Re: [PATCH net-next v2 03/12] iavf: optimize Rx buffer allocation a bunch

[Alexander Lobakin <aleksander.lobakin@intel.com>]

From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 31 May 2023 13:14:12 +0200

> On Tue, May 30, 2023 at 09:18:40AM -0700, Alexander H Duyck wrote:
> 
> FWIW I agree with what Alex is saying over here.

There are 2 Alexes, "choose wisely" :P

> 
>> On Thu, 2023-05-25 at 14:57 +0200, Alexander Lobakin wrote:
>>> The Rx hotpath code of IAVF is not well-optimized TBH. Before doing any
>>> further buffer model changes, shake it up a bit. Notably:
>>>
>>> 1. Cache more variables on the stack.
>>>    DMA device, Rx page size, NTC -- these are the most common things
>>>    used all throughout the hotpath, often in loops on each iteration.
>>>    Instead of fetching (or even calculating, as with the page size) them
>>>    from the ring all the time, cache them on the stack at the beginning
>>>    of the NAPI polling callback. NTC will be written back at the end,
>>>    the rest are used read-only, so no sync needed.
>>
>> The advantage of this is going to vary based on the attribute. One of
>> the reasons why I left most of this on the ring is because the section
>> of the ring most of these variables were meant to be read-mostly and
>> shouldn't have resulted in any additional overhead versus accessing
>> them from the stack.
> 
> I believe it depends on ring struct layout which vary across our drivers,
> no? On ice using making more usage of stack as described above improved
> perf.

It's +/- the same, most layout changes usually come with us moving stuff
around to optimize paddings and cachelines lol. Here's the same as with
ice, I don't think it's driver specific to get some positive results
from shortcutting more hotties. The sole time I was surprised is when
you were getting worse results storing xdp_buff on the stack vs on the
ring :D

> 
>>
>>> 2. Don't move the recycled buffers around the ring.
>>>    The idea of passing the page of the right-now-recycled-buffer to a
>>>    different buffer, in this case, the first one that needs to be
>>>    allocated, moreover, on each new frame, is fundamentally wrong. It
>>>    involves a few o' fetches, branches and then writes (and one Rx
>>>    buffer struct is at least 32 bytes) where they're completely unneeded,
>>>    but gives no good -- the result is the same as if we'd recycle it
>>>    inplace, at the same position where it was used. So drop this and let
>>>    the main refilling function take care of all the buffers, which were
>>>    processed and now need to be recycled/refilled.
>>
>> The next_to_alloc logic was put in place to deal with systems that are
>> experiencing memory issues. Specifically what can end up happening is
>> that the ring can stall due to failing memory allocations and the
>> memory can get stuck on the ring. For that reason we were essentially
>> defragmenting the buffers when we started suffering memory pressure so
>> that they could be reusued and/or freed following immediate use.
>>
>> Basically what you are trading off is some exception handling for
>> performance by removing it.
> 
> With all of the mix of the changes this patch carries, I find it hard to
> follow from description which parts of diff I should be looking at.

Huge piece removed before add_rx_frag_blah.

> 
>>
>>> 3. Don't allocate with %GPF_ATOMIC on ifup.
>>>    This involved introducing the @gfp parameter to a couple functions.
>>>    Doesn't change anything for Rx -> softirq.

[...]

>>> + up to 2% performance.
>>>
>>
>> What is the test you saw the 2% performance improvement in? Is it
>> something XDP related or a full stack test?
> 
> +1, can you say more about that measurement?

My prev reply to Alex.

> 
>>
>>> Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
>>
>> Also one thing I am not a huge fan of is a patch that is really a
>> patchset onto itself. With all 6 items called out here I would have
>> preferred to see this as 6 patches as it would have been easier to
>> review.
> 
> +1

+1 :D

[...]

>>>  	/* if we are the last buffer then there is nothing else to do */
>>>  #define IAVF_RXD_EOF BIT(IAVF_RX_DESC_STATUS_EOF_SHIFT)
>>>  	if (likely(iavf_test_staterr(rx_desc, IAVF_RXD_EOF)))
>>
>> You may want to see if you can get rid of this function entirely,
>> perhaps you do in a later patch. This function was added for ixgbe back
>> in the day to allow us to place the skb back in the ring for the RSC
>> based workloads where we had to deal with interleaved frames in the Rx
>> path.
>>
>> For example, one question here would be why are we passing skb? It
>> isn't used as far as I can tell.
>>
> this was used back when skb was stored within the Rx buffer and now we
> just store skb on Rx ring struct, so good catch, this arg is redundant.

Also prev reply. I'm removing it later in the series hehe.

> 
> I'll go and take a look at code on v3.

No changes apart fixing OcteonTX2 compilation =\

Thanks,
Olek