cgroups.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Michal Koutný" <mkoutny@suse.com>
To: Kuniyuki Iwashima <kuniyu@google.com>
Cc: "David S. Miller" <davem@davemloft.net>,
	 Eric Dumazet <edumazet@google.com>,
	Jakub Kicinski <kuba@kernel.org>,
	 Neal Cardwell <ncardwell@google.com>,
	Paolo Abeni <pabeni@redhat.com>,
	 Willem de Bruijn <willemb@google.com>,
	Matthieu Baerts <matttbe@kernel.org>,
	 Mat Martineau <martineau@kernel.org>,
	Johannes Weiner <hannes@cmpxchg.org>,
	 Michal Hocko <mhocko@kernel.org>,
	Roman Gushchin <roman.gushchin@linux.dev>,
	 Shakeel Butt <shakeel.butt@linux.dev>,
	Andrew Morton <akpm@linux-foundation.org>,
	 Simon Horman <horms@kernel.org>,
	Geliang Tang <geliang@kernel.org>,
	 Muchun Song <muchun.song@linux.dev>,
	Kuniyuki Iwashima <kuni1840@gmail.com>,
	netdev@vger.kernel.org,  mptcp@lists.linux.dev,
	cgroups@vger.kernel.org, linux-mm@kvack.org
Subject: Re: [PATCH v1 net-next 13/13] net-memcg: Allow decoupling memcg from global protocol memory accounting.
Date: Thu, 31 Jul 2025 15:38:57 +0200	[thread overview]
Message-ID: <fq3wlkkedbv6ijj7pgc7haopgafoovd7qem7myccqg2ot43kzk@dui4war55ufk> (raw)
In-Reply-To: <20250721203624.3807041-14-kuniyu@google.com>

[-- Attachment #1: Type: text/plain, Size: 1852 bytes --]

On Mon, Jul 21, 2025 at 08:35:32PM +0000, Kuniyuki Iwashima <kuniyu@google.com> wrote:
> Some protocols (e.g., TCP, UDP) implement memory accounting for socket
> buffers and charge memory to per-protocol global counters pointed to by
> sk->sk_proto->memory_allocated.
> 
> When running under a non-root cgroup, this memory is also charged to the
> memcg as sock in memory.stat.
> 
> Even when memory usage is controlled by memcg, sockets using such protocols
> are still subject to global limits (e.g., /proc/sys/net/ipv4/tcp_mem).

IIUC the envisioned use case is that some cgroups feed from global
resource and some from their own limit.
It means the admin knows both:
  a) how to configure individual cgroup,
  b) how to configure global limit (for the rest).
So why cannot they stick to a single model only?

> This makes it difficult to accurately estimate and configure appropriate
> global limits, especially in multi-tenant environments.
> 
> If all workloads were guaranteed to be controlled under memcg, the issue
> could be worked around by setting tcp_mem[0~2] to UINT_MAX.
> 
> In reality, this assumption does not always hold, and a single workload
> that opts out of memcg can consume memory up to the global limit,
> becoming a noisy neighbour.

That doesn't like a good idea to remove limits from possibly noisy
units.

> Let's decouple memcg from the global per-protocol memory accounting.
> 
> This simplifies memcg configuration while keeping the global limits
> within a reasonable range.

I think this is a configuration issue only, i.e. instead of preserving
the global limit because of _some_ memcgs, the configuration management
could have a default memcg limit that is substituted to those memcgs so
that there's no risk of runaways even in absence of global limit.

Regards,
Michal

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]

  parent reply	other threads:[~2025-07-31 13:39 UTC|newest]

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-07-21 20:35 [PATCH v1 net-next 00/13] net-memcg: Allow decoupling memcg from sk->sk_prot->memory_allocated Kuniyuki Iwashima
2025-07-21 20:35 ` [PATCH v1 net-next 01/13] mptcp: Fix up subflow's memcg when CONFIG_SOCK_CGROUP_DATA=n Kuniyuki Iwashima
2025-07-22 14:30   ` Eric Dumazet
2025-07-21 20:35 ` [PATCH v1 net-next 02/13] mptcp: Use tcp_under_memory_pressure() in mptcp_epollin_ready() Kuniyuki Iwashima
2025-07-22 14:33   ` Eric Dumazet
2025-07-21 20:35 ` [PATCH v1 net-next 03/13] tcp: Simplify error path in inet_csk_accept() Kuniyuki Iwashima
2025-07-22 14:34   ` Eric Dumazet
2025-07-21 20:35 ` [PATCH v1 net-next 04/13] net: Call trace_sock_exceed_buf_limit() for memcg failure with SK_MEM_RECV Kuniyuki Iwashima
2025-07-22 14:37   ` Eric Dumazet
2025-07-21 20:35 ` [PATCH v1 net-next 05/13] net: Clean up __sk_mem_raise_allocated() Kuniyuki Iwashima
2025-07-22 14:38   ` Eric Dumazet
2025-07-21 20:35 ` [PATCH v1 net-next 06/13] net-memcg: Introduce mem_cgroup_from_sk() Kuniyuki Iwashima
2025-07-22 14:39   ` Eric Dumazet
2025-07-21 20:35 ` [PATCH v1 net-next 07/13] net-memcg: Introduce mem_cgroup_sk_enabled() Kuniyuki Iwashima
2025-07-22 14:40   ` Eric Dumazet
2025-07-21 20:35 ` [PATCH v1 net-next 08/13] net-memcg: Pass struct sock to mem_cgroup_sk_(un)?charge() Kuniyuki Iwashima
2025-07-22 14:56   ` Eric Dumazet
2025-07-21 20:35 ` [PATCH v1 net-next 09/13] net-memcg: Pass struct sock to mem_cgroup_sk_under_memory_pressure() Kuniyuki Iwashima
2025-07-22 14:58   ` Eric Dumazet
2025-07-21 20:35 ` [PATCH v1 net-next 10/13] net: Define sk_memcg under CONFIG_MEMCG Kuniyuki Iwashima
2025-07-22 14:58   ` Eric Dumazet
2025-07-21 20:35 ` [PATCH v1 net-next 11/13] net-memcg: Add memory.socket_isolated knob Kuniyuki Iwashima
2025-07-22 15:00   ` Eric Dumazet
2025-07-31 13:39   ` Michal Koutný
2025-07-21 20:35 ` [PATCH v1 net-next 12/13] net-memcg: Store memcg->socket_isolated in sk->sk_memcg Kuniyuki Iwashima
2025-07-22 15:02   ` Eric Dumazet
2025-07-21 20:35 ` [PATCH v1 net-next 13/13] net-memcg: Allow decoupling memcg from global protocol memory accounting Kuniyuki Iwashima
2025-07-22 15:14   ` Shakeel Butt
2025-07-22 15:24     ` Eric Dumazet
2025-07-22 15:52       ` Shakeel Butt
2025-07-22 18:18         ` Kuniyuki Iwashima
2025-07-22 18:47           ` Shakeel Butt
2025-07-22 19:03             ` Kuniyuki Iwashima
2025-07-22 19:56               ` Shakeel Butt
2025-07-22 21:59                 ` Kuniyuki Iwashima
2025-07-23  0:29                   ` Shakeel Butt
2025-07-23  2:35                     ` Kuniyuki Iwashima
2025-07-23 17:28                       ` Shakeel Butt
2025-07-23 18:06                         ` Kuniyuki Iwashima
2025-07-25  1:49                           ` Jakub Kicinski
2025-07-25 18:50                             ` Kuniyuki Iwashima
2025-07-28 16:07   ` Johannes Weiner
2025-07-28 21:41     ` Kuniyuki Iwashima
2025-07-29 14:22       ` Johannes Weiner
2025-07-29 19:41         ` Kuniyuki Iwashima
2025-07-31  2:58   ` Roman Gushchin
2025-07-31 13:38   ` Michal Koutný [this message]
2025-07-31 23:51     ` Kuniyuki Iwashima
2025-08-01  7:00       ` Michal Koutný
2025-08-01 16:27         ` Kuniyuki Iwashima
2025-07-22 15:04 ` [PATCH v1 net-next 00/13] net-memcg: Allow decoupling memcg from sk->sk_prot->memory_allocated Shakeel Butt
2025-07-22 15:34   ` Eric Dumazet

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=fq3wlkkedbv6ijj7pgc7haopgafoovd7qem7myccqg2ot43kzk@dui4war55ufk \
    --to=mkoutny@suse.com \
    --cc=akpm@linux-foundation.org \
    --cc=cgroups@vger.kernel.org \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=geliang@kernel.org \
    --cc=hannes@cmpxchg.org \
    --cc=horms@kernel.org \
    --cc=kuba@kernel.org \
    --cc=kuni1840@gmail.com \
    --cc=kuniyu@google.com \
    --cc=linux-mm@kvack.org \
    --cc=martineau@kernel.org \
    --cc=matttbe@kernel.org \
    --cc=mhocko@kernel.org \
    --cc=mptcp@lists.linux.dev \
    --cc=muchun.song@linux.dev \
    --cc=ncardwell@google.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=roman.gushchin@linux.dev \
    --cc=shakeel.butt@linux.dev \
    --cc=willemb@google.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).