Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Wed, 19 Jul 2023 21:45:00 +0800
From:   Aaron Lu <aaron.lu@intel.com>
To:     Peter Zijlstra <peterz@infradead.org>
CC:     Ingo Molnar <mingo@redhat.com>, Juri Lelli <juri.lelli@redhat.com>,
        Vincent Guittot <vincent.guittot@linaro.org>,
        Daniel Jordan <daniel.m.jordan@oracle.com>,
        Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Ben Segall <bsegall@google.com>,
        "Mel Gorman" <mgorman@suse.de>,
        Daniel Bristot de Oliveira <bristot@redhat.com>,
        Valentin Schneider <vschneid@redhat.com>,
        Tim Chen <tim.c.chen@intel.com>,
        Nitin Tekchandani <nitin.tekchandani@intel.com>,
        Yu Chen <yu.c.chen@intel.com>,
        Waiman Long <longman@redhat.com>,
        <linux-kernel@vger.kernel.org>, <yury.norov@gmail.com>,
        <andriy.shevchenko@linux.intel.com>, <linux@rasmusvillemoes.dk>,
        <rppt@kernel.org>
Subject: Re: [RFC PATCH 2/4] sched/fair: Make tg->load_avg per node
Message-ID: <20230719134500.GB91858@ziqianlu-dell>
References: <20230718134120.81199-1-aaron.lu@intel.com>
 <20230718134120.81199-3-aaron.lu@intel.com>
 <20230719115358.GB3529734@hirez.programming.kicks-ass.net>
Content-Type: text/plain; charset="us-ascii"
Content-Disposition: inline
In-Reply-To: <20230719115358.GB3529734@hirez.programming.kicks-ass.net>
MIME-Version: 1.0
X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1
X-MS-Exchange-AntiSpam-MessageData-0: =?us-ascii?Q?NKtL09EwYtAcn6/AiiDJSYmTDcrKqu0a/D9vQNUpiiQmpNYW+RevXxr1aJjI?=
 =?us-ascii?Q?Zs3GpvxpdzIF28fm3ArkleI2jGzKieSW00xMVSF9C9SHwdeZwC9u3xMjSuV8?=
 =?us-ascii?Q?CxvfA2EJ3TGB6zrHdgqFLG8KN+fHMA6AP0UiYhG3QBiN7mIX+iFCYeuvY9GI?=
 =?us-ascii?Q?+2JqVfLObhA1wn9kAyJPiYUq0xJ/VGlLZK2c2xQlnyFJymKk5ricp06pXGoF?=
 =?us-ascii?Q?KjjmesCo2f6K56JjPmzYJX5+jXLUwKQsVCuox7RK/T2vUID9V+CSxkgHzYCz?=
 =?us-ascii?Q?USiGMxjgWWbMUMfEEkZUz2S1M7Ym68wy8Wwcvh1FUZIEwH/6tlu5GiOm4/Zy?=
 =?us-ascii?Q?nKRKoNALHhJFqAtM+i4ZqAWODvOIe0CL2ZzysqGjqOQyfxPXAYHgE3S7hsbq?=
 =?us-ascii?Q?vcxew9fMYubfbsWtZJ8eP1AOUk1VhbwBtNpjfzJH083gjQHkLwE+0yoRgJc6?=
 =?us-ascii?Q?JOf00PPZH+zfMaOVrUP4ZjPK46e6fPYkbjk207zf/mAmT2vaWZyhx+5ov5gG?=
 =?us-ascii?Q?pif8z73qwWQB/BWXKumoEjOlKk4WvFx/fXU4Gp8/CIbDZf+eTw+w46JJVmFT?=
 =?us-ascii?Q?Oq1DQ+yI2prphdILQcStAV7hufgs4hCmvArq5mIERYwXITX/r9/l4ZfGCw1Y?=
 =?us-ascii?Q?v1Mf2HZRDtcb2mjWCZCfYkbJ1E6s5z9ZbRk77cErFmW9jGiPIZCJLrLDgbz7?=
 =?us-ascii?Q?mevYZPCATd9sQQzEKwxs+ZdAq1sXPfkkRmkqj5zVch7gEf92mO2ZGzhOYbke?=
 =?us-ascii?Q?mpQn/0iQCOKWxxGkXZTzIQdNxS27aAf1kRTvtF90Rm4Mk+29mHXSbN3TBGz/?=
 =?us-ascii?Q?X8FuDHdQcSQiRkLN9gVKVQtBppvZskFYxFm3/PBaRXGqu6zcoe57QA7bIMNk?=
 =?us-ascii?Q?c4IT8x9vpkDe1y0vkWIqIwb2WKt3y9fLsgJL77csEWckLeZzWDDNHtaou1R9?=
 =?us-ascii?Q?sDi6Fa2NNX+ew2w65LwFFWVlbuekz+0xFIdETiqcrByFK2UK1xc08L7fhmOd?=
 =?us-ascii?Q?TS2ghQv1Rcar+gFCX1WoBvhBixjz4aMaWNIDpwo6E7oUg6gryE8jwbvLgtSG?=
 =?us-ascii?Q?W3CIjm+s2Bga1OCrpeKnytCDVCL2kvytJi3jVh9Rm/7oO8GanCB3iFuwJAEt?=
 =?us-ascii?Q?S/KyKWPfSigfjx0EpWQMV5ArSqSsjHuQBQjSacAoJ2MXVsvs/GgO+voh73EO?=
 =?us-ascii?Q?4JbgIFMf4mOMNzGGC6xz5GwYO3yAHRpnHgBl8dvSelzCo2ziVNCOXY9ID9dc?=
 =?us-ascii?Q?eLNTujWGpTbCF3zXz0MjLtF6fiwDJVZ81SSGl1FO04dquBhp7bv3rflZyeaS?=
 =?us-ascii?Q?kQqeaSN6INqAoH+l0GRpwLhJjenJcuWWKOmqTTanRJmvLk9FPH85olWeAoHz?=
 =?us-ascii?Q?XK4vQ6+tj6MeleFEsG7AIJFXTD2XKIT88QVFFY0ah8hDV1yY7D3PMFs3l5fE?=
 =?us-ascii?Q?7aJnToJyFUJ0y7AxAg58539ogDPo5SlyWSojJBs9disK7B3PqkcuzC4whZE4?=
 =?us-ascii?Q?89v5XBPNQyfmA3qPIOTRi8+hjlj+jC7LP0tDQX22ny8J4dYjmkk22d43BG3E?=
 =?us-ascii?Q?T9Ie5p2VIbKr1LWLCPaEfxYD0RQeVn2sSe3VU+OG?=
X-MS-Exchange-CrossTenant-Network-Message-Id: 5fa894c7-dcab-4c15-3a9c-08db885e6229
X-MS-Exchange-CrossTenant-AuthSource: BL0PR11MB3060.namprd11.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Internal
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 19 Jul 2023 13:45:16.8346
 (UTC)
X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted
X-MS-Exchange-CrossTenant-Id: 46c98d88-e344-4ed4-8496-4ed7712e255d
X-MS-Exchange-CrossTenant-MailboxType: HOSTED
X-MS-Exchange-CrossTenant-UserPrincipalName: Hg93QHYxhF+y4zFGF5CgeMAkjV73Y1kKaizcjO08gEwoxlW2l0l1fNUSDqIe33sfKcKdWcs9ZeN5YZ1pLmMF0w==
X-MS-Exchange-Transport-CrossTenantHeadersStamped: DS7PR11MB6037
X-OriginatorOrg: intel.com
X-Spam-Status: No, score=-2.1 required=5.0 tests=BAYES_00,DKIMWL_WL_HIGH,
        DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,
        RCVD_IN_DNSWL_BLOCKED,RCVD_IN_MSPIKE_H2,SPF_HELO_NONE,SPF_NONE,
        T_SCC_BODY_TEXT_LINE,URIBL_BLOCKED autolearn=ham autolearn_force=no
        version=3.4.6
X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on
        lindbergh.monkeyblade.net
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Wed, Jul 19, 2023 at 01:53:58PM +0200, Peter Zijlstra wrote:
> On Tue, Jul 18, 2023 at 09:41:18PM +0800, Aaron Lu wrote:
> > +#if defined(CONFIG_FAIR_GROUP_SCHED) && defined(CONFIG_SMP)
> > +static inline long tg_load_avg(struct task_group *tg)
> > +{
> > +	long load_avg = 0;
> > +	int i;
> > +
> > +	/*
> > +	 * The only path that can give us a root_task_group
> > +	 * here is from print_cfs_rq() thus unlikely.
> > +	 */
> > +	if (unlikely(tg == &root_task_group))
> > +		return 0;
> > +
> > +	for_each_node(i)
> > +		load_avg += atomic_long_read(&tg->node_info[i]->load_avg);
> > +
> > +	return load_avg;
> > +}
> > +#endif
> 
> So I was working on something else numa and noticed that for_each_node()
> (and most of the nodemask stuff) is quite moronic, afaict we should do
> something like the below.
> 
> I now see Mike added the nr_node_ids thing fairly recent, but given
> distros have NODES_SHIFT=10 and actual machines typically only have <=4
> nodes, this would save a factor of 256 scanning.

Nice :-)

> 
> Specifically, your for_each_node() would scan the full 1024 bit bitmap
> looking for more bits that would never be there.

Yes indeed.
I'll rebase this per-node patch on top of below diff.

Thanks for the info.

> 
> ---
> 
> diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
> index 8d07116caaf1..c23c0889b8cf 100644
> --- a/include/linux/nodemask.h
> +++ b/include/linux/nodemask.h
> @@ -109,7 +109,7 @@ extern nodemask_t _unused_nodemask_arg_;
>  				__nodemask_pr_bits(maskp)
>  static inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m)
>  {
> -	return m ? MAX_NUMNODES : 0;
> +	return m ? nr_node_ids : 0;
>  }
>  static inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m)
>  {
> @@ -137,13 +137,13 @@ static inline void __node_clear(int node, volatile nodemask_t *dstp)
>  	clear_bit(node, dstp->bits);
>  }
>  
> -#define nodes_setall(dst) __nodes_setall(&(dst), MAX_NUMNODES)
> +#define nodes_setall(dst) __nodes_setall(&(dst), nr_node_ids)
>  static inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits)
>  {
>  	bitmap_fill(dstp->bits, nbits);
>  }
>  
> -#define nodes_clear(dst) __nodes_clear(&(dst), MAX_NUMNODES)
> +#define nodes_clear(dst) __nodes_clear(&(dst), nr_node_ids)
>  static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits)
>  {
>  	bitmap_zero(dstp->bits, nbits);
> @@ -160,7 +160,7 @@ static inline bool __node_test_and_set(int node, nodemask_t *addr)
>  }
>  
>  #define nodes_and(dst, src1, src2) \
> -			__nodes_and(&(dst), &(src1), &(src2), MAX_NUMNODES)
> +			__nodes_and(&(dst), &(src1), &(src2), nr_node_ids)
>  static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p,
>  					const nodemask_t *src2p, unsigned int nbits)
>  {
> @@ -168,7 +168,7 @@ static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p,
>  }
>  
>  #define nodes_or(dst, src1, src2) \
> -			__nodes_or(&(dst), &(src1), &(src2), MAX_NUMNODES)
> +			__nodes_or(&(dst), &(src1), &(src2), nr_node_ids)
>  static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p,
>  					const nodemask_t *src2p, unsigned int nbits)
>  {
> @@ -176,7 +176,7 @@ static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p,
>  }
>  
>  #define nodes_xor(dst, src1, src2) \
> -			__nodes_xor(&(dst), &(src1), &(src2), MAX_NUMNODES)
> +			__nodes_xor(&(dst), &(src1), &(src2), nr_node_ids)
>  static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p,
>  					const nodemask_t *src2p, unsigned int nbits)
>  {
> @@ -184,7 +184,7 @@ static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p,
>  }
>  
>  #define nodes_andnot(dst, src1, src2) \
> -			__nodes_andnot(&(dst), &(src1), &(src2), MAX_NUMNODES)
> +			__nodes_andnot(&(dst), &(src1), &(src2), nr_node_ids)
>  static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p,
>  					const nodemask_t *src2p, unsigned int nbits)
>  {
> @@ -192,7 +192,7 @@ static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p,
>  }
>  
>  #define nodes_complement(dst, src) \
> -			__nodes_complement(&(dst), &(src), MAX_NUMNODES)
> +			__nodes_complement(&(dst), &(src), nr_node_ids)
>  static inline void __nodes_complement(nodemask_t *dstp,
>  					const nodemask_t *srcp, unsigned int nbits)
>  {
> @@ -200,7 +200,7 @@ static inline void __nodes_complement(nodemask_t *dstp,
>  }
>  
>  #define nodes_equal(src1, src2) \
> -			__nodes_equal(&(src1), &(src2), MAX_NUMNODES)
> +			__nodes_equal(&(src1), &(src2), nr_node_ids)
>  static inline bool __nodes_equal(const nodemask_t *src1p,
>  					const nodemask_t *src2p, unsigned int nbits)
>  {
> @@ -208,7 +208,7 @@ static inline bool __nodes_equal(const nodemask_t *src1p,
>  }
>  
>  #define nodes_intersects(src1, src2) \
> -			__nodes_intersects(&(src1), &(src2), MAX_NUMNODES)
> +			__nodes_intersects(&(src1), &(src2), nr_node_ids)
>  static inline bool __nodes_intersects(const nodemask_t *src1p,
>  					const nodemask_t *src2p, unsigned int nbits)
>  {
> @@ -216,33 +216,33 @@ static inline bool __nodes_intersects(const nodemask_t *src1p,
>  }
>  
>  #define nodes_subset(src1, src2) \
> -			__nodes_subset(&(src1), &(src2), MAX_NUMNODES)
> +			__nodes_subset(&(src1), &(src2), nr_node_ids)
>  static inline bool __nodes_subset(const nodemask_t *src1p,
>  					const nodemask_t *src2p, unsigned int nbits)
>  {
>  	return bitmap_subset(src1p->bits, src2p->bits, nbits);
>  }
>  
> -#define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES)
> +#define nodes_empty(src) __nodes_empty(&(src), nr_node_ids)
>  static inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits)
>  {
>  	return bitmap_empty(srcp->bits, nbits);
>  }
>  
> -#define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES)
> +#define nodes_full(nodemask) __nodes_full(&(nodemask), nr_node_ids)
>  static inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits)
>  {
>  	return bitmap_full(srcp->bits, nbits);
>  }
>  
> -#define nodes_weight(nodemask) __nodes_weight(&(nodemask), MAX_NUMNODES)
> +#define nodes_weight(nodemask) __nodes_weight(&(nodemask), nr_node_ids)
>  static inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits)
>  {
>  	return bitmap_weight(srcp->bits, nbits);
>  }
>  
>  #define nodes_shift_right(dst, src, n) \
> -			__nodes_shift_right(&(dst), &(src), (n), MAX_NUMNODES)
> +			__nodes_shift_right(&(dst), &(src), (n), nr_node_ids)
>  static inline void __nodes_shift_right(nodemask_t *dstp,
>  					const nodemask_t *srcp, int n, int nbits)
>  {
> @@ -250,7 +250,7 @@ static inline void __nodes_shift_right(nodemask_t *dstp,
>  }
>  
>  #define nodes_shift_left(dst, src, n) \
> -			__nodes_shift_left(&(dst), &(src), (n), MAX_NUMNODES)
> +			__nodes_shift_left(&(dst), &(src), (n), nr_node_ids)
>  static inline void __nodes_shift_left(nodemask_t *dstp,
>  					const nodemask_t *srcp, int n, int nbits)
>  {
> @@ -385,7 +385,7 @@ static inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp,
>  #if MAX_NUMNODES > 1
>  #define for_each_node_mask(node, mask)				    \
>  	for ((node) = first_node(mask);				    \
> -	     (node) < MAX_NUMNODES;				    \
> +	     (node) < nr_node_ids;				    \
>  	     (node) = next_node((node), (mask)))
>  #else /* MAX_NUMNODES == 1 */
>  #define for_each_node_mask(node, mask)                                  \