fq_codel: Fair Queue Codel AQM

Fair Queue Codel packet scheduler

Principles :

- Packets are classified (internal classifier or external) on flows.
- This is a Stochastic model (as we use a hash, several flows might
                              be hashed on same slot)
- Each flow has a CoDel managed queue.
- Flows are linked onto two (Round Robin) lists,
  so that new flows have priority on old ones.

- For a given flow, packets are not reordered (CoDel uses a FIFO)
- head drops only.
- ECN capability is on by default.
- Very low memory footprint (64 bytes per flow)

tc qdisc ... fq_codel [ limit PACKETS ] [ flows number ]
                      [ target TIME ] [ interval TIME ] [ noecn ]
                      [ quantum BYTES ]

defaults : 1024 flows, 10240 packets limit, quantum : device MTU
           target : 5ms (CoDel default)
           interval : 100ms (CoDel default)

Impressive results on load :

class htb 1:1 root leaf 10: prio 0 quantum 1514 rate 200000Kbit ceil 200000Kbit burst 1475b/8 mpu 0b overhead 0b cburst 1475b/8 mpu 0b overhead 0b level 0
 Sent 43304920109 bytes 3306310 pkt (dropped 0, overlimits 0 requeues 0)
 rate 201691Kbit 28595pps backlog 0b 312p requeues 0
 lended: 3306310 borrowed: 0 giants: 0
 tokens: -912 ctokens: -912

class fq_codel 10:1735 parent 10:
 (dropped 1292, overlimits 0 requeues 0)
 backlog 15140b 10p requeues 0
  deficit 1514 count 1 lastcount 1 ldelay 7.1ms
class fq_codel 10:4524 parent 10:
 (dropped 1291, overlimits 0 requeues 0)
 backlog 16654b 11p requeues 0
  deficit 1514 count 1 lastcount 1 ldelay 7.1ms
class fq_codel 10:4e74 parent 10:
 (dropped 1290, overlimits 0 requeues 0)
 backlog 6056b 4p requeues 0
  deficit 1514 count 1 lastcount 1 ldelay 6.4ms dropping drop_next 92.0ms
class fq_codel 10:628a parent 10:
 (dropped 1289, overlimits 0 requeues 0)
 backlog 7570b 5p requeues 0
  deficit 1514 count 1 lastcount 1 ldelay 5.4ms dropping drop_next 90.9ms
class fq_codel 10:a4b3 parent 10:
 (dropped 302, overlimits 0 requeues 0)
 backlog 16654b 11p requeues 0
  deficit 1514 count 1 lastcount 1 ldelay 7.1ms
class fq_codel 10:c3c2 parent 10:
 (dropped 1284, overlimits 0 requeues 0)
 backlog 13626b 9p requeues 0
  deficit 1514 count 1 lastcount 1 ldelay 5.9ms
class fq_codel 10:d331 parent 10:
 (dropped 299, overlimits 0 requeues 0)
 backlog 15140b 10p requeues 0
  deficit 1514 count 1 lastcount 1 ldelay 7.0ms
class fq_codel 10:d526 parent 10:
 (dropped 12160, overlimits 0 requeues 0)
 backlog 35870b 211p requeues 0
  deficit 1508 count 12160 lastcount 1 ldelay 15.3ms dropping drop_next 247us
class fq_codel 10:e2c6 parent 10:
 (dropped 1288, overlimits 0 requeues 0)
 backlog 15140b 10p requeues 0
  deficit 1514 count 1 lastcount 1 ldelay 7.1ms
class fq_codel 10:eab5 parent 10:
 (dropped 1285, overlimits 0 requeues 0)
 backlog 16654b 11p requeues 0
  deficit 1514 count 1 lastcount 1 ldelay 5.9ms
class fq_codel 10:f220 parent 10:
 (dropped 1289, overlimits 0 requeues 0)
 backlog 15140b 10p requeues 0
  deficit 1514 count 1 lastcount 1 ldelay 7.1ms

qdisc htb 1: root refcnt 6 r2q 10 default 1 direct_packets_stat 0 ver 3.17
 Sent 43331086547 bytes 33092812 pkt (dropped 0, overlimits 66063544 requeues 71)
 rate 201697Kbit 28602pps backlog 0b 260p requeues 71
qdisc fq_codel 10: parent 1:1 limit 10240p flows 65536 target 5.0ms interval 100.0ms ecn
 Sent 43331086547 bytes 33092812 pkt (dropped 949359, overlimits 0 requeues 0)
 rate 201697Kbit 28602pps backlog 189352b 260p requeues 0
  maxpacket 1514 drop_overlimit 0 new_flow_count 5582 ecn_mark 125593
  new_flows_len 0 old_flows_len 11

PING 172.30.42.18 (172.30.42.18) 56(84) bytes of data.
64 bytes from 172.30.42.18: icmp_req=1 ttl=64 time=0.227 ms
64 bytes from 172.30.42.18: icmp_req=2 ttl=64 time=0.165 ms
64 bytes from 172.30.42.18: icmp_req=3 ttl=64 time=0.166 ms
64 bytes from 172.30.42.18: icmp_req=4 ttl=64 time=0.151 ms
64 bytes from 172.30.42.18: icmp_req=5 ttl=64 time=0.164 ms
64 bytes from 172.30.42.18: icmp_req=6 ttl=64 time=0.172 ms
64 bytes from 172.30.42.18: icmp_req=7 ttl=64 time=0.175 ms
64 bytes from 172.30.42.18: icmp_req=8 ttl=64 time=0.183 ms
64 bytes from 172.30.42.18: icmp_req=9 ttl=64 time=0.158 ms
64 bytes from 172.30.42.18: icmp_req=10 ttl=64 time=0.200 ms

10 packets transmitted, 10 received, 0% packet loss, time 8999ms
rtt min/avg/max/mdev = 0.151/0.176/0.227/0.022 ms

Much better than SFQ because of priority given to new flows, and fast
path dirtying less cache lines.

Signed-off-by: Eric Dumazet <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Author: edumazet

include/linux/pkt_sched.h

@@ -681,4 +681,58 @@ struct tc_codel_xstats {
 	__u32	dropping;  /* are we in dropping state ? */
 };
 
+/* FQ_CODEL */
+
+enum {
+	TCA_FQ_CODEL_UNSPEC,
+	TCA_FQ_CODEL_TARGET,
+	TCA_FQ_CODEL_LIMIT,
+	TCA_FQ_CODEL_INTERVAL,
+	TCA_FQ_CODEL_ECN,
+	TCA_FQ_CODEL_FLOWS,
+	TCA_FQ_CODEL_QUANTUM,
+	__TCA_FQ_CODEL_MAX
+};
+
+#define TCA_FQ_CODEL_MAX	(__TCA_FQ_CODEL_MAX - 1)
+
+enum {
+	TCA_FQ_CODEL_XSTATS_QDISC,
+	TCA_FQ_CODEL_XSTATS_CLASS,
+};
+
+struct tc_fq_codel_qd_stats {
+	__u32	maxpacket;	/* largest packet we've seen so far */
+	__u32	drop_overlimit; /* number of time max qdisc
+				 * packet limit was hit
+				 */
+	__u32	ecn_mark;	/* number of packets we ECN marked
+				 * instead of being dropped
+				 */
+	__u32	new_flow_count; /* number of time packets
+				 * created a 'new flow'
+				 */
+	__u32	new_flows_len;	/* count of flows in new list */
+	__u32	old_flows_len;	/* count of flows in old list */
+};
+
+struct tc_fq_codel_cl_stats {
+	__s32	deficit;
+	__u32	ldelay;		/* in-queue delay seen by most recently
+				 * dequeued packet
+				 */
+	__u32	count;
+	__u32	lastcount;
+	__u32	dropping;
+	__s32	drop_next;
+};
+
+struct tc_fq_codel_xstats {
+	__u32	type;
+	union {
+		struct tc_fq_codel_qd_stats qdisc_stats;
+		struct tc_fq_codel_cl_stats class_stats;
+	};
+};
+
 #endif

net/sched/Kconfig

@@ -261,6 +261,17 @@ config NET_SCH_CODEL
 
 	  If unsure, say N.
 
+config NET_SCH_FQ_CODEL
+	tristate "Fair Queue Controlled Delay AQM (FQ_CODEL)"
+	help
+	  Say Y here if you want to use the FQ Controlled Delay (FQ_CODEL)
+	  packet scheduling algorithm.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called sch_fq_codel.
+
+	  If unsure, say N.
+
 config NET_SCH_INGRESS
 	tristate "Ingress Qdisc"
 	depends on NET_CLS_ACT

net/sched/Makefile

@@ -38,6 +38,7 @@ obj-$(CONFIG_NET_SCH_MQPRIO)	+= sch_mqprio.o
 obj-$(CONFIG_NET_SCH_CHOKE)	+= sch_choke.o
 obj-$(CONFIG_NET_SCH_QFQ)	+= sch_qfq.o
 obj-$(CONFIG_NET_SCH_CODEL)	+= sch_codel.o
+obj-$(CONFIG_NET_SCH_FQ_CODEL)	+= sch_fq_codel.o
 
 obj-$(CONFIG_NET_CLS_U32)	+= cls_u32.o
 obj-$(CONFIG_NET_CLS_ROUTE4)	+= cls_route.o