Re: UDP sockets oddities

[Florian Fainelli <f.fainelli@gmail.com>]

On 08/26/2017 11:56 AM, Florian Fainelli wrote:
> 
> 
> On 08/26/2017 05:47 AM, Eric Dumazet wrote:
>> On Fri, 2017-08-25 at 21:19 -0700, David Miller wrote:
>>
>>> Agreed, but the ARP resolution queue really needs to scale it's backlog
>>> to the physical technology it is attached to.
>> Yes, last time (in 2011) we increased the old limit of 3 packets :/
>>
>> We probably should match sysctl_wmem_max so that a single socket
>> provider would hit its sk_sndbuf limit

Eric, do you want to post this as a formal patch? I don't think I
understand these tunables enough to provide a good commit message
anyways. Thanks!

> 
> Before:
> /proc/sys/net/ipv4/neigh/eth0/unres_qlen:34
> /proc/sys/net/ipv4/neigh/eth0/unres_qlen_bytes:65536
> /proc/sys/net/ipv4/neigh/gphy/unres_qlen:34
> /proc/sys/net/ipv4/neigh/gphy/unres_qlen_bytes:65536
> 
> After:
> /proc/sys/net/ipv4/neigh/eth0/unres_qlen:106
> /proc/sys/net/ipv4/neigh/eth0/unres_qlen_bytes:229376
> /proc/sys/net/ipv4/neigh/gphy/unres_qlen:106
> /proc/sys/net/ipv4/neigh/gphy/unres_qlen_bytes:229376
> 
> and this does help a lot with the test case reported over an hour, only
> 2 packets lost:
> 
> # perf record -a -g -e skb:kfree_skb iperf -c 192.168.1.23 -b 900M -t
> 3600 -u
> ------------------------------------------------------------
> Client connecting to 192.168.1.23, UDP port 5001
> Sending 1470 byte datagrams, IPG target: 13.07 us (kalman adjust)
> UDP buffer size:  224 KByte (default)
> ------------------------------------------------------------
> [  4] local 192.168.1.66 port 48209 connected with 192.168.1.23 port 5001
> write failed: Invalid argument
> [ ID] Interval       Transfer     Bandwidth
> [  4]  0.0-404.9 sec  4.51 GBytes  95.7 Mbits/sec
> [  4] Sent 3294727 datagrams
> [  4] Server Report:
> [  4]  0.0-405.1 sec  4.51 GBytes  95.6 Mbits/sec  14.979 ms
> 2/3294728 (6.1e-05%)
> 
> Thanks Eric!
> 
>>
>> Something like :
>>
>> diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
>> index 6b0bc0f715346a097a6df46e2ba2771359abcd23..7777dceb78107c0019fb39d5b69be1959005b78e 100644
>> --- a/Documentation/networking/ip-sysctl.txt
>> +++ b/Documentation/networking/ip-sysctl.txt
>> @@ -109,7 +109,8 @@ neigh/default/unres_qlen_bytes - INTEGER
>>  	queued for each	unresolved address by other network layers.
>>  	(added in linux 3.3)
>>  	Setting negative value is meaningless and will return error.
>> -	Default: 65536 Bytes(64KB)
>> +	Default: SK_WMEM_MAX, enough to store 256 packets of medium size
>> +		 (less than 256 bytes per packet)
>>  
>>  neigh/default/unres_qlen - INTEGER
>>  	The maximum number of packets which may be queued for each
>> diff --git a/include/net/sock.h b/include/net/sock.h
>> index 1c2912d433e81b10f3fdc87bcfcbb091570edc03..03a362568357acc7278a318423dd3873103f90ca 100644
>> --- a/include/net/sock.h
>> +++ b/include/net/sock.h
>> @@ -2368,6 +2368,16 @@ bool sk_net_capable(const struct sock *sk, int cap);
>>  
>>  void sk_get_meminfo(const struct sock *sk, u32 *meminfo);
>>  
>> +/* Take into consideration the size of the struct sk_buff overhead in the
>> + * determination of these values, since that is non-constant across
>> + * platforms.  This makes socket queueing behavior and performance
>> + * not depend upon such differences.
>> + */
>> +#define _SK_MEM_PACKETS		256
>> +#define _SK_MEM_OVERHEAD	SKB_TRUESIZE(256)
>> +#define SK_WMEM_MAX		(_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)
>> +#define SK_RMEM_MAX		(_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)
>> +
>>  extern __u32 sysctl_wmem_max;
>>  extern __u32 sysctl_rmem_max;
>>  
>> diff --git a/net/core/sock.c b/net/core/sock.c
>> index dfdd14cac775e9bfcee0085ee32ffcd0ab28b67b..9b7b6bbb2a23e7652a1f34a305f29d49de00bc8c 100644
>> --- a/net/core/sock.c
>> +++ b/net/core/sock.c
>> @@ -307,16 +307,6 @@ static struct lock_class_key af_wlock_keys[AF_MAX];
>>  static struct lock_class_key af_elock_keys[AF_MAX];
>>  static struct lock_class_key af_kern_callback_keys[AF_MAX];
>>  
>> -/* Take into consideration the size of the struct sk_buff overhead in the
>> - * determination of these values, since that is non-constant across
>> - * platforms.  This makes socket queueing behavior and performance
>> - * not depend upon such differences.
>> - */
>> -#define _SK_MEM_PACKETS		256
>> -#define _SK_MEM_OVERHEAD	SKB_TRUESIZE(256)
>> -#define SK_WMEM_MAX		(_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)
>> -#define SK_RMEM_MAX		(_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)
>> -
>>  /* Run time adjustable parameters. */
>>  __u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX;
>>  EXPORT_SYMBOL(sysctl_wmem_max);
>> diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c
>> index 21dedf6fd0f76dec22b2b3685beb89cfefea7ded..22bf0b95d6edc3c27ef3a99d27cb70a1551e3e0e 100644
>> --- a/net/decnet/dn_neigh.c
>> +++ b/net/decnet/dn_neigh.c
>> @@ -94,7 +94,7 @@ struct neigh_table dn_neigh_table = {
>>  			[NEIGH_VAR_BASE_REACHABLE_TIME] = 30 * HZ,
>>  			[NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ,
>>  			[NEIGH_VAR_GC_STALETIME] = 60 * HZ,
>> -			[NEIGH_VAR_QUEUE_LEN_BYTES] = 64*1024,
>> +			[NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_MAX,
>>  			[NEIGH_VAR_PROXY_QLEN] = 0,
>>  			[NEIGH_VAR_ANYCAST_DELAY] = 0,
>>  			[NEIGH_VAR_PROXY_DELAY] = 0,
>> diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
>> index 8b52179ddc6e54eabf6d3c2ed0132083228680bb..7c45b8896709815c5dde5972fd57cb5c3bcb2648 100644
>> --- a/net/ipv4/arp.c
>> +++ b/net/ipv4/arp.c
>> @@ -171,7 +171,7 @@ struct neigh_table arp_tbl = {
>>  			[NEIGH_VAR_BASE_REACHABLE_TIME] = 30 * HZ,
>>  			[NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ,
>>  			[NEIGH_VAR_GC_STALETIME] = 60 * HZ,
>> -			[NEIGH_VAR_QUEUE_LEN_BYTES] = 64 * 1024,
>> +			[NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_MAX,
>>  			[NEIGH_VAR_PROXY_QLEN] = 64,
>>  			[NEIGH_VAR_ANYCAST_DELAY] = 1 * HZ,
>>  			[NEIGH_VAR_PROXY_DELAY]	= (8 * HZ) / 10,
>> diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
>> index 5e338eb89509b1df6ebd060f8bd19fcb4b86fe05..266a530414d7be4f1e7be922e465bbab46f7cbac 100644
>> --- a/net/ipv6/ndisc.c
>> +++ b/net/ipv6/ndisc.c
>> @@ -127,7 +127,7 @@ struct neigh_table nd_tbl = {
>>  			[NEIGH_VAR_BASE_REACHABLE_TIME] = ND_REACHABLE_TIME,
>>  			[NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ,
>>  			[NEIGH_VAR_GC_STALETIME] = 60 * HZ,
>> -			[NEIGH_VAR_QUEUE_LEN_BYTES] = 64 * 1024,
>> +			[NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_MAX,
>>  			[NEIGH_VAR_PROXY_QLEN] = 64,
>>  			[NEIGH_VAR_ANYCAST_DELAY] = 1 * HZ,
>>  			[NEIGH_VAR_PROXY_DELAY] = (8 * HZ) / 10,
>>
>>
> 


-- 
Florian