diff mbox series

[net-next,v2] trace: tcp: Add tracepoint for tcp_cwnd_reduction()

Message ID 20250214-cwnd_tracepoint-v2-1-ef8d15162d95@debian.org (mailing list archive)
State New
Headers show
Series [net-next,v2] trace: tcp: Add tracepoint for tcp_cwnd_reduction() | expand

Commit Message

Breno Leitao Feb. 14, 2025, 5:07 p.m. UTC 
Add a lightweight tracepoint to monitor TCP congestion window
adjustments via tcp_cwnd_reduction(). This tracepoint enables tracking
of:
- TCP window size fluctuations
- Active socket behavior
- Congestion window reduction events

Meta has been using BPF programs to monitor this function for years.
Adding a proper tracepoint provides a stable API for all users who need
to monitor TCP congestion window behavior.

Use DECLARE_TRACE instead of TRACE_EVENT to avoid creating trace event
infrastructure and exporting to tracefs, keeping the implementation
minimal. (Thanks Steven Rostedt)

Given that this patch creates a rawtracepoint, you could hook into it
using regular tooling, like bpftrace, using regular rawtracepoint
infrastructure, such as:

	rawtracepoint:tcp_cwnd_reduction_tp {
		....
	}

Signed-off-by: Breno Leitao <leitao@debian.org>
---
---
Changes in v2:
- Close the parenthesis in a new line to honor the tcp.h format (Jakub).
- Add the bpftrace example in the commit message (Jakub)
- Link to v1: https://lore.kernel.org/r/20250207-cwnd_tracepoint-v1-1-13650f3ca96d@debian.org

Changes since RFC:
- Change from a full tracepoint to DECLARE_TRACE() as suggested by
  Steven
- Link to RFC: https://lore.kernel.org/r/20250120-cwnd_tracepoint-v1-1-36b0e0d643fa@debian.org
---
 include/trace/events/tcp.h | 6 ++++++
 net/ipv4/tcp_input.c       | 2 ++
 2 files changed, 8 insertions(+)


---
base-commit: 7a7e0197133d18cfd9931e7d3a842d0f5730223f
change-id: 20250120-cwnd_tracepoint-2e11c996a9cb

Best regards,

Comments

Paolo Abeni Feb. 18, 2025, 12:53 p.m. UTC | #1 
Hi,

On 2/14/25 6:07 PM, Breno Leitao wrote:
> Add a lightweight tracepoint to monitor TCP congestion window
> adjustments via tcp_cwnd_reduction(). This tracepoint enables tracking
> of:
> - TCP window size fluctuations
> - Active socket behavior
> - Congestion window reduction events
> 
> Meta has been using BPF programs to monitor this function for years.
> Adding a proper tracepoint provides a stable API for all users who need
> to monitor TCP congestion window behavior.
> 
> Use DECLARE_TRACE instead of TRACE_EVENT to avoid creating trace event
> infrastructure and exporting to tracefs, keeping the implementation
> minimal. (Thanks Steven Rostedt)
> 
> Given that this patch creates a rawtracepoint, you could hook into it
> using regular tooling, like bpftrace, using regular rawtracepoint
> infrastructure, such as:
> 
> 	rawtracepoint:tcp_cwnd_reduction_tp {
> 		....
> 	}
> 
> Signed-off-by: Breno Leitao <leitao@debian.org>
> ---
> ---
> Changes in v2:
> - Close the parenthesis in a new line to honor the tcp.h format (Jakub).
> - Add the bpftrace example in the commit message (Jakub)
> - Link to v1: https://lore.kernel.org/r/20250207-cwnd_tracepoint-v1-1-13650f3ca96d@debian.org

For future similar situations, note that it's expected to carry-on the
tag already collected in the previous versions, since the delta is only
cosmetic.

No further actions required on your side.

Cheers,

Paolo
Eric Dumazet Feb. 18, 2025, 1:21 p.m. UTC | #2 
On Fri, Feb 14, 2025 at 6:07 PM Breno Leitao <leitao@debian.org> wrote:
>
> Add a lightweight tracepoint to monitor TCP congestion window
> adjustments via tcp_cwnd_reduction(). This tracepoint enables tracking
> of:
> - TCP window size fluctuations
> - Active socket behavior
> - Congestion window reduction events
>
> Meta has been using BPF programs to monitor this function for years.
> Adding a proper tracepoint provides a stable API for all users who need
> to monitor TCP congestion window behavior.
>
> Use DECLARE_TRACE instead of TRACE_EVENT to avoid creating trace event
> infrastructure and exporting to tracefs, keeping the implementation
> minimal. (Thanks Steven Rostedt)
>
> Given that this patch creates a rawtracepoint, you could hook into it
> using regular tooling, like bpftrace, using regular rawtracepoint
> infrastructure, such as:
>
>         rawtracepoint:tcp_cwnd_reduction_tp {
>                 ....
>         }
>
> Signed-off-by: Breno Leitao <leitao@debian.org>

Reviewed-by: Eric Dumazet <edumazet@google.com>
Breno Leitao Feb. 18, 2025, 1:33 p.m. UTC | #3 
Hello Paolo,

On Tue, Feb 18, 2025 at 01:53:15PM +0100, Paolo Abeni wrote:
> On 2/14/25 6:07 PM, Breno Leitao wrote:
> > Add a lightweight tracepoint to monitor TCP congestion window
> > adjustments via tcp_cwnd_reduction(). This tracepoint enables tracking
> > of:
> > - TCP window size fluctuations
> > - Active socket behavior
> > - Congestion window reduction events
> > 
> > Meta has been using BPF programs to monitor this function for years.
> > Adding a proper tracepoint provides a stable API for all users who need
> > to monitor TCP congestion window behavior.
> > 
> > Use DECLARE_TRACE instead of TRACE_EVENT to avoid creating trace event
> > infrastructure and exporting to tracefs, keeping the implementation
> > minimal. (Thanks Steven Rostedt)
> > 
> > Given that this patch creates a rawtracepoint, you could hook into it
> > using regular tooling, like bpftrace, using regular rawtracepoint
> > infrastructure, such as:
> > 
> > 	rawtracepoint:tcp_cwnd_reduction_tp {
> > 		....
> > 	}
> > 
> > Signed-off-by: Breno Leitao <leitao@debian.org>
> > ---
> > ---
> > Changes in v2:
> > - Close the parenthesis in a new line to honor the tcp.h format (Jakub).
> > - Add the bpftrace example in the commit message (Jakub)
> > - Link to v1: https://lore.kernel.org/r/20250207-cwnd_tracepoint-v1-1-13650f3ca96d@debian.org
> 
> For future similar situations, note that it's expected to carry-on the
> tag already collected in the previous versions, since the delta is only
> cosmetic.

That is fair. I simply forgot about it. Sorry about it.
patchwork-bot+netdevbpf@kernel.org Feb. 18, 2025, 2:40 p.m. UTC | #4 
Hello:

This patch was applied to netdev/net-next.git (main)
by Paolo Abeni <pabeni@redhat.com>:

On Fri, 14 Feb 2025 09:07:11 -0800 you wrote:
> Add a lightweight tracepoint to monitor TCP congestion window
> adjustments via tcp_cwnd_reduction(). This tracepoint enables tracking
> of:
> - TCP window size fluctuations
> - Active socket behavior
> - Congestion window reduction events
> 
> [...]

Here is the summary with links:
  - [net-next,v2] trace: tcp: Add tracepoint for tcp_cwnd_reduction()
    https://git.kernel.org/netdev/net-next/c/8e677a466145

You are awesome, thank you!
diff mbox series

Patch

diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
index a27c4b619dffd7dcc72fffa71bf0fd5e34fe6681..1a40c41ff8c30a31b5c7002a4109de1cd8ef389e 100644
--- a/include/trace/events/tcp.h
+++ b/include/trace/events/tcp.h
@@ -259,6 +259,12 @@  TRACE_EVENT(tcp_retransmit_synack,
 		  __entry->saddr_v6, __entry->daddr_v6)
 );
 
+DECLARE_TRACE(tcp_cwnd_reduction_tp,
+	TP_PROTO(const struct sock *sk, int newly_acked_sacked,
+		 int newly_lost, int flag),
+	TP_ARGS(sk, newly_acked_sacked, newly_lost, flag)
+);
+
 #include <trace/events/net_probe_common.h>
 
 TRACE_EVENT(tcp_probe,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 4686783b70defe0457571efd72d41ac88c528f7b..3f79718fdb1ec7a4352dc691147da527448c1f46 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2709,6 +2709,8 @@  void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int newly_lost,
 	if (newly_acked_sacked <= 0 || WARN_ON_ONCE(!tp->prior_cwnd))
 		return;
 
+	trace_tcp_cwnd_reduction_tp(sk, newly_acked_sacked, newly_lost, flag);
+
 	tp->prr_delivered += newly_acked_sacked;
 	if (delta < 0) {
 		u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered +