From: Stephen Hemminger <stephen@networkplumber.org>
To: "mannywang(王永峰)" <mannywang@tencent.com>
Cc: Konstantin Ananyev <konstantin.ananyev@huawei.com>, dev@dpdk.org
Subject: Re: [PATCH v3] acl: support custom memory allocator
Date: Thu, 11 Dec 2025 10:46:25 +0900 [thread overview]
Message-ID: <20251211104625.39632870@stephen-xps.local> (raw)
In-Reply-To: <16C60E2E552D75E0+20251125121446.41247-1-mannywang@tencent.com>
On Tue, 25 Nov 2025 12:14:46 +0000
"mannywang(王永峰)" <mannywang@tencent.com> wrote:
> Reduce memory fragmentation caused by dynamic memory allocations
> by allowing users to provide custom memory allocator.
>
> Add new members to struct rte_acl_config to allow passing custom
> allocator callbacks to rte_acl_build:
>
> - running_alloc: allocator callback for run-time internal memory
> - running_free: free callback for run-time internal memory
> - running_ctx: user-defined context passed to running_alloc/free
>
> - temp_alloc: allocator callback for temporary memory during ACL build
> - temp_reset: reset callback for temporary allocator
> - temp_ctx: user-defined context passed to temp_alloc/reset
>
> These callbacks allow users to provide their own memory pools or
> allocators for both persistent runtime structures and temporary
> build-time data.
>
> A typical approach is to pre-allocate a static memory region
> for rte_acl_ctx, and to provide a global temporary memory manager
> that supports multipleallocations and a single reset during ACL build.
>
> Since tb_mem_pool handles allocation failures using siglongjmp,
> temp_alloc follows the same approach for failure handling.
>
> Signed-off-by: YongFeng Wang <mannywang@tencent.com>
> ---
Rather than custom allocators, I did a couple of quick AI queries about
alternatives. It looks like there are some big global gains possible
here:
Summary of Recommendations
Improvement Benefit Complexity Priority
ACL Object Pooling Eliminates ACL-specific fragmentation Medium High
Size-Class Segregation Reduces general fragmentation High High
Slab Allocator for Build Better hugepage utilization Medium Medium
Deferred Coalescing Reduces fragmentation from churn Medium Medium
Thread-Local Caching Reduces contention, improves locality Medium Medium
Also adding some malloc_trim() would help.
https://claude.ai/share/75fcf73c-17e3-4f41-8590-f2ab640f9512
next prev parent reply other threads:[~2025-12-11 1:46 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-11-14 2:51 [RFC] rte_acl_build memory fragmentation concern and proposal for external memory support mannywang(王永峰)
2025-11-17 12:51 ` Konstantin Ananyev
2025-11-25 9:40 ` [PATCH] acl: support custom memory allocator =?gb18030?B?bWFubnl3YW5nKM3108C35Sk=?=
2025-11-25 12:06 ` [PATCH v2] " =?gb18030?B?bWFubnl3YW5nKM3108C35Sk=?=
2025-11-25 12:14 ` [PATCH v3] " =?gb18030?B?bWFubnl3YW5nKM3108C35Sk=?=
2025-11-25 14:59 ` Stephen Hemminger
2025-11-26 2:37 ` [Internet]Re: " =?gb18030?B?bWFubnl3YW5nKM3108C35Sk=?=
2025-11-25 18:01 ` Dmitry Kozlyuk
2025-11-26 2:44 ` [Internet]Re: " =?gb18030?B?bWFubnl3YW5nKM3108C35Sk=?=
2025-11-26 7:57 ` Dmitry Kozlyuk
2025-11-26 8:09 ` =?gb18030?B?bWFubnl3YW5nKM3108C35Sk=?=
2025-11-26 21:28 ` Stephen Hemminger
2025-11-27 2:05 ` [Internet]Re: " =?gb18030?B?bWFubnl3YW5nKM3108C35Sk=?=
2025-11-28 13:26 ` Konstantin Ananyev
2025-11-28 15:07 ` =?gb18030?B?bWFubnl3YW5nKM3108C35Sk=?=
2025-12-01 12:05 ` [PATCH v4] acl: support custom memory allocators in rte_acl_build =?gb18030?B?bWFubnl3YW5nKM3108C35Sk=?=
2025-12-01 15:59 ` Patrick Robb
2025-12-01 16:42 ` Stephen Hemminger
2025-12-02 9:33 ` [Internet]Re: " =?gb18030?B?bWFubnl3YW5nKM3108C35Sk=?=
2025-12-01 12:45 ` [PATCH v5] " =?gb18030?B?bWFubnl3YW5nKM3108C35Sk=?=
2025-12-02 2:47 ` fengchengwen
2025-12-02 9:25 ` [PATCH v6] acl: support custom memory allocators =?gb18030?B?bWFubnl3YW5nKM3108C35Sk=?=
2025-12-08 9:43 ` Konstantin Ananyev
2025-12-08 12:48 ` =?gb18030?B?bWFubnl3YW5nKM3108C35Sk=?=
2025-12-08 19:29 ` Stephen Hemminger
2025-12-09 2:30 ` [Internet]Re: " =?gb18030?B?bWFubnl3YW5nKM3108C35Sk=?=
2025-12-09 11:06 ` Konstantin Ananyev
2025-12-10 4:09 ` fengchengwen
2025-12-08 12:57 ` [PATCH v7] " =?gb18030?B?bWFubnl3YW5nKM3108C35Sk=?=
2025-12-09 10:59 ` Konstantin Ananyev
2025-12-09 12:56 ` [Internet]RE: " =?gb18030?B?bWFubnl3YW5nKM3108C35Sk=?=
2025-12-09 12:52 ` [PATCH v8] " =?gb18030?B?bWFubnl3YW5nKM3108C35Sk=?=
2025-12-02 9:31 ` [Internet]Re: [PATCH v5] acl: support custom memory allocators in rte_acl_build =?gb18030?B?bWFubnl3YW5nKM3108C35Sk=?=
2025-12-11 1:46 ` Stephen Hemminger [this message]
2025-12-11 2:22 ` [Internet]Re: [PATCH v3] acl: support custom memory allocator =?gb18030?B?bWFubnl3YW5nKM3108C35Sk=?=
2025-12-11 2:29 ` =?gb18030?B?bWFubnl3YW5nKM3108C35Sk=?=
2025-12-11 13:04 ` =?gb18030?B?bWFubnl3YW5nKM3108C35Sk=?=
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=20251211104625.39632870@stephen-xps.local \
--to=stephen@networkplumber.org \
--cc=dev@dpdk.org \
--cc=konstantin.ananyev@huawei.com \
--cc=mannywang@tencent.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).