All of lore.kernel.org
 help / color / mirror / Atom feed
From: hch@infradead.org (Christoph Hellwig)
Subject: [PATCH v4 0/8] Support for Open-Channel SSDs
Date: Tue, 9 Jun 2015 00:46:43 -0700	[thread overview]
Message-ID: <20150609074643.GA5707@infradead.org> (raw)
In-Reply-To: <1433508870-28251-1-git-send-email-m@bjorling.me>

Hi Matias,

I've been looking over this and I really think it needs a fundamental
rearchitecture still.  The design of using a separate stacking
block device and all kinds of private hooks does not look very
maintainable.

Here is my counter suggestion:

 - the stacking block device goes away
 - the nvm_target_type make_rq and prep_rq callbacks are combined
   into one and called from the nvme/null_blk ->queue_rq method
   early on to prepare the FTL state.  The drivers that are LightNVM
   enabled reserve a pointer to it in their per request data, which
   the unprep_rq callback is called on durign I/O completion.

WARNING: multiple messages have this Message-ID (diff)
From: Christoph Hellwig <hch@infradead.org>
To: Matias Bj??rling <m@bjorling.me>
Cc: hch@infradead.org, axboe@fb.com, linux-fsdevel@vger.kernel.org,
	linux-kernel@vger.kernel.org, linux-nvme@lists.infradead.org,
	Stephen.Bates@pmcs.com, keith.busch@intel.com,
	javier@lightnvm.io
Subject: Re: [PATCH v4 0/8] Support for Open-Channel SSDs
Date: Tue, 9 Jun 2015 00:46:43 -0700	[thread overview]
Message-ID: <20150609074643.GA5707@infradead.org> (raw)
In-Reply-To: <1433508870-28251-1-git-send-email-m@bjorling.me>

Hi Matias,

I've been looking over this and I really think it needs a fundamental
rearchitecture still.  The design of using a separate stacking
block device and all kinds of private hooks does not look very
maintainable.

Here is my counter suggestion:

 - the stacking block device goes away
 - the nvm_target_type make_rq and prep_rq callbacks are combined
   into one and called from the nvme/null_blk ->queue_rq method
   early on to prepare the FTL state.  The drivers that are LightNVM
   enabled reserve a pointer to it in their per request data, which
   the unprep_rq callback is called on durign I/O completion.

  parent reply	other threads:[~2015-06-09  7:46 UTC|newest]

Thread overview: 47+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-06-05 12:54 [PATCH v4 0/8] Support for Open-Channel SSDs Matias Bjørling
2015-06-05 12:54 ` Matias Bjørling
2015-06-05 12:54 ` Matias Bjørling
2015-06-05 12:54 ` [PATCH v4 1/8] nvme: add special param for nvme_submit_sync_cmd Matias Bjørling
2015-06-05 12:54   ` Matias Bjørling
2015-06-05 12:54 ` [PATCH v4 2/8] nvme: don't overwrite req->cmd_flags on sync cmd Matias Bjørling
2015-06-05 12:54   ` Matias Bjørling
2015-06-09  7:31   ` Christoph Hellwig
2015-06-09  7:31     ` Christoph Hellwig
2015-06-05 12:54 ` [PATCH v4 3/8] null_blk: wrong capacity when bs is not 512 bytes Matias Bjørling
2015-06-05 12:54   ` Matias Bjørling
2015-06-05 12:54 ` [PATCH v4 4/8] bio: Introduce LightNVM payload Matias Bjørling
2015-06-05 12:54   ` Matias Bjørling
2015-06-05 18:17   ` Matias Bjorling
2015-06-05 18:17     ` Matias Bjorling
2015-07-06 13:16     ` Pavel Machek
2015-07-06 13:16       ` Pavel Machek
2015-06-05 12:54 ` [PATCH v4 5/8] lightnvm: Support for Open-Channel SSDs Matias Bjørling
2015-06-05 12:54   ` Matias Bjørling
2015-06-05 12:54 ` [PATCH v4 6/8] lightnvm: RRPC target Matias Bjørling
2015-06-05 12:54   ` Matias Bjørling
2015-06-05 12:54   ` Matias Bjørling
2015-06-05 12:54 ` [PATCH v4 7/8] null_blk: LightNVM support Matias Bjørling
2015-06-05 12:54   ` Matias Bjørling
2015-06-05 12:54 ` [PATCH v4 8/8] nvme: " Matias Bjørling
2015-06-05 12:54   ` Matias Bjørling
2015-06-08 14:48 ` [PATCH v4 0/8] Support for Open-Channel SSDs Stephen Bates
2015-06-08 14:48   ` Stephen Bates
2015-06-08 14:48   ` Stephen Bates
2015-06-09  7:46 ` Christoph Hellwig [this message]
2015-06-09  7:46   ` Christoph Hellwig
2015-06-10 18:11   ` Matias Bjorling
2015-06-10 18:11     ` Matias Bjorling
2015-06-11 10:29     ` Christoph Hellwig
2015-06-11 10:29       ` Christoph Hellwig
2015-06-13 16:17       ` Matias Bjorling
2015-06-13 16:17         ` Matias Bjorling
2015-06-17 13:59         ` Christoph Hellwig
2015-06-17 13:59           ` Christoph Hellwig
2015-06-17 18:04           ` Matias Bjorling
2015-06-17 18:04             ` Matias Bjorling
2015-07-16 12:23           ` Matias Bjørling
2015-07-16 12:23             ` Matias Bjørling
2015-07-16 12:46             ` Christoph Hellwig
2015-07-16 12:46               ` Christoph Hellwig
2015-07-16 13:06               ` Matias Bjørling
2015-07-16 13:06                 ` Matias Bjørling

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=20150609074643.GA5707@infradead.org \
    --to=hch@infradead.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.