Commit dca145ff authored by Eric Dumazet's avatar Eric Dumazet Committed by David S. Miller
Browse files

tcp: allow for bigger reordering level 



While testing upcoming Yaogong patch (converting out of order queue
into an RB tree), I hit the max reordering level of linux TCP stack.

Reordering level was limited to 127 for no good reason, and some
network setups [1] can easily reach this limit and get limited
throughput.

Allow a new max limit of 300, and add a sysctl to allow admins to even
allow bigger (or lower) values if needed.

[1] Aggregation of links, per packet load balancing, fabrics not doing
 deep packet inspections, alternative TCP congestion modules...

Signed-off-by: default avatarEric Dumazet <edumazet@google.com>
Cc: Yaogong Wang <wygivan@google.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 7aef06db

Documentation/networking/bonding.txt

+2 −5
Original line number Diff line number Diff line
@@ -2230,11 +2230,8 @@ balance-rr: This mode is the only mode that will permit a single 


	It is possible to adjust TCP/IP's congestion limits by

	altering the net.ipv4.tcp_reordering sysctl parameter.  The

	usual default value is 3, and the maximum useful value is 127.

	For a four interface balance-rr bond, expect that a single

	TCP/IP stream will utilize no more than approximately 2.3

	interface's worth of throughput, even after adjusting

	tcp_reordering.

	usual default value is 3. But keep in mind TCP stack is able

	to automatically increase this when it detects reorders.



	Note that the fraction of packets that will be delivered out of

	order is highly variable, and is unlikely to be zero.  The level

Documentation/networking/ip-sysctl.txt

+9 −1
Original line number Diff line number Diff line
@@ -376,9 +376,17 @@ tcp_orphan_retries - INTEGER 
	may consume significant resources. Cf. tcp_max_orphans.



tcp_reordering - INTEGER

	Maximal reordering of packets in a TCP stream.

	Initial reordering level of packets in a TCP stream.

	TCP stack can then dynamically adjust flow reordering level

	between this initial value and tcp_max_reordering

	Default: 3



tcp_max_reordering - INTEGER

	Maximal reordering level of packets in a TCP stream.

	300 is a fairly conservative value, but you might increase it

	if paths are using per packet load balancing (like bonding rr mode)

	Default: 300



tcp_retrans_collapse - BOOLEAN

	Bug-to-bug compatibility with some broken printers.

	On retransmit try to send bigger packets to work around bugs in

include/linux/tcp.h

+2 −2
Original line number Diff line number Diff line
@@ -204,10 +204,10 @@ struct tcp_sock { 


	u16	urg_data;	/* Saved octet of OOB data and control flags */

	u8	ecn_flags;	/* ECN status bits.			*/

	u8	reordering;	/* Packet reordering metric.		*/

	u8	keepalive_probes; /* num of allowed keep alive probes	*/

	u32	reordering;	/* Packet reordering metric.		*/

	u32	snd_up;		/* Urgent pointer		*/



	u8	keepalive_probes; /* num of allowed keep alive probes	*/

/*

 *      Options received (usually on last packet, some only on SYN packets).

 */

include/net/tcp.h

+1 −3
Original line number Diff line number Diff line
@@ -70,9 +70,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); 
/* After receiving this amount of duplicate ACKs fast retransmit starts. */

#define TCP_FASTRETRANS_THRESH 3



/* Maximal reordering. */

#define TCP_MAX_REORDERING	127



/* Maximal number of ACKs sent quickly to accelerate slow-start. */

#define TCP_MAX_QUICKACKS	16U
@@ -252,6 +249,7 @@ extern int sysctl_tcp_abort_on_overflow; 
extern int sysctl_tcp_max_orphans;

extern int sysctl_tcp_fack;

extern int sysctl_tcp_reordering;

extern int sysctl_tcp_max_reordering;

extern int sysctl_tcp_dsack;

extern long sysctl_tcp_mem[3];

extern int sysctl_tcp_wmem[3];

net/ipv4/sysctl_net_ipv4.c

+7 −0
Original line number Diff line number Diff line
@@ -495,6 +495,13 @@ static struct ctl_table ipv4_table[] = { 
		.mode		= 0644,

		.proc_handler	= proc_dointvec

	},

	{

		.procname	= "tcp_max_reordering",

		.data		= &sysctl_tcp_max_reordering,

		.maxlen		= sizeof(int),

		.mode		= 0644,

		.proc_handler	= proc_dointvec

	},

	{

		.procname	= "tcp_dsack",

		.data		= &sysctl_tcp_dsack,

CRA Git | Maintained and supported by SUSTech CRA and CCSE