From: James Smart <james.smart@broadcom.com>
To: Sagi Grimberg <sagi@grimberg.me>, linux-nvme@lists.infradead.org
Cc: linux-block@vger.kernel.org, Keith Busch <keith.busch@intel.com>,
Christoph Hellwig <hch@lst.de>
Subject: Re: [PATCH v2 0/5] implement nvmf read/write queue maps
Date: Wed, 12 Dec 2018 09:23:57 -0800 [thread overview]
Message-ID: <477ef7e7-bc81-5c27-84ba-27c75989bdc4@broadcom.com> (raw)
In-Reply-To: <20181211233519.9350-1-sagi@grimberg.me>
On 12/11/2018 3:35 PM, Sagi Grimberg wrote:
> This set implements read/write queue maps to nvmf (implemented in tcp
> and rdma). We basically allow the users to pass in nr_write_queues
> argument that will basically maps a separate set of queues to host
> write I/O (or more correctly non-read I/O) and a set of queues to
> hold read I/O (which is now controlled by the known nr_io_queues).
>
> A patchset that restores nvme-rdma polling is in the pipe.
> The polling is less trivial because:
> 1. we can find non I/O completions in the cq (i.e. memreg)
> 2. we need to start with non-polling for a sane connect and
> then switch to polling which is not trivial behind the
> cq API we use.
>
> Note that read/write separation for rdma but especially tcp this can be
> very clear win as we minimize the risk for head-of-queue blocking for
> mixed workloads over a single tcp byte stream.
Sagi,
What other wins are there for this split ?
I'm considering whether its worthwhile for fc as well, but the hol issue
doesn't exist with fc. What else is being resolved ?
-- james
next prev parent reply other threads:[~2018-12-12 17:24 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-12-11 23:35 [PATCH v2 0/5] implement nvmf read/write queue maps Sagi Grimberg
2018-12-11 23:35 ` [PATCH v2 1/5] blk-mq-rdma: pass in queue map to blk_mq_rdma_map_queues Sagi Grimberg
2018-12-11 23:35 ` [PATCH v2 2/5] nvme-fabrics: add missing nvmf_ctrl_options documentation Sagi Grimberg
2018-12-11 23:35 ` [PATCH v2 3/5] nvme-fabrics: allow user to set nr_write_queues for separate queue maps Sagi Grimberg
2018-12-11 23:35 ` [PATCH v2 4/5] nvme-tcp: support separate queue maps for read and write Sagi Grimberg
2018-12-12 7:05 ` Christoph Hellwig
2018-12-12 7:10 ` Sagi Grimberg
2018-12-11 23:35 ` [PATCH v2 5/5] nvme-rdma: " Sagi Grimberg
2018-12-12 7:05 ` Christoph Hellwig
2018-12-11 23:35 ` [PATCH v2 nvme-cli 6/5] fabrics: pass in number of write queues Sagi Grimberg
2018-12-12 17:23 ` James Smart [this message]
2018-12-12 17:58 ` [PATCH v2 0/5] implement nvmf read/write queue maps Sagi Grimberg
2018-12-12 19:15 ` James Smart
2018-12-13 12:04 ` Hannes Reinecke
2018-12-13 14:02 ` Jens Axboe
2018-12-13 14:19 ` Hannes Reinecke
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=477ef7e7-bc81-5c27-84ba-27c75989bdc4@broadcom.com \
--to=james.smart@broadcom.com \
--cc=hch@lst.de \
--cc=keith.busch@intel.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=sagi@grimberg.me \
/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;
as well as URLs for NNTP newsgroup(s).