From: Yunsheng Lin <linyunsheng@huawei.com>
To: Jesper Dangaard Brouer <jbrouer@redhat.com>,
<davem@davemloft.net>, <kuba@kernel.org>
Cc: <brouer@redhat.com>, <netdev@vger.kernel.org>,
<linux-kernel@vger.kernel.org>, <linuxarm@openeuler.org>,
<hawk@kernel.org>, <ilias.apalodimas@linaro.org>,
<jonathan.lemon@gmail.com>, <alobakin@pm.me>,
<willemb@google.com>, <cong.wang@bytedance.com>,
<pabeni@redhat.com>, <haokexin@gmail.com>, <nogikh@google.com>,
<elver@google.com>, <memxor@gmail.com>, <edumazet@google.com>,
<alexander.duyck@gmail.com>, <dsahern@gmail.com>
Subject: Re: [Linuxarm] Re: [PATCH net-next 2/7] page_pool: support non-split page with PP_FLAG_PAGE_FRAG
Date: Thu, 30 Sep 2021 15:28:39 +0800 [thread overview]
Message-ID: <d33d5a8d-bf51-c0d6-f600-1b06973f3748@huawei.com> (raw)
In-Reply-To: <2f5a4b07-7acf-1838-cb42-fd8b5d4ba4c6@huawei.com>
On 2021/9/24 15:23, Yunsheng Lin wrote:
> On 2021/9/23 20:08, Jesper Dangaard Brouer wrote:
>>
>>
>> On 22/09/2021 11.41, Yunsheng Lin wrote:
>>> Currently when PP_FLAG_PAGE_FRAG is set, the caller is not
>>> expected to call page_pool_alloc_pages() directly because of
>>> the PP_FLAG_PAGE_FRAG checking in __page_pool_put_page().
>>>
>>> The patch removes the above checking to enable non-split page
>>> support when PP_FLAG_PAGE_FRAG is set.
>>>
>>> Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
>>> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
>>> ---
>>> net/core/page_pool.c | 12 +++++++-----
>>> 1 file changed, 7 insertions(+), 5 deletions(-)
>>>
>>> diff --git a/net/core/page_pool.c b/net/core/page_pool.c
>>> index a65bd7972e37..f7e71dcb6a2e 100644
>>> --- a/net/core/page_pool.c
>>> +++ b/net/core/page_pool.c
>>> @@ -315,11 +315,14 @@ struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp)
>>> /* Fast-path: Get a page from cache */
>>> page = __page_pool_get_cached(pool);
>>> - if (page)
>>> - return page;
>>> /* Slow-path: cache empty, do real allocation */
>>> - page = __page_pool_alloc_pages_slow(pool, gfp);
>>> + if (!page)
>>> + page = __page_pool_alloc_pages_slow(pool, gfp);
>>> +
>>> + if (likely(page))
>>> + page_pool_set_frag_count(page, 1);
>>> +
>>
>> I really don't like that you add one atomic_long_set operation per page alloc call.
>> This is a fast-path for XDP use-cases, which you are ignoring as you drivers doesn't implement XDP.
>>
>> As I cannot ask you to run XDP benchmarks, I fortunately have some page_pool specific microbenchmarks you can run instead.
>>
>> I will ask you to provide before and after results from running these benchmarks [1] and [2].
>>
>> [1] https://github.com/netoptimizer/prototype-kernel/blob/master/kernel/lib/bench_page_pool_simple.c
>>
>> [2] https://github.com/netoptimizer/prototype-kernel/blob/master/kernel/lib/bench_page_pool_cross_cpu.c
>>
>> How to use these module is documented here[3]:
>> [3] https://prototype-kernel.readthedocs.io/en/latest/prototype-kernel/build-process.html
>
> Will running these benchmarks to see if any performance overhead noticable here,
> thanks for the benchmarks.
You are right, there is notiable overhead for bench_page_pool_cross_cpu test
case above, possibly due to the cache bouncing caused by page_pool_set_frag_count().
As memntioned by Ilias, mlx5 use page pool and also do the recycling internally,
so handling the page frag tracking consistently for both PP_FLAG_PAGE_FRAG and
non-PP_FLAG_PAGE_FRAG will break the mlx5 driver.
So I will drop this patch for now.
>
>>
>>> return page;
>>> }
>>> EXPORT_SYMBOL(page_pool_alloc_pages);
>>> @@ -428,8 +431,7 @@ __page_pool_put_page(struct page_pool *pool, struct page *page,
>>> unsigned int dma_sync_size, bool allow_direct)
>>> {
>>> /* It is not the last user for the page frag case */
>>> - if (pool->p.flags & PP_FLAG_PAGE_FRAG &&
>>> - page_pool_atomic_sub_frag_count_return(page, 1))
>>> + if (page_pool_atomic_sub_frag_count_return(page, 1))
>>> return NULL;
>>
>> This adds an atomic_long_read, even when PP_FLAG_PAGE_FRAG is not set.
>
> The point here is to have consistent handling for both PP_FLAG_PAGE_FRAG
> and non-PP_FLAG_PAGE_FRAG case in the following patch.
>
> As the page->_refcount is accessed in "page_ref_count(page) == 1" checking
> in __page_pool_put_page(), and page->pp_frag_count is most likely in the
> same cache line as the page->_refcount, So I am not expecting a noticable
> overhead here.
>
> Anyway, will use the above benchmarks as an example to verify it.
>
>
>>
>>> /* This allocator is optimized for the XDP mode that uses
>>>
>>
>> .
>>
> _______________________________________________
> Linuxarm mailing list -- linuxarm@openeuler.org
> To unsubscribe send an email to linuxarm-leave@openeuler.org
>
next prev parent reply other threads:[~2021-09-30 7:28 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-09-22 9:41 [PATCH net-next 0/7] some optimization for page pool Yunsheng Lin
2021-09-22 9:41 ` [PATCH net-next 1/7] page_pool: disable dma mapping support for 32-bit arch with 64-bit DMA Yunsheng Lin
2021-09-23 9:10 ` Ilias Apalodimas
2021-09-23 9:33 ` Jesper Dangaard Brouer
2021-09-23 10:02 ` Ilias Apalodimas
2021-09-23 11:13 ` Yunsheng Lin
2021-09-23 13:07 ` Ilias Apalodimas
2021-09-24 7:04 ` Yunsheng Lin
2021-09-24 7:25 ` Ilias Apalodimas
2021-09-24 8:01 ` Yunsheng Lin
2021-09-22 9:41 ` [PATCH net-next 2/7] page_pool: support non-split page with PP_FLAG_PAGE_FRAG Yunsheng Lin
2021-09-23 12:08 ` Jesper Dangaard Brouer
2021-09-24 7:23 ` Yunsheng Lin
2021-09-30 7:28 ` Yunsheng Lin [this message]
2021-09-22 9:41 ` [PATCH net-next 3/7] pool_pool: avoid calling compound_head() for skb frag page Yunsheng Lin
2021-09-23 8:33 ` Ilias Apalodimas
2021-09-23 11:24 ` Yunsheng Lin
2021-09-23 11:47 ` Ilias Apalodimas
2021-09-24 7:33 ` Yunsheng Lin
2021-09-24 7:44 ` Ilias Apalodimas
2021-09-22 9:41 ` [PATCH net-next 4/7] page_pool: change BIAS_MAX to support incrementing Yunsheng Lin
2021-09-22 9:41 ` [PATCH net-next 5/7] skbuff: keep track of pp page when __skb_frag_ref() is called Yunsheng Lin
2021-09-22 9:41 ` [PATCH net-next 6/7] skbuff: only use pp_magic identifier for a skb' head page Yunsheng Lin
2021-09-22 9:41 ` [PATCH net-next 7/7] skbuff: remove unused skb->pp_recycle Yunsheng Lin
2021-09-23 7:07 ` [PATCH net-next 0/7] some optimization for page pool Ilias Apalodimas
2021-09-23 11:12 ` Yunsheng Lin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=d33d5a8d-bf51-c0d6-f600-1b06973f3748@huawei.com \
--to=linyunsheng@huawei.com \
--cc=alexander.duyck@gmail.com \
--cc=alobakin@pm.me \
--cc=brouer@redhat.com \
--cc=cong.wang@bytedance.com \
--cc=davem@davemloft.net \
--cc=dsahern@gmail.com \
--cc=edumazet@google.com \
--cc=elver@google.com \
--cc=haokexin@gmail.com \
--cc=hawk@kernel.org \
--cc=ilias.apalodimas@linaro.org \
--cc=jbrouer@redhat.com \
--cc=jonathan.lemon@gmail.com \
--cc=kuba@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxarm@openeuler.org \
--cc=memxor@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=nogikh@google.com \
--cc=pabeni@redhat.com \
--cc=willemb@google.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).