 7       2       3       6-7
> > 
> > I didn't pay attention to the detailed discussion of this issue
> > over the past 2 to 3 weeks during the holidays in the U.S., but
> > the above doesn't align with the original problem as I understood
> > it.  I thought the original problem was to avoid putting IRQs on
> > both hyper-threads in the same core, and that the perf
> > improvements are based on that configuration.  At least that's
> > what the commit message for Patch 4/4 in this series says.
> > 
> > The above chart results in 8 IRQs being assigned to the 8 CPUs,
> > probably with 1 IRQ per CPU.   At least on x86, if the affinity
> > mask for an IRQ contains multiple CPUs, matrix_find_best_cpu()
> > should balance the IRQ assignments between the CPUs in the mask.
> > So the original problem is still present because both hyper-threads
> > in a core are likely to have an IRQ assigned.
> > 
> > Of course, this example has 8 IRQs and 8 CPUs, so assigning an
> > IRQ to every hyper-thread may be the only choice.  If that's the
> > case, maybe this just isn't a good example to illustrate the
> > original problem and solution.  But even with a better example
> > where the # of IRQs is <= half the # of CPUs in a NUMA node,
> > I don't think the code below accomplishes the original intent.
> > 
> > Maybe I've missed something along the way in getting to this
> > version of the patch.  Please feel free to set me straight. :-)
> > 
> > Michael
> 
> I have the same question as Michael. Also, I'm asking Souradeep
> in another channel: So, the algorithm still uses up all current 
> NUMA node before moving on to the next NUMA node, right?
> 
> Except each IRQ is affinitized to 2 CPUs. 
> For example, a system with 2 IRQs:
> IRQ     Nodes   Cores  CPUs
> 0       1       0      0-1
> 1       1       1      2-3
>  
> Is this performing better than the algorithm in earlier patches? like below:
> IRQ     Nodes   Cores  CPUs
> 0       1       0      0
> 1       1       1      2
> 
The details for this approach has been shared by Yury later in this thread.
The main intention with this approach is kernel may pick any
sibling for the IRQ.
> Thanks,
> - Haiyang