From 95400b975dd32d2398ecff4dcc6f7bf0ffbd725f Mon Sep 17 00:00:00 2001 From: "Mohit P. Tahiliani" Date: Tue, 26 Feb 2019 00:40:00 +0530 Subject: net: sched: pie: add derandomization mechanism Random dropping of packets to achieve latency control may introduce outlier situations where packets are dropped too close to each other or too far from each other. This can cause the real drop percentage to temporarily deviate from the intended drop probability. In certain scenarios, such as a small number of simultaneous TCP flows, these deviations can cause significant deviations in link utilization and queuing latency. RFC 8033 suggests using a derandomization mechanism to avoid these deviations. Signed-off-by: Mohit P. Tahiliani Signed-off-by: Dhaval Khandla Signed-off-by: Hrishikesh Hiraskar Signed-off-by: Manish Kumar B Signed-off-by: Sachin D. Patil Signed-off-by: Leslie Monis Acked-by: Dave Taht Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- net/sched/sch_pie.c | 28 +++++++++++++++++++++++++++- 1 file changed, 27 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index 30f158582499..916b878d3491 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -55,8 +55,10 @@ struct pie_vars { psched_time_t qdelay_old; u64 dq_count; /* measured in bytes */ psched_time_t dq_tstamp; /* drain rate */ + u64 accu_prob; /* accumulated drop probability */ u32 avg_dq_rate; /* bytes per pschedtime tick,scaled */ u32 qlen_old; /* in bytes */ + u8 accu_prob_overflows; /* overflows of accu_prob */ }; /* statistics gathering */ @@ -91,9 +93,11 @@ static void pie_params_init(struct pie_params *params) static void pie_vars_init(struct pie_vars *vars) { vars->dq_count = DQCOUNT_INVALID; + vars->accu_prob = 0; vars->avg_dq_rate = 0; /* default of 150 ms in pschedtime */ vars->burst_time = PSCHED_NS2TICKS(150 * NSEC_PER_MSEC); + vars->accu_prob_overflows = 0; } static bool drop_early(struct Qdisc *sch, u32 packet_size) @@ -128,9 +132,29 @@ static bool drop_early(struct Qdisc *sch, u32 packet_size) else local_prob = q->vars.prob; + if (local_prob == 0) { + q->vars.accu_prob = 0; + q->vars.accu_prob_overflows = 0; + } + + if (local_prob > MAX_PROB - q->vars.accu_prob) + q->vars.accu_prob_overflows++; + + q->vars.accu_prob += local_prob; + + if (q->vars.accu_prob_overflows == 0 && + q->vars.accu_prob < (MAX_PROB / 100) * 85) + return false; + if (q->vars.accu_prob_overflows == 8 && + q->vars.accu_prob >= MAX_PROB / 2) + return true; + prandom_bytes(&rnd, 8); - if (rnd < local_prob) + if (rnd < local_prob) { + q->vars.accu_prob = 0; + q->vars.accu_prob_overflows = 0; return true; + } return false; } @@ -168,6 +192,8 @@ static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, out: q->stats.dropped++; + q->vars.accu_prob = 0; + q->vars.accu_prob_overflows = 0; return qdisc_drop(skb, sch, to_free); } -- cgit v1.2.3-59-g8ed1b