Re: [bpf-next V2 PATCH 10/15] xdp: rhashtable with allocator ID to pointer mapping

2018-03-21 Thread Jason Wang
On 2018年03月20日 22:27, Jesper Dangaard Brouer wrote: On Tue, 20 Mar 2018 10:26:50 +0800 Jason Wang wrote: On 2018年03月19日 17:48, Jesper Dangaard Brouer wrote: On Fri, 16 Mar 2018 16:45:30 +0800 Jason Wang wrote: On 2018年03月10日 00:07, Jesper Dangaard Brouer wrote: On Fri, 9 Mar 2018 21:0

Re: [bpf-next V2 PATCH 10/15] xdp: rhashtable with allocator ID to pointer mapping

2018-03-20 Thread Jesper Dangaard Brouer
On Tue, 20 Mar 2018 10:26:50 +0800 Jason Wang wrote: > On 2018年03月19日 17:48, Jesper Dangaard Brouer wrote: > > On Fri, 16 Mar 2018 16:45:30 +0800 > > Jason Wang wrote: > > > >> On 2018年03月10日 00:07, Jesper Dangaard Brouer wrote: > >>> On Fri, 9 Mar 2018 21:07:36 +0800 > >>> Jason Wang wrote

Re: [bpf-next V2 PATCH 10/15] xdp: rhashtable with allocator ID to pointer mapping

2018-03-19 Thread Jason Wang
On 2018年03月19日 17:48, Jesper Dangaard Brouer wrote: On Fri, 16 Mar 2018 16:45:30 +0800 Jason Wang wrote: On 2018年03月10日 00:07, Jesper Dangaard Brouer wrote: On Fri, 9 Mar 2018 21:07:36 +0800 Jason Wang wrote: Use the IDA infrastructure for getting a cyclic increasing ID number, that is

Re: [bpf-next V2 PATCH 10/15] xdp: rhashtable with allocator ID to pointer mapping

2018-03-19 Thread Jesper Dangaard Brouer
On Fri, 16 Mar 2018 16:45:30 +0800 Jason Wang wrote: > On 2018年03月10日 00:07, Jesper Dangaard Brouer wrote: > > On Fri, 9 Mar 2018 21:07:36 +0800 > > Jason Wang wrote: > > > > Use the IDA infrastructure for getting a cyclic increasing ID number, > > that is used for keeping track of eac

Re: [bpf-next V2 PATCH 10/15] xdp: rhashtable with allocator ID to pointer mapping

2018-03-16 Thread Jason Wang
On 2018年03月10日 00:07, Jesper Dangaard Brouer wrote: On Fri, 9 Mar 2018 21:07:36 +0800 Jason Wang wrote: Use the IDA infrastructure for getting a cyclic increasing ID number, that is used for keeping track of each registered allocator per RX-queue xdp_rxq_info. Signed-off-by: Jesper Dangaard

Re: [bpf-next V2 PATCH 10/15] xdp: rhashtable with allocator ID to pointer mapping

2018-03-09 Thread Jesper Dangaard Brouer
On Fri, 9 Mar 2018 21:07:36 +0800 Jason Wang wrote: > >>> Use the IDA infrastructure for getting a cyclic increasing ID number, > >>> that is used for keeping track of each registered allocator per > >>> RX-queue xdp_rxq_info. > >>> > >>> Signed-off-by: Jesper Dangaard Brouer > >> A stupid q

Re: [bpf-next V2 PATCH 10/15] xdp: rhashtable with allocator ID to pointer mapping

2018-03-09 Thread Jason Wang
On 2018年03月09日 17:37, Jesper Dangaard Brouer wrote: On Fri, 9 Mar 2018 16:08:58 +0800 Jason Wang wrote: On 2018年03月08日 21:08, Jesper Dangaard Brouer wrote: Use the IDA infrastructure for getting a cyclic increasing ID number, that is used for keeping track of each registered allocator per R

Re: [bpf-next V2 PATCH 10/15] xdp: rhashtable with allocator ID to pointer mapping

2018-03-09 Thread Jesper Dangaard Brouer
On Fri, 9 Mar 2018 16:08:58 +0800 Jason Wang wrote: > On 2018年03月08日 21:08, Jesper Dangaard Brouer wrote: > > Use the IDA infrastructure for getting a cyclic increasing ID number, > > that is used for keeping track of each registered allocator per > > RX-queue xdp_rxq_info. Instead of using the

Re: [bpf-next V2 PATCH 10/15] xdp: rhashtable with allocator ID to pointer mapping

2018-03-09 Thread Jason Wang
On 2018年03月08日 21:08, Jesper Dangaard Brouer wrote: Use the IDA infrastructure for getting a cyclic increasing ID number, that is used for keeping track of each registered allocator per RX-queue xdp_rxq_info. Instead of using the IDR infrastructure, which uses a radix tree, use a dynamic rhash

[bpf-next V2 PATCH 10/15] xdp: rhashtable with allocator ID to pointer mapping

2018-03-08 Thread Jesper Dangaard Brouer
Use the IDA infrastructure for getting a cyclic increasing ID number, that is used for keeping track of each registered allocator per RX-queue xdp_rxq_info. Instead of using the IDR infrastructure, which uses a radix tree, use a dynamic rhashtable, for creating ID to pointer lookup table, because