From: David Howells <dhowells@redhat.com>
To: netdev@vger.kernel.org
Cc: David Howells <dhowells@redhat.com>,
Marc Dionne <marc.dionne@auristor.com>,
Yunsheng Lin <linyunsheng@huawei.com>,
"David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
linux-afs@lists.infradead.org, linux-kernel@vger.kernel.org,
Simon Wilkinson <sxw@auristor.com>
Subject: [PATCH net-next 27/37] rxrpc: Fix the calculation and use of RTO
Date: Mon, 2 Dec 2024 14:30:45 +0000 [thread overview]
Message-ID: <20241202143057.378147-28-dhowells@redhat.com> (raw)
In-Reply-To: <20241202143057.378147-1-dhowells@redhat.com>
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 --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index 48bc06842f99..1f9b1964e142 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);
}
/*
next prev parent reply other threads:[~2024-12-02 14:33 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-12-02 14:30 [PATCH net-next 00/37] rxrpc: Implement jumbo DATA transmission and RACK-TLP David Howells
2024-12-02 14:30 ` [PATCH net-next 01/37] rxrpc: Fix handling of received connection abort David Howells
2024-12-02 14:30 ` [PATCH net-next 02/37] rxrpc: Use umin() and umax() rather than min_t()/max_t() where possible David Howells
2024-12-05 2:37 ` David Laight
2024-12-05 10:50 ` David Howells
2024-12-05 11:01 ` David Laight
2024-12-02 14:30 ` [PATCH net-next 03/37] rxrpc: Clean up Tx header flags generation handling David Howells
2024-12-02 14:30 ` [PATCH net-next 04/37] rxrpc: Don't set the MORE-PACKETS rxrpc wire header flag David Howells
2024-12-03 3:42 ` Jakub Kicinski
2024-12-02 14:30 ` [PATCH net-next 05/37] rxrpc: Show stats counter for received reason-0 ACKs David Howells
2024-12-02 14:30 ` [PATCH net-next 06/37] rxrpc: Request an ACK on impending Tx stall David Howells
2024-12-02 14:30 ` [PATCH net-next 07/37] rxrpc: Use a large kvec[] in rxrpc_local rather than every rxrpc_txbuf David Howells
2024-12-02 14:30 ` [PATCH net-next 08/37] rxrpc: Implement path-MTU probing using padded PING ACKs (RFC8899) David Howells
2024-12-02 14:30 ` [PATCH net-next 09/37] rxrpc: Separate the packet length from the data length in rxrpc_txbuf David Howells
2024-12-02 14:30 ` [PATCH net-next 10/37] rxrpc: Prepare to be able to send jumbo DATA packets David Howells
2024-12-03 3:43 ` Jakub Kicinski
2024-12-03 19:52 ` David Howells
2024-12-02 14:30 ` [PATCH net-next 11/37] rxrpc: Add a tracepoint to show variables pertinent to jumbo packet size David Howells
2024-12-02 14:30 ` [PATCH net-next 12/37] rxrpc: Fix CPU time starvation in I/O thread David Howells
2024-12-02 14:30 ` [PATCH net-next 13/37] rxrpc: Fix injection of packet loss David Howells
2024-12-02 14:30 ` [PATCH net-next 14/37] rxrpc: Only set DF=1 on initial DATA transmission David Howells
2024-12-02 14:30 ` [PATCH net-next 15/37] rxrpc: Timestamp DATA packets before transmitting them David Howells
2024-12-02 14:30 ` [PATCH net-next 16/37] rxrpc: Implement progressive transmission queue struct David Howells
2024-12-03 3:44 ` Jakub Kicinski
2024-12-02 14:30 ` [PATCH net-next 17/37] rxrpc: call->acks_hard_ack is now the same call->tx_bottom, so remove it David Howells
2024-12-02 14:30 ` [PATCH net-next 18/37] rxrpc: Replace call->acks_first_seq with tracking of the hard ACK point David Howells
2024-12-02 14:30 ` [PATCH net-next 19/37] rxrpc: Display stats about jumbo packets transmitted and received David Howells
2024-12-02 14:30 ` [PATCH net-next 20/37] rxrpc: Adjust names and types of congestion-related fields David Howells
2024-12-02 14:30 ` [PATCH net-next 21/37] rxrpc: Use the new rxrpc_tx_queue struct to more efficiently process ACKs David Howells
2024-12-02 14:30 ` [PATCH net-next 22/37] rxrpc: Store the DATA serial in the txqueue and use this in RTT calc David Howells
2024-12-02 14:30 ` [PATCH net-next 23/37] rxrpc: Don't use received skbuff timestamps David Howells
2024-12-02 14:30 ` [PATCH net-next 24/37] rxrpc: Generate rtt_min David Howells
2024-12-02 14:30 ` [PATCH net-next 25/37] rxrpc: Adjust the rxrpc_rtt_rx tracepoint David Howells
2024-12-02 14:30 ` [PATCH net-next 26/37] rxrpc: Display userStatus in rxrpc_rx_ack trace David Howells
2024-12-02 14:30 ` David Howells [this message]
2024-12-02 14:30 ` [PATCH net-next 28/37] rxrpc: Fix initial resend timeout David Howells
2024-12-02 14:30 ` [PATCH net-next 29/37] rxrpc: Send jumbo DATA packets David Howells
2024-12-02 14:30 ` [PATCH net-next 30/37] rxrpc: Don't allocate a txbuf for an ACK transmission David Howells
2024-12-02 14:30 ` [PATCH net-next 31/37] rxrpc: Use irq-disabling spinlocks between app and I/O thread David Howells
2024-12-02 14:30 ` [PATCH net-next 32/37] rxrpc: Tidy up the ACK parsing a bit David Howells
2024-12-02 14:30 ` [PATCH net-next 33/37] rxrpc: Add a reason indicator to the tx_data tracepoint David Howells
2024-12-02 14:30 ` [PATCH net-next 34/37] rxrpc: Add a reason indicator to the tx_ack tracepoint David Howells
2024-12-02 14:30 ` [PATCH net-next 35/37] rxrpc: Manage RTT per-call rather than per-peer David Howells
2024-12-02 14:30 ` [PATCH net-next 36/37] rxrpc: Fix request for an ACK when cwnd is minimum David Howells
2024-12-02 14:30 ` [PATCH net-next 37/37] rxrpc: Implement RACK/TLP to deal with transmission stalls [RFC8985] David Howells
2024-12-03 3:48 ` Jakub Kicinski
2024-12-03 19:54 ` David Howells
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20241202143057.378147-28-dhowells@redhat.com \
--to=dhowells@redhat.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=kuba@kernel.org \
--cc=linux-afs@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linyunsheng@huawei.com \
--cc=marc.dionne@auristor.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=sxw@auristor.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox