From: wangyunjian <wangyunjian@huawei.com>
To: Ferruh Yigit <ferruh.yigit@intel.com>, "dev@dpdk.org" <dev@dpdk.org>
Cc: "liucheng (J)" <liucheng11@huawei.com>,
dingxiaoxiong <dingxiaoxiong@huawei.com>
Subject: Re: [dpdk-dev] [PATCH] kni: fix wrong mbuf alloc count in kni_allocate_mbufs
Date: Tue, 22 Jun 2021 07:32:42 +0000 [thread overview]
Message-ID: <ca00888417ad4c8496ff44a8796a0240@huawei.com> (raw)
In-Reply-To: <e375f491-b331-68cc-e207-7c51e24d02f2@intel.com>
> -----Original Message-----
> From: Ferruh Yigit [mailto:ferruh.yigit@intel.com]
> Sent: Monday, June 21, 2021 7:26 PM
> To: wangyunjian <wangyunjian@huawei.com>; dev@dpdk.org
> Cc: liucheng (J) <liucheng11@huawei.com>; dingxiaoxiong
> <dingxiaoxiong@huawei.com>
> Subject: Re: [dpdk-dev] [PATCH] kni: fix wrong mbuf alloc count in
> kni_allocate_mbufs
>
> On 6/21/2021 4:27 AM, wangyunjian wrote:
> >> -----Original Message-----
> >> From: Ferruh Yigit [mailto:ferruh.yigit@intel.com]
> >> Sent: Friday, June 18, 2021 9:37 PM
> >> To: wangyunjian <wangyunjian@huawei.com>; dev@dpdk.org
> >> Cc: liucheng (J) <liucheng11@huawei.com>; dingxiaoxiong
> >> <dingxiaoxiong@huawei.com>
> >> Subject: Re: [dpdk-dev] [PATCH] kni: fix wrong mbuf alloc count in
> >> kni_allocate_mbufs
> >>
> >> On 5/31/2021 1:09 PM, wangyunjian wrote:
> >>> From: Yunjian Wang <wangyunjian@huawei.com>
> >>>
> >>> In kni_allocate_mbufs(), we alloc mbuf for alloc_q as this code.
> >>> allocq_free = (kni->alloc_q->read - kni->alloc_q->write - 1) \
> >>> & (MAX_MBUF_BURST_NUM - 1);
> >>> The value of allocq_free maybe zero (e.g 32 & (32 - 1) = 0), and it
> >>> will not fill the alloc_q. When the alloc_q's free count is zero, it
> >>> will drop the packet in kernel kni.
> >>>
> >>
> >> nack
> >>
> >> Both 'read' & 'write' pointers can be max 'len-1', so 'read - write -
> >> 1' can't be 'len'.
> >> For above example first part can't be '32'.
> >>
> >> But if you are observing a problem, can you please describe it a
> >> little more, it may be because of something else.
> >
> > The ring size is 1024. After init, write = read = 0. Then we fill kni->alloc_q to
> full. At this time, write = 1023, read = 0.
> > Then the kernel send 32 packets to userspace. At this time, write = 1023,
> read = 32.
> > And then the userspace recieve this 32 packets. Then fill the kni->alloc_q, (32
> - 1023 - 1)&31 = 0, fill nothing.
> > ...
> > Then the kernel send 32 packets to userspace. At this time, write = 1023,
> read = 992.
> > And then the userspace recieve this 32 packets. Then fill the kni->alloc_q,
> (992 - 1023 - 1)&31 = 0, fill nothing.
> > Then the kernel send 32 packets to userspace. The kni->alloc_q only has 31
> mbufs and will drop one packet.
> >
> > Absolutely, this is a special scene. Normally, it will fill some mbufs everytime,
> but may not enough for the kernel to use.
> > In this patch, we always keep the kni->alloc_q to full for the kernel to use.
> >
>
> I see now, yes it is technically possible to have above scenario and it can cause
> glitch in the datapath.
>
> Below fix looks good, +1 to use 'kni_fifo_free_count()' instead of calculation
> within the function which may be wrong for the 'RTE_USE_C11_MEM_MODEL'
> case.
I compiled them on the ARM and x86 platforms with the 'RTE_USE_C11_MEM_MODEL'
case, and no error is reported.
>
> Can you please add fixes line too?
OK, will include it in next version.
Thanks
>
> > Thanks
> >
> >>
> >>> In this patch, we set the allocq_free as the min between
> >>> MAX_MBUF_BURST_NUM and the free count of the alloc_q.
> >>>
> >>> Signed-off-by: Cheng Liu <liucheng11@huawei.com>
> >>> Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
> >>> ---
> >>> lib/kni/rte_kni.c | 5 +++--
> >>> 1 file changed, 3 insertions(+), 2 deletions(-)
> >>>
> >>> diff --git a/lib/kni/rte_kni.c b/lib/kni/rte_kni.c index
> >>> 9dae6a8d7c..20d8f20cef 100644
> >>> --- a/lib/kni/rte_kni.c
> >>> +++ b/lib/kni/rte_kni.c
> >>> @@ -677,8 +677,9 @@ kni_allocate_mbufs(struct rte_kni *kni)
> >>> return;
> >>> }
> >>>
> >>> - allocq_free = (kni->alloc_q->read - kni->alloc_q->write - 1)
> >>> - & (MAX_MBUF_BURST_NUM - 1);
> >>> + allocq_free = kni_fifo_free_count(kni->alloc_q);
> >>> + allocq_free = (allocq_free > MAX_MBUF_BURST_NUM) ?
> >>> + MAX_MBUF_BURST_NUM : allocq_free;
> >>> for (i = 0; i < allocq_free; i++) {
> >>> pkts[i] = rte_pktmbuf_alloc(kni->pktmbuf_pool);
> >>> if (unlikely(pkts[i] == NULL)) {
> >>>
> >
next prev parent reply other threads:[~2021-06-22 7:32 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-05-31 12:09 wangyunjian
2021-06-18 13:37 ` Ferruh Yigit
2021-06-21 3:27 ` wangyunjian
2021-06-21 11:26 ` Ferruh Yigit
2021-06-22 7:32 ` wangyunjian [this message]
2021-06-22 7:43 ` Ferruh Yigit
2021-06-22 10:57 ` [dpdk-dev] [PATCH v2] " wangyunjian
2021-06-22 12:27 ` Ferruh Yigit
2021-06-22 12:32 ` wangyunjian
2021-06-22 12:44 ` [dpdk-dev] [PATCH v3] kni: fix mbuf allocation for alloc FIFO wangyunjian
2021-06-22 20:46 ` [dpdk-dev] [dpdk-stable] " Thomas Monjalon
2021-06-23 12:16 ` wangyunjian
2021-06-23 14:11 ` Ferruh Yigit
2021-06-23 14:41 ` Thomas Monjalon
2021-06-24 1:55 ` Ajit Khaparde
2021-06-24 7:43 ` Thomas Monjalon
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=ca00888417ad4c8496ff44a8796a0240@huawei.com \
--to=wangyunjian@huawei.com \
--cc=dev@dpdk.org \
--cc=dingxiaoxiong@huawei.com \
--cc=ferruh.yigit@intel.com \
--cc=liucheng11@huawei.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).