diff --git a/share/man/man4/cc_dctcp.4 b/share/man/man4/cc_dctcp.4 index c242ccd392de..5c5be4fed96e 100644 --- a/share/man/man4/cc_dctcp.4 +++ b/share/man/man4/cc_dctcp.4 @@ -28,7 +28,7 @@ .\" .\" $FreeBSD$ .\" -.Dd January 12, 2015 +.Dd July 29, 2019 .Dt CC_DCTCP 4 .Os .Sh NAME @@ -60,7 +60,7 @@ In addition, when classic ECN is used as sender and DCTCP is used as receiver, DCTCP avoids to mirror back ACKs only when the CWR flag is set in the incoming packet. .Pp -The other specifications are based on the paper and Internet Draft referenced +The other specifications are based on the paper and the RFC referenced in the .Sx SEE ALSO section below. @@ -70,16 +70,27 @@ The algorithm exposes the following tunable variables in the branch of the .Xr sysctl 3 MIB: -.Bl -tag -width ".Va alpha" +.Bl -tag -width ".Va slowstart" .It Va alpha -An initial estimator of the congestion on the link. -Default is 0. -.It Va dctcp_shift_g -An estimation gain in the alpha calculation. -Default is 16. +The initial value to estimate the congestion on the link. +The valid range is from 0 to 1024, where 1024 reduces the congestion +window to half, if a CE is observed in the first window and +.Va alpha +could not yet adjust to the congestion level on that path. +Default is 1024. +.It Va shift_g +An estimation gain in the +.Va alpha +calculation. +This influences the responsiveness when adjusting alpha +to the most recent observed window. +Valid range from 0 to 10, the default is 4, resulting in an effective +gain of 1 / ( 2 ^ +.Va shift_g +), or 1/16th. .It Va slowstart -A trigger to halve congestion window after slow start. -Default does nothing to halve window. +A flag if the congestion window should be reduced by one half after slow start. +Valid settings 0 and 1, default 0. .El .Sh SEE ALSO .Xr cc_chd 4 , @@ -108,10 +119,12 @@ Default does nothing to halve window. .Re .Rs .%A "Stephen Bensley" -.%A "Lars Eggert" .%A "Dave Thaler" -.%T "Microsoft's Datacenter TCP (DCTCP): TCP Congestion Control for Datacenters" -.%U "http://tools.ietf.org/html/draft-bensley-tcpm-dctcp-01" +.%A "Praveen Balasubramanian" +.%A "Lars Eggert" +.%A "Glenn Judd" +.%T "Data Center TCP (DCTCP): TCP Congestion Control for Data Centers" +.%U "https://tools.ietf.org/html/rfc8257" .Re .Sh HISTORY The diff --git a/sys/netinet/cc/cc_dctcp.c b/sys/netinet/cc/cc_dctcp.c index 9affd0da2b32..2e11253fb1d2 100644 --- a/sys/netinet/cc/cc_dctcp.c +++ b/sys/netinet/cc/cc_dctcp.c @@ -56,8 +56,9 @@ __FBSDID("$FreeBSD$"); #include #include -#define MAX_ALPHA_VALUE 1024 -VNET_DEFINE_STATIC(uint32_t, dctcp_alpha) = 0; +#define DCTCP_SHIFT 10 +#define MAX_ALPHA_VALUE (1<bytes_total = max(dctcp_data->bytes_total, 1); /* - * Update alpha: alpha = (1 - g) * alpha + g * F. + * Update alpha: alpha = (1 - g) * alpha + g * M. * Here: * g is weight factor * recommaded to be set to 1/16 * small g = slow convergence between competitive DCTCP flows * large g = impacts low utilization of bandwidth at switches - * F is fraction of marked segments in last RTT + * M is fraction of marked segments in last RTT * updated every RTT * Alpha must be round to 0 - MAX_ALPHA_VALUE. */ - dctcp_data->alpha = min(alpha_prev - (alpha_prev >> V_dctcp_shift_g) + - (dctcp_data->bytes_ecn << (10 - V_dctcp_shift_g)) / + dctcp_data->alpha = ulmin(alpha_prev - (alpha_prev >> V_dctcp_shift_g) + + ((uint64_t)dctcp_data->bytes_ecn << (DCTCP_SHIFT - V_dctcp_shift_g)) / dctcp_data->bytes_total, MAX_ALPHA_VALUE); /* Initialize internal parameters for next alpha calculation */ @@ -398,14 +399,10 @@ dctcp_alpha_handler(SYSCTL_HANDLER_ARGS) new = V_dctcp_alpha; error = sysctl_handle_int(oidp, &new, 0, req); if (error == 0 && req->newptr != NULL) { - if (new > 1) + if (new > MAX_ALPHA_VALUE) error = EINVAL; - else { - if (new > MAX_ALPHA_VALUE) - V_dctcp_alpha = MAX_ALPHA_VALUE; - else - V_dctcp_alpha = new; - } + else + V_dctcp_alpha = new; } return (error); @@ -420,7 +417,7 @@ dctcp_shift_g_handler(SYSCTL_HANDLER_ARGS) new = V_dctcp_shift_g; error = sysctl_handle_int(oidp, &new, 0, req); if (error == 0 && req->newptr != NULL) { - if (new > 1) + if (new > DCTCP_SHIFT) error = EINVAL; else V_dctcp_shift_g = new; @@ -454,7 +451,7 @@ SYSCTL_NODE(_net_inet_tcp_cc, OID_AUTO, dctcp, CTLFLAG_RW, NULL, SYSCTL_PROC(_net_inet_tcp_cc_dctcp, OID_AUTO, alpha, CTLFLAG_VNET|CTLTYPE_UINT|CTLFLAG_RW, &VNET_NAME(dctcp_alpha), 0, &dctcp_alpha_handler, - "IU", "dctcp alpha parameter"); + "IU", "dctcp alpha parameter at start of session"); SYSCTL_PROC(_net_inet_tcp_cc_dctcp, OID_AUTO, shift_g, CTLFLAG_VNET|CTLTYPE_UINT|CTLFLAG_RW, &VNET_NAME(dctcp_shift_g), 4,