Re: [PATCH 1/2] net: Remove ndo_xmit_flush netdev operation, use signalling instead.

2015-09-01 Thread yzhu1
On 08/26/2014 07:35 AM, David Miller wrote: As reported by Jesper Dangaard Brouer, for high packet rates the overhead of having another indirect call in the TX path is non-trivial. There is the indirect call itself, and then there is all of the reloading of the state to refetch the tail pointer

Re: [PATCH 1/2] net: Remove ndo_xmit_flush netdev operation, use signalling instead.

2015-09-01 Thread David Miller
From: yzhu1 Date: Tue, 1 Sep 2015 14:46:38 +0800 > After I applied this patch, the skb->xmit_more is not always zero. There have been thousands upon thousands of commits since that change. You should be testing the tree as it currently stands, to see if xmit_more

Re: [PATCH 1/2] net: Remove ndo_xmit_flush netdev operation, use signalling instead.

2015-09-01 Thread yzhu1
On 09/01/2015 03:00 PM, David Miller wrote: From: yzhu1 Date: Tue, 1 Sep 2015 14:46:38 +0800 After I applied this patch, the skb->xmit_more is not always zero. There have been thousands upon thousands of commits since that change. You should be testing the tree as

Re: [PATCH 1/2] net: Remove ndo_xmit_flush netdev operation, use signalling instead.

2015-09-01 Thread David Miller
From: yzhu1 Date: Tue, 1 Sep 2015 15:10:23 +0800 > After running for several days, the following messages will > appear. Then you need to figure out why the value is being set. It is initialized to zero by every SKB allocation, and only very specific controlled code

Re: [PATCH 1/2] net: Remove ndo_xmit_flush netdev operation, use signalling instead.

2015-09-01 Thread yzhu1
On 09/01/2015 04:23 PM, Daniel Borkmann wrote: On 09/01/2015 09:10 AM, yzhu1 wrote: On 09/01/2015 03:00 PM, David Miller wrote: From: yzhu1 Date: Tue, 1 Sep 2015 14:46:38 +0800 After I applied this patch, the skb->xmit_more is not always zero. There have been

Re: [PATCH 1/2] net: Remove ndo_xmit_flush netdev operation, use signalling instead.

2015-09-01 Thread Daniel Borkmann
On 09/01/2015 09:10 AM, yzhu1 wrote: On 09/01/2015 03:00 PM, David Miller wrote: From: yzhu1 Date: Tue, 1 Sep 2015 14:46:38 +0800 After I applied this patch, the skb->xmit_more is not always zero. There have been thousands upon thousands of commits since that

Re: [PATCH 1/2] net: Remove ndo_xmit_flush netdev operation, use signalling instead.

2015-09-01 Thread Alexander Duyck
On 09/01/2015 02:21 AM, yzhu1 wrote: On 09/01/2015 04:23 PM, Daniel Borkmann wrote: On 09/01/2015 09:10 AM, yzhu1 wrote: On 09/01/2015 03:00 PM, David Miller wrote: From: yzhu1 Date: Tue, 1 Sep 2015 14:46:38 +0800 After I applied this patch, the skb->xmit_more is

Re: [PATCH 1/2] net: Remove ndo_xmit_flush netdev operation, use signalling instead.

2015-09-01 Thread Paul Gortmaker
On Tue, Sep 1, 2015 at 5:21 AM, yzhu1 wrote: > On 09/01/2015 04:23 PM, Daniel Borkmann wrote: >> [...] >> >> As Dave said, please retest with something up to date, like 4.2 kernel, >> or latest -net git tree. >> >> Besides, the *upstream* xmit_more changes first went