diff mbox series

[net-next,v2,29/39] rxrpc: Fix the calculation and use of RTO

Message ID 20241204074710.990092-30-dhowells@redhat.com (mailing list archive)
State New
Delegated to: Netdev Maintainers
Headers show
Series rxrpc: Implement jumbo DATA transmission and RACK-TLP | expand

Checks

Context Check Description
netdev/series_format fail Series longer than 15 patches
netdev/tree_selection success Clearly marked for net-next
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 3 this patch: 3
netdev/build_tools success No tools touched, skip
netdev/cc_maintainers warning 1 maintainers not CCed: horms@kernel.org
netdev/build_clang success Errors and warnings before: 3 this patch: 3
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success Fixes tag looks correct
netdev/build_allmodconfig_warn success Errors and warnings before: 304 this patch: 304
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 17 lines checked
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

David Howells Dec. 4, 2024, 7:46 a.m. UTC 
Make the following changes to the calculation and use of RTO:

 (1) Fix rxrpc_resend() to use the backed-off RTO value obtained by calling
     rxrpc_get_rto_backoff() rather than extracting the value itself.
     Without this, it may retransmit packets too early.

 (2) The RTO value being similar to the RTT causes a lot of extraneous
     resends because the RTT doesn't end up taking account of clearing out
     of the receive queue on the server.  Worse, responses to PING-ACKs are
     made as fast as possible and so are less than the DATA-requested-ACK
     RTT and so skew the RTT down.

     Fix this by putting a lower bound on the RTO by adding 100ms to it and
     limiting the lower end to 200ms.

Fixes: c410bf01933e ("rxrpc: Fix the excessive initial retransmission timeout")
Fixes: 37473e416234 ("rxrpc: Clean up the resend algorithm")
Signed-off-by: David Howells <dhowells@redhat.com>
Suggested-by: Simon Wilkinson <sxw@auristor.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: linux-afs@lists.infradead.org
cc: netdev@vger.kernel.org
---
 net/rxrpc/call_event.c | 3 ++-
 net/rxrpc/rtt.c        | 2 +-
 2 files changed, 3 insertions(+), 2 deletions(-)
diff mbox series

Patch

diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index f71773b18e22..4390c97e3ba6 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -103,7 +103,8 @@  void rxrpc_resend(struct rxrpc_call *call, rxrpc_serial_t ack_serial, bool ping_
 		.now	= ktime_get_real(),
 	};
 	struct rxrpc_txqueue *tq = call->tx_queue;
-	ktime_t lowest_xmit_ts = KTIME_MAX, rto	= ns_to_ktime(call->peer->rto_us * NSEC_PER_USEC);
+	ktime_t lowest_xmit_ts = KTIME_MAX;
+	ktime_t rto = rxrpc_get_rto_backoff(call->peer, false);
 	bool unacked = false;
 
 	_enter("{%d,%d}", call->tx_bottom, call->tx_top);
diff --git a/net/rxrpc/rtt.c b/net/rxrpc/rtt.c
index e0b7d99854b4..3f1ec8e420a6 100644
--- a/net/rxrpc/rtt.c
+++ b/net/rxrpc/rtt.c
@@ -27,7 +27,7 @@  static u32 __rxrpc_set_rto(const struct rxrpc_peer *peer)
 
 static u32 rxrpc_bound_rto(u32 rto)
 {
-	return umin(rto, RXRPC_RTO_MAX);
+	return clamp(200000, rto + 100000, RXRPC_RTO_MAX);
 }
 
 /*