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;
From:   Hangliang Lai <laihangliang1@huawei.com>
To:     <namhyung@kernel.org>
CC:     <acme@kernel.org>, <adrian.hunter@intel.com>,
        <alexander.shishkin@linux.intel.com>, <brauner@kernel.org>,
        <hewenliang4@huawei.com>, <irogers@google.com>, <jolsa@kernel.org>,
        <laihangliang1@huawei.com>, <linfeilong@huawei.com>,
        <linux-kernel@vger.kernel.org>, <linux-perf-users@vger.kernel.org>,
        <liuwenyu7@huawei.com>, <mark.rutland@arm.com>, <mingo@redhat.com>,
        <yeyunfeng@huawei.com>
Subject: Re: [PATCH v2] perf top: expand the range of multithreaded phase
Date:   Mon, 10 Apr 2023 10:58:08 +0800
Message-ID: <20230410025808.2008-1-laihangliang1@huawei.com>
In-Reply-To: <CAM9d7cgK-P5KuDy7hkAR4j7oB4ydE6Mw3KexqgwPPhJF6MKtXQ@mail.gmail.com>
References: <CAM9d7cgK-P5KuDy7hkAR4j7oB4ydE6Mw3KexqgwPPhJF6MKtXQ@mail.gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8BIT
Content-Type: text/plain
Precedence: bulk

Thanks for your reply Kim ,


On 2023-04-07 21:21   you  wrote:


>  Not always, the synthesis can run in a single thread.


But I think in machine__synthesize_threads, there are thread_nr threads will be created to do synthesize_threads_worker(tools/perf/util/synthetic-events.c:970)


It’s not a single thread part. So we're supposed to call perf_set_multithreaded() before synthesize?


Thanks,

Hangliang Lai