Re: [PATCH] procfs: add syscall statistics

From: Peter Zijlstra <peterz@infradead.org>
To: Zhang Yuchen <zhangyuchen.lcr@bytedance.com>
Cc: akpm@linux-foundation.org, david@redhat.com, mingo@redhat.com,
	ast@kernel.org, linux-kernel@vger.kernel.org,
	linux-fsdevel@vger.kernel.org, linux-doc@vger.kernel.org,
	linux-arm-kernel@lists.infradead.org, linux-s390@vger.kernel.org,
	linux-api@vger.kernel.org, fam.zheng@bytedance.com
Subject: Re: [PATCH] procfs: add syscall statistics
Date: Fri, 27 May 2022 14:18:20 +0200	[thread overview]
Message-ID: <YpDBjDTpS4evca3F@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <20220527110959.54559-1-zhangyuchen.lcr@bytedance.com>

On Fri, May 27, 2022 at 07:09:59PM +0800, Zhang Yuchen wrote:
> Add /proc/syscalls to display percpu syscall count.
> 
> We need a less resource-intensive way to count syscall per cpu
> for system problem location.
> 
> There is a similar utility syscount in the BCC project, but syscount
> has a high performance cost.
> 
> The following is a comparison on the same machine, using UnixBench
> System Call Overhead:
> 
>     ┏━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━┓
>     ┃ Change        ┃ Unixbench Score ┃ Loss   ┃
>     ┡━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━┩
>     │ no change     │ 1072.6          │ ---    │
>     │ syscall count │ 982.5           │ 8.40%  │
>     │ bpf syscount  │ 614.2           │ 42.74% │
>     └───────────────┴─────────────────┴────────┘
> 
> UnixBench System Call Use sys_gettid to test, this system call only reads
> one variable, so the performance penalty seems large. When tested with
> fork, the test scores were almost the same.
> 
> So the conclusion is that it does not have a significant impact on system
> call performance.
> 
> This function depends on CONFIG_FTRACE_SYSCALLS because the system call
> number is stored in syscall_metadata.

Death by a thousand cuts. 99% of people won't ever use this.

NAK