All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Min Hu (Connor)" <humin29@huawei.com>
To: David Christensen <drc@linux.vnet.ibm.com>, <dev@dpdk.org>
Cc: Maxime Coquelin <maxime.coquelin@redhat.com>,
	<chenbo.xia@intel.com>, Thomas Monjalon <thomas@monjalon.net>,
	Ferruh Yigit <ferruh.yigit@intel.com>
Subject: Re: [dpdk-dev] Questions about vm2vm vhost-user/virtio-net test
Date: Fri, 8 Oct 2021 14:55:39 +0800	[thread overview]
Message-ID: <8516a885-3427-9b7b-0891-afd8b430788f@huawei.com> (raw)
In-Reply-To: <a832b361-3e4d-29ff-70ff-a7703096c2ce@linux.vnet.ibm.com>

Hi, David, thanks for your reply,
  other question as below,

在 2021/10/1 2:25, David Christensen 写道:
> 
> 
> On 9/30/21 2:07 AM, Min Hu (Connor) wrote:
>> Hi, all,
>>      I got the answer: testpmd fwd mode should be set "io", then ping
>> OK.
>>
>>      IO fwd mode, it will not change packet MAC address info, and
>> ping OK
>>      MAC fwd mode, it will change packet MAC address info, like:
>>      "rte_ether_addr_copy(&peer_eth_addrs[fs->peer_addr],
>>                  &eth_hdr->d_addr);
>>      rte_ether_addr_copy(&ports[fs->tx_port].eth_addr,
>>                  &eth_hdr->s_addr)"
>>      Then, ping failed.
>>
>>      So, everyone, I got one question: how could this happen?
>>      router change packet src MAC and dst MAC, but ping OK,
>>      testpmd vhost, treated as switch, also changes packert src MAC
>>      and dst MAC, but ping failed ?
> 
> Running testpmd in this configuration is more like a virtual wire, not a 
> switch, though in both cases the SRC/DST MAC addresses aren't typically 
Well, if SRC/DST MAC addresses modifed in some case, what will happen?
That is, A send ping request to B, while SRC/DST MAC addresses
modified,B can get the packet, but B cannot send ping reply.
This is the result of my test. Why?


> modified by the wire/switch when the frame is in transit. Both endpoints 
> reside in the same Ethernet broadcast domain and can talk to each other 
> directly.
> 
> A router typically connects two different broadcast domains, which may 
> or may not be using Ethernet, so the router usually changes the SRC/DST 
> MAC address to work correctly as the frame transitions from one 
> broadcast domain into another. See 
> https://en.wikipedia.org/wiki/Broadcast_domain.
> 
> Dave
> .

      reply	other threads:[~2021-10-08  6:55 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-29 12:09 [dpdk-dev] Questions about vm2vm vhost-user/virtio-net test Min Hu (Connor)
2021-09-30  9:07 ` Min Hu (Connor)
2021-09-30 18:25   ` David Christensen
2021-10-08  6:55     ` Min Hu (Connor) [this message]

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=8516a885-3427-9b7b-0891-afd8b430788f@huawei.com \
    --to=humin29@huawei.com \
    --cc=chenbo.xia@intel.com \
    --cc=dev@dpdk.org \
    --cc=drc@linux.vnet.ibm.com \
    --cc=ferruh.yigit@intel.com \
    --cc=maxime.coquelin@redhat.com \
    --cc=thomas@monjalon.net \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.