From: Alexander Drozdov
Date: Tue, 24 Feb 2015 08:18:28 +0300
> Before da413eec729d ("packet: Fixed TPACKET V3 to signal poll when block is
> closed rather than every packet") poll listening for an af_packet socket was
> not signaled if there was no packets to process. After the patch poll is
> s
Before da413eec729d ("packet: Fixed TPACKET V3 to signal poll when block is
closed rather than every packet") poll listening for an af_packet socket was
not signaled if there was no packets to process. After the patch poll is
signaled evety time when block retire timer expires. That happens because
On Thu, Feb 5, 2015 at 10:54 PM, Alexander Drozdov wrote:
> On 05.02.2015 23:01:38 +0300 Willem de Bruijn wrote:
>>
>> On Wed, Feb 4, 2015 at 9:58 PM, Alexander Drozdov
>> wrote:
>>>
>>> Don't close an empty block on timeout. Its meaningless to
>>> pass it to the user. Moreover, passing empty blo
On 05.02.2015 23:01:38 +0300 Willem de Bruijn wrote:
On Wed, Feb 4, 2015 at 9:58 PM, Alexander Drozdov wrote:
Don't close an empty block on timeout. Its meaningless to
pass it to the user. Moreover, passing empty blocks wastes
CPU & buffer space increasing probability of packets
dropping on sma
On 06.02.2015 00:16:30 +0300 Guy Harris wrote:
On Feb 5, 2015, at 12:01 PM, Willem de Bruijn wrote:
On Wed, Feb 4, 2015 at 9:58 PM, Alexander Drozdov wrote:
Don't close an empty block on timeout. Its meaningless to
pass it to the user. Moreover, passing empty blocks wastes
CPU & buffer spac
On Feb 5, 2015, at 12:01 PM, Willem de Bruijn wrote:
> On Wed, Feb 4, 2015 at 9:58 PM, Alexander Drozdov
> wrote:
>> Don't close an empty block on timeout. Its meaningless to
>> pass it to the user. Moreover, passing empty blocks wastes
>> CPU & buffer space increasing probability of packets
>
On Wed, Feb 4, 2015 at 9:58 PM, Alexander Drozdov wrote:
> Don't close an empty block on timeout. Its meaningless to
> pass it to the user. Moreover, passing empty blocks wastes
> CPU & buffer space increasing probability of packets
> dropping on small timeouts.
>
> Side effect of this patch is in
Don't close an empty block on timeout. Its meaningless to
pass it to the user. Moreover, passing empty blocks wastes
CPU & buffer space increasing probability of packets
dropping on small timeouts.
Side effect of this patch is indefinite user-space wait
in poll on idle links. But, I believe its be
8 matches
Mail list logo