All of lore.kernel.org
 help / color / mirror / Atom feed
From: Guixin Liu <kanie@linux.alibaba.com>
To: hch@lst.de, sagi@grimberg.me, kch@nvidia.com, axboe@kernel.dk
Cc: linux-nvme@lists.infradead.org
Subject: [RFC PATCH 2/3] nvmet: rdma: utilize ib_device capability for setting max_queue_size
Date: Mon, 18 Dec 2023 19:05:32 +0800	[thread overview]
Message-ID: <1702897533-49685-3-git-send-email-kanie@linux.alibaba.com> (raw)
In-Reply-To: <1702897533-49685-1-git-send-email-kanie@linux.alibaba.com>

Respond with the smaller value between 1024 and the ib_device's
max_qp_wr as the RDMA max queue size.

Signed-off-by: Guixin Liu <kanie@linux.alibaba.com>
---
 drivers/nvme/target/rdma.c | 7 ++++++-
 include/linux/nvme-rdma.h  | 2 ++
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 8a728c5..c3884dd 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -2002,7 +2002,12 @@ static u8 nvmet_rdma_get_mdts(const struct nvmet_ctrl *ctrl)
 
 static u16 nvmet_rdma_get_max_queue_size(const struct nvmet_sq *nvmet_sq)
 {
-	return NVME_RDMA_MAX_QUEUE_SIZE;
+	struct nvmet_rdma_queue *queue =
+		container_of(nvmet_sq, struct nvmet_rdma_queue, nvme_sq);
+	int max_qp_wr = queue->dev->device->attrs.max_qp_wr;
+
+	return (u16)min_t(int, NVMET_QUEUE_SIZE,
+			  max_qp_wr / (NVME_RDMA_SEND_WR_FACTOR + 1));
 }
 
 static const struct nvmet_fabrics_ops nvmet_rdma_ops = {
diff --git a/include/linux/nvme-rdma.h b/include/linux/nvme-rdma.h
index 4dd7e6f..c19858b 100644
--- a/include/linux/nvme-rdma.h
+++ b/include/linux/nvme-rdma.h
@@ -8,6 +8,8 @@
 
 #define NVME_RDMA_MAX_QUEUE_SIZE	128
 
+#define NVME_RDMA_SEND_WR_FACTOR 3  /* MR, SEND, INV */
+
 enum nvme_rdma_cm_fmt {
 	NVME_RDMA_CM_FMT_1_0 = 0x0,
 };
-- 
1.8.3.1



  parent reply	other threads:[~2023-12-18 11:06 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-12-18 11:05 [RFC PATCH 0/3] *** use rdma device capability to limit queue size *** Guixin Liu
2023-12-18 11:05 ` [RFC PATCH 1/3] nvmet: change get_max_queue_size param to nvmet_sq Guixin Liu
2023-12-18 11:52   ` Sagi Grimberg
2023-12-18 11:05 ` Guixin Liu [this message]
2023-12-18 11:57   ` [RFC PATCH 2/3] nvmet: rdma: utilize ib_device capability for setting max_queue_size Sagi Grimberg
2023-12-18 12:41     ` Guixin Liu
2023-12-18 11:05 ` [RFC PATCH 3/3] nvme: rdma: use ib_device's max_qp_wr to limit sqsize Guixin Liu
2023-12-18 11:57   ` Sagi Grimberg
2023-12-18 12:31     ` Guixin Liu

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=1702897533-49685-3-git-send-email-kanie@linux.alibaba.com \
    --to=kanie@linux.alibaba.com \
    --cc=axboe@kernel.dk \
    --cc=hch@lst.de \
    --cc=kch@nvidia.com \
    --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 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.