From: maxg@mellanox.com (Max Gurtovoy)
Subject: [PATCH 3/3] nvmet-rdma: add module parameter for SRQ size
Date: Tue, 5 Sep 2017 13:59:17 +0300 [thread overview]
Message-ID: <1504609157-3004-4-git-send-email-maxg@mellanox.com> (raw)
In-Reply-To: <1504609157-3004-1-git-send-email-maxg@mellanox.com>
Adjust SRQ size according to the expected load. Make sure the
size is >= 256 to avoid lack of resources.
Signed-off-by: Max Gurtovoy <maxg at mellanox.com>
---
drivers/nvme/target/rdma.c | 23 ++++++++++++++++++++++-
1 files changed, 22 insertions(+), 1 deletions(-)
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 1b52080..34868ad 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -134,6 +134,16 @@ struct nvmet_rdma_device {
module_param_named(use_srq, nvmet_rdma_use_srq, bool, 0444);
MODULE_PARM_DESC(use_srq, "Use shared receive queue.");
+static int srq_size_set(const char *val, const struct kernel_param *kp);
+static const struct kernel_param_ops srq_size_ops = {
+ .set = srq_size_set,
+ .get = param_get_int,
+};
+
+static int nvmet_rdma_srq_size = 4095;
+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: 4095)");
+
static DEFINE_IDA(nvmet_rdma_queue_ida);
static LIST_HEAD(nvmet_rdma_queue_list);
static DEFINE_MUTEX(nvmet_rdma_queue_mutex);
@@ -150,6 +160,17 @@ struct nvmet_rdma_device {
static struct nvmet_fabrics_ops nvmet_rdma_ops;
+static int srq_size_set(const char *val, const struct kernel_param *kp)
+{
+ int n = 0, ret;
+
+ ret = kstrtoint(val, 10, &n);
+ if (ret != 0 || n < 256)
+ return -EINVAL;
+
+ return param_set_int(val, kp);
+}
+
/* XXX: really should move to a generic header sooner or later.. */
static inline u32 get_unaligned_le24(const u8 *p)
{
@@ -825,7 +846,7 @@ static int nvmet_rdma_init_srq(struct nvmet_rdma_device *ndev, int index)
if (!nsrq)
return -ENOMEM;
- srq_size = 4095; /* XXX: tune */
+ srq_size = nvmet_rdma_srq_size;
srq_attr.attr.max_wr = srq_size;
srq_attr.attr.max_sge = 2;
--
1.7.1
next prev parent reply other threads:[~2017-09-05 10:59 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-09-05 10:59 [PATCH 0/3] nvmet-rdma: SRQ per completion vector Max Gurtovoy
2017-09-05 10:59 ` [PATCH 1/3] nvmet-rdma: use srq pointer in rdma_cmd Max Gurtovoy
2017-09-06 10:30 ` Christoph Hellwig
2017-09-05 10:59 ` [PATCH 2/3] nvmet-rdma: use SRQ per completion vector Max Gurtovoy
2017-09-06 10:38 ` Christoph Hellwig
2017-09-06 14:57 ` Sagi Grimberg
2017-09-07 12:03 ` Christoph Hellwig
2017-09-06 14:50 ` Sagi Grimberg
2017-09-07 10:47 ` Max Gurtovoy
2017-09-05 10:59 ` Max Gurtovoy [this message]
2017-09-06 10:39 ` [PATCH 3/3] nvmet-rdma: add module parameter for SRQ size Christoph Hellwig
2017-09-06 15:02 ` Sagi Grimberg
2017-09-06 14:40 ` [PATCH 0/3] nvmet-rdma: SRQ per completion vector Sagi Grimberg
2017-11-07 14:40 ` Max Gurtovoy
2017-11-08 10:07 ` Sagi Grimberg
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=1504609157-3004-4-git-send-email-maxg@mellanox.com \
--to=maxg@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