Netdev List
 help / color / mirror / Atom feed
From: Jakub Kicinski <kuba@kernel.org>
To: Vimal Agrawal <avimalin@gmail.com>, kuniyu@google.com
Cc: pabeni@redhat.com, netdev@vger.kernel.org, edumazet@google.com,
	vimal.agrawal@sophos.com
Subject: Re: [PATCH v4 net-next] net: neigh: avoid calling neigh_forced_gc on every alloc when table is full
Date: Tue, 21 Jul 2026 14:09:11 -0700	[thread overview]
Message-ID: <20260721140911.2e12e60c@kernel.org> (raw)
In-Reply-To: <20260715055311.90403-1-vimal.agrawal@sophos.com>

On Wed, 15 Jul 2026 05:53:11 +0000 Vimal Agrawal wrote:
> Once the neighbour table exceeds gc_thresh3, neigh_forced_gc() is called
> on every allocation attempt with no rate limiting. In workloads with mostly
> active/reachable entries, the GC walk traverses a large portion of the
> neighbour table without reclaiming entries, holding tbl->lock for an
> extended period. This causes severe lock contention and allocation
> latencies exceeding 16ms under sustained neighbour creation.
> 
> Add a pre-lock check in neigh_forced_gc() to skip the GC run if one was
> performed within the last 50 ms, but only when the table actually contains
> NEIGH_FORCED_GC_LARGE_TABLE_THRESH (16384) or more entries. This avoids
> repeated full table scans and lock acquisitions on the hot allocation path
> while leaving tables with few entries completely unaffected regardless of
> how gc_thresh3 is configured.

Hi Kuniyuki, are you still unconvinced by this?

  reply	other threads:[~2026-07-21 21:09 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-06-18  8:17 neigh: poor scalability of forced GC when neighbour count exceeds gc_thresh3 Vimal Agrawal
2026-06-25 10:20 ` [PATCH net-next] net: neigh: avoid calling neigh_forced_gc on every alloc when table is full Vimal Agrawal
2026-06-25 15:42   ` Jakub Kicinski
2026-07-06  6:58     ` [PATCH v2 " Vimal Agrawal
2026-07-06 14:19       ` Paolo Abeni
2026-07-14 13:39         ` [PATCH v3 " Vimal Agrawal
2026-07-15  5:53           ` [PATCH v4 " Vimal Agrawal
2026-07-21 21:09             ` Jakub Kicinski [this message]
2026-07-24 23:17               ` Jakub Kicinski
2026-08-03 13:51                 ` Vimal Agrawal
2026-06-25 21:45   ` [PATCH " Kuniyuki Iwashima
2026-06-29  7:57     ` Vimal Agrawal
2026-06-29 18:05       ` Kuniyuki Iwashima
2026-06-30 12:01         ` Vimal Agrawal
2026-06-30 16:36           ` Kuniyuki Iwashima
2026-07-01  8:30             ` Vimal Agrawal

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=20260721140911.2e12e60c@kernel.org \
    --to=kuba@kernel.org \
    --cc=avimalin@gmail.com \
    --cc=edumazet@google.com \
    --cc=kuniyu@google.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=vimal.agrawal@sophos.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