From: Sagi Grimberg <sagig@dev.mellanox.co.il>
To: Christoph Hellwig <hch@lst.de>, linux-rdma@vger.kernel.org
Cc: swise@opengridcomputing.com, sagig@mellanox.com,
bart.vanassche@sandisk.com, target-devel@vger.kernel.org
Subject: Re: [PATCH 7/9] IB/core: generic RDMA READ/WRITE API
Date: Thu, 3 Mar 2016 12:53:04 +0200 [thread overview]
Message-ID: <56D81790.8090305@dev.mellanox.co.il> (raw)
In-Reply-To: <1456784410-20166-8-git-send-email-hch@lst.de>
> +int rdma_rw_init_mrs(struct ib_qp *qp, struct ib_qp_init_attr *attr)
> +{
> + struct ib_device *dev = qp->pd->device;
> + int ret = 0;
> +
> + if (rdma_rw_use_mr(dev, attr->port_num)) {
> + ret = ib_mr_pool_init(qp, &qp->rdma_mrs,
> + attr->cap.max_rdma_ctxs, IB_MR_TYPE_MEM_REG,
> + dev->attrs.max_fast_reg_page_list_len);
Christoph,
This is a problem for mlx5 which exposes:
props->max_fast_reg_page_list_len = (unsigned int)-1;
Which is obviously wrong and needs to be corrected, but this is sort of
an overkill to allocate max supported unconditionally.
How about choosing a sane default of 256/512 pages for now? I don't
think we'll see a lot of larger transfers in iser/nvmf (which actually
need MRs for iWARP).
Alternatively we can allow the caller to limit the MR size?
next prev parent reply other threads:[~2016-03-03 10:53 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-02-29 22:20 generic RDMA READ/WRITE API V2 Christoph Hellwig
2016-02-29 22:20 ` [PATCH 3/9] IB/core: add a helper to check for READ WITH INVALIDATE support Christoph Hellwig
2016-03-01 9:02 ` Sagi Grimberg
2016-03-01 9:14 ` Christoph Hellwig
[not found] ` <56D55ABA.6070007-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
2016-03-01 15:45 ` Steve Wise
2016-03-03 13:10 ` 'Christoph Hellwig'
2016-03-03 15:31 ` Steve Wise
2016-03-03 17:53 ` Jason Gunthorpe
[not found] ` <20160303175301.GD15387-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2016-03-03 17:56 ` 'Christoph Hellwig'
[not found] ` <1456784410-20166-1-git-send-email-hch-jcswGhMUV9g@public.gmane.org>
2016-02-29 22:20 ` [PATCH 1/9] IB/cma: pass the port number to ib_create_qp Christoph Hellwig
2016-02-29 22:20 ` [PATCH 2/9] IB/core: allow passing mapping an offset into the SG in ib_map_mr_sg Christoph Hellwig
2016-02-29 23:13 ` Bart Van Assche
2016-03-01 6:50 ` Christoph Hellwig
2016-02-29 22:20 ` [PATCH 4/9] IB/core: refactor ib_create_qp Christoph Hellwig
2016-02-29 22:20 ` [PATCH 5/9] IB/core: add a simple MR pool Christoph Hellwig
2016-02-29 22:36 ` Bart Van Assche
2016-03-01 6:48 ` Christoph Hellwig
2016-03-01 19:12 ` Bart Van Assche
[not found] ` <56D5E989.9010006-XdAiOPVOjttBDgjK7y7TUQ@public.gmane.org>
2016-03-02 9:14 ` Christoph Hellwig
2016-02-29 22:20 ` [PATCH 6/9] IB/core: add a need_inval flag to struct ib_mr Christoph Hellwig
2016-02-29 22:40 ` Bart Van Assche
[not found] ` <56D4C8EC.8020805-XdAiOPVOjttBDgjK7y7TUQ@public.gmane.org>
2016-03-01 7:09 ` Christoph Hellwig
2016-02-29 22:20 ` [PATCH 7/9] IB/core: generic RDMA READ/WRITE API Christoph Hellwig
[not found] ` <1456784410-20166-8-git-send-email-hch-jcswGhMUV9g@public.gmane.org>
2016-02-29 22:28 ` Steve Wise
[not found] ` <56D4C615.5010202-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>
2016-03-01 7:21 ` Christoph Hellwig
2016-03-01 9:00 ` Sagi Grimberg
[not found] ` <56D55A1B.6030902-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
2016-03-01 9:13 ` Christoph Hellwig
[not found] ` <20160301091338.GA2208-jcswGhMUV9g@public.gmane.org>
2016-03-01 9:19 ` Sagi Grimberg
[not found] ` <56D55EB3.2050707-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
2016-03-01 15:47 ` Steve Wise
2016-03-01 15:44 ` Steve Wise
2016-02-29 23:12 ` Bart Van Assche
2016-03-01 6:50 ` Christoph Hellwig
2016-03-03 10:53 ` Sagi Grimberg [this message]
2016-03-03 12:02 ` Christoph Hellwig
[not found] ` <20160303120209.GC20543-jcswGhMUV9g@public.gmane.org>
2016-03-03 12:08 ` Sagi Grimberg
2016-03-03 12:22 ` Christoph Hellwig
2016-03-03 12:54 ` Sagi Grimberg
[not found] ` <56D8293C.1050306-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
2016-03-03 15:29 ` Steve Wise
2016-03-03 18:05 ` 'Christoph Hellwig'
2016-02-29 22:20 ` [PATCH 8/9] target: enhance and export target_alloc_sgl/target_free_sgl Christoph Hellwig
2016-02-29 22:20 ` [PATCH 9/9] IB/srpt: convert to the generic RDMA READ/WRITE API Christoph Hellwig
2016-03-01 21:38 ` Bart Van Assche
2016-03-02 9:14 ` Christoph Hellwig
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=56D81790.8090305@dev.mellanox.co.il \
--to=sagig@dev.mellanox.co.il \
--cc=bart.vanassche@sandisk.com \
--cc=hch@lst.de \
--cc=linux-rdma@vger.kernel.org \
--cc=sagig@mellanox.com \
--cc=swise@opengridcomputing.com \
--cc=target-devel@vger.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox