mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Juri Lelli <juri.lelli@redhat.com>
To: Yuri Andriaccio <yurand2000@gmail.com>
Cc: "Ingo Molnar" <mingo@redhat.com>,
	"Peter Zijlstra" <peterz@infradead.org>,
	"Vincent Guittot" <vincent.guittot@linaro.org>,
	"Dietmar Eggemann" <dietmar.eggemann@arm.com>,
	"Steven Rostedt" <rostedt@goodmis.org>,
	"Ben Segall" <bsegall@google.com>, "Mel Gorman" <mgorman@suse.de>,
	"Valentin Schneider" <vschneid@redhat.com>,
	"Tejun Heo" <tj@kernel.org>,
	"Johannes Weiner" <hannes@cmpxchg.org>,
	"Michal Koutný" <mkoutny@suse.com>,
	cgroups@vger.kernel.org, linux-kernel@vger.kernel.org,
	"Luca Abeni" <luca.abeni@santannapisa.it>,
	"Yuri Andriaccio" <yuri.andriaccio@santannapisa.it>
Subject: Re: [RFC PATCH v6 00/25] Hierarchical Constant Bandwidth Server
Date: Tue, 23 Jun 2026 12:15:08 +0200	[thread overview]
Message-ID: <ajpcrDn2g2G9mGKp@jlelli-thinkpadt14gen4.remote.csb> (raw)
In-Reply-To: <20260608121546.69910-1-yurand2000@gmail.com>

Hi Yuri,

On 08/06/26 14:15, Yuri Andriaccio wrote:
> Hello,
> 
> This is the v6 for Hierarchical Constant Bandwidth Server, aiming at replacing
> the current RT_GROUP_SCHED mechanism with something more robust and
> theoretically sound. The patchset has been presented at OSPM25 and OSPM26
> (https://retis.sssup.it/ospm-summit/), and a summary of its inner workings can
> be found at https://lwn.net/Articles/1021332/ . You can find the previous
> versions of this patchset at the bottom of the page, in particular version 1
> which talks in more detail what this patchset is all about and how it is
> implemented.
> 
> This v6 version works on the comments by the reviewers and introduces the
> following meaningful changes:
> - Update to kernel version 7.1.
> - Refactorings and general cleanups.
> - Removal of substantial duplicated code.
> - Express more locking constraints in code.
> - New cpu.rt.max interface.
> - Refactoring of migration code to reduce code duplication.
>   The new migration code now reuses the existing push/pull and similar functions
>   and specializes where needed, substantially reducing the footprint of group
>   migration code from previous versions.

I've been working on a simple demo and benchmark suite for HCBS to
explore real-world like use cases and characterize the feature's
behavior. Different angle wrt your unit test suite (I believe).

The demo is available at:

  https://github.com/jlelli/hcbs-demo

The demo models three scenarios — Industrial PLC Convergence, Robotics
Compute Platform, and Precision Motion Control — each with multiple
cooperating SCHED_FIFO tasks at different priorities sharing a cgroup,
which is the key differentiator vs. plain SCHED_DEADLINE. An aggressor
subsystem overloads the system while HCBS contains it to its budget.

A side-by-side compare mode runs baseline and HCBS simultaneously on
separate cpuset partitions, with a live terminal dashboard showing the
contrast in real time.

Key findings from testing on an Intel Xeon Gold 6433N (4 isolated CPUs
via cpuset partition):

 - At 10ms task periods, HCBS provides perfect temporal isolation: zero
   victim deadline misses across all scenarios, while aggressors are
   correctly throttled to their budget.

 - At 1ms task periods, the dl-server period is the critical tuning
   parameter, less the bandwidth. A 10ms dl-server with 60% bandwidth
   caused ~10% miss rates because the worst-case throttle gap (4ms)
   spanned multiple 1ms deadlines. Switching to a 2ms dl-server period
   at just 30% bandwidth eliminated all misses.

 - A simple Rule of thumb might be to set the dl-server period to at
   most 2x the shortest task period in the cgroup (e.g., 2ms dl-server
   for 1ms tasks, 10ms for 10ms tasks). Would you (and Luca?) agree or
   would you suggest something different?

 - dl-server overhead itself appears negligible: a parameter sweep
   confirmed zero misses for a single task at all bandwidth/period
   combinations tested.

 - The current v6 has been quite stable throughout my testing — no
   warnings, no crashes, and the bandwidth isolation works as expected
   across all the scenarios and workload combinations I've tried.

The demo supports three workload backends:
 - rt-app (default): synthetic periodic tasks with configurable periods
 - RT-Bench TACLeBench (--rtbench): real algorithms (susan, dijkstra,
   FFT, mpeg2, etc.) matching each scenario's computation profile
 - stress-ng (--stress): mixed CPU/IO/cache/memory aggressors for
   realistic interference patterns

Recorded demos (asciinema):
  Industrial: https://asciinema.org/a/5e4BMdWxS7hmm4hI
  Robotics:   https://asciinema.org/a/Msj48XnJGgcCev7M
  Precision:  https://asciinema.org/a/56WC3bu7yrcQe9nz

Thanks for the great work on this patchset. Happy to hear if this demo
is of any interest, discuss any of the findings and/or understand if/how
this can be further expanded.

Best,
Juri


  parent reply	other threads:[~2026-06-23 10:15 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-06-08 12:15 Yuri Andriaccio
2026-06-08 12:15 ` [RFC PATCH v6 01/25] sched/deadline: Fix replenishment logic for non-deferred servers Yuri Andriaccio
2026-06-08 12:15 ` [RFC PATCH v6 02/25] sched/rt: Update default bandwidth for real-time tasks to ONE Yuri Andriaccio
2026-06-08 12:15 ` [RFC PATCH v6 03/25] sched/deadline: Do not access dl_se->rq directly Yuri Andriaccio
2026-06-08 12:15 ` [RFC PATCH v6 04/25] sched/deadline: Distinguish between dl_rq and my_q Yuri Andriaccio
2026-06-08 12:15 ` [RFC PATCH v6 05/25] sched/rt: Pass an rt_rq instead of an rq where needed Yuri Andriaccio
2026-06-08 12:15 ` [RFC PATCH v6 06/25] sched/rt: Move functions from rt.c to sched.h Yuri Andriaccio
2026-06-08 12:15 ` [RFC PATCH v6 07/25] sched/rt: Disable RT_GROUP_SCHED Yuri Andriaccio
2026-06-08 12:15 ` [RFC PATCH v6 08/25] sched/rt: Remove unnecessary runqueue pointer in struct rt_rq Yuri Andriaccio
2026-06-08 12:15 ` [RFC PATCH v6 09/25] sched/rt: Introduce HCBS specific structs in task_group Yuri Andriaccio
2026-06-08 12:15 ` [RFC PATCH v6 10/25] sched/core: Initialize HCBS specific structures Yuri Andriaccio
2026-06-08 12:15 ` [RFC PATCH v6 11/25] sched/deadline: Add dl_init_tg Yuri Andriaccio
2026-06-08 12:15 ` [RFC PATCH v6 12/25] sched/rt: Add {alloc/unregister/free}_rt_sched_group Yuri Andriaccio
2026-06-11  8:42   ` Juri Lelli
2026-06-08 12:15 ` [RFC PATCH v6 13/25] sched/deadline: Account rt-cgroups bandwidth in deadline tasks schedulability tests Yuri Andriaccio
2026-06-08 12:15 ` [RFC PATCH v6 14/25] sched/rt: Implement dl-server operations for rt-cgroups Yuri Andriaccio
2026-06-08 12:15 ` [RFC PATCH v6 15/25] sched/rt: Update task event callbacks for HCBS scheduling Yuri Andriaccio
2026-06-08 12:15 ` [RFC PATCH v6 16/25] sched/rt: Remove support for cgroups-v1 Yuri Andriaccio
2026-06-08 12:15 ` [RFC PATCH v6 17/25] sched/rt: Update rt-cgroup schedulability checks Yuri Andriaccio
2026-06-08 12:15 ` [RFC PATCH v6 18/25] sched/rt: Update task's RT runqueue when switching scheduling class Yuri Andriaccio
2026-06-08 12:15 ` [RFC PATCH v6 19/25] sched/rt: Remove old RT_GROUP_SCHED data structures Yuri Andriaccio
2026-06-08 12:15 ` [RFC PATCH v6 20/25] sched/rt: Add HCBS migration code to related functions Yuri Andriaccio
2026-06-08 12:15 ` [RFC PATCH v6 21/25] sched/rt: Hook HCBS migration functions Yuri Andriaccio
2026-06-08 12:15 ` [RFC PATCH v6 22/25] sched/core: Execute enqueued balance callbacks when changing allowed CPUs Yuri Andriaccio
2026-06-08 12:15 ` [RFC PATCH v6 23/25] sched/rt: Try pull task on empty server pick Yuri Andriaccio
2026-06-08 12:15 ` [RFC PATCH v6 24/25] sched/core: Execute enqueued balance callbacks after migrate_disable_switch Yuri Andriaccio
2026-06-08 12:15 ` [RFC PATCH v6 25/25] Documentation: Update documentation for real-time cgroups Yuri Andriaccio
2026-06-09 15:46 ` [RFC PATCH v6 00/25] Hierarchical Constant Bandwidth Server Juri Lelli
2026-06-09 16:23   ` Yuri Andriaccio
2026-06-10  9:21     ` Juri Lelli
2026-06-15 20:38 ` Tejun Heo
2026-06-16  7:52   ` luca abeni
2026-06-23 10:15 ` Juri Lelli [this message]
2026-06-24  7:19   ` luca abeni
2026-06-24 10:35     ` Juri Lelli

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=ajpcrDn2g2G9mGKp@jlelli-thinkpadt14gen4.remote.csb \
    --to=juri.lelli@redhat.com \
    --cc=bsegall@google.com \
    --cc=cgroups@vger.kernel.org \
    --cc=dietmar.eggemann@arm.com \
    --cc=hannes@cmpxchg.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luca.abeni@santannapisa.it \
    --cc=mgorman@suse.de \
    --cc=mingo@redhat.com \
    --cc=mkoutny@suse.com \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=tj@kernel.org \
    --cc=vincent.guittot@linaro.org \
    --cc=vschneid@redhat.com \
    --cc=yurand2000@gmail.com \
    --cc=yuri.andriaccio@santannapisa.it \
    /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®