backing up to a Drobo CIFS VFS: Error -11 sending data on socket to server, Bufferbloat?

[Robert Kudyba]

We back up via a cron job using tar via a campus to campus dedicated fiber line. We get this error about 4 out of 5 times the job runs:

May  8 01:08:10 ourserver kernel: cifs_vfs_err: 2 callbacks suppressed
May  8 01:08:10 ourserver kernel: CIFS VFS: Server ourserver has not responded in 120 seconds. Reconnecting...
May  8 01:10:01 ourserver kernel: CIFS VFS: sends on sock ffff9f2900764f00 stuck for 15 seconds
May  8 01:10:01 ourserver kernel: CIFS VFS: Error -11 sending data on socket to server
May  8 01:10:45 ourserver kernel: CIFS VFS: sends on sock ffff9f2900764f00 stuck for 15 seconds
May  8 01:10:45 ourserver kernel: CIFS VFS: Error -11 sending data on socket to server

This is on Fedora 25. I saw this 2013 thread, http://linux-cifs.vger.kernel.narkive.com/qolENUBe/errors-writing-large-files-to-cifs-shares <http://linux-cifs.vger.kernel.narkive.com/qolENUBe/errors-writing-large-files-to-cifs-shares> which mentions Bufferbloat. Is there a way to perhaps tune a kernel parameter in /etc/sysctl.conf?

cat /proc/fs/cifs/DebugData
Display Internal CIFS Data Structures for Debugging
---------------------------------------------------
CIFS Version 2.09
Features: dfs fscache lanman posix spnego xattr acl
Active VFS Requests: 0
Servers:
Number of credits: 50
1) Name: ip  Domain: WORKGROUP Uses: 1 OS: Unix
	NOS: Samba 3.4.4	Capability: 0x8000f3fd
	SMB session status: 1	TCP status: 1
	Local Users To Server: 1 SecMode: 0x3 Req On Wire: 0
	Shares:
	1) \\ourdomain Mounts: 1 Type: NTFS DevInfo: 0x0 Attributes: 0x1002f
	PathComponentMax: 255 Status: 1 type: 0 

	MIDs: