> Swapped the location of the private data and the local cache, > so the private data is located immediately after the mempool header, > and the local cache after that. > This way, getting the address of the private data is as simple as > adding a constant to the address of the mempool. > > The local cache is accessed by dereferencing a pointer to it anyway, so > the performance of accessing it is not affected by moving its location.
In theory, if we keep current layout, we can access local cache by just pointer arithmetic, without actual pointer de-referencing. I am not oppose to that change - it does make sense to me, and I don't know would it make any real difference in terms of performance (my guess - it wouldn't). Just another option to consider. > > Note: > The mempool private data API describes the private data as following the > mempool header; but it has been implemented differently for a long time > without causing problems, so this is considered an optimization, > not a bugfix. > > Signed-off-by: Morten Brørup <[email protected]> > --- > Supersedes: patch-169235 > ("[v2] mempool: no cache size limit") > --- > app/test/test_mempool.c | 3 +-- > lib/mempool/rte_mempool.c | 17 +++++++++++++---- > lib/mempool/rte_mempool.h | 20 ++++++-------------- > 3 files changed, 20 insertions(+), 20 deletions(-) > > diff --git a/app/test/test_mempool.c b/app/test/test_mempool.c > index 0bb051cb31..6ff8746474 100644 > --- a/app/test/test_mempool.c > +++ b/app/test/test_mempool.c > @@ -112,8 +112,7 @@ test_mempool_basic(struct rte_mempool *mp, int > use_external_cache) > GOTO_ERR(ret, out); > > printf("get private data\n"); > - if (rte_mempool_get_priv(mp) != (char *)mp + > - RTE_MEMPOOL_HEADER_SIZE(mp, mp->cache_size)) > + if (rte_mempool_get_priv(mp) != (char *)mp + sizeof(struct[] I'd say - remove that completely. From my perspective it is wrong to make assumptions on internal structure layout. > rte_mempool)) > GOTO_ERR(ret, out); > > #ifndef RTE_EXEC_ENV_FREEBSD /* rte_mem_virt2iova() not supported on bsd > */ > diff --git a/lib/mempool/rte_mempool.c b/lib/mempool/rte_mempool.c > index 04766f55d6..211763aced 100644 > --- a/lib/mempool/rte_mempool.c > +++ b/lib/mempool/rte_mempool.c > @@ -873,6 +873,13 @@ rte_mempool_create_empty(const char *name, > unsigned n, unsigned elt_size, > * cache-aligned > */ > private_data_size = RTE_CACHE_LINE_ROUNDUP(private_data_size); > + /* > + * If any private data, add padding, to guard against false sharing-like > + * effects on systems with a next-N-lines hardware prefetcher, when > + * accessing private data. > + */ > + if (private_data_size != 0) > + private_data_size += RTE_CACHE_GUARD_LINES * > RTE_CACHE_LINE_SIZE; > > /* try to allocate tailq entry */ > te = rte_zmalloc("MEMPOOL_TAILQ_ENTRY", sizeof(*te), 0); > @@ -881,8 +888,10 @@ rte_mempool_create_empty(const char *name, > unsigned n, unsigned elt_size, > goto exit_unlock; > } > > - mempool_size = RTE_MEMPOOL_HEADER_SIZE(mp, cache_size); > + mempool_size = sizeof(struct rte_mempool); > mempool_size += private_data_size; > + if (cache_size != 0) > + mempool_size += RTE_MAX_LCORE * sizeof(struct > rte_mempool_cache); > > ret = snprintf(mz_name, sizeof(mz_name), > RTE_MEMPOOL_MZ_FORMAT, name); > if (ret < 0 || ret >= (int)sizeof(mz_name)) { > @@ -896,7 +905,7 @@ rte_mempool_create_empty(const char *name, > unsigned n, unsigned elt_size, > > /* init the mempool structure */ > mp = mz->addr; > - memset(mp, 0, RTE_MEMPOOL_HEADER_SIZE(mp, cache_size)); > + memset(mp, 0, mempool_size); > ret = strlcpy(mp->name, name, sizeof(mp->name)); > if (ret < 0 || ret >= (int)sizeof(mp->name)) { > rte_errno = ENAMETOOLONG; > @@ -935,10 +944,10 @@ rte_mempool_create_empty(const char *name, > unsigned n, unsigned elt_size, > > /* > * local_cache pointer is set even if cache_size is zero. > - * The local_cache points to just past the elt_pa[] array. > + * The local_cache points to just past the private data. > */ > mp->local_cache = (struct rte_mempool_cache *) > - RTE_PTR_ADD(mp, RTE_MEMPOOL_HEADER_SIZE(mp, 0)); > + RTE_PTR_ADD(mp, sizeof(struct rte_mempool) + > private_data_size); > > /* Init all default caches. */ > if (cache_size != 0) { > diff --git a/lib/mempool/rte_mempool.h b/lib/mempool/rte_mempool.h > index 4cdbb3f778..5a81e53a9f 100644 > --- a/lib/mempool/rte_mempool.h > +++ b/lib/mempool/rte_mempool.h > @@ -278,6 +278,11 @@ struct __rte_cache_aligned rte_mempool { > */ > struct rte_mempool_debug_stats stats[RTE_MAX_LCORE + 1]; > #endif > + > + /* > + * Private data, if any, is located after the mempool header. > + * Per-lcore local cache, if any, is located after the private data. > + */ > }; > > /** Spreading among memory channels not required. */ > @@ -369,18 +374,6 @@ struct __rte_cache_aligned rte_mempool { > #define RTE_MEMPOOL_CACHE_STAT_ADD(cache, name, n) do {} while (0) > #endif > > -/** > - * @internal Calculate the size of the mempool header. > - * > - * @param mp > - * Pointer to the memory pool. > - * @param cs > - * Size of the per-lcore cache. > - */ > -#define RTE_MEMPOOL_HEADER_SIZE(mp, cs) \ > - (sizeof(*(mp)) + (((cs) == 0) ? 0 : \ > - (sizeof(struct rte_mempool_cache) * RTE_MAX_LCORE))) > - > /* return the header of a mempool object (internal) */ > static inline struct rte_mempool_objhdr * > rte_mempool_get_header(void *obj) > @@ -1902,8 +1895,7 @@ void rte_mempool_audit(struct rte_mempool *mp); > */ > static inline void *rte_mempool_get_priv(struct rte_mempool *mp) > { > - return (char *)mp + > - RTE_MEMPOOL_HEADER_SIZE(mp, mp->cache_size); > + return (void *)(mp + 1); > } > > /** > -- > 2.43.0
