Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
MIME-Version: 1.0
References: <20201009220524.485102-1-axelrasmussen@google.com> <20201009220524.485102-3-axelrasmussen@google.com>
In-Reply-To: <20201009220524.485102-3-axelrasmussen@google.com>
From:   Michel Lespinasse <walken@google.com>
Date:   Fri, 9 Oct 2020 15:35:00 -0700
Message-ID: <CANN689FYh6Uv+STH6f0oNHDwPdtg1etO8WM8GygFW55zH+ZrQQ@mail.gmail.com>
Subject: Re: [PATCH v3 2/2] mmap_lock: add tracepoints around lock acquisition
To:     Axel Rasmussen <axelrasmussen@google.com>
Cc:     Steven Rostedt <rostedt@goodmis.org>,
        Ingo Molnar <mingo@redhat.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Vlastimil Babka <vbabka@suse.cz>,
        Daniel Jordan <daniel.m.jordan@oracle.com>,
        Laurent Dufour <ldufour@linux.ibm.com>,
        Jann Horn <jannh@google.com>,
        Chinwen Chang <chinwen.chang@mediatek.com>,
        Yafang Shao <laoar.shao@gmail.com>,
        LKML <linux-kernel@vger.kernel.org>,
        linux-mm <linux-mm@kvack.org>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Fri, Oct 9, 2020 at 3:05 PM Axel Rasmussen <axelrasmussen@google.com> wrote:
> The goal of these tracepoints is to be able to debug lock contention
> issues. This lock is acquired on most (all?) mmap / munmap / page fault
> operations, so a multi-threaded process which does a lot of these can
> experience significant contention.
>
> We trace just before we start acquisition, when the acquisition returns
> (whether it succeeded or not), and when the lock is released (or
> downgraded). The events are broken out by lock type (read / write).
>
> The events are also broken out by memcg path. For container-based
> workloads, users often think of several processes in a memcg as a single
> logical "task", so collecting statistics at this level is useful.
>
> The end goal is to get latency information. This isn't directly included
> in the trace events. Instead, users are expected to compute the time
> between "start locking" and "acquire returned", using e.g. synthetic
> events or BPF. The benefit we get from this is simpler code.
>
> Because we use tracepoint_enabled() to decide whether or not to trace,
> this patch has effectively no overhead unless tracepoints are enabled at
> runtime. If tracepoints are enabled, there is a performance impact, but
> how much depends on exactly what e.g. the BPF program does.
>
> Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>

Reviewed-by: Michel Lespinasse <walken@google.com>

Looks good to me, thanks!