All of lore.kernel.org
 help / color / mirror / Atom feed
From: sagi@grimberg.me (Sagi Grimberg)
Subject: [PATCH 3/3] nvme-rdma: Support ctrl_loss_tmo
Date: Sun, 19 Mar 2017 00:42:21 +0200	[thread overview]
Message-ID: <1489876941-6401-4-git-send-email-sagi@grimberg.me> (raw)
In-Reply-To: <1489876941-6401-1-git-send-email-sagi@grimberg.me>

Before scheduling a reconnect attempt, check
nr_reconnects against max_reconnects, if not
exhausted (or max_reconnects is not -1), schedule
a reconnect attempts, otherwise schedule ctrl
removal.

Signed-off-by: Sagi Grimberg <sagi at grimberg.me>
---
 drivers/nvme/host/rdma.c | 41 ++++++++++++++++++++++++++++-------------
 1 file changed, 28 insertions(+), 13 deletions(-)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 33f18636ea99..71d1e1a6b928 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -711,6 +711,26 @@ static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl)
 	kfree(ctrl);
 }
 
+static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl)
+{
+	/* If we are resetting/deleting then do nothing */
+	if (ctrl->ctrl.state != NVME_CTRL_RECONNECTING) {
+		WARN_ON_ONCE(ctrl->ctrl.state == NVME_CTRL_NEW ||
+			ctrl->ctrl.state == NVME_CTRL_LIVE);
+		return;
+	}
+
+	if (nvmf_should_reconnect(&ctrl->ctrl)) {
+		dev_info(ctrl->ctrl.device, "Reconnecting in %d seconds...\n",
+			ctrl->ctrl.opts->reconnect_delay);
+		queue_delayed_work(nvme_rdma_wq, &ctrl->reconnect_work,
+				ctrl->ctrl.opts->reconnect_delay * HZ);
+	} else {
+		dev_info(ctrl->ctrl.device, "Removing controller...\n");
+		queue_work(nvme_rdma_wq, &ctrl->delete_work);
+	}
+}
+
 static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
 {
 	struct nvme_rdma_ctrl *ctrl = container_of(to_delayed_work(work),
@@ -718,6 +738,8 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
 	bool changed;
 	int ret;
 
+	++ctrl->ctrl.opts->nr_reconnects;
+
 	if (ctrl->queue_count > 1) {
 		nvme_rdma_free_io_queues(ctrl);
 
@@ -762,6 +784,7 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
 
 	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
 	WARN_ON_ONCE(!changed);
+	ctrl->ctrl.opts->nr_reconnects = 0;
 
 	if (ctrl->queue_count > 1) {
 		nvme_start_queues(&ctrl->ctrl);
@@ -776,13 +799,9 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
 stop_admin_q:
 	blk_mq_stop_hw_queues(ctrl->ctrl.admin_q);
 requeue:
-	/* Make sure we are not resetting/deleting */
-	if (ctrl->ctrl.state == NVME_CTRL_RECONNECTING) {
-		dev_info(ctrl->ctrl.device,
-			"Failed reconnect attempt, requeueing...\n");
-		queue_delayed_work(nvme_rdma_wq, &ctrl->reconnect_work,
-				ctrl->ctrl.opts->reconnect_delay * HZ);
-	}
+	dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d\n",
+			ctrl->ctrl.opts->nr_reconnects);
+	nvme_rdma_reconnect_or_remove(ctrl);
 }
 
 static void nvme_rdma_error_recovery_work(struct work_struct *work)
@@ -809,11 +828,7 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
 	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
 				nvme_cancel_request, &ctrl->ctrl);
 
-	dev_info(ctrl->ctrl.device, "reconnecting in %d seconds\n",
-		ctrl->ctrl.opts->reconnect_delay);
-
-	queue_delayed_work(nvme_rdma_wq, &ctrl->reconnect_work,
-				ctrl->ctrl.opts->reconnect_delay * HZ);
+	nvme_rdma_reconnect_or_remove(ctrl);
 }
 
 static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl)
@@ -2011,7 +2026,7 @@ static struct nvmf_transport_ops nvme_rdma_transport = {
 	.name		= "rdma",
 	.required_opts	= NVMF_OPT_TRADDR,
 	.allowed_opts	= NVMF_OPT_TRSVCID | NVMF_OPT_RECONNECT_DELAY |
-			  NVMF_OPT_HOST_TRADDR,
+			  NVMF_OPT_HOST_TRADDR | NVMF_OPT_CTRL_LOSS_TMO,
 	.create_ctrl	= nvme_rdma_create_ctrl,
 };
 
-- 
2.7.4

  parent reply	other threads:[~2017-03-18 22:42 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-03-18 22:42 [PATCH 0/3] Introduce fabrics controller loss timeout Sagi Grimberg
2017-03-18 22:42 ` [PATCH 1/3] nvme-rdma: get rid of local reconnect_delay Sagi Grimberg
2017-03-27  9:50   ` Christoph Hellwig
2017-03-18 22:42 ` [PATCH 2/3] nvme-fabrics: Allow ctrl loss timeout configuration Sagi Grimberg
2017-03-27  9:50   ` Christoph Hellwig
2017-04-17 22:29   ` James Smart
2017-04-20 10:20     ` Sagi Grimberg
2017-03-18 22:42 ` Sagi Grimberg [this message]
2017-03-27  9:50   ` [PATCH 3/3] nvme-rdma: Support ctrl_loss_tmo Christoph Hellwig
2017-04-25  0:46   ` James Smart
2017-05-03  8:05     ` Sagi Grimberg
2017-03-27  0:41 ` [PATCH 0/3] Introduce fabrics controller loss timeout Yi Zhang
2017-03-28 11:37   ` 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=1489876941-6401-4-git-send-email-sagi@grimberg.me \
    --to=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.