All of lore.kernel.org
 help / color / mirror / Atom feed
From: Dave Hansen <dave.hansen@intel.com>
To: Zi Yan <ziy@nvidia.com>, Saravanan D <saravanand@fb.com>,
	Xing Zhengjun <zhengjun.xing@linux.intel.com>
Cc: x86@kernel.org, dave.hansen@linux.intel.com, luto@kernel.org,
	peterz@infradead.org, corbet@lwn.net, willy@infradead.org,
	linux-kernel@vger.kernel.org, kernel-team@fb.com,
	linux-doc@vger.kernel.org, linux-mm@kvack.org,
	songliubraving@fb.com
Subject: Re: [PATCH V5] x86/mm: Tracking linear mapping split events
Date: Thu, 28 Jan 2021 08:41:26 -0800	[thread overview]
Message-ID: <15a29679-ea0b-d1c8-1a1f-698d3db35293@intel.com> (raw)
In-Reply-To: <EBB7E363-FE25-453C-89C6-9FC4A90615B9@nvidia.com>

On 1/28/21 8:33 AM, Zi Yan wrote:
>> One of the many lasting (as we don't coalesce back) sources for
>> huge page splits is tracing as the granular page
>> attribute/permission changes would force the kernel to split code
>> segments mapped to huge pages to smaller ones thereby increasing
>> the probability of TLB miss/reload even after tracing has been
>> stopped.
> It is interesting to see this statement saying splitting kernel
> direct mappings causes performance loss, when Zhengjun (cc’d) from
> Intel recently posted a kernel direct mapping performance report[1]
> saying 1GB mappings are good but not much better than 2MB and 4KB
> mappings.

No, that's not what the report said.

*Overall*, there is no clear winner between 4k, 2M and 1G.  In other
words, no one page size is best for *ALL* workloads.

There were *ABSOLUTELY* individual workloads in those tests that saw
significant deltas between the direct map sizes.  There are also
real-world workloads that feel the impact here.

  reply	other threads:[~2021-01-28 16:46 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <BYAPR01MB40856478D5BE74CB6A7D5578CFBD9@BYAPR01MB4085.prod.exchangelabs.com>
2021-01-25 20:15 ` [PATCH] x86/mm: Tracking linear mapping split events since boot Dave Hansen
2021-01-25 20:32   ` Tejun Heo
2021-01-26  0:47     ` Dave Hansen
2021-01-26  0:53       ` Tejun Heo
2021-01-26  1:04         ` Dave Hansen
2021-01-26  1:17           ` Tejun Heo
2021-01-27 17:51           ` [PATCH V2] x86/mm: Tracking linear mapping split events Saravanan D
2021-01-27 21:03             ` Tejun Heo
2021-01-27 21:32               ` Dave Hansen
2021-01-27 21:36                 ` Tejun Heo
2021-01-27 21:42                   ` Saravanan D
2021-01-27 22:50                   ` [PATCH V3] " Saravanan D
2021-01-27 23:00                     ` Randy Dunlap
2021-01-27 23:56                       ` Saravanan D
2021-01-27 23:41                     ` Dave Hansen
2021-01-28  0:15                       ` Saravanan D
2021-01-28  4:35                       ` [PATCH V4] " Saravanan D
2021-01-28  4:51                         ` Matthew Wilcox
2021-01-28 10:49                           ` [PATCH V5] " Saravanan D
2021-01-28 15:04                             ` Matthew Wilcox
2021-01-28 19:49                               ` Saravanan D
2021-01-28 16:33                             ` Zi Yan
2021-01-28 16:41                               ` Dave Hansen [this message]
2021-01-28 16:56                                 ` Zi Yan
2021-01-28 16:59                               ` Song Liu
2021-01-28 19:17                             ` Dave Hansen
2021-01-28 21:20                               ` Saravanan D
2021-01-28 23:34                                 ` [PATCH V6] " Saravanan D
2021-01-28 23:41                                   ` Tejun Heo
2021-01-29 19:27                                   ` Johannes Weiner
2021-02-08 23:17                                     ` Saravanan D
2021-02-08 23:30                                   ` Dave Hansen

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=15a29679-ea0b-d1c8-1a1f-698d3db35293@intel.com \
    --to=dave.hansen@intel.com \
    --cc=corbet@lwn.net \
    --cc=dave.hansen@linux.intel.com \
    --cc=kernel-team@fb.com \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@kernel.org \
    --cc=peterz@infradead.org \
    --cc=saravanand@fb.com \
    --cc=songliubraving@fb.com \
    --cc=willy@infradead.org \
    --cc=x86@kernel.org \
    --cc=zhengjun.xing@linux.intel.com \
    --cc=ziy@nvidia.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.