From: Dan Williams <dan.j.williams@intel.com>
To: Jeff Moyer <jmoyer@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>, Jens Axboe <axboe@kernel.dk>,
"linux-nvdimm@lists.01.org" <linux-nvdimm@ml01.01.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Linux ACPI <linux-acpi@vger.kernel.org>,
linux-fsdevel <linux-fsdevel@vger.kernel.org>,
Ingo Molnar <mingo@kernel.org>
Subject: Re: [PATCH 14/15] libnvdimm: support read-only btt backing devices
Date: Mon, 22 Jun 2015 12:04:05 -0700 [thread overview]
Message-ID: <CAPcyv4gr5rVBFcx-4xzs9z8zPGOXUMdQ-O5n7Tpo7ur2FxzNaw@mail.gmail.com> (raw)
In-Reply-To: <x49fv5jvasv.fsf@segfault.boston.devel.redhat.com>
On Mon, Jun 22, 2015 at 11:48 AM, Jeff Moyer <jmoyer@redhat.com> wrote:
> Christoph Hellwig <hch@lst.de> writes:
>
>> On Mon, Jun 22, 2015 at 12:42:44PM -0400, Jeff Moyer wrote:
>>> OK, add torn sector detection/recovery to that statement, then. More
>>> importantly, do you agree with the sentiment or not?
>>
>> I think we're getting on a very slipper slope if we think about
>> application here. Buffered I/O application must deal with torn
>> writes at any granulairty anyway, e.g. fsync + rename is the
>> only thing they can rely on right now (I actually have software O_ATOMIC
>> code to avoid this, but that's another story).
>
> OK, so you think applications using buffered I/O will Just Work(TM)? My
> guess is that things will start to break that hadn't broken in the
> past. Sure, the application isn't designed properly, and that should be
> fixed, but we shouldn't foist this on users as the default.
>
>> Direct I/O using application can make assumption if they know the sector
>> size, and we must have a way for them to be able to see our new
>> "subsector sector size".
>
> You need to let them determine that when NOT using the btt, yes. Right
> now, I don't think there's a way to determine what the underlying atomic
> write unit is. That's something the NFIT spec probably should have
> defined.
There are no atomic write units for NFIT to advertise beyond cpu register width.
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
WARNING: multiple messages have this Message-ID (diff)
From: Dan Williams <dan.j.williams@intel.com>
To: Jeff Moyer <jmoyer@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>, Jens Axboe <axboe@kernel.dk>,
"linux-nvdimm@lists.01.org" <linux-nvdimm@ml01.01.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Linux ACPI <linux-acpi@vger.kernel.org>,
linux-fsdevel <linux-fsdevel@vger.kernel.org>,
Ingo Molnar <mingo@kernel.org>
Subject: Re: [PATCH 14/15] libnvdimm: support read-only btt backing devices
Date: Mon, 22 Jun 2015 12:04:05 -0700 [thread overview]
Message-ID: <CAPcyv4gr5rVBFcx-4xzs9z8zPGOXUMdQ-O5n7Tpo7ur2FxzNaw@mail.gmail.com> (raw)
In-Reply-To: <x49fv5jvasv.fsf@segfault.boston.devel.redhat.com>
On Mon, Jun 22, 2015 at 11:48 AM, Jeff Moyer <jmoyer@redhat.com> wrote:
> Christoph Hellwig <hch@lst.de> writes:
>
>> On Mon, Jun 22, 2015 at 12:42:44PM -0400, Jeff Moyer wrote:
>>> OK, add torn sector detection/recovery to that statement, then. More
>>> importantly, do you agree with the sentiment or not?
>>
>> I think we're getting on a very slipper slope if we think about
>> application here. Buffered I/O application must deal with torn
>> writes at any granulairty anyway, e.g. fsync + rename is the
>> only thing they can rely on right now (I actually have software O_ATOMIC
>> code to avoid this, but that's another story).
>
> OK, so you think applications using buffered I/O will Just Work(TM)? My
> guess is that things will start to break that hadn't broken in the
> past. Sure, the application isn't designed properly, and that should be
> fixed, but we shouldn't foist this on users as the default.
>
>> Direct I/O using application can make assumption if they know the sector
>> size, and we must have a way for them to be able to see our new
>> "subsector sector size".
>
> You need to let them determine that when NOT using the btt, yes. Right
> now, I don't think there's a way to determine what the underlying atomic
> write unit is. That's something the NFIT spec probably should have
> defined.
There are no atomic write units for NFIT to advertise beyond cpu register width.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
Please read the FAQ at http://www.tux.org/lkml/
next prev parent reply other threads:[~2015-06-22 19:04 UTC|newest]
Thread overview: 164+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-06-17 23:54 [PATCH 00/15] libnvdimm: ->rw_bytes(), BLK-mode, unit tests, and misc features Dan Williams
2015-06-17 23:54 ` Dan Williams
2015-06-17 23:54 ` [PATCH 01/15] block: introduce an ->rw_bytes() block device operation Dan Williams
2015-06-17 23:54 ` Dan Williams
2015-06-18 19:25 ` Dan Williams
2015-06-18 19:25 ` Dan Williams
2015-06-17 23:54 ` [PATCH 02/15] libnvdimm: infrastructure for btt devices Dan Williams
2015-06-17 23:54 ` Dan Williams
2015-06-22 16:34 ` Christoph Hellwig
2015-06-22 16:34 ` Christoph Hellwig
2015-06-22 16:48 ` Dan Williams
2015-06-22 16:48 ` Dan Williams
2015-06-22 16:48 ` Christoph Hellwig
2015-06-22 16:48 ` Christoph Hellwig
2015-06-22 16:48 ` Christoph Hellwig
2015-06-22 18:32 ` Jeff Moyer
2015-06-22 18:32 ` Jeff Moyer
2015-06-22 18:32 ` Jeff Moyer
2015-06-22 19:02 ` Dan Williams
2015-06-22 19:02 ` Dan Williams
2015-06-22 19:02 ` Dan Williams
2015-06-22 19:09 ` Jeff Moyer
2015-06-22 19:09 ` Jeff Moyer
2015-06-22 19:09 ` Jeff Moyer
2015-06-23 10:20 ` Christoph Hellwig
2015-06-23 10:19 ` Christoph Hellwig
2015-06-23 15:19 ` Dan Williams
2015-06-23 20:33 ` Dan Williams
2015-06-24 12:10 ` Christoph Hellwig
2015-06-23 10:10 ` Christoph Hellwig
2015-06-17 23:55 ` [PATCH 03/15] nd_btt: atomic sector updates Dan Williams
2015-06-17 23:55 ` Dan Williams
2015-06-21 10:03 ` Christoph Hellwig
2015-06-21 10:03 ` Christoph Hellwig
2015-06-21 10:03 ` Christoph Hellwig
2015-06-21 16:31 ` Dan Williams
2015-06-21 16:31 ` Dan Williams
2015-06-17 23:55 ` [PATCH 04/15] libnvdimm, nfit, nd_blk: driver for BLK-mode access persistent memory Dan Williams
2015-06-17 23:55 ` Dan Williams
2015-06-21 10:05 ` Christoph Hellwig
2015-06-21 10:05 ` Christoph Hellwig
2015-06-21 10:05 ` Christoph Hellwig
2015-06-21 13:31 ` Dan Williams
2015-06-21 13:31 ` Dan Williams
2015-06-21 13:56 ` Christoph Hellwig
2015-06-21 13:56 ` Christoph Hellwig
2015-06-21 13:56 ` Christoph Hellwig
2015-06-21 14:39 ` Dan Williams
2015-06-21 14:39 ` Dan Williams
2015-06-21 14:39 ` Dan Williams
2015-06-17 23:55 ` [PATCH 05/15] tools/testing/nvdimm: libnvdimm unit test infrastructure Dan Williams
2015-06-17 23:55 ` Dan Williams
2015-06-17 23:55 ` [PATCH 06/15] libnvdimm: Non-Volatile Devices Dan Williams
2015-06-17 23:55 ` Dan Williams
2015-06-17 23:55 ` [PATCH 07/15] fs/block_dev.c: skip rw_page if bdev has integrity Dan Williams
2015-06-17 23:55 ` Dan Williams
2015-06-17 23:55 ` [PATCH 08/15] libnvdimm, btt: add support for blk integrity Dan Williams
2015-06-17 23:55 ` Dan Williams
2015-06-17 23:55 ` [PATCH 09/15] libnvdimm, blk: " Dan Williams
2015-06-17 23:55 ` Dan Williams
2015-06-17 23:55 ` [PATCH 10/15] libnvdimm: fix up max_hw_sectors Dan Williams
2015-06-17 23:55 ` Dan Williams
2015-06-21 10:08 ` Christoph Hellwig
2015-06-21 10:08 ` Christoph Hellwig
2015-06-21 10:08 ` Christoph Hellwig
2015-06-21 13:28 ` Dan Williams
2015-06-21 13:28 ` Dan Williams
2015-06-17 23:55 ` [PATCH 11/15] libnvdimm: pmem, blk, and btt make_request cleanups Dan Williams
2015-06-17 23:55 ` Dan Williams
2015-06-21 10:10 ` Christoph Hellwig
2015-06-21 10:10 ` Christoph Hellwig
2015-06-21 13:26 ` Dan Williams
2015-06-21 13:26 ` Dan Williams
2015-06-21 13:26 ` Dan Williams
2015-06-17 23:55 ` [PATCH 12/15] libnvdimm: enable iostat Dan Williams
2015-06-17 23:55 ` Dan Williams
2015-06-19 8:34 ` Christoph Hellwig
2015-06-19 8:34 ` Christoph Hellwig
2015-06-19 9:02 ` Dan Williams
2015-06-19 9:02 ` Dan Williams
2015-06-21 10:11 ` Christoph Hellwig
2015-06-21 10:11 ` Christoph Hellwig
2015-06-21 13:22 ` Dan Williams
2015-06-21 13:22 ` Dan Williams
2015-06-21 13:22 ` Dan Williams
2015-06-17 23:55 ` [PATCH 13/15] libnvdimm: flag libnvdimm block devices as non-rotational Dan Williams
2015-06-17 23:55 ` Dan Williams
2015-06-17 23:56 ` [PATCH 14/15] libnvdimm: support read-only btt backing devices Dan Williams
2015-06-17 23:56 ` Dan Williams
2015-06-18 22:55 ` Vishal Verma
2015-06-18 22:55 ` Vishal Verma
2015-06-21 10:13 ` Christoph Hellwig
2015-06-21 10:13 ` Christoph Hellwig
2015-06-21 13:21 ` Dan Williams
2015-06-21 13:21 ` Dan Williams
2015-06-21 13:21 ` Dan Williams
2015-06-21 13:54 ` Christoph Hellwig
2015-06-21 13:54 ` Christoph Hellwig
2015-06-21 13:54 ` Christoph Hellwig
2015-06-21 15:11 ` Dan Williams
2015-06-21 15:11 ` Dan Williams
2015-06-22 6:30 ` Christoph Hellwig
2015-06-22 6:30 ` Christoph Hellwig
2015-06-22 6:30 ` Christoph Hellwig
2015-06-22 7:17 ` Dan Williams
2015-06-22 7:17 ` Dan Williams
2015-06-22 7:17 ` Dan Williams
2015-06-22 7:28 ` Christoph Hellwig
2015-06-22 7:28 ` Christoph Hellwig
2015-06-22 7:28 ` Christoph Hellwig
2015-06-22 7:39 ` Dan Williams
2015-06-22 7:39 ` Dan Williams
2015-06-22 7:39 ` Dan Williams
2015-06-22 15:02 ` Jeff Moyer
2015-06-22 15:02 ` Jeff Moyer
2015-06-22 15:02 ` Jeff Moyer
2015-06-22 15:41 ` Christoph Hellwig
2015-06-22 15:41 ` Christoph Hellwig
2015-06-22 15:41 ` Christoph Hellwig
2015-06-22 16:00 ` Jeff Moyer
2015-06-22 16:00 ` Jeff Moyer
2015-06-22 16:00 ` Jeff Moyer
2015-06-22 16:32 ` Christoph Hellwig
2015-06-22 16:32 ` Christoph Hellwig
2015-06-22 16:32 ` Christoph Hellwig
2015-06-22 16:42 ` Jeff Moyer
2015-06-22 16:42 ` Jeff Moyer
2015-06-22 16:42 ` Jeff Moyer
2015-06-22 16:48 ` Christoph Hellwig
2015-06-22 16:48 ` Christoph Hellwig
2015-06-22 16:48 ` Christoph Hellwig
2015-06-22 18:48 ` Jeff Moyer
2015-06-22 18:48 ` Jeff Moyer
2015-06-22 18:48 ` Jeff Moyer
2015-06-22 19:04 ` Dan Williams [this message]
2015-06-22 19:04 ` Dan Williams
2015-06-22 19:11 ` Jeff Moyer
2015-06-22 19:11 ` Jeff Moyer
2015-06-22 19:11 ` Jeff Moyer
2015-06-23 10:10 ` Christoph Hellwig
2015-06-23 10:10 ` Christoph Hellwig
2015-06-22 15:40 ` Christoph Hellwig
2015-06-22 15:40 ` Christoph Hellwig
2015-06-22 15:40 ` Christoph Hellwig
2015-06-22 16:36 ` Dan Williams
2015-06-22 16:36 ` Dan Williams
2015-06-22 16:36 ` Dan Williams
2015-06-22 16:45 ` Christoph Hellwig
2015-06-22 16:45 ` Christoph Hellwig
2015-06-22 16:45 ` Christoph Hellwig
2015-06-22 16:54 ` Dan Williams
2015-06-22 16:54 ` Dan Williams
2015-06-22 16:54 ` Dan Williams
2015-06-22 16:57 ` Christoph Hellwig
2015-06-22 16:57 ` Christoph Hellwig
2015-06-22 16:59 ` Dan Williams
2015-06-22 16:59 ` Dan Williams
2015-06-22 16:59 ` Dan Williams
2015-06-23 19:30 ` Matthew Wilcox
2015-06-23 19:30 ` Matthew Wilcox
2015-06-24 12:11 ` Christoph Hellwig
2015-06-24 12:11 ` Christoph Hellwig
2015-06-17 23:56 ` [PATCH 15/15] libnvdimm, nfit: handle acpi_nfit_memory_map flags Dan Williams
2015-06-17 23:56 ` 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=CAPcyv4gr5rVBFcx-4xzs9z8zPGOXUMdQ-O5n7Tpo7ur2FxzNaw@mail.gmail.com \
--to=dan.j.williams@intel.com \
--cc=axboe@kernel.dk \
--cc=hch@lst.de \
--cc=jmoyer@redhat.com \
--cc=linux-acpi@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvdimm@ml01.01.org \
--cc=mingo@kernel.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.