page-server: Fine grained corking control (v3)br-1.7-stable

When live migrating a container with large amount of processes
inside the time to do page-server-ed dump may be up to 10 times
slower than for the local dump.

The delay is always introduced in the open_page_server_xfer()
when criu negotiates the has_parent bit on the 2nd task. This
likely happens because of the Nagel algo taking place -- after
the write() of the OPEN2 command happened kernel delays this
command sending waiting for more data.

v2:
Fix this by turning on CORK option on memory transfer sockets
on send side, and NODELAY one once on urgent data. Receive
side is always NODELAY-ed. According to Alexey Kuznetsov this
is the best mode ever for such type of transfers.

v3:
Push packets in pre-dump's check_parent_server_xfer too.

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Acked-by: Andrew Vagin <avagin@odin.com>

Conflicts:
	include/util.h
	util.c

3 files changed, 38 insertions, 2 deletions

diff --git a/include/util.h b/include/util.h
index f2300a95f..5c8d5a865 100644
--- a/include/util.h
+++ b/include/util.h
@@ -261,4 +261,6 @@ void split(char *str, char token, char ***out, int *n);
 
 int fd_has_data(int lfd);
 
+void tcp_nodelay(int sk, bool on);
+void tcp_cork(int sk, bool on);
 #endif /* __CR_UTIL_H__ */
diff --git a/page-xfer.c b/page-xfer.c
index dc7e81593..f8e999cf0 100644
--- a/page-xfer.c
+++ b/page-xfer.c
@@ -13,7 +13,7 @@
 #include "image.h"
 #include "page-xfer.h"
 #include "page-pipe.h"
-
+#include "util.h"
 #include "protobuf.h"
 #include "protobuf/pagemap.pb-c.h"
 
@@ -183,6 +183,13 @@ static int page_server_serve(int sk)
 	int ret = -1;
 	bool flushed = false;
 
+	/*
+	 * This socket only accepts data except one thing -- it
+	 * writes back the has_parent bit from time to time, so
+	 * make it NODELAY all the time.
+	 */
+	tcp_nodelay(sk, true);
+
 	if (pipe(cxfer.p)) {
 		pr_perror("Can't make pipe for xfer");
 		close(sk);
@@ -386,7 +393,7 @@ int connect_to_page_server(void)
 	if (opts.ps_socket != -1) {
 		page_server_sk = opts.ps_socket;
 		pr_info("Re-using ps socket %d\n", page_server_sk);
-		return 0;
+		goto out;
 	}
 
 	pr_info("Connecting to server %s:%u\n",
@@ -406,6 +413,13 @@ int connect_to_page_server(void)
 		return -1;
 	}
 
+out:
+	/*
+	 * CORK the socket at the very beginning. As per ANK
+	 * the corked by default socket with sporadic NODELAY-s
+	 * on urgent data is the smartest mode ever.
+	 */
+	tcp_cork(page_server_sk, true);
 	return 0;
 }
 
@@ -524,6 +538,9 @@ static int open_page_server_xfer(struct page_xfer *xfer, int fd_type, long id)
 		return -1;
 	}
 
+	/* Push the command NOW */
+	tcp_nodelay(xfer->sk, true);
+
 	if (read(xfer->sk, &has_parent, 1) != 1) {
 		pr_perror("The page server doesn't answer");
 		return -1;
@@ -826,6 +843,8 @@ static int check_parent_server_xfer(int fd_type, long id)
 		return -1;
 	}
 
+	tcp_nodelay(page_server_sk, true);
+
 	if (read(page_server_sk, &has_parent, sizeof(int)) != sizeof(int)) {
 		pr_perror("The page server doesn't answer");
 		return -1;
diff --git a/util.c b/util.c
index b916eca3c..b89448640 100644
--- a/util.c
+++ b/util.c
@@ -28,6 +28,9 @@
 #include <sys/wait.h>
 #include <sys/resource.h>
 #include <sys/wait.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <netinet/tcp.h>
 
 #include "compiler.h"
 #include "asm/types.h"
@@ -845,3 +848,15 @@ int fd_has_data(int lfd)
 
 	return ret;
 }
+
+void tcp_cork(int sk, bool on)
+{
+	int val = on ? 1 : 0;
+	setsockopt(sk, SOL_TCP, TCP_CORK, &val, sizeof(val));
+}
+
+void tcp_nodelay(int sk, bool on)
+{
+	int val = on ? 1 : 0;
+	setsockopt(sk, SOL_TCP, TCP_NODELAY, &val, sizeof(val));
+}