tcp: Probe net.core.{r,w}mem_max, don't set SO_{RCV,SND}BUF if low

If net.core.rmem_max and net.core.wmem_max sysctls have low values,
we can get bigger buffers by not trying to set them high -- the
kernel would lock their values to what we get.

Try, instead, to get bigger buffers by queueing as much as possible,
and if maximum values in tcp_wmem and tcp_rmem are bigger than this,
that will work.

While at it, drop QUICKACK option for non-spliced sockets, I set
that earlier by mistake.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>

1 files changed, 4 insertions, 0 deletions

diff --git a/tcp.h b/tcp.h
index ef78b51..fd483a1 100644
--- a/tcp.h
+++ b/tcp.h
@@ -51,6 +51,8 @@ union tcp_epoll_ref {
  * @pipe_size:		Size of pipes for spliced connections
  * @refill_ts:		Time of last refill operation for pools of sockets/pipes
  * @port_detect_ts:	Time of last TCP port detection/rebind, if enabled
+ * @low_wmem:		Low probed net.core.wmem_max
+ * @low_rmem:		Low probed net.core.rmem_max
  */
 struct tcp_ctx {
 	uint64_t hash_secret[2];
@@ -65,6 +67,8 @@ struct tcp_ctx {
 	size_t pipe_size;
 	struct timespec refill_ts;
 	struct timespec port_detect_ts;
+	int low_wmem;
+	int low_rmem;
 };
 
 #endif /* TCP_H */