From: Leon Romanovsky <leon@kernel.org>
To: Mykola Marzhan <mykola@meshstor.io>
Cc: Logan Gunthorpe <logang@deltatee.com>,
Jens Axboe <axboe@kernel.dk>, Song Liu <song@kernel.org>,
Yu Kuai <yukuai@fygo.io>, Keith Busch <kbusch@kernel.org>,
Christoph Hellwig <hch@lst.de>, Sagi Grimberg <sagi@grimberg.me>,
linux-block@vger.kernel.org, linux-raid@vger.kernel.org,
linux-nvme@lists.infradead.org,
Li Nan <magiclinan@didiglobal.com>, Xiao Ni <xiao@kernel.org>,
Guoqing Jiang <guoqing.jiang@linux.dev>,
Jason Gunthorpe <jgg@ziepe.ca>,
Kiran Kumar Modukuri <kmodukuri@nvidia.com>,
Chaitanya Kulkarni <kch@nvidia.com>,
Bjorn Helgaas <bhelgaas@google.com>,
Shivaji Kant <shivajikant@google.com>,
Pranjal Shrivastava <praan@google.com>,
Henrique Carvalho <henrique.carvalho@suse.com>,
linux-kernel@vger.kernel.org, linux-rdma@vger.kernel.org,
linux-pci@vger.kernel.org
Subject: Re: [PATCH v2 6/7] md/raid1,raid10: skip futile retries on P2PDMA mapping failures
Date: Thu, 23 Jul 2026 09:11:18 +0300 [thread overview]
Message-ID: <20260723061118.GA110966@unreal> (raw)
In-Reply-To: <CAPzsNDuGfneEmx_nWqw5vYLyPyK8krfWChNRcsxO7icTEDDX5g@mail.gmail.com>
On Wed, Jul 22, 2026 at 09:00:16PM +0200, Mykola Marzhan wrote:
> > I had thoughts about this series too. It seems best to avoid
> > the P2P path entirely unless all legs support P2P.
> >
> > Can the md/raid code determine P2P support in advance?
>
> Yes, and it already does: the block layer ANDs the P2PDMA queue
> feature across all legs, so an array with a non-P2P member
> (e.g. an nvme-tcp leg) never advertises P2P at all.
>
> But that flag can only say "this driver can do P2P in general".
> md cannot see which HCA device does the DMA for a fabrics leg —
> and with multipath failover it can change at any time.
>
> So the up-front gate covers what is knowable up front.
> This series is about the remainder.
> In mixed case, one local P2P leg plus a remote replica, with it:
> 1) a failed read just redirects to a capable mirror;
> 2) a failed write records bad blocks instead of retrying forever.
Thanks for the explanation.
>
> Mykola
>
next prev parent reply other threads:[~2026-07-23 6:11 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-07-19 10:53 [PATCH v2 0/7] block,md,nvme: correct handling of unsupported P2PDMA transfers Mykola Marzhan
2026-07-19 10:53 ` [PATCH v2 1/7] blk-mq-dma: restore BLK_STS_TARGET for unsupported P2P transfers Mykola Marzhan
2026-07-19 11:01 ` sashiko-bot
2026-07-20 14:49 ` Christoph Hellwig
[not found] ` <CAPzsNDv6hUV3gHdaxuwjRcr4couUKq_M5DKObFNaYqCHnm7ZMw@mail.gmail.com>
2026-07-20 18:42 ` Logan Gunthorpe
2026-07-20 18:49 ` Logan Gunthorpe
2026-07-21 17:49 ` Mykola Marzhan
2026-07-19 10:53 ` [PATCH v2 2/7] md: ensure REQ_NOMERGE is set on P2PDMA bios Mykola Marzhan
2026-07-19 11:02 ` sashiko-bot
2026-07-19 10:53 ` [PATCH v2 3/7] md/raid1: serialize non-write-behind writes on CollisionCheck rdevs Mykola Marzhan
2026-07-19 11:08 ` sashiko-bot
2026-07-19 10:53 ` [PATCH v2 4/7] md/raid1: don't use write-behind for P2PDMA bios Mykola Marzhan
2026-07-19 11:05 ` sashiko-bot
2026-07-20 16:31 ` Logan Gunthorpe
2026-07-19 10:53 ` [PATCH v2 5/7] md/raid1,raid10: keep REQ_NOMERGE on narrow_write_error() retry clones Mykola Marzhan
2026-07-19 11:20 ` sashiko-bot
2026-07-20 16:32 ` Logan Gunthorpe
2026-07-19 10:53 ` [PATCH v2 6/7] md/raid1,raid10: skip futile retries on P2PDMA mapping failures Mykola Marzhan
2026-07-19 11:11 ` sashiko-bot
2026-07-20 16:49 ` Logan Gunthorpe
2026-07-21 17:50 ` Mykola Marzhan
2026-07-21 23:38 ` Logan Gunthorpe
2026-07-22 8:30 ` Leon Romanovsky
2026-07-22 19:00 ` Mykola Marzhan
2026-07-23 6:11 ` Leon Romanovsky [this message]
2026-07-22 18:59 ` Mykola Marzhan
2026-07-19 10:53 ` [PATCH v2 7/7] nvme-rdma: return BLK_STS_TARGET for unsupported P2P transfers Mykola Marzhan
2026-07-19 11:17 ` sashiko-bot
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=20260723061118.GA110966@unreal \
--to=leon@kernel.org \
--cc=axboe@kernel.dk \
--cc=bhelgaas@google.com \
--cc=guoqing.jiang@linux.dev \
--cc=hch@lst.de \
--cc=henrique.carvalho@suse.com \
--cc=jgg@ziepe.ca \
--cc=kbusch@kernel.org \
--cc=kch@nvidia.com \
--cc=kmodukuri@nvidia.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=linux-pci@vger.kernel.org \
--cc=linux-raid@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=logang@deltatee.com \
--cc=magiclinan@didiglobal.com \
--cc=mykola@meshstor.io \
--cc=praan@google.com \
--cc=sagi@grimberg.me \
--cc=shivajikant@google.com \
--cc=song@kernel.org \
--cc=xiao@kernel.org \
--cc=yukuai@fygo.io \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox