Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Tue, 3 Dec 2019 11:12:52 +0100
From:   Jiri Olsa <jolsa@redhat.com>
To:     Alexey Budankov <alexey.budankov@linux.intel.com>
Cc:     Arnaldo Carvalho de Melo <acme@kernel.org>,
        Namhyung Kim <namhyung@kernel.org>,
        Alexander Shishkin <alexander.shishkin@linux.intel.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Ingo Molnar <mingo@redhat.com>,
        Andi Kleen <ak@linux.intel.com>,
        linux-kernel <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH v4 3/3] perf record: adapt affinity to machines with
 #CPUs > 1K
Message-ID: <20191203101252.GD17468@krava>
References: <f1e6e809-9e41-e410-57eb-1740512285a1@linux.intel.com>
 <2095b034-bf53-c374-0e34-adc006b00fbb@linux.intel.com>
MIME-Version: 1.0
In-Reply-To: <2095b034-bf53-c374-0e34-adc006b00fbb@linux.intel.com>
User-Agent: Mutt/1.12.1 (2019-06-15)
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: quoted-printable
Content-Disposition: inline
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Mon, Dec 02, 2019 at 09:58:48AM +0300, Alexey Budankov wrote:

SNIP

> =20
> -static void build_node_mask(int node, cpu_set_t *mask)
> +static void build_node_mask(int node, struct mmap_cpu_mask *mask)
>  {
>  =09int c, cpu, nr_cpus;
>  =09const struct perf_cpu_map *cpu_map =3D NULL;
> @@ -240,17 +242,23 @@ static void build_node_mask(int node, cpu_set_t *ma=
sk)
>  =09for (c =3D 0; c < nr_cpus; c++) {
>  =09=09cpu =3D cpu_map->map[c]; /* map c index to online cpu index */
>  =09=09if (cpu__get_node(cpu) =3D=3D node)
> -=09=09=09CPU_SET(cpu, mask);
> +=09=09=09set_bit(cpu, mask->bits);
>  =09}
>  }
> =20
> -static void perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap=
_params *mp)
> +static int perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_=
params *mp)
>  {
> -=09CPU_ZERO(&map->affinity_mask);
> +=09map->affinity_mask.nbits =3D cpu__max_cpu();
> +=09map->affinity_mask.bits =3D bitmap_alloc(map->affinity_mask.nbits);
> +=09if (!map->affinity_mask.bits)
> +=09=09return -1;

hum, this one should be also behind (rec->opts.affinity !=3D PERF_AFFINITY_=
SYS)
condition, right? sry I haven't noticed that before..

other than that it looks all good

thanks,
jirka