[newlib 54/65] tcp: Add a socket option to rack

Sebastian Huber sebastian.huber at embedded-brains.de
Thu Jul 7 11:59:01 UTC 2022


From: Randall Stewart <rrs at FreeBSD.org>

so we can test various changes to the slop value in timers.

Timer_slop, in TCP, has been 200ms for a long time. This value dates back
a long time when delayed ack timers were longer and links were slower. A
200ms timer slop allows 1 MSS to be sent over a 60kbps link. Its possible that
lowering this value to something more in line with todays delayed ack values (40ms)
might improve TCP. This bit of code makes it so rack can, via a socket option,
adjust the timer slop.

Reviewed by: mtuexen
Sponsered by: Netflix Inc
Differential Revision:	https://reviews.freebsd.org/D30249
---
 newlib/libc/sys/rtems/include/netinet/tcp.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/newlib/libc/sys/rtems/include/netinet/tcp.h b/newlib/libc/sys/rtems/include/netinet/tcp.h
index 7ba99df51..45bece9fa 100644
--- a/newlib/libc/sys/rtems/include/netinet/tcp.h
+++ b/newlib/libc/sys/rtems/include/netinet/tcp.h
@@ -306,6 +306,7 @@ struct tcphdr {
 #define TCP_FAST_RSM_HACK 1137 /* Do we do the broken thing where we don't twiddle the TLP bits properly in fast_rsm_output? */
 #define TCP_RACK_PACING_BETA 1138	/* Changing the beta for pacing */
 #define TCP_RACK_PACING_BETA_ECN 1139	/* Changing the beta for ecn with pacing */
+#define TCP_RACK_TIMER_SLOP 1140	/* Set or get the timer slop used */
 
 /* Start of reserved space for third-party user-settable options. */
 #define	TCP_VENDOR	SO_VENDOR
-- 
2.35.3



More information about the devel mailing list