search for: ewma_read

...d_skb->len); Hi, I looked at how ewma works, and although it is computationally efficient, and it does what it is supposed to do, initially (at the first samples) it is strongly biased towards the value that was added at the first ewma_add. I suggest that you print the values of ewma_add() and ewma_read(). If you are happy with the results, then ignore my comments. If you are not, then I can provide a version that does better for the first samples. Unfortunately, it will be slightly less efficient. Ronen. > return 0; > } > > @@ -382,16 +404,21 @@ static void receive_buf(struc...

...d_skb->len); Hi, I looked at how ewma works, and although it is computationally efficient, and it does what it is supposed to do, initially (at the first samples) it is strongly biased towards the value that was added at the first ewma_add. I suggest that you print the values of ewma_add() and ewma_read(). If you are happy with the results, then ignore my comments. If you are not, then I can provide a version that does better for the first samples. Unfortunately, it will be slightly less efficient. Ronen. > return 0; > } > > @@ -382,16 +404,21 @@ static void receive_buf(struc...

...fp_t gfp) return err; } -static int add_recvbuf_mergeable(struct receive_queue *rq, gfp_t gfp) +static unsigned int get_mergeable_buf_len(struct ewma *avg_pkt_len) { const size_t hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf); + unsigned int len; + + len = hdr_len + clamp_t(unsigned int, ewma_read(avg_pkt_len), + GOOD_PACKET_LEN, PAGE_SIZE - hdr_len); + return ALIGN(len, MERGEABLE_BUFFER_ALIGN); +} + +static int add_recvbuf_mergeable(struct receive_queue *rq, gfp_t gfp) +{ struct page_frag *alloc_frag = &rq->alloc_frag; char *buf; unsigned long ctx; int err; unsigned int l...

...fp_t gfp) return err; } -static int add_recvbuf_mergeable(struct receive_queue *rq, gfp_t gfp) +static unsigned int get_mergeable_buf_len(struct ewma *avg_pkt_len) { const size_t hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf); + unsigned int len; + + len = hdr_len + clamp_t(unsigned int, ewma_read(avg_pkt_len), + GOOD_PACKET_LEN, PAGE_SIZE - hdr_len); + return ALIGN(len, MERGEABLE_BUFFER_ALIGN); +} + +static int add_recvbuf_mergeable(struct receive_queue *rq, gfp_t gfp) +{ struct page_frag *alloc_frag = &rq->alloc_frag; char *buf; unsigned long ctx; int err; unsigned int l...

...static int add_recvbuf_mergeable(struct receive_queue *rq, gfp_t gfp) > +static unsigned int get_mergeable_buf_len(struct ewma *avg_pkt_len) > { > const size_t hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf); > + unsigned int len; > + > + len = hdr_len + clamp_t(unsigned int, ewma_read(avg_pkt_len), > + GOOD_PACKET_LEN, PAGE_SIZE - hdr_len); > + return ALIGN(len, MERGEABLE_BUFFER_ALIGN); > +} > + > +static int add_recvbuf_mergeable(struct receive_queue *rq, gfp_t gfp) > +{ > struct page_frag *alloc_frag = &rq->alloc_frag; > char *buf; > u...

...static int add_recvbuf_mergeable(struct receive_queue *rq, gfp_t gfp) > +static unsigned int get_mergeable_buf_len(struct ewma *avg_pkt_len) > { > const size_t hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf); > + unsigned int len; > + > + len = hdr_len + clamp_t(unsigned int, ewma_read(avg_pkt_len), > + GOOD_PACKET_LEN, PAGE_SIZE - hdr_len); > + return ALIGN(len, MERGEABLE_BUFFER_ALIGN); > +} > + > +static int add_recvbuf_mergeable(struct receive_queue *rq, gfp_t gfp) > +{ > struct page_frag *alloc_frag = &rq->alloc_frag; > char *buf; > u...

...E_BUFFER_MIN; return (void *) ((uintptr)base | (len >> MERGEABLE_BUFFER_SHIFT)); } /* Compute the packet buffer length for a receive queue. */ static u16 get_mergeable_buffer_len(struct receive_queue *rq) { u16 len = clamp_t(u16, MERGEABLE_BUFFER_MIN, ewma_read(&rq->avg_pkt_len), MERGEABLE_BUFFER_MAX); return ALIGN(len, MERGEABLE_BUFFER_ALIGN); } Best, Mike

...E_BUFFER_MIN; return (void *) ((uintptr)base | (len >> MERGEABLE_BUFFER_SHIFT)); } /* Compute the packet buffer length for a receive queue. */ static u16 get_mergeable_buffer_len(struct receive_queue *rq) { u16 len = clamp_t(u16, MERGEABLE_BUFFER_MIN, ewma_read(&rq->avg_pkt_len), MERGEABLE_BUFFER_MAX); return ALIGN(len, MERGEABLE_BUFFER_ALIGN); } Best, Mike

skb_page_frag_refill currently permits only order-0 page allocs unless GFP_WAIT is used. Change skb_page_frag_refill to attempt higher-order page allocations whether or not GFP_WAIT is used. If memory cannot be allocated, the allocator will fall back to successively smaller page allocs (down to order-0 page allocs). This change brings skb_page_frag_refill in line with the existing page allocation

skb_page_frag_refill currently permits only order-0 page allocs unless GFP_WAIT is used. Change skb_page_frag_refill to attempt higher-order page allocations whether or not GFP_WAIT is used. If memory cannot be allocated, the allocator will fall back to successively smaller page allocs (down to order-0 page allocs). This change brings skb_page_frag_refill in line with the existing page allocation

skb_page_frag_refill currently permits only order-0 page allocs unless GFP_WAIT is used. Change skb_page_frag_refill to attempt higher-order page allocations whether or not GFP_WAIT is used. If memory cannot be allocated, the allocator will fall back to successively smaller page allocs (down to order-0 page allocs). This change brings skb_page_frag_refill in line with the existing page allocation

skb_page_frag_refill currently permits only order-0 page allocs unless GFP_WAIT is used. Change skb_page_frag_refill to attempt higher-order page allocations whether or not GFP_WAIT is used. If memory cannot be allocated, the allocator will fall back to successively smaller page allocs (down to order-0 page allocs). This change brings skb_page_frag_refill in line with the existing page allocation

The virtio-net device currently uses aligned MTU-sized mergeable receive packet buffers. Network throughput for workloads with large average packet size can be improved by posting larger receive packet buffers. However, due to SKB truesize effects, posting large (e.g, PAGE_SIZE) buffers reduces the throughput of workloads that do not benefit from GRO and have no large inbound packets. This

The virtio-net device currently uses aligned MTU-sized mergeable receive packet buffers. Network throughput for workloads with large average packet size can be improved by posting larger receive packet buffers. However, due to SKB truesize effects, posting large (e.g, PAGE_SIZE) buffers reduces the throughput of workloads that do not benefit from GRO and have no large inbound packets. This

...> I looked at how ewma works, and although it is computationally efficient, > and it does what it is supposed to do, initially (at the first samples) it is strongly > biased towards the value that was added at the first ewma_add. > I suggest that you print the values of ewma_add() and ewma_read(). If you are > happy with the results, then ignore my comments. If you are not, then I can > provide a version that does better for the first samples. > Unfortunately, it will be slightly less efficient. Value is clamped by (GOOD_PACKET_LEN, PAGE_SIZE - hdr_len) So initial value is cons...

...irtio buffer to unsigned long immediately and pass that around everywhere. > /* Compute the packet buffer length for a receive queue. */ > static u16 get_mergeable_buffer_len(struct receive_queue *rq) { > u16 len = clamp_t(u16, MERGEABLE_BUFFER_MIN, > ewma_read(&rq->avg_pkt_len), > MERGEABLE_BUFFER_MAX); > return ALIGN(len, MERGEABLE_BUFFER_ALIGN); > } > > Best, > > Mike

To ensure ewma_read() without a lock returns a valid but possibly out of date average, modify ewma_add() by using ACCESS_ONCE to prevent intermediate wrong values from being written to avg->internal. Suggested-by: Eric Dumazet <eric.dumazet at gmail.com> Signed-off-by: Michael Dalton <mwdalton at google.c...

The virtio-net device currently uses aligned MTU-sized mergeable receive packet buffers. Network throughput for workloads with large average packet size can be improved by posting larger receive packet buffers. However, due to SKB truesize effects, posting large (e.g, PAGE_SIZE) buffers reduces the throughput of workloads that do not benefit from GRO and have no large inbound packets. This

The virtio-net device currently uses aligned MTU-sized mergeable receive packet buffers. Network throughput for workloads with large average packet size can be improved by posting larger receive packet buffers. However, due to SKB truesize effects, posting large (e.g, PAGE_SIZE) buffers reduces the throughput of workloads that do not benefit from GRO and have no large inbound packets. This

...00,18 +638,30 @@ static int add_recvbuf_big(struct receive_queue *rq, gfp_t gfp) return err; } +static unsigned int get_mergeable_buf_len(struct ewma *avg_pkt_len) +{ + const size_t hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf); + unsigned int len; + + len = hdr_len + clamp_t(unsigned int, ewma_read(avg_pkt_len), + GOOD_PACKET_LEN, PAGE_SIZE - hdr_len); + return ALIGN(len, L1_CACHE_BYTES); +} + static int add_recvbuf_mergeable(struct receive_queue *rq, gfp_t gfp) { const unsigned int ring_size = rq->mrg_buf_ctx_size; - const size_t hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf);...