lkml.org 
[lkml]   [2021]   [Apr]   [8]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH net v4] atl1c: move tx cleanup processing out of interrupt
On 2021-04-07 19:55, Eric Dumazet wrote:
> On 4/6/21 4:49 PM, Gatis Peisenieks wrote:
>> Tx queue cleanup happens in interrupt handler on same core as rx queue
>> processing. Both can take considerable amount of processing in high
>> packet-per-second scenarios.
>>
>> Sending big amounts of packets can stall the rx processing which is
>> unfair
>> and also can lead to out-of-memory condition since __dev_kfree_skb_irq
>> queues the skbs for later kfree in softirq which is not allowed to
>> happen
>> with heavy load in interrupt handler.
>>
>
> [ ... ]
>
>> diff --git a/net/core/dev.c b/net/core/dev.c
>> index 0f72ff5d34ba..489ac60b530c 100644
>> --- a/net/core/dev.c
>> +++ b/net/core/dev.c
>> @@ -6789,6 +6789,7 @@ int dev_set_threaded(struct net_device *dev,
>> bool threaded)
>>
>>      return err;
>>  }
>> +EXPORT_SYMBOL(dev_set_threaded);
>>
>>  void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
>>              int (*poll)(struct napi_struct *, int), int weight)
>
> This has already been done in net-next
>
> Please base your patch on top of net-next, this can not be backported
> to old
> versions anyway, without some amount of pain.

Thank you Eric, for heads up, the v5 patch sent for net-next in response
to
David Miller comment already does that.

\
 
 \ /
  Last update: 2021-04-08 07:22    [W:0.075 / U:0.272 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site