On 8 September 2016 at 11:53, Maxim Uvarov <[email protected]> wrote:
> Remove todo around copying packet data from > shared pool as it's not a bug and can be > considered as future request. But left small > comment that we coping packet data to make > it more visible. > https://bugs.linaro.org/show_bug.cgi?id=2408 > > Signed-off-by: Maxim Uvarov <[email protected]> > I think this is reasonable, if someone starts to use this I assume we will get patches to remove the copy becasue the performance will suffer. Reviewed-by: Mike Holmes <[email protected]> > --- > platform/linux-generic/pktio/ipc.c | 7 +------ > 1 file changed, 1 insertion(+), 6 deletions(-) > > diff --git a/platform/linux-generic/pktio/ipc.c b/platform/linux-generic/ > pktio/ipc.c > index b779ab7..c1f28db 100644 > --- a/platform/linux-generic/pktio/ipc.c > +++ b/platform/linux-generic/pktio/ipc.c > @@ -373,11 +373,6 @@ static int _ipc_slave_start(pktio_entry_t > *pktio_entry) > pinfo->master.mdata_offset; > pktio_entry->s.ipc.pkt_size = pinfo->master.shm_pkt_size; > > - /* @todo: to simplify in odp-linux implementation we create pool > for > - * packets from IPC queue. On receive implementation copies > packets to > - * that pool. Later we can try to reuse original pool without > packets > - * copying. (pkt refcounts needs to be implemented). > - */ > _ipc_export_pool(pinfo, pktio_entry->s.ipc.pool); > > odp_atomic_store_u32(&pktio_entry->s.ipc.ready, 1); > @@ -573,7 +568,7 @@ static int ipc_pktio_recv_lockless(pktio_entry_t > *pktio_entry, > (PKTIO_TYPE_IPC_SLAVE == > pktio_entry->s.ipc.type)); > > - /* @todo fix copy packet!!! */ > + /* Copy packet data from shared pool to local pool. */ > memcpy(pkt_data, remote_pkt_data, phdr.frame_len); > > /* Copy packets L2, L3 parsed offsets and size */ > -- > 2.7.1.250.gff4ea60 > > -- Mike Holmes Program Manager - Linaro Networking Group Linaro.org <http://www.linaro.org/> *│ *Open source software for ARM SoCs "Work should be fun and collaborative, the rest follows"
