SO_RCVBUF and SO_SNDBUF have limited range today, unless distros or system admins change rmem_max and wmem_max. Even iproute2 uses 1 MB SO_RCVBUF which is capped by the kernel. Decouple [rw]mem_max and [rw]mem_default and increase [rw]mem_max to 4 MB. Before: $ sysctl net.core.rmem_default net.core.rmem_max net.core.wmem_default net.core.wmem_max net.core.rmem_default = 212992 net.core.rmem_max = 212992 net.core.wmem_default = 212992 net.core.wmem_max = 212992 After: $ sysctl net.core.rmem_default net.core.rmem_max net.core.wmem_default net.core.wmem_max net.core.rmem_default = 212992 net.core.rmem_max = 4194304 net.core.wmem_default = 212992 net.core.wmem_max = 4194304 Signed-off-by: Eric Dumazet --- Documentation/admin-guide/sysctl/net.rst | 4 ++++ Documentation/networking/ip-sysctl.rst | 6 +++--- include/net/sock.h | 4 ++-- net/core/sock.c | 8 ++++---- net/ipv4/arp.c | 2 +- net/ipv6/ndisc.c | 2 +- 6 files changed, 15 insertions(+), 11 deletions(-) diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst index 7b0c4291c6861e5694c36f89ddbb19d0397e4190..2ef50828aff16b01baf32f5ded9b75a6e699b184 100644 --- a/Documentation/admin-guide/sysctl/net.rst +++ b/Documentation/admin-guide/sysctl/net.rst @@ -222,6 +222,8 @@ rmem_max The maximum receive socket buffer size in bytes. +Default: 4194304 + rps_default_mask ---------------- @@ -247,6 +249,8 @@ wmem_max The maximum send socket buffer size in bytes. +Default: 4194304 + message_burst and message_cost ------------------------------ diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 9756d16e3df1400626ce24726feceaeefa5da523..cb0fce8512bfa3ed6c61654787eca1b2bd9312d8 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -209,7 +209,7 @@ neigh/default/unres_qlen_bytes - INTEGER Setting negative value is meaningless and will return error. - Default: SK_WMEM_MAX, (same as net.core.wmem_default). + Default: SK_WMEM_DEFAULT, (same as net.core.wmem_default). Exact value depends on architecture and kernel options, but should be enough to allow queuing 256 packets @@ -805,8 +805,8 @@ tcp_rmem - vector of 3 INTEGERs: min, default, max This value results in initial window of 65535. max: maximal size of receive buffer allowed for automatically - selected receiver buffers for TCP socket. This value does not override - net.core.rmem_max. Calling setsockopt() with SO_RCVBUF disables + selected receiver buffers for TCP socket. + Calling setsockopt() with SO_RCVBUF disables automatic tuning of that socket's receive buffer size, in which case this value is ignored. Default: between 131072 and 32MB, depending on RAM size. diff --git a/include/net/sock.h b/include/net/sock.h index c8a4b283df6fc4b931270502ddbb5df7ae1e4aa2..4a9169a8d92493db64315b09c2fc105a6d55966d 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2924,8 +2924,8 @@ void sk_get_meminfo(const struct sock *sk, u32 *meminfo); */ #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) +#define SK_WMEM_DEFAULT (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) +#define SK_RMEM_DEFAULT (_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 7c26ec8dce630f0d24a622a418c15e6594d1babb..66c65f4a03f38850b9f42e82188a9df1c3485ce1 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -281,12 +281,12 @@ static struct lock_class_key af_elock_keys[AF_MAX]; static struct lock_class_key af_kern_callback_keys[AF_MAX]; /* Run time adjustable parameters. */ -__u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX; +__u32 sysctl_wmem_max __read_mostly = 4 << 20; EXPORT_SYMBOL(sysctl_wmem_max); -__u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX; +__u32 sysctl_rmem_max __read_mostly = 4 << 20; EXPORT_SYMBOL(sysctl_rmem_max); -__u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX; -__u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; +__u32 sysctl_wmem_default __read_mostly = SK_WMEM_DEFAULT; +__u32 sysctl_rmem_default __read_mostly = SK_RMEM_DEFAULT; DEFINE_STATIC_KEY_FALSE(memalloc_socks_key); EXPORT_SYMBOL_GPL(memalloc_socks_key); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 5cfc1c9396732171b79ce0aac2b0ee11ddfcbd05..833f2cf97178ee6a50fb3c99d02ed5b17ab5a879 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -170,7 +170,7 @@ struct neigh_table arp_tbl = { [NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ, [NEIGH_VAR_INTERVAL_PROBE_TIME_MS] = 5 * HZ, [NEIGH_VAR_GC_STALETIME] = 60 * HZ, - [NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_MAX, + [NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_DEFAULT, [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 7d5abb3158ec9640a45d4f36fbbfdfce070c0dd0..57aaa7ae8ac3109d808dd46e8cfe54b57e48b214 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -130,7 +130,7 @@ struct neigh_table nd_tbl = { [NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ, [NEIGH_VAR_INTERVAL_PROBE_TIME_MS] = 5 * HZ, [NEIGH_VAR_GC_STALETIME] = 60 * HZ, - [NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_MAX, + [NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_DEFAULT, [NEIGH_VAR_PROXY_QLEN] = 64, [NEIGH_VAR_ANYCAST_DELAY] = 1 * HZ, [NEIGH_VAR_PROXY_DELAY] = (8 * HZ) / 10, -- 2.51.0.rc1.193.gad69d77794-goog