From mboxrd@z Thu Jan  1 00:00:00 1970
From: gmate.amit@gmail.com (Kumar amit mehta)
Date: Tue, 2 Jul 2013 11:06:46 -0700
Subject: block layer: request unplugging threshold: unplug_thresh
Message-ID: <20130702180646.GA1572@gmail.com>
To: kernelnewbies@lists.kernelnewbies.org
List-Id: kernelnewbies.lists.kernelnewbies.org

Hi,

While trying to understand the block layer in Linux, I stumbled upon this
request(struct request) unplugging threshold(q->unplug_thresh), which is 
hardcoded to '4'. So far, my understanding is that there could be explicit
request unplugging(e.g. multipath module registering it's unplug_fn and later
calling blk_unplug) as well as implicit ones(either due to timeout or
read/write request threshold reaching to unplug_thresh. 

So having, q->unplug_thresh = 4 (ref. blk_queue_make_request), seem like a very
small value and even if it's not, then why shouldn't the driver such as RAID 
framework(dm/md), be allowed to manipulate this threshold value ?

-Amit