summaryrefslogtreecommitdiffstats
path: root/net/ipv4/tcp.c
diff options
context:
space:
mode:
authorEric Dumazet <edumazet@google.com>2017-06-07 13:29:12 -0700
committerDavid S. Miller <davem@davemloft.net>2017-06-08 11:26:19 -0400
commit0604475119de5f80dc051a5db055c6a2a75bd542 (patch)
tree292c38e390647ef05fc445510c4d2a89b10b3f2a /net/ipv4/tcp.c
parent06fcb3b69fb8699afa04b020d2a95bd6c4c798ac (diff)
downloadlinux-0604475119de5f80dc051a5db055c6a2a75bd542.tar.bz2
tcp: add TCPMemoryPressuresChrono counter
DRAM supply shortage and poor memory pressure tracking in TCP stack makes any change in SO_SNDBUF/SO_RCVBUF (or equivalent autotuning limits) and tcp_mem[] quite hazardous. TCPMemoryPressures SNMP counter is an indication of tcp_mem sysctl limits being hit, but only tracking number of transitions. If TCP stack behavior under stress was perfect : 1) It would maintain memory usage close to the limit. 2) Memory pressure state would be entered for short times. We certainly prefer 100 events lasting 10ms compared to one event lasting 200 seconds. This patch adds a new SNMP counter tracking cumulative duration of memory pressure events, given in ms units. $ cat /proc/sys/net/ipv4/tcp_mem 3088 4117 6176 $ grep TCP /proc/net/sockstat TCP: inuse 180 orphan 0 tw 2 alloc 234 mem 4140 $ nstat -n ; sleep 10 ; nstat |grep Pressure TcpExtTCPMemoryPressures 1700 TcpExtTCPMemoryPressuresChrono 5209 v2: Used EXPORT_SYMBOL_GPL() instead of EXPORT_SYMBOL() as David instructed. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4/tcp.c')
-rw-r--r--net/ipv4/tcp.c31
1 files changed, 25 insertions, 6 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 87981fcdfcf2..cc8fd8b747a4 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -320,17 +320,36 @@ struct tcp_splice_state {
* All the __sk_mem_schedule() is of this nature: accounting
* is strict, actions are advisory and have some latency.
*/
-int tcp_memory_pressure __read_mostly;
-EXPORT_SYMBOL(tcp_memory_pressure);
+unsigned long tcp_memory_pressure __read_mostly;
+EXPORT_SYMBOL_GPL(tcp_memory_pressure);
void tcp_enter_memory_pressure(struct sock *sk)
{
- if (!tcp_memory_pressure) {
+ unsigned long val;
+
+ if (tcp_memory_pressure)
+ return;
+ val = jiffies;
+
+ if (!val)
+ val--;
+ if (!cmpxchg(&tcp_memory_pressure, 0, val))
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURES);
- tcp_memory_pressure = 1;
- }
}
-EXPORT_SYMBOL(tcp_enter_memory_pressure);
+EXPORT_SYMBOL_GPL(tcp_enter_memory_pressure);
+
+void tcp_leave_memory_pressure(struct sock *sk)
+{
+ unsigned long val;
+
+ if (!tcp_memory_pressure)
+ return;
+ val = xchg(&tcp_memory_pressure, 0);
+ if (val)
+ NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURESCHRONO,
+ jiffies_to_msecs(jiffies - val));
+}
+EXPORT_SYMBOL_GPL(tcp_leave_memory_pressure);
/* Convert seconds to retransmits based on initial and max timeout */
static u8 secs_to_retrans(int seconds, int timeout, int rto_max)