Skip to contentSkip to conversation

nvme: core: shorten duration of multipath namespace rescan

PATCH Superseded Martin Wilck 4 participants 5 messages Aug 26, 2024 – Aug 27, 2024 NVMe

v2 of 3 Superseded Latest is v3 →

lore
Share & tools
lore
#0 lore raw

PATCH v2 1/1 nvme: core: shorten duration of multipath namespace rescan

For multipath devices, nvme_update_ns_info() needs to freeze both the queue of the path and the queue of the multipath device. For both operations, it waits for one RCU grace period to pass, ~25ms on my test system. By calling blk_freeze_queue_start() for the multipath queue early, we avoid waiting twice; tests using ftrace have shown that the second blk_mq_freeze_queue_wait() call finishes in just a few microseconds. The path queue is unfrozen before calling blk_mq_freeze_queue_wait() on the multipath queue, so that possibly outstanding IO in the multipath queue can be flushed.

I tested this using the "controller rescan under I/O load" test I submitted recently [1].

[1] https://lore.kernel.org/linux-nvme/[email protected]/T/#u

---
v2: (all changes suggested by Sagi Grimberg)
- patch subject changed from "nvme: core: freeze multipath queue early in nvme_update_ns_info()" to "nvme: core: shorten duration of multipath namespace rescan"
- inserted comment explaining why blk_freeze_queue_start() is called early
- wait for queue to be frozen even if ret != 0
- make code structure more obvious vs. freeze_start / freeze_wait / unfreeze

Hannes and Daniel had already added Reviewed-by: tags to the v1 patch, but I didn't add them above, because the patch looks quite different now.

---
 drivers/nvme/host/core.c | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)
drivers/nvme/host/core.c +16 -5
index 0dc8bcc664f2..1ea052450846 100644
@@ -2217,6 +2217,16 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)
 	bool unsupported = false;
 	int ret;
 
+	/*
+	 * The controller queue is going to be frozen in
+	 * nvme_update_ns_info_{generic,block}(). Every freeze implies waiting
+	 * for an RCU grace period to pass. For multipath devices, we
+	 * need to freeze the multipath queue, too. Start freezing the
+	 * multipath queue now, lest we need to wait for two grace periods.
+	 */
+	if (nvme_ns_head_multipath(ns->head))
+		blk_freeze_queue_start(ns->head->disk->queue);
+
 	switch (info->ids.csi) {
 	case NVME_CSI_ZNS:
 		if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
@@ -2250,11 +2260,13 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)
 		ret = 0;
 	}
 
-	if (!ret && nvme_ns_head_multipath(ns->head)) {
+	if (!nvme_ns_head_multipath(ns->head))
+		return ret;
+
+	blk_mq_freeze_queue_wait(ns->head->disk->queue);
+	if (!ret) {
 		struct queue_limits *ns_lim = &ns->disk->queue->limits;
 		struct queue_limits lim;
-
-		blk_mq_freeze_queue(ns->head->disk->queue);
 		/*
 		 * queue_limits mixes values that are the hardware limitations
 		 * for bio splitting with what is the device configuration.
@@ -2286,9 +2298,8 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)
 		set_capacity_and_notify(ns->head->disk, get_capacity(ns->disk));
 		set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
 		nvme_mpath_revalidate_paths(ns);
-
-		blk_mq_unfreeze_queue(ns->head->disk->queue);
 	}
+	blk_mq_unfreeze_queue(ns->head->disk->queue);
 
 	return ret;
 }
Signature · 1 line
2.46.0
maintainer
#1 lore raw
Quoted 16 lines · Martin Wilck

For multipath devices, nvme_update_ns_info() needs to freeze both the queue of the path and the queue of the multipath device. For both operations, it waits for one RCU grace period to pass, ~25ms on my test system. By calling blk_freeze_queue_start() for the multipath queue early, we avoid waiting twice; tests using ftrace have shown that the second blk_mq_freeze_queue_wait() call finishes in just a few microseconds. The path queue is unfrozen before calling blk_mq_freeze_queue_wait() on the multipath queue, so that possibly outstanding IO in the multipath queue can be flushed.

I tested this using the "controller rescan under I/O load" test I submitted recently [1].

[1] https://lore.kernel.org/linux-nvme/[email protected]/T/#u

Quoted 8 lines

---
v2: (all changes suggested by Sagi Grimberg)
- patch subject changed from "nvme: core: freeze multipath queue early in nvme_update_ns_info()" to "nvme: core: shorten duration of multipath namespace rescan"
- inserted comment explaining why blk_freeze_queue_start() is called early
- wait for queue to be frozen even if ret != 0
- make code structure more obvious vs. freeze_start / freeze_wait / unfreeze

This looks a lot better, thanks.

Quoted 47 lines

Hannes and Daniel had already added Reviewed-by: tags to the v1 patch, but I didn't add them above, because the patch looks quite different now.

---
  drivers/nvme/host/core.c | 21 ++++++++++++++++-----
  1 file changed, 16 insertions(+), 5 deletions(-)
drivers/nvme/host/core.c +15 -3
index 0dc8bcc664f2..1ea052450846 100644
@@ -2217,6 +2217,16 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)
  	bool unsupported = false;
  	int ret;
 
+	/*
+	 * The controller queue is going to be frozen in
+	 * nvme_update_ns_info_{generic,block}(). Every freeze implies waiting
+	 * for an RCU grace period to pass. For multipath devices, we
+	 * need to freeze the multipath queue, too. Start freezing the
+	 * multipath queue now, lest we need to wait for two grace periods.
+	 */
+	if (nvme_ns_head_multipath(ns->head))
+		blk_freeze_queue_start(ns->head->disk->queue);
+
  	switch (info->ids.csi) {
  	case NVME_CSI_ZNS:
  		if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
@@ -2250,11 +2260,13 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)
  		ret = 0;
  	}
 
-	if (!ret && nvme_ns_head_multipath(ns->head)) {
+	if (!nvme_ns_head_multipath(ns->head))
+		return ret;
+
+	blk_mq_freeze_queue_wait(ns->head->disk->queue);
+	if (!ret) {
  		struct queue_limits *ns_lim = &ns->disk->queue->limits;
  		struct queue_limits lim;
-
-		blk_mq_freeze_queue(ns->head->disk->queue);
  		/*
  		 * queue_limits mixes values that are the hardware limitations
  		 * for bio splitting with what is the device configuration.

drivers/nvme/host/core.c static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info) · line 2302

Quoted 7 lines
drivers/nvme/host/core.c +1 -2
@@ -2286,9 +2298,8 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)
  		set_capacity_and_notify(ns->head->disk, get_capacity(ns->disk));
  		set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
  		nvme_mpath_revalidate_paths(ns);
-
-		blk_mq_unfreeze_queue(ns->head->disk->queue);
  	}
+	blk_mq_unfreeze_queue(ns->head->disk->queue);

I'd even make it nicer with adding an out label and reverse the ret condition polarity.
--
blk_mq_freeze_queue_wait(ns->head->disk->queue); if (ret) goto out; ... ... out: blk_mq_unfreeze_queue(ns->head->disk->queue); return ret;
--

maintainer
#2 lore raw
Quoted 5 lines
Signature · 4 lines
-- 
blk_mq_freeze_queue_wait(ns->head->disk->queue); if (ret) goto out; ... ... out: blk_mq_unfreeze_queue(ns->head->disk->queue);
        return ret;
-- 

Not sure what happened here....

#3 lore raw
In reply to Sagi Grimberg
Quoted 3 lines · Sagi Grimberg

I'd even make it nicer with adding an out label and reverse the ret condition polarity.

Ok, if you prefer that ... I thought you might like the if block better, as the goto variant comes with lots of whitespace changes. I'll send a v3.

Thanks
Martin

Reviewed-by on v2 1/1
#4 lore raw
In reply to Martin Wilck
Quoted 25 lines · Martin Wilck

For multipath devices, nvme_update_ns_info() needs to freeze both the queue of the path and the queue of the multipath device. For both operations, it waits for one RCU grace period to pass, ~25ms on my test system. By calling blk_freeze_queue_start() for the multipath queue early, we avoid waiting twice; tests using ftrace have shown that the second blk_mq_freeze_queue_wait() call finishes in just a few microseconds. The path queue is unfrozen before calling blk_mq_freeze_queue_wait() on the multipath queue, so that possibly outstanding IO in the multipath queue can be flushed.

I tested this using the "controller rescan under I/O load" test I submitted recently [1].

[1] https://lore.kernel.org/linux-nvme/[email protected]/T/#u

---
v2: (all changes suggested by Sagi Grimberg)
- patch subject changed from "nvme: core: freeze multipath queue early in nvme_update_ns_info()" to "nvme: core: shorten duration of multipath namespace rescan"
- inserted comment explaining why blk_freeze_queue_start() is called early
- wait for queue to be frozen even if ret != 0
- make code structure more obvious vs. freeze_start / freeze_wait / unfreeze

Quoted 7 lines

Hannes and Daniel had already added Reviewed-by: tags to the v1 patch, but I didn't add them above, because the patch looks quite different now.

---
  drivers/nvme/host/core.c | 21 ++++++++++++++++-----
  1 file changed, 16 insertions(+), 5 deletions(-)

Cheers,

Hannes

Signature · 4 lines
Dr. Hannes Reinecke                  Kernel Storage Architect
[email protected]                                +49 911 74053 688
SUSE Software Solutions GmbH, Frankenstr. 146, 90461 Nürnberg
HRB 36809 (AG Nürnberg), GF: I. Totev, A. McDonald, W. Knoblich