From: Christoph Hellwig <hch-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>
To: Dan Williams <dan.j.williams-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
Cc: "linux-nvdimm-hn68Rpc1hR1g9hUCZPvPmw@public.gmane.org"
<linux-nvdimm-y27Ovi1pjclAfugRpC6u6w@public.gmane.org>,
Linux Kernel Mailing List
<linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
linux-f2fs-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org,
Christoph Hellwig <hch-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>,
linux-fsdevel
<linux-fsdevel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
Jaegeuk Kim <jaegeuk-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>,
sunqiuyang <sunqiuyang-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
Subject: Re: [PATCH v8 1/1] f2fs: dax: implement direct access
Date: Wed, 26 Jul 2017 10:20:11 -0700 [thread overview]
Message-ID: <20170726172011.GA30142@infradead.org> (raw)
In-Reply-To: <CAPcyv4iNP0qxL5vToffBivkQWyUquD7HrgNmvYXQW9ejhFrAmA-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
On Wed, Jul 26, 2017 at 10:11:08AM -0700, Dan Williams wrote:
> Until HMAT came along we had no data in the kernel how to pick a sane
> default, but we could now very easily make a "if pmem performance <
> dram, disable dax by default" policy in the kernel.
I'd rather do it the other way around - if HMAT is present and
pmem performance >= dram use dax. Else require the explicit -o dax
for now to enable it. If an explicit -o nodax is specified disable
DAX even if HMAT says it is faster.
> The question for this patch is do we want to add yet another
> filesystem that adds "-o dax" or require use of per-inode flags to
> enable dax.
Please stick to the mount option. After spending a lot of time with
DAX and various memory techologies I'm pretty confident that the inode
flag is the wrong thing to do.
WARNING: multiple messages have this Message-ID (diff)
From: Christoph Hellwig <hch@infradead.org>
To: Dan Williams <dan.j.williams@intel.com>
Cc: "linux-nvdimm@lists.01.org" <linux-nvdimm@ml01.01.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
linux-f2fs-devel@lists.sourceforge.net,
Christoph Hellwig <hch@infradead.org>,
linux-fsdevel <linux-fsdevel@vger.kernel.org>,
Jaegeuk Kim <jaegeuk@kernel.org>,
sunqiuyang <sunqiuyang@huawei.com>
Subject: Re: [PATCH v8 1/1] f2fs: dax: implement direct access
Date: Wed, 26 Jul 2017 10:20:11 -0700 [thread overview]
Message-ID: <20170726172011.GA30142@infradead.org> (raw)
In-Reply-To: <CAPcyv4iNP0qxL5vToffBivkQWyUquD7HrgNmvYXQW9ejhFrAmA@mail.gmail.com>
On Wed, Jul 26, 2017 at 10:11:08AM -0700, Dan Williams wrote:
> Until HMAT came along we had no data in the kernel how to pick a sane
> default, but we could now very easily make a "if pmem performance <
> dram, disable dax by default" policy in the kernel.
I'd rather do it the other way around - if HMAT is present and
pmem performance >= dram use dax. Else require the explicit -o dax
for now to enable it. If an explicit -o nodax is specified disable
DAX even if HMAT says it is faster.
> The question for this patch is do we want to add yet another
> filesystem that adds "-o dax" or require use of per-inode flags to
> enable dax.
Please stick to the mount option. After spending a lot of time with
DAX and various memory techologies I'm pretty confident that the inode
flag is the wrong thing to do.
_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm
WARNING: multiple messages have this Message-ID (diff)
From: Christoph Hellwig <hch@infradead.org>
To: Dan Williams <dan.j.williams@intel.com>
Cc: Christoph Hellwig <hch@infradead.org>,
"linux-nvdimm@lists.01.org" <linux-nvdimm@ml01.01.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
linux-f2fs-devel@lists.sourceforge.net,
linux-fsdevel <linux-fsdevel@vger.kernel.org>,
Jaegeuk Kim <jaegeuk@kernel.org>,
sunqiuyang <sunqiuyang@huawei.com>
Subject: Re: [PATCH v8 1/1] f2fs: dax: implement direct access
Date: Wed, 26 Jul 2017 10:20:11 -0700 [thread overview]
Message-ID: <20170726172011.GA30142@infradead.org> (raw)
In-Reply-To: <CAPcyv4iNP0qxL5vToffBivkQWyUquD7HrgNmvYXQW9ejhFrAmA@mail.gmail.com>
On Wed, Jul 26, 2017 at 10:11:08AM -0700, Dan Williams wrote:
> Until HMAT came along we had no data in the kernel how to pick a sane
> default, but we could now very easily make a "if pmem performance <
> dram, disable dax by default" policy in the kernel.
I'd rather do it the other way around - if HMAT is present and
pmem performance >= dram use dax. Else require the explicit -o dax
for now to enable it. If an explicit -o nodax is specified disable
DAX even if HMAT says it is faster.
> The question for this patch is do we want to add yet another
> filesystem that adds "-o dax" or require use of per-inode flags to
> enable dax.
Please stick to the mount option. After spending a lot of time with
DAX and various memory techologies I'm pretty confident that the inode
flag is the wrong thing to do.
next prev parent reply other threads:[~2017-07-26 17:20 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-07-20 12:10 [PATCH v8 1/1] f2fs: dax: implement direct access sunqiuyang
2017-07-20 12:10 ` sunqiuyang
2017-07-22 0:34 ` Jaegeuk Kim
2017-07-24 12:03 ` Sun Qiuyang
2017-07-24 12:03 ` Sun Qiuyang
[not found] ` <1500552639-18523-1-git-send-email-sunqiuyang-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
2017-07-26 0:15 ` Dan Williams
2017-07-26 0:15 ` Dan Williams
2017-07-26 0:15 ` Dan Williams
2017-07-26 2:16 ` Jaegeuk Kim
2017-07-26 2:16 ` Jaegeuk Kim
2017-07-26 6:47 ` sunqiuyang
2017-07-26 6:47 ` sunqiuyang
[not found] ` <CAA9_cmeyVXgu1-ozb7b346ANq+P3e3ATWYfoVGkAKrn5cmo=Hw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2017-07-26 7:26 ` Christoph Hellwig
2017-07-26 7:26 ` Christoph Hellwig
2017-07-26 7:26 ` Christoph Hellwig
2017-07-26 16:53 ` Dan Williams
2017-07-26 16:53 ` Dan Williams
2017-07-26 17:01 ` Christoph Hellwig
2017-07-26 17:01 ` Christoph Hellwig
[not found] ` <20170726170147.GA31930-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>
2017-07-26 17:11 ` Dan Williams
2017-07-26 17:11 ` Dan Williams
2017-07-26 17:11 ` Dan Williams
[not found] ` <CAPcyv4iNP0qxL5vToffBivkQWyUquD7HrgNmvYXQW9ejhFrAmA-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2017-07-26 17:20 ` Christoph Hellwig [this message]
2017-07-26 17:20 ` Christoph Hellwig
2017-07-26 17:20 ` Christoph Hellwig
2017-07-26 19:16 ` Dan Williams
2017-07-26 19:16 ` Dan Williams
[not found] ` <CAPcyv4hdk8XyYJ5pYvAgUZRoE-SzACNprQm1xaM1KUqBONC8Qw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2017-07-26 20:11 ` Christoph Hellwig
2017-07-26 20:11 ` Christoph Hellwig
2017-07-26 20:11 ` Christoph Hellwig
2017-07-26 20:29 ` Dan Williams
2017-07-26 20:29 ` Dan Williams
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=20170726172011.GA30142@infradead.org \
--to=hch-wegcikhe2lqwvfeawa7xhq@public.gmane.org \
--cc=dan.j.williams-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org \
--cc=jaegeuk-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org \
--cc=linux-f2fs-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org \
--cc=linux-fsdevel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=linux-nvdimm-y27Ovi1pjclAfugRpC6u6w@public.gmane.org \
--cc=sunqiuyang-hv44wF8Li93QT0dZR+AlfA@public.gmane.org \
/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.