* block layer: request unplugging threshold: unplug_thresh
@ 2013-07-02 18:06 Kumar amit mehta
0 siblings, 0 replies; only message in thread
From: Kumar amit mehta @ 2013-07-02 18:06 UTC (permalink / raw)
To: kernelnewbies
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
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2013-07-02 18:06 UTC | newest]
Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2013-07-02 18:06 block layer: request unplugging threshold: unplug_thresh Kumar amit mehta
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).