ceph-devel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Xiubo Li <xiubli@redhat.com>
To: Venky Shankar <vshankar@redhat.com>,
	jlayton@redhat.com, pdonnell@redhat.com
Cc: ceph-devel@vger.kernel.org
Subject: Re: [PATCH v2 2/4] ceph: track average/stdev r/w/m latency
Date: Tue, 14 Sep 2021 20:52:55 +0800	[thread overview]
Message-ID: <b9d1a0ea-147c-251b-1618-111d869687a0@redhat.com> (raw)
In-Reply-To: <20210914084902.1618064-3-vshankar@redhat.com>


On 9/14/21 4:49 PM, Venky Shankar wrote:
> The math involved in tracking average and standard deviation
> for r/w/m latencies looks incorrect. Fix that up. Also, change
> the variable name that tracks standard deviation (*_sq_sum) to
> *_stdev.
>
> Signed-off-by: Venky Shankar <vshankar@redhat.com>
> ---
>   fs/ceph/debugfs.c | 14 +++++-----
>   fs/ceph/metric.c  | 70 ++++++++++++++++++++++-------------------------
>   fs/ceph/metric.h  |  9 ++++--
>   3 files changed, 45 insertions(+), 48 deletions(-)
>
> diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
> index 38b78b45811f..3abfa7ae8220 100644
> --- a/fs/ceph/debugfs.c
> +++ b/fs/ceph/debugfs.c
> @@ -152,7 +152,7 @@ static int metric_show(struct seq_file *s, void *p)
>   	struct ceph_mds_client *mdsc = fsc->mdsc;
>   	struct ceph_client_metric *m = &mdsc->metric;
>   	int nr_caps = 0;
> -	s64 total, sum, avg, min, max, sq;
> +	s64 total, sum, avg, min, max, stdev;
>   	u64 sum_sz, avg_sz, min_sz, max_sz;
>   
>   	sum = percpu_counter_sum(&m->total_inodes);
> @@ -175,9 +175,9 @@ static int metric_show(struct seq_file *s, void *p)
>   	avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0;
>   	min = m->read_latency_min;
>   	max = m->read_latency_max;
> -	sq = m->read_latency_sq_sum;
> +	stdev = m->read_latency_stdev;
>   	spin_unlock(&m->read_metric_lock);
> -	CEPH_LAT_METRIC_SHOW("read", total, avg, min, max, sq);
> +	CEPH_LAT_METRIC_SHOW("read", total, avg, min, max, stdev);
>   
>   	spin_lock(&m->write_metric_lock);
>   	total = m->total_writes;
> @@ -185,9 +185,9 @@ static int metric_show(struct seq_file *s, void *p)
>   	avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0;
>   	min = m->write_latency_min;
>   	max = m->write_latency_max;
> -	sq = m->write_latency_sq_sum;
> +	stdev = m->write_latency_stdev;
>   	spin_unlock(&m->write_metric_lock);
> -	CEPH_LAT_METRIC_SHOW("write", total, avg, min, max, sq);
> +	CEPH_LAT_METRIC_SHOW("write", total, avg, min, max, stdev);

Hi Venky,

Sorry I missed you V1 patch set.

Previously the "sq_sum" just counting the square sum and only when 
showing them in the debug file will it to compute the stdev in 
CEPH_LAT_METRIC_SHOW().

So with this patch I think you also need to fix the 
CEPH_LAT_METRIC_SHOW(), no need to compute it twice ?

Thanks.

>   
>   	spin_lock(&m->metadata_metric_lock);
>   	total = m->total_metadatas;
> @@ -195,9 +195,9 @@ static int metric_show(struct seq_file *s, void *p)
>   	avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0;
>   	min = m->metadata_latency_min;
>   	max = m->metadata_latency_max;
> -	sq = m->metadata_latency_sq_sum;
> +	stdev = m->metadata_latency_stdev;
>   	spin_unlock(&m->metadata_metric_lock);
> -	CEPH_LAT_METRIC_SHOW("metadata", total, avg, min, max, sq);
> +	CEPH_LAT_METRIC_SHOW("metadata", total, avg, min, max, stdev);
>   
>   	seq_printf(s, "\n");
>   	seq_printf(s, "item          total       avg_sz(bytes)   min_sz(bytes)   max_sz(bytes)  total_sz(bytes)\n");
> diff --git a/fs/ceph/metric.c b/fs/ceph/metric.c
> index 226dc38e2909..6b774b1a88ce 100644
> --- a/fs/ceph/metric.c
> +++ b/fs/ceph/metric.c
> @@ -244,7 +244,8 @@ int ceph_metric_init(struct ceph_client_metric *m)
>   		goto err_i_caps_mis;
>   
>   	spin_lock_init(&m->read_metric_lock);
> -	m->read_latency_sq_sum = 0;
> +	m->read_latency_stdev = 0;
> +	m->avg_read_latency = 0;
>   	m->read_latency_min = KTIME_MAX;
>   	m->read_latency_max = 0;
>   	m->total_reads = 0;
> @@ -254,7 +255,8 @@ int ceph_metric_init(struct ceph_client_metric *m)
>   	m->read_size_sum = 0;
>   
>   	spin_lock_init(&m->write_metric_lock);
> -	m->write_latency_sq_sum = 0;
> +	m->write_latency_stdev = 0;
> +	m->avg_write_latency = 0;
>   	m->write_latency_min = KTIME_MAX;
>   	m->write_latency_max = 0;
>   	m->total_writes = 0;
> @@ -264,7 +266,8 @@ int ceph_metric_init(struct ceph_client_metric *m)
>   	m->write_size_sum = 0;
>   
>   	spin_lock_init(&m->metadata_metric_lock);
> -	m->metadata_latency_sq_sum = 0;
> +	m->metadata_latency_stdev = 0;
> +	m->avg_metadata_latency = 0;
>   	m->metadata_latency_min = KTIME_MAX;
>   	m->metadata_latency_max = 0;
>   	m->total_metadatas = 0;
> @@ -322,20 +325,26 @@ void ceph_metric_destroy(struct ceph_client_metric *m)
>   		max = new;			\
>   }
>   
> -static inline void __update_stdev(ktime_t total, ktime_t lsum,
> -				  ktime_t *sq_sump, ktime_t lat)
> +static inline void __update_latency(ktime_t *ctotal, ktime_t *lsum,
> +				    ktime_t *lavg, ktime_t *min, ktime_t *max,
> +				    ktime_t *lstdev, ktime_t lat)
>   {
> -	ktime_t avg, sq;
> +	ktime_t total, avg, stdev;
>   
> -	if (unlikely(total == 1))
> -		return;
> +	total = ++(*ctotal);
> +	*lsum += lat;
> +
> +	METRIC_UPDATE_MIN_MAX(*min, *max, lat);
>   
> -	/* the sq is (lat - old_avg) * (lat - new_avg) */
> -	avg = DIV64_U64_ROUND_CLOSEST((lsum - lat), (total - 1));
> -	sq = lat - avg;
> -	avg = DIV64_U64_ROUND_CLOSEST(lsum, total);
> -	sq = sq * (lat - avg);
> -	*sq_sump += sq;
> +	if (unlikely(total == 1)) {
> +		*lavg = lat;
> +		*lstdev = 0;
> +	} else {
> +		avg = *lavg + div64_s64(lat - *lavg, total);
> +		stdev = *lstdev + (lat - *lavg)*(lat - avg);
> +		*lstdev = int_sqrt(div64_u64(stdev, total - 1));
> +		*lavg = avg;
> +	}
>   }
>   
>   void ceph_update_read_metrics(struct ceph_client_metric *m,
> @@ -343,23 +352,18 @@ void ceph_update_read_metrics(struct ceph_client_metric *m,
>   			      unsigned int size, int rc)
>   {
>   	ktime_t lat = ktime_sub(r_end, r_start);
> -	ktime_t total;
>   
>   	if (unlikely(rc < 0 && rc != -ENOENT && rc != -ETIMEDOUT))
>   		return;
>   
>   	spin_lock(&m->read_metric_lock);
> -	total = ++m->total_reads;
>   	m->read_size_sum += size;
> -	m->read_latency_sum += lat;
>   	METRIC_UPDATE_MIN_MAX(m->read_size_min,
>   			      m->read_size_max,
>   			      size);
> -	METRIC_UPDATE_MIN_MAX(m->read_latency_min,
> -			      m->read_latency_max,
> -			      lat);
> -	__update_stdev(total, m->read_latency_sum,
> -		       &m->read_latency_sq_sum, lat);
> +	__update_latency(&m->total_reads, &m->read_latency_sum,
> +			 &m->avg_read_latency, &m->read_latency_min,
> +			 &m->read_latency_max, &m->read_latency_stdev, lat);
>   	spin_unlock(&m->read_metric_lock);
>   }
>   
> @@ -368,23 +372,18 @@ void ceph_update_write_metrics(struct ceph_client_metric *m,
>   			       unsigned int size, int rc)
>   {
>   	ktime_t lat = ktime_sub(r_end, r_start);
> -	ktime_t total;
>   
>   	if (unlikely(rc && rc != -ETIMEDOUT))
>   		return;
>   
>   	spin_lock(&m->write_metric_lock);
> -	total = ++m->total_writes;
>   	m->write_size_sum += size;
> -	m->write_latency_sum += lat;
>   	METRIC_UPDATE_MIN_MAX(m->write_size_min,
>   			      m->write_size_max,
>   			      size);
> -	METRIC_UPDATE_MIN_MAX(m->write_latency_min,
> -			      m->write_latency_max,
> -			      lat);
> -	__update_stdev(total, m->write_latency_sum,
> -		       &m->write_latency_sq_sum, lat);
> +	__update_latency(&m->total_writes, &m->write_latency_sum,
> +			 &m->avg_write_latency, &m->write_latency_min,
> +			 &m->write_latency_max, &m->write_latency_stdev, lat);
>   	spin_unlock(&m->write_metric_lock);
>   }
>   
> @@ -393,18 +392,13 @@ void ceph_update_metadata_metrics(struct ceph_client_metric *m,
>   				  int rc)
>   {
>   	ktime_t lat = ktime_sub(r_end, r_start);
> -	ktime_t total;
>   
>   	if (unlikely(rc && rc != -ENOENT))
>   		return;
>   
>   	spin_lock(&m->metadata_metric_lock);
> -	total = ++m->total_metadatas;
> -	m->metadata_latency_sum += lat;
> -	METRIC_UPDATE_MIN_MAX(m->metadata_latency_min,
> -			      m->metadata_latency_max,
> -			      lat);
> -	__update_stdev(total, m->metadata_latency_sum,
> -		       &m->metadata_latency_sq_sum, lat);
> +	__update_latency(&m->total_metadatas, &m->metadata_latency_sum,
> +			 &m->avg_metadata_latency, &m->metadata_latency_min,
> +			 &m->metadata_latency_max, &m->metadata_latency_stdev, lat);
>   	spin_unlock(&m->metadata_metric_lock);
>   }
> diff --git a/fs/ceph/metric.h b/fs/ceph/metric.h
> index 103ed736f9d2..a5da21b8f8ed 100644
> --- a/fs/ceph/metric.h
> +++ b/fs/ceph/metric.h
> @@ -138,7 +138,8 @@ struct ceph_client_metric {
>   	u64 read_size_min;
>   	u64 read_size_max;
>   	ktime_t read_latency_sum;
> -	ktime_t read_latency_sq_sum;
> +	ktime_t avg_read_latency;
> +	ktime_t read_latency_stdev;
>   	ktime_t read_latency_min;
>   	ktime_t read_latency_max;
>   
> @@ -148,14 +149,16 @@ struct ceph_client_metric {
>   	u64 write_size_min;
>   	u64 write_size_max;
>   	ktime_t write_latency_sum;
> -	ktime_t write_latency_sq_sum;
> +	ktime_t avg_write_latency;
> +	ktime_t write_latency_stdev;
>   	ktime_t write_latency_min;
>   	ktime_t write_latency_max;
>   
>   	spinlock_t metadata_metric_lock;
>   	u64 total_metadatas;
>   	ktime_t metadata_latency_sum;
> -	ktime_t metadata_latency_sq_sum;
> +	ktime_t avg_metadata_latency;
> +	ktime_t metadata_latency_stdev;
>   	ktime_t metadata_latency_min;
>   	ktime_t metadata_latency_max;
>   


  reply	other threads:[~2021-09-14 12:53 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-14  8:48 [PATCH v2 0/4] ceph: forward average read/write/metadata latency Venky Shankar
2021-09-14  8:48 ` [PATCH v2 1/4] ceph: use "struct ceph_timespec" for r/w/m latencies Venky Shankar
2021-09-14  8:49 ` [PATCH v2 2/4] ceph: track average/stdev r/w/m latency Venky Shankar
2021-09-14 12:52   ` Xiubo Li [this message]
2021-09-14 13:03     ` Venky Shankar
2021-09-14 13:09   ` Xiubo Li
2021-09-14 13:30     ` Venky Shankar
2021-09-14 13:45       ` Xiubo Li
2021-09-14 13:52         ` Xiubo Li
2021-09-14 14:00           ` Venky Shankar
2021-09-14 14:10             ` Xiubo Li
2021-09-14 13:53         ` Venky Shankar
2021-09-14 13:58           ` Xiubo Li
2021-09-14 13:13   ` Xiubo Li
2021-09-14 13:32     ` Jeff Layton
2021-09-14 13:32     ` Venky Shankar
2021-09-14  8:49 ` [PATCH v2 3/4] ceph: include average/stddev r/w/m latency in mds metrics Venky Shankar
2021-09-14 13:57   ` Xiubo Li
2021-09-14  8:49 ` [PATCH v2 4/4] ceph: use tracked average r/w/m latencies to display metrics in debugfs Venky Shankar

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=b9d1a0ea-147c-251b-1618-111d869687a0@redhat.com \
    --to=xiubli@redhat.com \
    --cc=ceph-devel@vger.kernel.org \
    --cc=jlayton@redhat.com \
    --cc=pdonnell@redhat.com \
    --cc=vshankar@redhat.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;
as well as URLs for NNTP newsgroup(s).