From: Olivier MATZ <olivier.matz@6wind.com>
To: Bruce Richardson <bruce.richardson@intel.com>,
"Ananyev, Konstantin" <konstantin.ananyev@intel.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] [PATCH 2/2] Remove RTE_MBUF_REFCNT references
Date: Wed, 18 Feb 2015 11:14:42 +0100 [thread overview]
Message-ID: <54E46612.7050809@6wind.com> (raw)
In-Reply-To: <20150218100003.GA14728@bricha3-MOBL3>
On 02/18/2015 11:00 AM, Bruce Richardson wrote:
> On Wed, Feb 18, 2015 at 09:48:58AM +0000, Ananyev, Konstantin wrote:
>> Hi lads,
>>
>>> -----Original Message-----
>>> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Bruce Richardson
>>> Sent: Wednesday, February 18, 2015 9:36 AM
>>> To: Olivier MATZ
>>> Cc: dev@dpdk.org
>>> Subject: Re: [dpdk-dev] [PATCH 2/2] Remove RTE_MBUF_REFCNT references
>>>
>>> On Wed, Feb 18, 2015 at 10:16:56AM +0100, Olivier MATZ wrote:
>>>> Hi Sergio,
>>>>
>>>> On 02/16/2015 05:08 PM, Sergio Gonzalez Monroy wrote:
>>>>> This patch removes all references to RTE_MBUF_REFCNT, setting the refcnt
>>>>> field in the mbuf struct permanently.
>>>>>
>>>>> Signed-off-by: Sergio Gonzalez Monroy <sergio.gonzalez.monroy@intel.com>
>>>>
>>>> I think removing the refcount compile option goes in the right
>>>> direction. However, activating the refcount will break the applications
>>>> that reserve a private zone in mbufs. This is due to the macros
>>>> RTE_MBUF_TO_BADDR() and RTE_MBUF_FROM_BADDR() that suppose that
>>>> the beginning of the mbuf is 128 bytes (sizeof mbuf) before the
>>>> data buffer.
>>>>
>>>
>>> While I understand how the macros make certain assumptions, how does activating
>>> the refcnt specifically lead to the problems you describe? Could you explain
>>> that part in a bit more detail?
>>>
>>> Thanks,
>>> /Bruce
>>>
>>
>> Olivier, I also don't understand your concern here.
>> As I can see, that patch has nothing to do with RTE_MBUF_FROM_BADDR/ RTE_MBUF_FROM_BADDR macros.
>> They are still there, for example rte_pktmbuf_detach() still uses it to restore mbuf's buf_addr.
>> The only principal change here, is that we don't rely more on RTE_MBUF_FROM_BADDR to determine,
>> Is that indirect mbuf or not.
>> Instead we use a special falg for that purpose:
>>
>> -#define RTE_MBUF_INDIRECT(mb) (RTE_MBUF_FROM_BADDR((mb)->buf_addr) != (mb))
>> +#define RTE_MBUF_INDIRECT(mb) (mb->ol_flags & IND_ATTACHED_MBUF)
>>
>> BTW, Sergio as I said before, I think it should be:
>> #define RTE_MBUF_INDIRECT(mb) ((mb)->ol_flags & IND_ATTACHED_MBUF)
>>
>> Konstantin
>>
>>
>>>> For RTE_MBUF_TO_BADDR(), it's relatively easy to replace it. The
>>>> mbuf pool could store the size of the private size like it's done
>>>> for mbp_priv->mbuf_data_room_size. Using rte_mempool_from_obj(m)
>>>> or m->pool, we can retrieve the mbuf pool and this value, then
>>>> compute the buffer address.
>
> Agreed, that makes sense.
>
>>>>
>>>> For RTE_MBUF_FROM_BADDR(), it's more complex. We could ensure that
>>>> a backpointer to the mbuf is always located before the data buffer,
>>>> but it looks difficult to do.
>
> On the other hand, with the proposed refcnt change Sergio proposes, we no
> longer use this macro in any of the built-in mbuf handling for freeing mbufs.
> Does this need to be solved at anything other than the application level?
It's still used in __rte_pktmbuf_prefree_seg() to retrieve the
parent mbuf (direct) from the indirect mbuf beeing freed.
>>>>
>>>> Another idea would be to add a field in indirect mbufs that stores
>>>> the pointer to the "parent" mbuf.
>>>>
>>>> Regards,
>>>> Olivier
>>>>
next prev parent reply other threads:[~2015-02-18 10:14 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-02-16 16:08 [dpdk-dev] [PATCH 0/2] Removal of RTE_MBUF_REFCNT Sergio Gonzalez Monroy
2015-02-16 16:08 ` [dpdk-dev] [PATCH 1/2] mbuf: Introduce IND_ATTACHED_MBUF flag Sergio Gonzalez Monroy
2015-02-16 16:08 ` [dpdk-dev] [PATCH 2/2] Remove RTE_MBUF_REFCNT references Sergio Gonzalez Monroy
2015-02-18 9:16 ` Olivier MATZ
2015-02-18 9:35 ` Bruce Richardson
2015-02-18 9:48 ` Ananyev, Konstantin
2015-02-18 10:00 ` Bruce Richardson
2015-02-18 10:14 ` Olivier MATZ [this message]
2015-02-18 10:22 ` Ananyev, Konstantin
2015-02-18 10:22 ` Bruce Richardson
2015-02-18 10:33 ` Olivier MATZ
2015-02-18 10:37 ` Bruce Richardson
2015-02-18 10:47 ` Olivier MATZ
2015-02-18 10:47 ` Ananyev, Konstantin
2015-02-18 11:01 ` Olivier MATZ
2015-02-18 9:52 ` Olivier MATZ
2015-02-16 20:47 ` [dpdk-dev] [PATCH 0/2] Removal of RTE_MBUF_REFCNT Stephen Hemminger
2015-02-17 8:43 ` Gonzalez Monroy, Sergio
2015-02-18 11:03 ` [dpdk-dev] [PATCH v2 " Sergio Gonzalez Monroy
2015-02-18 11:03 ` [dpdk-dev] [PATCH v2 1/2] mbuf: Introduce IND_ATTACHED_MBUF flag Sergio Gonzalez Monroy
2015-02-18 11:03 ` [dpdk-dev] [PATCH v2 2/2] Remove RTE_MBUF_REFCNT references Sergio Gonzalez Monroy
2015-02-18 12:05 ` [dpdk-dev] [PATCH v2 0/2] Removal of RTE_MBUF_REFCNT Ananyev, Konstantin
2015-02-23 18:36 ` 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=54E46612.7050809@6wind.com \
--to=olivier.matz@6wind.com \
--cc=bruce.richardson@intel.com \
--cc=dev@dpdk.org \
--cc=konstantin.ananyev@intel.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).