From: Yuchung Cheng <ycheng@google.com>
To: davem@davemloft.net
Cc: netdev@vger.kernel.org, Yuchung Cheng <ycheng@google.com>,
Neal Cardwell <ncardwell@google.com>,
Eric Dumazet <edumazet@google.com>
Subject: [PATCH net-next 3/3] tcp: a small refactor of RACK loss detection
Date: Wed, 4 Oct 2017 13:00:00 -0700 [thread overview]
Message-ID: <20171004200000.39257-4-ycheng@google.com> (raw)
In-Reply-To: <20171004200000.39257-1-ycheng@google.com>
Refactor the RACK loop to improve readability and speed up the checks.
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
net/ipv4/tcp_recovery.c | 40 ++++++++++++++++++----------------------
1 file changed, 18 insertions(+), 22 deletions(-)
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index 8aa56caefde8..cda6074a429a 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -61,32 +61,28 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout)
list_for_each_entry_safe(skb, n, &tp->tsorted_sent_queue,
tcp_tsorted_anchor) {
struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
+ s32 remaining;
- if (tcp_rack_sent_after(tp->rack.mstamp, skb->skb_mstamp,
- tp->rack.end_seq, scb->end_seq)) {
- /* Step 3 in draft-cheng-tcpm-rack-00.txt:
- * A packet is lost if its elapsed time is beyond
- * the recent RTT plus the reordering window.
- */
- u32 elapsed = tcp_stamp_us_delta(tp->tcp_mstamp,
- skb->skb_mstamp);
- s32 remaining = tp->rack.rtt_us + reo_wnd - elapsed;
-
- if (remaining < 0) {
- tcp_rack_mark_skb_lost(sk, skb);
- list_del_init(&skb->tcp_tsorted_anchor);
- continue;
- }
-
- /* Skip ones marked lost but not yet retransmitted */
- if ((scb->sacked & TCPCB_LOST) &&
- !(scb->sacked & TCPCB_SACKED_RETRANS))
- continue;
+ /* Skip ones marked lost but not yet retransmitted */
+ if ((scb->sacked & TCPCB_LOST) &&
+ !(scb->sacked & TCPCB_SACKED_RETRANS))
+ continue;
+ if (!tcp_rack_sent_after(tp->rack.mstamp, skb->skb_mstamp,
+ tp->rack.end_seq, scb->end_seq))
+ break;
+
+ /* A packet is lost if it has not been s/acked beyond
+ * the recent RTT plus the reordering window.
+ */
+ remaining = tp->rack.rtt_us + reo_wnd -
+ tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp);
+ if (remaining < 0) {
+ tcp_rack_mark_skb_lost(sk, skb);
+ list_del_init(&skb->tcp_tsorted_anchor);
+ } else {
/* Record maximum wait time (+1 to avoid 0) */
*reo_timeout = max_t(u32, *reo_timeout, 1 + remaining);
- } else {
- break;
}
}
}
--
2.14.2.920.gcf0c67979c-goog
next prev parent reply other threads:[~2017-10-04 20:00 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-10-04 19:59 [PATCH net-next 0/3] tcp: improving RACK cpu performance Yuchung Cheng
2017-10-04 19:59 ` [PATCH net-next 1/3] tcp: new list for sent but unacked skbs for RACK recovery Yuchung Cheng
2017-10-04 19:59 ` [PATCH net-next 2/3] tcp: more efficient RACK loss detection Yuchung Cheng
2017-10-04 20:00 ` Yuchung Cheng [this message]
2017-10-06 4:26 ` [PATCH net-next 0/3] tcp: improving RACK cpu performance David Miller
2017-10-06 16:34 ` Yuchung Cheng
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=20171004200000.39257-4-ycheng@google.com \
--to=ycheng@google.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=ncardwell@google.com \
--cc=netdev@vger.kernel.org \
/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;
as well as URLs for NNTP newsgroup(s).