> -----Original Message----- > From: dev [mailto:[email protected]] On Behalf Of Verma, Shally > Sent: Thursday, May 17, 2018 7:10 AM > To: Trahe, Fiona <[email protected]>; [email protected] > Cc: De Lara Guarch, Pablo <[email protected]>; Gupta, Ashish > <[email protected]>; Sahu, Sunila <[email protected]> > Subject: Re: [dpdk-dev] [PATCH] compressdev: clarify buffer size limitation > > > > >-----Original Message----- > >From: dev [mailto:[email protected]] On Behalf Of Fiona Trahe > >Sent: 16 May 2018 19:49 > >To: [email protected] > >Cc: [email protected]; [email protected] > >Subject: [dpdk-dev] [PATCH] compressdev: clarify buffer size limitation > > > >Signed-off-by: Fiona Trahe <[email protected]> > >--- > > lib/librte_compressdev/rte_comp.h | 11 +++++++++-- > > 1 file changed, 9 insertions(+), 2 deletions(-) > > > >diff --git a/lib/librte_compressdev/rte_comp.h > b/lib/librte_compressdev/rte_comp.h > >index 4c802195f..9826086b1 100644 > >--- a/lib/librte_compressdev/rte_comp.h > >+++ b/lib/librte_compressdev/rte_comp.h > >@@ -295,12 +295,19 @@ struct rte_comp_op { > > struct rte_mbuf *m_src; > > /**< source mbuf > > * The total size of the input buffer(s) can be retrieved using > >- * rte_pktmbuf_data_len(m_src) > >+ * rte_pktmbuf_data_len(m_src). The max data size which can fit in a > >+ * single mbuf is limited by the uint16_t rte_mbuf.data_len to 64k-1. > >+ * If the input data is bigger than this it can be passed to the PMD in > >+ * a chain of mbufs if the PMD's capabilities indicate it supports this. > > */ > > struct rte_mbuf *m_dst; > > /**< destination mbuf > > * The total size of the output buffer(s) can be retrieved using > >- * rte_pktmbuf_data_len(m_dst) > >+ * rte_pktmbuf_data_len(m_dst). The max data size which can fit in a > >+ * single mbuf is limited by the uint16_t rte_mbuf.data_len to 64k-1. > >+ * If the output data is expected to be bigger than this a chain of > >+ * mbufs can be passed to the PMD if the PMD's capabilities indicate > >+ * it supports this. > > */ > [Shally] It will be good idea to add bit more clarification regarding > src.offset and > dst.offset as well, that is, offset is offset from start of very first > segment of > m_src and m_dst in chained bufs.
I'd say there should be a separate patch addressing this comment. This one looks ok to me. Acked-by: Pablo de Lara <[email protected]>
