From: Natale Patriciello <natale.patriciello@gmail.com>
To: "David S . Miller" <davem@davemloft.net>,
Eric Dumazet <eric.dumazet@gmail.com>
Cc: netdev <netdev@vger.kernel.org>,
Ahmed Said <ahmed.said@uniroma2.it>,
Natale Patriciello <natale.patriciello@gmail.com>,
Francesco Zampognaro <zampognaro@ing.uniroma2.it>,
Cesare Roseti <roseti@ing.uniroma2.it>
Subject: [RFC PATCH v2 1/5] tcp: Added a function to retrieve pacing timer
Date: Sat, 14 Oct 2017 13:47:10 +0200 [thread overview]
Message-ID: <20171014114714.3694-2-natale.patriciello@gmail.com> (raw)
In-Reply-To: <20171014114714.3694-1-natale.patriciello@gmail.com>
Allow congestion control modules to set a custom pacing time between
the transmission of segments.
Moreover, it is assumed that the time returned by the congestion module
in the past is firm, until the timer expires; therefore, do not re-start
the timer if it is already active.
Signed-off-by: Natale Patriciello <natale.patriciello@gmail.com>
---
include/net/tcp.h | 2 ++
net/ipv4/tcp_output.c | 36 +++++++++++++++++++++++++-----------
2 files changed, 27 insertions(+), 11 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 89974c5286d8..42c7aa96c4cf 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1015,6 +1015,8 @@ struct tcp_congestion_ops {
/* get info for inet_diag (optional) */
size_t (*get_info)(struct sock *sk, u32 ext, int *attr,
union tcp_cc_info *info);
+ /* get the expiration time for the pacing timer (optional) */
+ u64 (*get_pacing_time)(struct sock *sk);
char name[TCP_CA_NAME_MAX];
struct module *owner;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 0bc9e46a5369..ec5977156c26 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -950,22 +950,36 @@ static bool tcp_needs_internal_pacing(const struct sock *sk)
return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED;
}
+static bool tcp_pacing_timer_check(const struct sock *sk)
+{
+ return hrtimer_active(&tcp_sk(sk)->pacing_timer);
+}
+
static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb)
{
+ const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
u64 len_ns;
- u32 rate;
if (!tcp_needs_internal_pacing(sk))
return;
- rate = sk->sk_pacing_rate;
- if (!rate || rate == ~0U)
- return;
-
- /* Should account for header sizes as sch_fq does,
- * but lets make things simple.
- */
- len_ns = (u64)skb->len * NSEC_PER_SEC;
- do_div(len_ns, rate);
+
+ if (ca_ops && ca_ops->get_pacing_time) {
+ if (tcp_pacing_timer_check(sk))
+ return;
+
+ len_ns = ca_ops->get_pacing_time(sk);
+ } else {
+ u32 rate = sk->sk_pacing_rate;
+
+ if (!rate || rate == ~0U)
+ return;
+
+ /* Should account for header sizes as sch_fq does,
+ * but lets make things simple.
+ */
+ len_ns = (u64)skb->len * NSEC_PER_SEC;
+ do_div(len_ns, rate);
+ }
hrtimer_start(&tcp_sk(sk)->pacing_timer,
ktime_add_ns(ktime_get(), len_ns),
HRTIMER_MODE_ABS_PINNED);
@@ -2123,7 +2137,7 @@ static int tcp_mtu_probe(struct sock *sk)
static bool tcp_pacing_check(const struct sock *sk)
{
return tcp_needs_internal_pacing(sk) &&
- hrtimer_active(&tcp_sk(sk)->pacing_timer);
+ tcp_pacing_timer_check(sk);
}
/* TCP Small Queues :
--
2.14.2
next prev parent reply other threads:[~2017-10-14 11:49 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-10-14 11:47 [RFC PATCH v2 0/5] TCP Wave Natale Patriciello
2017-10-14 11:47 ` Natale Patriciello [this message]
2017-10-14 11:47 ` [RFC PATCH v2 2/5] tcp: implemented pacing_expired Natale Patriciello
2017-10-15 17:30 ` Eric Dumazet
2017-10-14 11:47 ` [RFC PATCH v2 3/5] tcp: added get_segs_per_round Natale Patriciello
2017-10-15 17:32 ` Eric Dumazet
2017-10-14 11:47 ` [RFC PATCH v2 4/5] tcp: added segment sent Natale Patriciello
2017-10-14 11:47 ` [RFC PATCH v2 5/5] wave: Added TCP Wave Natale Patriciello
2017-10-15 17:43 ` Eric Dumazet
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=20171014114714.3694-2-natale.patriciello@gmail.com \
--to=natale.patriciello@gmail.com \
--cc=ahmed.said@uniroma2.it \
--cc=davem@davemloft.net \
--cc=eric.dumazet@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=roseti@ing.uniroma2.it \
--cc=zampognaro@ing.uniroma2.it \
/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