From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: Slow speed of tcp connections in a network namespace Date: Sat, 29 Dec 2012 19:58:36 +0100 Message-ID: <1356807516.4102.4.camel@edumazet-laptop> References: <20121229092417.GA4038@paralelels.com> <1356789203.21409.3923.camel@edumazet-glaptop> <20121229145030.GA7959@paralelels.com> <1356802828.21409.4623.camel@edumazet-glaptop> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: netdev@vger.kernel.org, vvs@parallels.com, =?UTF-8?Q?Micha=C5=82_Miros=C5=82aw?= To: Andrew Vagin Return-path: Received: from mail-da0-f54.google.com ([209.85.210.54]:53275 "EHLO mail-da0-f54.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753091Ab2L2S6j (ORCPT ); Sat, 29 Dec 2012 13:58:39 -0500 Received: by mail-da0-f54.google.com with SMTP id n2so5269396dad.41 for ; Sat, 29 Dec 2012 10:58:38 -0800 (PST) In-Reply-To: <1356802828.21409.4623.camel@edumazet-glaptop> Sender: netdev-owner@vger.kernel.org List-ID: Le samedi 29 d=C3=A9cembre 2012 =C3=A0 09:40 -0800, Eric Dumazet a =C3=A9= crit : >=20 > Please post your new tcpdump then ;) >=20 > also post "netstat -s" from root and test ns after your wgets Also try following bnx2 patch. It should help GRO / TCP coalesce bnx2 should be the last driver not using skb head_frag diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/etherne= t/broadcom/bnx2.c index a1adfaf..08a2d40 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -2726,6 +2726,14 @@ bnx2_free_rx_page(struct bnx2 *bp, struct bnx2_r= x_ring_info *rxr, u16 index) rx_pg->page =3D NULL; } =20 +static void bnx2_frag_free(const struct bnx2 *bp, void *data) +{ + if (bp->rx_frag_size) + put_page(virt_to_head_page(data)); + else + kfree(data); +} + static inline int bnx2_alloc_rx_data(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr, u16= index, gfp_t gfp) { @@ -2735,7 +2743,10 @@ bnx2_alloc_rx_data(struct bnx2 *bp, struct bnx2_= rx_ring_info *rxr, u16 index, gf struct bnx2_rx_bd *rxbd =3D &rxr->rx_desc_ring[BNX2_RX_RING(index)][BNX2_RX_IDX(index)]; =20 - data =3D kmalloc(bp->rx_buf_size, gfp); + if (bp->rx_frag_size) + data =3D netdev_alloc_frag(bp->rx_frag_size); + else + data =3D kmalloc(bp->rx_buf_size, gfp); if (!data) return -ENOMEM; =20 @@ -2744,7 +2755,7 @@ bnx2_alloc_rx_data(struct bnx2 *bp, struct bnx2_r= x_ring_info *rxr, u16 index, gf bp->rx_buf_use_size, PCI_DMA_FROMDEVICE); if (dma_mapping_error(&bp->pdev->dev, mapping)) { - kfree(data); + bnx2_frag_free(bp, data); return -EIO; } =20 @@ -3014,9 +3025,9 @@ error: =20 dma_unmap_single(&bp->pdev->dev, dma_addr, bp->rx_buf_use_size, PCI_DMA_FROMDEVICE); - skb =3D build_skb(data, 0); + skb =3D build_skb(data, bp->rx_frag_size); if (!skb) { - kfree(data); + bnx2_frag_free(bp, data); goto error; } skb_reserve(skb, ((u8 *)get_l2_fhdr(data) - data) + BNX2_RX_OFFSET); @@ -5358,6 +5369,10 @@ bnx2_set_rx_ring_size(struct bnx2 *bp, u32 size) /* hw alignment + build_skb() overhead*/ bp->rx_buf_size =3D SKB_DATA_ALIGN(bp->rx_buf_use_size + BNX2_RX_ALIG= N) + NET_SKB_PAD + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + if (bp->rx_buf_size <=3D PAGE_SIZE) + bp->rx_frag_size =3D bp->rx_buf_size; + else + bp->rx_frag_size =3D 0; bp->rx_jumbo_thresh =3D rx_size - BNX2_RX_OFFSET; bp->rx_ring_size =3D size; bp->rx_max_ring =3D bnx2_find_max_ring(size, BNX2_MAX_RX_RINGS); @@ -5436,7 +5451,7 @@ bnx2_free_rx_skbs(struct bnx2 *bp) =20 rx_buf->data =3D NULL; =20 - kfree(data); + bnx2_frag_free(bp, data); } for (j =3D 0; j < bp->rx_max_pg_ring_idx; j++) bnx2_free_rx_page(bp, rxr, j); diff --git a/drivers/net/ethernet/broadcom/bnx2.h b/drivers/net/etherne= t/broadcom/bnx2.h index 172efbe..11f5dee 100644 --- a/drivers/net/ethernet/broadcom/bnx2.h +++ b/drivers/net/ethernet/broadcom/bnx2.h @@ -6804,6 +6804,7 @@ struct bnx2 { =20 u32 rx_buf_use_size; /* useable size */ u32 rx_buf_size; /* with alignment */ + u32 rx_frag_size; /* 0 if kmalloced(), or rx_buf_size */ u32 rx_copy_thresh; u32 rx_jumbo_thresh; u32 rx_max_ring_idx;