From: Max Gurtovoy <maxg@mellanox.com>
To: Bart Van Assche <bvanassche@acm.org>,
<linux-nvme@lists.infradead.org>, <sagi@grimberg.me>,
<hch@lst.de>, <loberman@redhat.com>, <linux-rdma@vger.kernel.org>
Cc: rgirase@redhat.com, vladimirk@mellanox.com, shlomin@mellanox.com,
leonro@mellanox.com, dledford@redhat.com, jgg@mellanox.com,
oren@mellanox.com, kbusch@kernel.org, idanb@mellanox.com
Subject: Re: [PATCH v2 3/5] nvmet-rdma: use SRQ per completion vector
Date: Thu, 19 Mar 2020 11:15:50 +0200 [thread overview]
Message-ID: <5623419a-39e6-6090-4ae2-d4725a8b9740@mellanox.com> (raw)
In-Reply-To: <d72e0312-1dfd-460e-bc83-49699d86dd64@acm.org>
On 3/19/2020 6:09 AM, Bart Van Assche wrote:
> On 2020-03-18 08:02, Max Gurtovoy wrote:
>> In order to save resource allocation and utilize the completion
> ^^^^^^^^^^^^^^^^^^^
> resources?
thanks.
>
>> +static int nvmet_rdma_srq_size = 1024;
>> +module_param_cb(srq_size, &srq_size_ops, &nvmet_rdma_srq_size, 0644);
>> +MODULE_PARM_DESC(srq_size, "set Shared Receive Queue (SRQ) size, should >= 256 (default: 1024)");
> Is an SRQ overflow fatal? Isn't the SRQ size something that should be
> computed by the nvmet_rdma driver such that SRQ overflows do not happen?
I've added the following code to make sure that the size is not greater
than device capability:
+ndev->srq_size = min(ndev->device->attrs.max_srq_wr,
+ nvmet_rdma_srq_size);
In case the SRQ doesn't have enough credits it will send rnr to the
initiator and the initiator will retry later on.
We might need to change the min_rnr_timer during the connection
establishment, but still didn't see the need for it.
-Max
>
> Thanks,
>
> Bart.
_______________________________________________
linux-nvme mailing list
linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme
next prev parent reply other threads:[~2020-03-19 9:16 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-18 15:02 [PATCH v2 0/5] nvmet-rdma/srpt: SRQ per completion vector Max Gurtovoy
2020-03-18 15:02 ` [PATCH v2 1/5] IB/core: add a simple SRQ pool per PD Max Gurtovoy
2020-03-20 5:59 ` Sagi Grimberg
2020-03-20 13:21 ` Max Gurtovoy
2020-03-20 14:27 ` Leon Romanovsky
2020-03-18 15:02 ` [PATCH v2 2/5] nvmet-rdma: add srq pointer to rdma_cmd Max Gurtovoy
2020-03-18 23:32 ` Jason Gunthorpe
2020-03-19 8:48 ` Max Gurtovoy
2020-03-19 9:14 ` Leon Romanovsky
2020-03-19 10:55 ` Max Gurtovoy
2020-03-19 11:54 ` Jason Gunthorpe
2020-03-19 14:08 ` Konstantin Ryabitsev
2020-03-19 21:58 ` Konstantin Ryabitsev
2020-03-19 4:05 ` Bart Van Assche
2020-03-18 15:02 ` [PATCH v2 3/5] nvmet-rdma: use SRQ per completion vector Max Gurtovoy
2020-03-19 4:09 ` Bart Van Assche
2020-03-19 9:15 ` Max Gurtovoy [this message]
2020-03-19 11:56 ` Jason Gunthorpe
2020-03-19 12:48 ` Max Gurtovoy
2020-03-19 13:53 ` Jason Gunthorpe
2020-03-19 14:49 ` Bart Van Assche
[not found] ` <50dd8f5d-d092-54bc-236d-1e702fb95240@mellanox.com>
[not found] ` <6e3cc1c4-b24e-f607-42b3-5b83dd8c312c@mellanox.com>
2020-03-19 16:27 ` Max Gurtovoy
2020-03-20 5:47 ` Sagi Grimberg
2020-03-18 15:02 ` [PATCH v2 4/5] RDMA/srpt: use ib_alloc_cq instead of ib_alloc_cq_any Max Gurtovoy
2020-03-19 4:15 ` Bart Van Assche
2020-03-18 15:02 ` [PATCH v2 5/5] RDMA/srpt: use SRQ per completion vector Max Gurtovoy
2020-03-19 4:20 ` Bart Van Assche
2020-03-19 4:02 ` [PATCH v2 0/5] nvmet-rdma/srpt: " Bart Van Assche
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=5623419a-39e6-6090-4ae2-d4725a8b9740@mellanox.com \
--to=maxg@mellanox.com \
--cc=bvanassche@acm.org \
--cc=dledford@redhat.com \
--cc=hch@lst.de \
--cc=idanb@mellanox.com \
--cc=jgg@mellanox.com \
--cc=kbusch@kernel.org \
--cc=leonro@mellanox.com \
--cc=linux-nvme@lists.infradead.org \
--cc=linux-rdma@vger.kernel.org \
--cc=loberman@redhat.com \
--cc=oren@mellanox.com \
--cc=rgirase@redhat.com \
--cc=sagi@grimberg.me \
--cc=shlomin@mellanox.com \
--cc=vladimirk@mellanox.com \
/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).