[dpdk-dev] [PATCH] mbuf: add helpers to prefetch mbuf

2016-05-10 Thread Olivier MATZ
Hi, On 05/10/2016 12:02 AM, Wiles, Keith wrote: >> diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h >> index 529debb..e3ee0b3 100644 >> --- a/lib/librte_mbuf/rte_mbuf.h >> +++ b/lib/librte_mbuf/rte_mbuf.h >> @@ -842,6 +842,44 @@ struct rte_mbuf { >> uint16_t timesync; >> }

[dpdk-dev] [PATCH] mbuf: add helpers to prefetch mbuf

2016-05-09 Thread Wiles, Keith
>diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h >index 529debb..e3ee0b3 100644 >--- a/lib/librte_mbuf/rte_mbuf.h >+++ b/lib/librte_mbuf/rte_mbuf.h >@@ -842,6 +842,44 @@ struct rte_mbuf { > uint16_t timesync; > } __rte_cache_aligned; > >+/** >+ * Prefetch the first part

[dpdk-dev] [PATCH] mbuf: add helpers to prefetch mbuf

2016-05-09 Thread Thomas Monjalon
2016-05-09 18:18, Olivier Matz: > +/** > + * Prefetch the second part of the mbuf > + * > + * The next 64 bytes of the mbuf corresponds to fields that are used in the > + * transmit path. If the cache line of the architecture is higher than 64B, > + * this function does nothing as it is expected th

[dpdk-dev] [PATCH] mbuf: add helpers to prefetch mbuf

2016-05-09 Thread Olivier Matz
Some architectures (ex: Power8) have a cache line size of 128 bytes, so the drivers should not expect that prefetching the second part of the mbuf is valid. This commit add helpers that can be used by drivers to prefetch the rx or tx part of the mbuf, whatever the cache line size. Signed-off-by: