netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Simon Horman <horms@kernel.org>
To: John Ousterhout <ouster@cs.stanford.edu>
Cc: netdev@vger.kernel.org, pabeni@redhat.com, edumazet@google.com,
	kuba@kernel.org
Subject: Re: [PATCH net-next v9 08/15] net: homa: create homa_pacer.h and homa_pacer.c
Date: Fri, 13 Jun 2025 15:43:40 +0100	[thread overview]
Message-ID: <20250613144340.GL414686@horms.kernel.org> (raw)
In-Reply-To: <20250609154051.1319-9-ouster@cs.stanford.edu>

On Mon, Jun 09, 2025 at 08:40:41AM -0700, John Ousterhout wrote:
> These files provide facilities to pace packet output in order to prevent
> queue buildup in the NIC. This functionality is needed to implement SRPT
> on output, so short messages don't get stuck in long NIC queues. Note: the
> pacer eventually needs to be replaced with a Homa-specific qdisc, which can
> better manage simultaneous transmissions by Homa and TCP. The current
> implementation can coexist with TCP and doesn't harm TCP, but
> Homa's latency suffers when TCP runs concurrently.
> 
> Signed-off-by: John Ousterhout <ouster@cs.stanford.edu>
> 
> ---
> Changes for v9:
> * Add support for homa_net objects
> * Use new homa_clock abstraction layer
> * Various name improvements (e.g. use "alloc" instead of "new" for functions
>   that allocate memory)
> 
> Changes for v8:
> * This file is new in v8 (functionality extracted from other files)
> ---
>  net/homa/homa_impl.h  |   1 +
>  net/homa/homa_pacer.c | 316 ++++++++++++++++++++++++++++++++++++++++++
>  net/homa/homa_pacer.h | 190 +++++++++++++++++++++++++
>  3 files changed, 507 insertions(+)
>  create mode 100644 net/homa/homa_pacer.c
>  create mode 100644 net/homa/homa_pacer.h
> 

> diff --git a/net/homa/homa_impl.h b/net/homa/homa_impl.h

...

> +/**
> + * homa_pacer_manage_rpc() - Arrange for the pacer to transmit packets
> + * from this RPC (make sure that an RPC is on the throttled list and wake up
> + * the pacer thread if necessary).
> + * @rpc:     RPC with outbound packets that have been granted but can't be
> + *           sent because of NIC queue restrictions. Must be locked by caller.
> + */
> +void homa_pacer_manage_rpc(struct homa_rpc *rpc)
> +	__must_hold(rpc_bucket_lock)
> +{
> +	struct homa_pacer *pacer = rpc->hsk->homa->pacer;
> +	struct homa_rpc *candidate;
> +	int bytes_left;
> +	int checks = 0;

Checks is set but otherwise unused in this function.
Probably it can be removed.

Flagged by Clang 20.1.4 as:

  .../homa_pacer.c:252:6: warning: variable 'checks' set but not used [-Wunused-but-set-variable]
    252 |         int checks = 0;
        |             ^
> +
> +	if (!list_empty(&rpc->throttled_links))
> +		return;
> +	bytes_left = rpc->msgout.length - rpc->msgout.next_xmit_offset;
> +	homa_pacer_throttle_lock(pacer);
> +	list_for_each_entry(candidate, &pacer->throttled_rpcs,
> +			    throttled_links) {
> +		int bytes_left_cand;
> +
> +		checks++;
> +
> +		/* Watch out: the pacer might have just transmitted the last
> +		 * packet from candidate.
> +		 */
> +		bytes_left_cand = candidate->msgout.length -
> +				candidate->msgout.next_xmit_offset;
> +		if (bytes_left_cand > bytes_left) {
> +			list_add_tail(&rpc->throttled_links,
> +				      &candidate->throttled_links);
> +			goto done;
> +		}
> +	}
> +	list_add_tail(&rpc->throttled_links, &pacer->throttled_rpcs);
> +done:
> +	homa_pacer_throttle_unlock(pacer);
> +	wake_up(&pacer->wait_queue);
> +}

...

  reply	other threads:[~2025-06-13 14:43 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-06-09 15:40 [PATCH net-next v9 00/15] Begin upstreaming Homa transport protocol John Ousterhout
2025-06-09 15:40 ` [PATCH net-next v9 01/15] net: homa: define user-visible API for Homa John Ousterhout
2025-06-09 15:40 ` [PATCH net-next v9 02/15] net: homa: create homa_wire.h John Ousterhout
2025-06-09 15:40 ` [PATCH net-next v9 03/15] net: homa: create shared Homa header files John Ousterhout
2025-06-13 14:40   ` Simon Horman
2025-06-13 18:36     ` John Ousterhout
2025-06-09 15:40 ` [PATCH net-next v9 04/15] net: homa: create homa_pool.h and homa_pool.c John Ousterhout
2025-06-09 15:40 ` [PATCH net-next v9 05/15] net: homa: create homa_peer.h and homa_peer.c John Ousterhout
2025-06-13 14:39   ` Simon Horman
2025-06-13 17:12     ` John Ousterhout
2025-06-13 17:18       ` Simon Horman
2025-06-13 18:02         ` John Ousterhout
2025-06-09 15:40 ` [PATCH net-next v9 06/15] net: homa: create homa_sock.h and homa_sock.c John Ousterhout
2025-06-13 14:42   ` Simon Horman
2025-06-13 18:47     ` John Ousterhout
2025-06-09 15:40 ` [PATCH net-next v9 07/15] net: homa: create homa_interest.h and homa_interest John Ousterhout
2025-06-09 15:40 ` [PATCH net-next v9 08/15] net: homa: create homa_pacer.h and homa_pacer.c John Ousterhout
2025-06-13 14:43   ` Simon Horman [this message]
2025-06-13 18:50     ` John Ousterhout
2025-06-09 15:40 ` [PATCH net-next v9 09/15] net: homa: create homa_rpc.h and homa_rpc.c John Ousterhout
2025-06-09 15:40 ` [PATCH net-next v9 10/15] net: homa: create homa_outgoing.c John Ousterhout
2025-06-09 15:40 ` [PATCH net-next v9 11/15] net: homa: create homa_utils.c John Ousterhout
2025-06-09 15:40 ` [PATCH net-next v9 12/15] net: homa: create homa_incoming.c John Ousterhout
2025-06-09 15:40 ` [PATCH net-next v9 13/15] net: homa: create homa_timer.c John Ousterhout
2025-06-13 14:41   ` Simon Horman
2025-06-13 18:44     ` John Ousterhout
2025-06-09 15:40 ` [PATCH net-next v9 14/15] net: homa: create homa_plumbing.c John Ousterhout
2025-06-09 15:40 ` [PATCH net-next v9 15/15] net: homa: create Makefile and Kconfig John Ousterhout
  -- strict thread matches above, loose matches on Subject: below --
2025-05-26  4:28 [PATCH net-next v9 00/15] Begin upstreaming Homa transport protocol John Ousterhout
2025-05-26  4:28 ` [PATCH net-next v9 08/15] net: homa: create homa_pacer.h and homa_pacer.c John Ousterhout

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=20250613144340.GL414686@horms.kernel.org \
    --to=horms@kernel.org \
    --cc=edumazet@google.com \
    --cc=kuba@kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=ouster@cs.stanford.edu \
    --cc=pabeni@redhat.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;
as well as URLs for NNTP newsgroup(s).