RE: [PATCHv6 net-next 20/31] iw_cxgb4: adjust tcp snd/rcv window based on link speed
From: Steve Wise <hidden>
Date: 2014-03-12 21:29:27
Also in:
linux-rdma
Subsystem:
cxgb4 iwarp rnic driver (iw_cxgb4), infiniband subsystem, networking [general], networking [tcp], the rest · Maintainers:
Potnuri Bharat Teja, Jason Gunthorpe, Leon Romanovsky, "David S. Miller", Eric Dumazet, Jakub Kicinski, Paolo Abeni, Neal Cardwell, Linus Torvalds
Possibly related (same subject, not in this thread)
- 2014-03-12 · RE: [PATCHv6 net-next 20/31] iw_cxgb4: adjust tcp snd/rcv window based on link speed · Steve Wise <hidden>
- 2014-03-12 · Re: [PATCHv6 net-next 20/31] iw_cxgb4: adjust tcp snd/rcv window based on link speed · David Miller <hidden>
- 2014-03-12 · RE: [PATCHv6 net-next 20/31] iw_cxgb4: adjust tcp snd/rcv window based on link speed · Steve Wise <hidden>
- 2014-03-12 · Re: [PATCHv6 net-next 20/31] iw_cxgb4: adjust tcp snd/rcv window based on link speed · David Miller <hidden>
- 2014-03-12 · [PATCHv6 net-next 20/31] iw_cxgb4: adjust tcp snd/rcv window based on link speed · Hariprasad Shenai <hidden>
quoted
quoted
You can just use the TCP settings the kernel already provides for the real TCP stack.Do you mean use sysctl_tcp_*mem, sysctl_tcp_timestamps, sysctl_tcp_window_scaling,
etc?
quoted
I'll look into this.And the socket memory limits, which we use to compute default window sizes.
How's this look (compile-tested only)? Note I had to export some of the tcp limits.
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index e2fe4a2..ff95fa3 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c@@ -81,19 +81,6 @@ int c4iw_max_read_depth = 8; module_param(c4iw_max_read_depth, int, 0644); MODULE_PARM_DESC(c4iw_max_read_depth, "Per-connection max ORD/IRD (default=8)"); -static int enable_tcp_timestamps; -module_param(enable_tcp_timestamps, int, 0644); -MODULE_PARM_DESC(enable_tcp_timestamps, "Enable tcp timestamps (default=0)"); - -static int enable_tcp_sack; -module_param(enable_tcp_sack, int, 0644); -MODULE_PARM_DESC(enable_tcp_sack, "Enable tcp SACK (default=0)"); - -static int enable_tcp_window_scaling = 1; -module_param(enable_tcp_window_scaling, int, 0644); -MODULE_PARM_DESC(enable_tcp_window_scaling, - "Enable tcp window scaling (default=1)"); - int c4iw_debug; module_param(c4iw_debug, int, 0644); MODULE_PARM_DESC(c4iw_debug, "Enable debug logging (default=0)");
@@ -126,19 +113,6 @@ static int crc_enabled = 1; module_param(crc_enabled, int, 0644); MODULE_PARM_DESC(crc_enabled, "Enable MPA CRC (default(1)=enabled)"); -static int rcv_win = 256 * 1024; -module_param(rcv_win, int, 0644); -MODULE_PARM_DESC(rcv_win, "TCP receive window in bytes (default=256KB)"); - -static int snd_win = 128 * 1024; -module_param(snd_win, int, 0644); -MODULE_PARM_DESC(snd_win, "TCP send window in bytes (default=128KB)"); - -static int adjust_win = 1; -module_param(adjust_win, int, 0644); -MODULE_PARM_DESC(adjust_win, - "Adjust TCP window based on link speed (default=1)"); - static struct workqueue_struct *workq; static struct sk_buff_head rxq;
@@ -572,7 +546,7 @@ static int send_connect(struct c4iw_ep *ep) set_wr_txq(skb, CPL_PRIORITY_SETUP, ep->ctrlq_idx); cxgb4_best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx); - wscale = compute_wscale(rcv_win); + wscale = compute_wscale(ep->rcv_win); /* * Specify the largest window that will fit in opt0. The
@@ -596,11 +570,11 @@ static int send_connect(struct c4iw_ep *ep) opt2 = RX_CHANNEL(0) | CCTRL_ECN(enable_ecn) | RSS_QUEUE_VALID | RSS_QUEUE(ep->rss_qid); - if (enable_tcp_timestamps) + if (sysctl_tcp_timestamps) opt2 |= TSTAMPS_EN(1); - if (enable_tcp_sack) + if (sysctl_tcp_sack) opt2 |= SACK_EN(1); - if (wscale && enable_tcp_window_scaling) + if (wscale && sysctl_tcp_window_scaling) opt2 |= WND_SCALE_EN(1); t4_set_arp_err_handler(skb, NULL, act_open_req_arp_failure);
@@ -1652,7 +1626,7 @@ static void send_fw_act_open_req(struct c4iw_ep *ep, unsigned intatid) req->tcb.tx_max = (__force __be32) jiffies; req->tcb.rcv_adv = htons(1); cxgb4_best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx); - wscale = compute_wscale(rcv_win); + wscale = compute_wscale(ep->rcv_win); /* * Specify the largest window that will fit in opt0. The
@@ -1679,11 +1653,11 @@ static void send_fw_act_open_req(struct c4iw_ep *ep, unsigned intatid) RX_CHANNEL(0) | CCTRL_ECN(enable_ecn) | RSS_QUEUE_VALID | RSS_QUEUE(ep->rss_qid)); - if (enable_tcp_timestamps) + if (sysctl_tcp_timestamps) req->tcb.opt2 |= (__force __be32) TSTAMPS_EN(1); - if (enable_tcp_sack) + if (sysctl_tcp_sack) req->tcb.opt2 |= (__force __be32) SACK_EN(1); - if (wscale && enable_tcp_window_scaling) + if (wscale && sysctl_tcp_window_scaling) req->tcb.opt2 |= (__force __be32) WND_SCALE_EN(1); req->tcb.opt0 = cpu_to_be64((__force u64) req->tcb.opt0); req->tcb.opt2 = cpu_to_be32((__force u32) req->tcb.opt2);
@@ -1712,11 +1686,14 @@ static int is_neg_adv(unsigned int status) static void set_tcp_window(struct c4iw_ep *ep, struct port_info *pi) { + u32 snd_win = max_t(u32, sysctl_tcp_rmem[2], sysctl_rmem_max); + u32 rcv_win = max_t(u32, sysctl_tcp_wmem[2], sysctl_wmem_max); + ep->snd_win = snd_win; ep->rcv_win = rcv_win; - if (adjust_win && pi->link_cfg.speed == 40000) { - ep->snd_win *= 4; - ep->rcv_win *= 4; + if (pi->link_cfg.speed == 40000) { + ep->snd_win = min_t(u32, ep->snd_win * 4, snd_win); + ep->rcv_win = min_t(u32, ep->rcv_win * 4, rcv_win); } PDBG("%s snd_win %d rcv_win %d\n", __func__, ep->snd_win, ep->rcv_win); }
@@ -2026,7 +2003,7 @@ static void accept_cr(struct c4iw_ep *ep, struct sk_buff *skb, skb_trim(skb, sizeof(*rpl)); skb_get(skb); cxgb4_best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx); - wscale = compute_wscale(rcv_win); + wscale = compute_wscale(ep->rcv_win); /* * Specify the largest window that will fit in opt0. The
@@ -2049,11 +2026,11 @@ static void accept_cr(struct c4iw_ep *ep, struct sk_buff *skb, opt2 = RX_CHANNEL(0) | RSS_QUEUE_VALID | RSS_QUEUE(ep->rss_qid); - if (enable_tcp_timestamps && req->tcpopt.tstamp) + if (sysctl_tcp_timestamps && req->tcpopt.tstamp) opt2 |= TSTAMPS_EN(1); - if (enable_tcp_sack && req->tcpopt.sack) + if (sysctl_tcp_sack && req->tcpopt.sack) opt2 |= SACK_EN(1); - if (wscale && enable_tcp_window_scaling) + if (wscale && sysctl_tcp_window_scaling) opt2 |= WND_SCALE_EN(1); if (enable_ecn) { const struct tcphdr *tcph;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 227cba7..65ed4e8 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c@@ -76,8 +76,11 @@ #include <net/netdma.h> int sysctl_tcp_timestamps __read_mostly = 1; +EXPORT_SYMBOL(sysctl_tcp_timestamps); int sysctl_tcp_window_scaling __read_mostly = 1; +EXPORT_SYMBOL(sysctl_tcp_window_scaling); int sysctl_tcp_sack __read_mostly = 1; +EXPORT_SYMBOL(sysctl_tcp_sack); int sysctl_tcp_fack __read_mostly = 1; int sysctl_tcp_reordering __read_mostly = TCP_FASTRETRANS_THRESH; EXPORT_SYMBOL(sysctl_tcp_reordering); --
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org More majordomo info at http://vger.kernel.org/majordomo-info.html