Linux-NVME Archive on
 help / color / Atom feed
From: Victor Gladkov <>
To: "" <>
Subject: [PATCH] nvme-fabrics: reject I/O to offline device
Date: Sun, 1 Dec 2019 07:59:35 +0000
Message-ID: <> (raw)

Issue Description:
Commands get stuck while Host NVMe controller (TCP or RDMA) is in reconnect state. 
NVMe controller enters into reconnect state when it loses connection with the target. It tries to reconnect every 10 seconds (default) until successful reconnection or until reconnect time-out is reached. The default reconnect time out is 10 minutes.
This behavior is different than ISCSI where Commands during reconnect state returns with the following error: "rejecting I/O to offline device"

Fix Description:
Added a kernel module parameter "nvmef_reconnect_failfast" for nvme-fabrics module (default is true).
Interfere in the decision whether to queue IO command or retry IO command. The interface takes into account the controller reconnect state, in a way that during reconnect state, IO commands shall fail immediacy (default) or according to IO command timeout (depends on the module parameter value), and IO retry is prevented. As a result, commands do not get stuck in in reconnect state.

branch nvme-5.5

diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 74b8818..ef89aff 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -13,6 +13,10 @@
 #include "nvme.h"
 #include "fabrics.h"

+static bool nvmef_reconnect_failfast = 1;
+module_param_named(nvmef_reconnect_failfast, nvmef_reconnect_failfast, bool, S_IRUGO);
+MODULE_PARM_DESC(nvmef_reconnect_failfast, "failfast flag for I/O when controler is reconnecting, else use I/O command timeout (default true).");
 static LIST_HEAD(nvmf_transports);
 static DECLARE_RWSEM(nvmf_transports_rwsem);

@@ -549,6 +553,7 @@ blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl,
        if (ctrl->state != NVME_CTRL_DELETING &&
            ctrl->state != NVME_CTRL_DEAD &&
+           !(ctrl->state == NVME_CTRL_CONNECTING && (((ktime_get_ns() - rq->start_time_ns) > jiffies_to_nsecs(rq->timeout)) || nvmef_reconnect_failfast)) &&
            !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
                return BLK_STS_RESOURCE;


linux-nvme mailing list

             reply index

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-12-01  7:59 Victor Gladkov [this message]
2019-12-02 22:26 ` Chaitanya Kulkarni
2019-12-02 22:47 ` James Smart
2019-12-03 10:04   ` Victor Gladkov
2019-12-03 16:19     ` James Smart
2019-12-04  8:28       ` Victor Gladkov
2019-12-06  0:38         ` James Smart
2019-12-06 22:18           ` Sagi Grimberg
2019-12-08 12:31             ` Hannes Reinecke
2019-12-09 15:30               ` Victor Gladkov
2019-12-17 18:03                 ` James Smart
2019-12-17 21:46                 ` Sagi Grimberg
2019-12-18 22:20                   ` James Smart
2019-12-15 12:33               ` Victor Gladkov

Reply instructions:

You may reply publically 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:

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \ \ \ \

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-NVME Archive on

Archives are clonable:
	git clone --mirror linux-nvme/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-nvme linux-nvme/ \
	public-inbox-index linux-nvme

Example config snippet for mirrors

Newsgroup available over NNTP:

AGPL code for this site: git clone