| Message ID | 161419300618.2718959.11165518489200268845.stgit@firesoul (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | [RFC,net-next,1/3] net: page_pool: refactor dma_map into own function page_pool_dma_map | expand |
Hi Jesper, On Wed, Feb 24, 2021 at 07:56:46PM +0100, Jesper Dangaard Brouer wrote: > There are cases where the page_pool need to refill with pages from the > page allocator. Some workloads cause the page_pool to release pages > instead of recycling these pages. > > For these workload it can improve performance to bulk alloc pages from > the page-allocator to refill the alloc cache. > > For XDP-redirect workload with 100G mlx5 driver (that use page_pool) > redirecting xdp_frame packets into a veth, that does XDP_PASS to create > an SKB from the xdp_frame, which then cannot return the page to the > page_pool. In this case, we saw[1] an improvement of 18.8% from using > the alloc_pages_bulk API (3,677,958 pps -> 4,368,926 pps). > > [1] https://github.com/xdp-project/xdp-project/blob/master/areas/mem/page_pool06_alloc_pages_bulk.org > > Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> [...] > + /* Remaining pages store in alloc.cache */ > + list_for_each_entry_safe(page, next, &page_list, lru) { > + list_del(&page->lru); > + if (pp_flags & PP_FLAG_DMA_MAP) { > + page = page_pool_dma_map(pool, page); > + if (!page) As I commented on the previous patch, i'd prefer the put_page() here to be explicitly called, instead of hiding in the page_pool_dma_map() > + continue; > + } > + if (likely(pool->alloc.count < PP_ALLOC_CACHE_SIZE)) { > + pool->alloc.cache[pool->alloc.count++] = page; > + pool->pages_state_hold_cnt++; > + trace_page_pool_state_hold(pool, page, > + pool->pages_state_hold_cnt); > + } else { > + put_page(page); > + } > + } > +out: > if (pool->p.flags & PP_FLAG_DMA_MAP) { > - page = page_pool_dma_map(pool, page); > - if (!page) > + first_page = page_pool_dma_map(pool, first_page); > + if (!first_page) > return NULL; > } > [...] Cheers /Ilias
On Wed, 24 Feb 2021 22:15:22 +0200 Ilias Apalodimas <ilias.apalodimas@linaro.org> wrote: > Hi Jesper, > > On Wed, Feb 24, 2021 at 07:56:46PM +0100, Jesper Dangaard Brouer wrote: > > There are cases where the page_pool need to refill with pages from the > > page allocator. Some workloads cause the page_pool to release pages > > instead of recycling these pages. > > > > For these workload it can improve performance to bulk alloc pages from > > the page-allocator to refill the alloc cache. > > > > For XDP-redirect workload with 100G mlx5 driver (that use page_pool) > > redirecting xdp_frame packets into a veth, that does XDP_PASS to create > > an SKB from the xdp_frame, which then cannot return the page to the > > page_pool. In this case, we saw[1] an improvement of 18.8% from using > > the alloc_pages_bulk API (3,677,958 pps -> 4,368,926 pps). > > > > [1] https://github.com/xdp-project/xdp-project/blob/master/areas/mem/page_pool06_alloc_pages_bulk.org > > > > Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> > > [...] > > > + /* Remaining pages store in alloc.cache */ > > + list_for_each_entry_safe(page, next, &page_list, lru) { > > + list_del(&page->lru); > > + if (pp_flags & PP_FLAG_DMA_MAP) { > > + page = page_pool_dma_map(pool, page); > > + if (!page) > > As I commented on the previous patch, i'd prefer the put_page() here to be > explicitly called, instead of hiding in the page_pool_dma_map() I fully agree. I will fixup the code. > > + continue; > > + } > > + if (likely(pool->alloc.count < PP_ALLOC_CACHE_SIZE)) { > > + pool->alloc.cache[pool->alloc.count++] = page; > > + pool->pages_state_hold_cnt++; > > + trace_page_pool_state_hold(pool, page, > > + pool->pages_state_hold_cnt); > > + } else { > > + put_page(page); > > + } > > + } > > +out: > > if (pool->p.flags & PP_FLAG_DMA_MAP) { > > - page = page_pool_dma_map(pool, page); > > - if (!page) > > + first_page = page_pool_dma_map(pool, first_page); > > + if (!first_page) > > return NULL; > > } > > > [...]
diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 50d52aa6fbeb..e0ae95fc59f0 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -210,44 +210,61 @@ noinline static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, gfp_t _gfp) { - struct page *page; + const int bulk = PP_ALLOC_CACHE_REFILL; + struct page *page, *next, *first_page; + unsigned int pp_flags = pool->p.flags; + unsigned int pp_order = pool->p.order; + int pp_nid = pool->p.nid; + LIST_HEAD(page_list); gfp_t gfp = _gfp; - /* We could always set __GFP_COMP, and avoid this branch, as - * prep_new_page() can handle order-0 with __GFP_COMP. - */ - if (pool->p.order) + /* Don't support bulk alloc for high-order pages */ + if (unlikely(pp_order)) { gfp |= __GFP_COMP; + first_page = alloc_pages_node(pp_nid, gfp, pp_order); + if (unlikely(!first_page)) + return NULL; + goto out; + } - /* FUTURE development: - * - * Current slow-path essentially falls back to single page - * allocations, which doesn't improve performance. This code - * need bulk allocation support from the page allocator code. - */ - - /* Cache was empty, do real allocation */ -#ifdef CONFIG_NUMA - page = alloc_pages_node(pool->p.nid, gfp, pool->p.order); -#else - page = alloc_pages(gfp, pool->p.order); -#endif - if (!page) + if (unlikely(!__alloc_pages_bulk_nodemask(gfp, pp_nid, NULL, + bulk, &page_list))) return NULL; + /* First page is extracted and returned to caller */ + first_page = list_first_entry(&page_list, struct page, lru); + list_del(&first_page->lru); + + /* Remaining pages store in alloc.cache */ + list_for_each_entry_safe(page, next, &page_list, lru) { + list_del(&page->lru); + if (pp_flags & PP_FLAG_DMA_MAP) { + page = page_pool_dma_map(pool, page); + if (!page) + continue; + } + if (likely(pool->alloc.count < PP_ALLOC_CACHE_SIZE)) { + pool->alloc.cache[pool->alloc.count++] = page; + pool->pages_state_hold_cnt++; + trace_page_pool_state_hold(pool, page, + pool->pages_state_hold_cnt); + } else { + put_page(page); + } + } +out: if (pool->p.flags & PP_FLAG_DMA_MAP) { - page = page_pool_dma_map(pool, page); - if (!page) + first_page = page_pool_dma_map(pool, first_page); + if (!first_page) return NULL; } /* Track how many pages are held 'in-flight' */ pool->pages_state_hold_cnt++; - - trace_page_pool_state_hold(pool, page, pool->pages_state_hold_cnt); + trace_page_pool_state_hold(pool, first_page, pool->pages_state_hold_cnt); /* When page just alloc'ed is should/must have refcnt 1. */ - return page; + return first_page; } /* For using page_pool replace: alloc_pages() API calls, but provide
There are cases where the page_pool need to refill with pages from the page allocator. Some workloads cause the page_pool to release pages instead of recycling these pages. For these workload it can improve performance to bulk alloc pages from the page-allocator to refill the alloc cache. For XDP-redirect workload with 100G mlx5 driver (that use page_pool) redirecting xdp_frame packets into a veth, that does XDP_PASS to create an SKB from the xdp_frame, which then cannot return the page to the page_pool. In this case, we saw[1] an improvement of 18.8% from using the alloc_pages_bulk API (3,677,958 pps -> 4,368,926 pps). [1] https://github.com/xdp-project/xdp-project/blob/master/areas/mem/page_pool06_alloc_pages_bulk.org Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> --- net/core/page_pool.c | 65 ++++++++++++++++++++++++++++++++------------------ 1 file changed, 41 insertions(+), 24 deletions(-)