[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <761811e5-d693-ed33-c6ba-ce8cf2e5046c@linux.intel.com>
Date: Sun, 23 May 2021 20:43:54 -0700
From: Andi Kleen <ak@...ux.intel.com>
To: Samuel Neves <sneves@....uc.pt>, x86@...nel.org,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH] x86/usercopy: speed up 64-bit __clear_user() with
stos{b,q}
On 5/23/2021 11:04 AM, Samuel Neves wrote:
> The
> This change is noticeable from userspace. That is in fact how I spotted it; in
> a hashing benchmark that read from /dev/zero, around 10-15% of the CPU time
> was spent in __clear_user. After this patch, on a Skylake CPU, these are the
> before/after figures:
>
> $ dd if=/dev/zero of=/dev/null bs=1024k status=progress
> 94402248704 bytes (94 GB, 88 GiB) copied, 6 s, 15.7 GB/s
The question is of course if this actually represents any real workload.
-Andi
Powered by blists - more mailing lists