mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Vivek Goyal <vgoyal@redhat.com>
To: Divyesh Shah <dpshah@google.com>
Cc: jens.axboe@oracle.com, linux-kernel@vger.kernel.org,
	nauman@google.com, ctalbott@google.com
Subject: Re: [PATCH] cfq-iosched: Add additional blktrace log messages in CFQ for easier debugging.
Date: Wed, 24 Mar 2010 21:00:52 -0400	[thread overview]
Message-ID: <20100325010052.GB13225@redhat.com> (raw)
In-Reply-To: <20100325001856.18289.83328.stgit@austin.mtv.corp.google.com>

On Wed, Mar 24, 2010 at 05:19:34PM -0700, Divyesh Shah wrote:
> These extra logging messages have helped us debug some issues we've noticed in
> earlier IO controller versions and should be useful now as well. The extra
> logging covers:
> - idling behavior. Since there are so many conditions based on which we decide
> to idle or not, this patch adds a log message for some conditions that we've
> found useful.
> - workload slices and current prio and workload type
> 
> Signed-off-by: Divyesh Shah<dpshah@google.com>
> ---
> 
>  block/cfq-iosched.c |   17 +++++++++++++++--
>  1 files changed, 15 insertions(+), 2 deletions(-)
> 
> diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
> index e6910dc..556124a 100644
> --- a/block/cfq-iosched.c
> +++ b/block/cfq-iosched.c
> @@ -1646,6 +1646,10 @@ static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd,
>  	if (!cfqq)
>  		cfqq = cfq_get_next_queue(cfqd);
>  
> +	if (cfqq)
> +		cfq_log_cfqq(cfqd, cfqq, "New timeslice for wl_prio:%d "
> +				"wl_type:%d", cfqd->serving_prio,
> +				cfqd->serving_type);
>  	__cfq_set_active_queue(cfqd, cfqq);

Divyesh, __cfq_set_active_queue(), is already logging message
"set_active". Why don't you simply extend that to also print prio and
workload type of the queue service tree.

>  	return cfqq;
>  }
> @@ -1789,7 +1793,11 @@ static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq)
>  	 * Otherwise, we do only if they are the last ones
>  	 * in their service tree.
>  	 */
> -	return service_tree->count == 1 && cfq_cfqq_sync(cfqq);
> +	if (service_tree->count == 1 && cfq_cfqq_sync(cfqq))
> +		return 1;
> +	cfq_log_cfqq(cfqd, cfqq, "Not idling. queue_count:%d",
> +			service_tree->count);
> +	return 0;

Instead of queue_count, probably st->count=%d will be better.

Rest of it looks ok to me.

Vivek

>  }
>  
>  static void cfq_arm_slice_timer(struct cfq_data *cfqd)
> @@ -1834,8 +1842,11 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
>  	 * time slice.
>  	 */
>  	if (sample_valid(cic->ttime_samples) &&
> -	    (cfqq->slice_end - jiffies < cic->ttime_mean))
> +	    (cfqq->slice_end - jiffies < cic->ttime_mean)) {
> +		cfq_log_cfqq(cfqd, cfqq, "Not idling. think_time:%d",
> +				cic->ttime_mean);
>  		return;
> +	}
>  
>  	cfq_mark_cfqq_wait_request(cfqq);
>  
> @@ -2043,6 +2054,7 @@ static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg)
>  		slice = max(slice, 2 * cfqd->cfq_slice_idle);
>  
>  	slice = max_t(unsigned, slice, CFQ_MIN_TT);
> +	cfq_log(cfqd, "workload slice:%d", slice);
>  	cfqd->workload_expires = jiffies + slice;
>  	cfqd->noidle_tree_requires_idle = false;
>  }
> @@ -3309,6 +3321,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
>  		if (cfq_should_wait_busy(cfqd, cfqq)) {
>  			cfqq->slice_end = jiffies + cfqd->cfq_slice_idle;
>  			cfq_mark_cfqq_wait_busy(cfqq);
> +			cfq_log_cfqq(cfqd, cfqq, "will busy wait");
>  		}
>  
>  		/*

      reply	other threads:[~2010-03-25  1:00 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-03-25  0:19 Divyesh Shah
2010-03-25  1:00 ` Vivek Goyal [this message]

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=20100325010052.GB13225@redhat.com \
    --to=vgoyal@redhat.com \
    --cc=ctalbott@google.com \
    --cc=dpshah@google.com \
    --cc=jens.axboe@oracle.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=nauman@google.com \
    /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

all inboxes | Powered by JetHome®