* [PATCH] nvme: add 'iopolicy' module parameter
@ 2021-05-17 8:13 Hannes Reinecke
0 siblings, 0 replies; 5+ messages in thread
From: Hannes Reinecke @ 2021-05-17 8:13 UTC (permalink / raw)
To: Christoph Hellwig; +Cc: Sagi Grimberg, Keith Busch, linux-nvme, Hannes Reinecke
While the 'iopolicy' sysfs attribute can be set at runtime, most
storage arrays prefer to use the 'round-robin' iopolicy to be
used. So to avoid having to code a large udev rule detailing
every single storage array add a module parameter 'iopolicy'
to allow the admin to switch the default.
Signed-off-by: Hannes Reinecke <hare@suse.de>
---
drivers/nvme/host/core.c | 4 +---
drivers/nvme/host/multipath.c | 10 ++++++++++
drivers/nvme/host/nvme.h | 4 ++++
3 files changed, 15 insertions(+), 3 deletions(-)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 6a5386267c10..37740e11eef3 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2608,9 +2608,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
subsys->vendor_id = le16_to_cpu(id->vid);
subsys->cmic = id->cmic;
subsys->awupf = le16_to_cpu(id->awupf);
-#ifdef CONFIG_NVME_MULTIPATH
- subsys->iopolicy = NVME_IOPOLICY_NUMA;
-#endif
+ nvme_mpath_default_iopolicy(subsys);
subsys->dev.class = nvme_subsys_class;
subsys->dev.release = nvme_release_subsystem;
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index ecc99bd5f8ad..9a67ac8347c3 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -13,6 +13,16 @@ module_param(multipath, bool, 0444);
MODULE_PARM_DESC(multipath,
"turn on native support for multiple controllers per subsystem");
+static int iopolicy = NVME_IOPOLICY_NUMA;
+module_param(iopolicy, int, 0444);
+MODULE_PARM_DESC(iopolicy,
+ "Default multipath I/O policy; 0 - NUMA (default), 1 - Round-robin");
+
+void nvme_mpath_default_iopolicy(struct nvme_subsystem *subsys)
+{
+ subsys->iopolicy = iopolicy;
+}
+
void nvme_mpath_unfreeze(struct nvme_subsystem *subsys)
{
struct nvme_ns_head *h;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 05f31a2c64bb..0ff7f9d3373f 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -706,6 +706,7 @@ static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
void nvme_mpath_unfreeze(struct nvme_subsystem *subsys);
void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys);
void nvme_mpath_start_freeze(struct nvme_subsystem *subsys);
+void nvme_mpath_default_iopolicy(struct nvme_subsystem *subsys);
bool nvme_mpath_set_disk_name(struct nvme_ns *ns, char *disk_name, int *flags);
void nvme_failover_req(struct request *req);
void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl);
@@ -803,6 +804,9 @@ static inline void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys)
static inline void nvme_mpath_start_freeze(struct nvme_subsystem *subsys)
{
}
+static inline void nvme_mpath_default_iopolicy(struct nvme_subsystem *subsys)
+{
+}
#endif /* CONFIG_NVME_MULTIPATH */
int nvme_revalidate_zones(struct nvme_ns *ns);
--
2.29.2
_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme
^ permalink raw reply related [flat|nested] 5+ messages in thread
* [PATCH] nvme: add 'iopolicy' module parameter
@ 2021-12-10 13:14 Hannes Reinecke
2021-12-12 9:31 ` Sagi Grimberg
` (2 more replies)
0 siblings, 3 replies; 5+ messages in thread
From: Hannes Reinecke @ 2021-12-10 13:14 UTC (permalink / raw)
To: Christoph Hellwig; +Cc: Sagi Grimberg, Keith Busch, linux-nvme, Hannes Reinecke
While the 'iopolicy' sysfs attribute can be set at runtime, most
storage arrays prefer to use the 'round-robin' iopolicy per default.
We can use udev rules to set this, but is getting rather unwieldy
for rebranded arrays as we would have to update the udev rules
anytime a new array shows up, leading to the same mess we currently
have in multipathd for configuring the RDAC arrays.
Hence this patch adds a module parameter 'iopolicy' to allow the
admin to switch the default, and to do away with the need for a
udev rule here.
Signed-off-by: Hannes Reinecke <hare@suse.de>
---
drivers/nvme/host/core.c | 4 +---
drivers/nvme/host/multipath.c | 10 ++++++++++
drivers/nvme/host/nvme.h | 4 ++++
3 files changed, 15 insertions(+), 3 deletions(-)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 58f5e8f454e2..282459a163e0 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2782,9 +2782,7 @@ static struct nvme_subsystem *nvme_init_subsystem(struct nvme_ctrl *ctrl,
kfree(subsys);
return ERR_PTR(-EINVAL);
}
-#ifdef CONFIG_NVME_MULTIPATH
- subsys->iopolicy = NVME_IOPOLICY_NUMA;
-#endif
+ nvme_mpath_default_iopolicy(subsys);
subsys->dev.class = nvme_subsys_class;
subsys->dev.release = nvme_release_subsystem;
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 63367a717805..8f4eea978af7 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -13,6 +13,16 @@ module_param(multipath, bool, 0444);
MODULE_PARM_DESC(multipath,
"turn on native support for multiple controllers per subsystem");
+static int iopolicy = NVME_IOPOLICY_NUMA;
+module_param(iopolicy, int, 0444);
+MODULE_PARM_DESC(iopolicy,
+ "Default multipath I/O policy; 0 - NUMA (default), 1 - Round-robin");
+
+void nvme_mpath_default_iopolicy(struct nvme_subsystem *subsys)
+{
+ subsys->iopolicy = iopolicy;
+}
+
void nvme_mpath_unfreeze(struct nvme_subsystem *subsys)
{
struct nvme_ns_head *h;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 6c786ea4185b..ac158b8e825d 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -771,6 +771,7 @@ static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
void nvme_mpath_unfreeze(struct nvme_subsystem *subsys);
void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys);
void nvme_mpath_start_freeze(struct nvme_subsystem *subsys);
+void nvme_mpath_default_iopolicy(struct nvme_subsystem *subsys);
bool nvme_mpath_set_disk_name(struct nvme_ns *ns, char *disk_name, int *flags);
void nvme_failover_req(struct request *req);
void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl);
@@ -869,6 +870,9 @@ static inline void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys)
static inline void nvme_mpath_start_freeze(struct nvme_subsystem *subsys)
{
}
+static inline void nvme_mpath_default_iopolicy(struct nvme_subsystem *subsys)
+{
+}
#endif /* CONFIG_NVME_MULTIPATH */
int nvme_revalidate_zones(struct nvme_ns *ns);
--
2.29.2
^ permalink raw reply related [flat|nested] 5+ messages in thread
* Re: [PATCH] nvme: add 'iopolicy' module parameter
2021-12-10 13:14 [PATCH] nvme: add 'iopolicy' module parameter Hannes Reinecke
@ 2021-12-12 9:31 ` Sagi Grimberg
2021-12-13 7:11 ` Chaitanya Kulkarni
2021-12-16 8:38 ` Christoph Hellwig
2 siblings, 0 replies; 5+ messages in thread
From: Sagi Grimberg @ 2021-12-12 9:31 UTC (permalink / raw)
To: Hannes Reinecke, Christoph Hellwig; +Cc: Keith Busch, linux-nvme
> While the 'iopolicy' sysfs attribute can be set at runtime, most
> storage arrays prefer to use the 'round-robin' iopolicy per default.
> We can use udev rules to set this, but is getting rather unwieldy
> for rebranded arrays as we would have to update the udev rules
> anytime a new array shows up, leading to the same mess we currently
> have in multipathd for configuring the RDAC arrays.
>
> Hence this patch adds a module parameter 'iopolicy' to allow the
> admin to switch the default, and to do away with the need for a
> udev rule here.
This seems fine to me:
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
What do other think?
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH] nvme: add 'iopolicy' module parameter
2021-12-10 13:14 [PATCH] nvme: add 'iopolicy' module parameter Hannes Reinecke
2021-12-12 9:31 ` Sagi Grimberg
@ 2021-12-13 7:11 ` Chaitanya Kulkarni
2021-12-16 8:38 ` Christoph Hellwig
2 siblings, 0 replies; 5+ messages in thread
From: Chaitanya Kulkarni @ 2021-12-13 7:11 UTC (permalink / raw)
To: Hannes Reinecke
Cc: Sagi Grimberg, Keith Busch, Christoph Hellwig,
linux-nvme@lists.infradead.org
On 12/10/21 5:14 AM, Hannes Reinecke wrote:
> While the 'iopolicy' sysfs attribute can be set at runtime, most
> storage arrays prefer to use the 'round-robin' iopolicy per default.
> We can use udev rules to set this, but is getting rather unwieldy
> for rebranded arrays as we would have to update the udev rules
> anytime a new array shows up, leading to the same mess we currently
> have in multipathd for configuring the RDAC arrays.
>
> Hence this patch adds a module parameter 'iopolicy' to allow the
> admin to switch the default, and to do away with the need for a
> udev rule here.
>
> Signed-off-by: Hannes Reinecke <hare@suse.de>
Looks good.
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH] nvme: add 'iopolicy' module parameter
2021-12-10 13:14 [PATCH] nvme: add 'iopolicy' module parameter Hannes Reinecke
2021-12-12 9:31 ` Sagi Grimberg
2021-12-13 7:11 ` Chaitanya Kulkarni
@ 2021-12-16 8:38 ` Christoph Hellwig
2 siblings, 0 replies; 5+ messages in thread
From: Christoph Hellwig @ 2021-12-16 8:38 UTC (permalink / raw)
To: Hannes Reinecke; +Cc: Christoph Hellwig, Sagi Grimberg, Keith Busch, linux-nvme
This looks good to me, but does not apply. Can you resend it against
the nvme-5.17 branch?
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2021-12-16 8:38 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2021-12-10 13:14 [PATCH] nvme: add 'iopolicy' module parameter Hannes Reinecke
2021-12-12 9:31 ` Sagi Grimberg
2021-12-13 7:11 ` Chaitanya Kulkarni
2021-12-16 8:38 ` Christoph Hellwig
-- strict thread matches above, loose matches on Subject: below --
2021-05-17 8:13 Hannes Reinecke
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox