mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Matt Fleming <mfleming@cloudflare.com>
To: Marco Elver <elver@google.com>, Caleb Kan <calebkan1106@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	linux-mm@kvack.org,  linux-kernel@vger.kernel.org,
	kasan-dev@googlegroups.com, Vlastimil Babka <vbabka@kernel.org>,
	 Alexander Potapenko <glider@google.com>,
	Dmitry Vyukov <dvyukov@google.com>,
	 Andrey Konovalov <andreyknvl@gmail.com>,
	Oscar Salvador <osalvador@suse.de>,
	 Caleb Kan <ckan@cloudflare.com>,
	kernel-team@cloudflare.com
Subject: Re: [PATCH RFC v2 00/11] stackdepot: reduce memory use for persistent stack records with a trie
Date: Wed, 7 Oct 2026 11:34:04 +0100	[thread overview]
Message-ID: <asYc-sRxG6kyu5yh@matt-Precision-5490> (raw)
In-Reply-To: <20260908-stackdepot-trie-v2-0-1996d5cef732@cloudflare.com>

On Tue, Sep 08, 2026 at 02:13:33PM +0100, Caleb Kan wrote:
> Hi,
> 
> This series reduces the memory used by persistent stack depot records by
> sharing common frame prefixes in a path-compressed trie.
> 
> Cloudflare runs KASAN on pre-production servers so allocation and free
> stack traces are available when diagnosing memory-safety bugs. On some of
> these servers, stack depot exhausted its pool budget even after we raised
> stack_depot_max_pools from 8,192 to 32,768. Once the depot is full, a new
> persistent trace returns no handle and a later KASAN report can lose the
> history needed to explain the bug.
> 
> With 4 KiB pages, 32,768 order-2 pools allow 512 MiB of stack storage.
> Doubling the limit again would allow 1 GiB, but it would not change the
> linear growth: the hash backend shares identical complete traces, while
> two traces that differ by one frame are still stored independently.
> 
> The trie is opt-in and disabled by default.

Hey Marco,

Do you have any more feedback on this series? Particularly the bug fix
in patch 1?

Thanks,
Matt

  parent reply	other threads:[~2026-10-07 10:34 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-08 13:13 Caleb Kan
2026-09-08 13:13 ` [PATCH RFC v2 01/11] stackdepot: stop preallocating after the final pool Caleb Kan
2026-10-16 16:53   ` Marco Elver
2026-09-08 13:13 ` [PATCH RFC v2 02/11] stackdepot: add caller-owned stack trace fetching Caleb Kan
2026-10-20 11:00   ` Marco Elver
2026-09-08 13:13 ` [PATCH RFC v2 03/11] mm/page_owner: preserve accounting with countable stack depot records Caleb Kan
2026-10-20 11:11   ` Marco Elver
2026-09-08 13:13 ` [PATCH RFC v2 04/11] mm/kmemleak: print trie-backed stack depot traces Caleb Kan
2026-09-08 13:13 ` [PATCH RFC v2 05/11] kmsan: report " Caleb Kan
2026-10-20 14:53   ` Marco Elver
2026-09-08 13:13 ` [PATCH RFC v2 06/11] mm/slub: materialize " Caleb Kan
2026-09-08 13:13 ` [PATCH RFC v2 07/11] drm/locking: preserve deadlock diagnostics for trie-backed stacks Caleb Kan
2026-09-08 13:13 ` [PATCH RFC v2 08/11] scripts/gdb: reject trie-backed stack depot handles Caleb Kan
2026-09-08 13:13 ` [PATCH RFC v2 09/11] stackdepot: add architecture hooks for compact frame storage Caleb Kan
2026-10-20 14:56   ` Marco Elver
2026-09-08 13:13 ` [PATCH RFC v2 10/11] stackdepot: share persistent stack prefixes with trie storage Caleb Kan
2026-10-20 15:04   ` Marco Elver
2026-09-08 13:13 ` [PATCH RFC v2 11/11] stackdepot: add KUnit tests for " Caleb Kan
2026-10-07 10:34 ` Matt Fleming [this message]
2026-10-20 15:07 ` [PATCH RFC v2 00/11] stackdepot: reduce memory use for persistent stack records with a trie Marco Elver

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=asYc-sRxG6kyu5yh@matt-Precision-5490 \
    --to=mfleming@cloudflare.com \
    --cc=akpm@linux-foundation.org \
    --cc=andreyknvl@gmail.com \
    --cc=calebkan1106@gmail.com \
    --cc=ckan@cloudflare.com \
    --cc=dvyukov@google.com \
    --cc=elver@google.com \
    --cc=glider@google.com \
    --cc=kasan-dev@googlegroups.com \
    --cc=kernel-team@cloudflare.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=osalvador@suse.de \
    --cc=vbabka@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
all inboxes | Powered by JetHome®