public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: "Alan D. Brunelle" <Alan.Brunelle@hp.com>
To: Jens Axboe <jens.axboe@oracle.com>
Cc: linux-kernel@vger.kernel.org
Subject: Re: [RFC][PATCH 0/3] Skip I/O merges when disabled
Date: Fri, 25 Apr 2008 07:17:15 -0400	[thread overview]
Message-ID: <4811BDBB.8010604@hp.com> (raw)
In-Reply-To: <20080425083809.GG12774@kernel.dk>

[-- Attachment #1: Type: text/plain, Size: 1120 bytes --]

>>
>> I'll look into retaining the one-hit cache merge functionality, remove
>> the errant elv_rqhas_del code, and repost w/ the results from the other
>> tests I've run.
> 
> Also please do a check where you only disable the front merge logic, as
> that is the most expensive bit (and the least likely to occur). I would
> not be surprised if just removing the front merge bit would get you the
> majority of the gain already. I have in the past considered just getting
> rid of that bit, as it rarely triggers and it is a costly rbtree lookup
> for each IO. The back merge lookup+merge should be cheaper, it's just a
> hash lookup.
> 

I have the results from leaving in just the one-hit cache merge
attempts, and started a run leaving in both that and the back-merge
rq_hash checks. (The patch below basically undoes patch 3/3 - putting
back in the addition of rqs onto the hash list, and moves the nomerges
check below the back merge attempts.)

We /could/ change the tunable to a dial (or a mask) - enabling/disabling
specific merge attempts, but that seems a bit confusing/complex.

Jens: What do you think?

Alan

[-- Attachment #2: 0005-Enables-back-merge-checks-and-one-hit-cache-checks.patch --]
[-- Type: text/x-patch, Size: 1485 bytes --]

>From eb158393a5fd2eec0582bbba8af588be7e08ef32 Mon Sep 17 00:00:00 2001
From: Alan D. Brunelle <alan.brunelle@hp.com>
Date: Fri, 25 Apr 2008 07:14:42 -0400
Subject: [PATCH] Enables back-merge checks (and one-hit cache checks) for merges

Undoes patch 3/3 -- puts rqs onto the rq_hash list -- and performs simple
hash list checks for back-merges only.

Signed-off-by: Alan D. Brunelle <alan.brunelle@hp.com>
---
 block/elevator.c |    8 ++++----
 1 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/block/elevator.c b/block/elevator.c
index 557ee38..59be58d 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -488,9 +488,6 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 		}
 	}
 
-	if (blk_queue_nomerges(q))
-		return ELEVATOR_NO_MERGE;
-
 	/*
 	 * See if our hash lookup can find a potential backmerge.
 	 */
@@ -500,6 +497,9 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 		return ELEVATOR_BACK_MERGE;
 	}
 
+	if (blk_queue_nomerges(q))
+		return ELEVATOR_NO_MERGE;
+
 	if (e->ops->elevator_merge_fn)
 		return e->ops->elevator_merge_fn(q, req, bio);
 
@@ -604,7 +604,7 @@ void elv_insert(struct request_queue *q, struct request *rq, int where)
 		BUG_ON(!blk_fs_request(rq));
 		rq->cmd_flags |= REQ_SORTED;
 		q->nr_sorted++;
-		if (!blk_queue_nomerges(q) && rq_mergeable(rq)) {
+		if (rq_mergeable(rq)) {
 			elv_rqhash_add(q, rq);
 			if (!q->last_merge)
 				q->last_merge = rq;
-- 
1.5.2.5


  reply	other threads:[~2008-04-25 11:17 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-04-23 19:08 [RFC][PATCH 0/3] Skip I/O merges when disabled Alan D. Brunelle
2008-04-23 19:12 ` [RFC][PATCH 1/3] Add flag and sysfs interfaces Alan D. Brunelle
2008-04-23 19:14 ` [RFC][PATCH 2/3] Have __make_request skip merges when disabled Alan D. Brunelle
2008-04-23 19:15 ` [RFC][PATCH 3/3] Do not use rqhash when merges disabled Alan D. Brunelle
2008-04-24  0:37   ` Aaron Carroll
2008-04-24  0:59     ` Alan D. Brunelle
2008-04-24  2:07       ` Aaron Carroll
2008-04-24  7:09 ` [RFC][PATCH 0/3] Skip I/O merges when disabled Jens Axboe
2008-04-24 12:09   ` Alan D. Brunelle
2008-04-25  8:38     ` Jens Axboe
2008-04-25 11:17       ` Alan D. Brunelle [this message]
2008-04-25 11:25         ` Jens Axboe
2008-04-25 12:06           ` Aaron Carroll
2008-04-25 12:14             ` Jens Axboe
2008-04-25 12:17         ` Alan D. Brunelle
2008-04-28 16:36           ` Alan D. Brunelle
2008-04-29  7:37             ` Jens Axboe
2008-04-24 20:38   ` Alan D. Brunelle
2008-04-24 13:29 ` Andi Kleen
2008-04-24 13:59   ` Jens Axboe
2008-04-24 14:13     ` Alan D. Brunelle
2008-04-24 15:05       ` Jens Axboe
2008-04-24 22:04       ` Carl Henrik Lunde
2008-04-25  7:13       ` Andi Kleen
2008-04-24 14:15     ` Andi Kleen
2008-04-24 15:04       ` Jens Axboe
2008-04-24 15:53         ` David Collier-Brown
2008-04-24 16:29           ` Alan D. Brunelle
2008-04-24 13:31 ` Alan D. Brunelle
2008-04-24 13:43   ` Alan D. Brunelle

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=4811BDBB.8010604@hp.com \
    --to=alan.brunelle@hp.com \
    --cc=jens.axboe@oracle.com \
    --cc=linux-kernel@vger.kernel.org \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox