linux-ext4.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: zwu.kernel@gmail.com
To: linux-fsdevel@vger.kernel.org
Cc: linux-ext4@vger.kernel.org, linux-btrfs@vger.kernel.org,
	linux-kernel@vger.kernel.org, linuxram@linux.vnet.ibm.com,
	viro@zeniv.linux.org.uk, david@fromorbit.com, dave@jikos.cz,
	tytso@mit.edu, cmm@us.ibm.com,
	Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
Subject: [RFC v3 07/13] vfs: add function for updating map arrays
Date: Wed, 10 Oct 2012 18:07:29 +0800	[thread overview]
Message-ID: <1349863655-29320-8-git-send-email-zwu.kernel@gmail.com> (raw)
In-Reply-To: <1349863655-29320-1-git-send-email-zwu.kernel@gmail.com>

From: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>

Signed-off-by: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
---
 fs/hot_tracking.c |  153 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/hot_tracking.h |   60 +++++++++++++++++++++
 2 files changed, 213 insertions(+), 0 deletions(-)

diff --git a/fs/hot_tracking.c b/fs/hot_tracking.c
index 08c42c5..717faa7 100644
--- a/fs/hot_tracking.c
+++ b/fs/hot_tracking.c
@@ -376,6 +376,159 @@ inline void hot_update_freqs(struct hot_info *root,
 	hot_inode_item_put(he);
 }
 
+static u64 hot_raw_shift(u64 counter, u32 bits, bool dir)
+{
+	if (dir)
+		return counter << bits;
+	else
+		return counter >> bits;
+}
+
+/*
+ * hot_temperature_calculate() is responsible for distilling the six heat
+ * criteria, which are described in detail in hot_tracking.h) down into a single
+ * temperature value for the data, which is an integer between 0
+ * and HEAT_MAX_VALUE.
+ *
+ * To accomplish this, the raw values from the hot_freq_data structure
+ * are shifted various ways in order to make the temperature calculation more
+ * or less sensitive to each value.
+ *
+ * Once this calibration has happened, we do some additional normalization and
+ * make sure that everything fits nicely in a u32. From there, we take a very
+ * rudimentary kind of "average" of each of the values, where the *_COEFF_POWER
+ * values act as weights for the average.
+ *
+ * Finally, we use the HEAT_HASH_BITS value, which determines the size of the
+ * heat list array, to normalize the temperature to the proper granularity.
+ */
+int hot_temperature_calculate(struct hot_freq_data *freq_data)
+{
+	u64 result = 0;
+
+	struct timespec ckt = current_kernel_time();
+	u64 cur_time = timespec_to_ns(&ckt);
+
+	u32 nrr_heat = (u32)hot_raw_shift((u64)freq_data->nr_reads,
+					NRR_MULTIPLIER_POWER, true);
+	u32 nrw_heat = (u32)hot_raw_shift((u64)freq_data->nr_writes,
+					NRW_MULTIPLIER_POWER, true);
+
+	u64 ltr_heat =
+	hot_raw_shift((cur_time - timespec_to_ns(&freq_data->last_read_time)),
+			LTR_DIVIDER_POWER, false);
+	u64 ltw_heat =
+	hot_raw_shift((cur_time - timespec_to_ns(&freq_data->last_write_time)),
+			LTW_DIVIDER_POWER, false);
+
+	u64 avr_heat =
+	hot_raw_shift((((u64) -1) - freq_data->avg_delta_reads),
+			AVR_DIVIDER_POWER, false);
+	u64 avw_heat =
+	hot_raw_shift((((u64) -1) - freq_data->avg_delta_writes),
+			AVW_DIVIDER_POWER, false);
+
+	/* ltr_heat is now guaranteed to be u32 safe */
+	if (ltr_heat >= hot_raw_shift((u64) 1, 32, true))
+		ltr_heat = 0;
+	else
+		ltr_heat = hot_raw_shift((u64) 1, 32, true) - ltr_heat;
+
+	/* ltw_heat is now guaranteed to be u32 safe */
+	if (ltw_heat >= hot_raw_shift((u64) 1, 32, true))
+		ltw_heat = 0;
+	else
+		ltw_heat = hot_raw_shift((u64) 1, 32, true) - ltw_heat;
+
+	/* avr_heat is now guaranteed to be u32 safe */
+	if (avr_heat >= hot_raw_shift((u64) 1, 32, true))
+		avr_heat = (u32) -1;
+
+	/* avw_heat is now guaranteed to be u32 safe */
+	if (avw_heat >= hot_raw_shift((u64) 1, 32, true))
+		avw_heat = (u32) -1;
+
+	nrr_heat = (u32)hot_raw_shift((u64)nrr_heat,
+		(3 - NRR_COEFF_POWER), false);
+	nrw_heat = (u32)hot_raw_shift((u64)nrw_heat,
+		(3 - NRW_COEFF_POWER), false);
+	ltr_heat = hot_raw_shift(ltr_heat, (3 - LTR_COEFF_POWER), false);
+	ltw_heat = hot_raw_shift(ltw_heat, (3 - LTW_COEFF_POWER), false);
+	avr_heat = hot_raw_shift(avr_heat, (3 - AVR_COEFF_POWER), false);
+	avw_heat = hot_raw_shift(avw_heat, (3 - AVW_COEFF_POWER), false);
+
+	result = nrr_heat + nrw_heat + (u32) ltr_heat +
+		(u32) ltw_heat + (u32) avr_heat + (u32) avw_heat;
+
+	return result >> (32 - HEAT_MAP_BITS);
+}
+
+/*
+ * Calculate a new temperature and, if necessary,
+ * move the list_head corresponding to this inode or range
+ * to the proper list with the new temperature
+ */
+static void hot_map_array_update(struct hot_freq_data *freq_data,
+				struct hot_info *root)
+{
+	struct hot_map_head *buckets, *cur_bucket;
+	struct hot_comm_item *comm_item;
+	struct hot_inode_item *he;
+	struct hot_range_item *hr;
+	u32 temperature = 0;
+
+	comm_item = container_of(freq_data,
+			struct hot_comm_item, hot_freq_data);
+
+	if (freq_data->flags & FREQ_DATA_TYPE_INODE) {
+		he = container_of(comm_item,
+			struct hot_inode_item, hot_inode);
+		buckets = root->heat_inode_map;
+
+		spin_lock(&he->hot_inode.lock);
+		temperature = hot_temperature_calculate(freq_data);
+		spin_unlock(&he->hot_inode.lock);
+
+		if (he == NULL)
+			return;
+
+		spin_lock(&he->hot_inode.lock);
+		if (list_empty(&he->hot_inode.n_list)
+			|| (freq_data->last_temperature != temperature)) {
+			if (!list_empty(&he->hot_inode.n_list))
+				list_del_init(&he->hot_inode.n_list);
+
+			cur_bucket = buckets + temperature;
+			list_add_tail(&he->hot_inode.n_list, &cur_bucket->node_list);
+			freq_data->last_temperature = temperature;
+		}
+		spin_unlock(&he->hot_inode.lock);
+	} else if (freq_data->flags & FREQ_DATA_TYPE_RANGE) {
+		hr = container_of(comm_item,
+			struct hot_range_item, hot_range);
+		buckets = root->heat_range_map;
+
+		spin_lock(&hr->hot_range.lock);
+		temperature = hot_temperature_calculate(freq_data);
+		spin_unlock(&hr->hot_range.lock);
+
+		if (hr == NULL)
+			return;
+
+		spin_lock(&hr->hot_range.lock);
+		if (list_empty(&hr->hot_range.n_list)
+			|| (freq_data->last_temperature != temperature)) {
+			if (!list_empty(&hr->hot_range.n_list))
+				list_del_init(&hr->hot_range.n_list);
+
+			cur_bucket = buckets + temperature;
+			list_add_tail(&hr->hot_range.n_list, &cur_bucket->node_list);
+			freq_data->last_temperature = temperature;
+		}
+		spin_unlock(&hr->hot_range.lock);
+	}
+}
+
 /*
  * Initialize inode and range map arrays.
  */
diff --git a/fs/hot_tracking.h b/fs/hot_tracking.h
index 42e0273..5a9517b 100644
--- a/fs/hot_tracking.h
+++ b/fs/hot_tracking.h
@@ -30,6 +30,64 @@
 
 #define FREQ_POWER 4
 
+/*
+ * The following comments explain what exactly comprises a unit of heat.
+ *
+ * Each of six values of heat are calculated and combined in order to form an
+ * overall temperature for the data:
+ *
+ * NRR - number of reads since mount
+ * NRW - number of writes since mount
+ * LTR - time elapsed since last read (ns)
+ * LTW - time elapsed since last write (ns)
+ * AVR - average delta between recent reads (ns)
+ * AVW - average delta between recent writes (ns)
+ *
+ * These values are divided (right-shifted) according to the *_DIVIDER_POWER
+ * values defined below to bring the numbers into a reasonable range. You can
+ * modify these values to fit your needs. However, each heat unit is a u32 and
+ * thus maxes out at 2^32 - 1. Therefore, you must choose your dividers quite
+ * carefully or else they could max out or be stuck at zero quite easily.
+ *
+ * (E.g., if you chose AVR_DIVIDER_POWER = 0, nothing less than 4s of atime
+ * delta would bring the temperature above zero, ever.)
+ *
+ * Finally, each value is added to the overall temperature between 0 and 8
+ * times, depending on its *_COEFF_POWER value. Note that the coefficients are
+ * also actually implemented with shifts, so take care to treat these values
+ * as powers of 2. (I.e., 0 means we'll add it to the temp once; 1 = 2x, etc.)
+ */
+
+/* NRR/NRW heat unit = 2^X accesses */
+#define NRR_MULTIPLIER_POWER 20
+#define NRR_COEFF_POWER 0
+#define NRW_MULTIPLIER_POWER 20
+#define NRW_COEFF_POWER 0
+
+/* LTR/LTW heat unit = 2^X ns of age */
+#define LTR_DIVIDER_POWER 30
+#define LTR_COEFF_POWER 1
+#define LTW_DIVIDER_POWER 30
+#define LTW_COEFF_POWER 1
+
+/*
+ * AVR/AVW cold unit = 2^X ns of average delta
+ * AVR/AVW heat unit = HEAT_MAX_VALUE - cold unit
+ *
+ * E.g., data with an average delta between 0 and 2^X ns
+ * will have a cold value of 0, which means a heat value
+ * equal to HEAT_MAX_VALUE.
+ */
+#define AVR_DIVIDER_POWER 40
+#define AVR_COEFF_POWER 0
+#define AVW_DIVIDER_POWER 40
+#define AVW_COEFF_POWER 0
+
+struct hot_update_work {
+	struct work_struct work;
+	struct hot_info *hot_info;
+};
+
 struct hot_inode_item
 *hot_inode_item_find(struct hot_info *root, u64 ino);
 void hot_inode_item_put(struct hot_inode_item *he);
@@ -37,6 +95,8 @@ inline void hot_update_freqs(struct hot_info *root,
                         struct inode *inode, u64 start,
                         u64 len, int rw);
 
+int hot_temperature_calculate(struct hot_freq_data *freq_data);
+
 void hot_track_init(struct super_block *sb);
 void hot_track_exit(struct super_block *sb);
 
-- 
1.7.6.5


  parent reply	other threads:[~2012-10-10 10:07 UTC|newest]

Thread overview: 54+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-10-10 10:07 [RFC v3 00/13] vfs: hot data tracking zwu.kernel
2012-10-10 10:07 ` [RFC v3 01/13] btrfs: add one new mount option '-o hot_track' zwu.kernel
     [not found]   ` <5075632c.03cc440a.1b33.7805SMTPIN_ADDED@mx.google.com>
2012-10-10 12:21     ` Zhi Yong Wu
2012-10-10 13:11       ` Lukáš Czerner
2012-10-10 13:16         ` Zhi Yong Wu
2012-10-10 16:28   ` David Sterba
2012-10-11 13:41     ` Zhi Yong Wu
2012-10-11 14:35     ` Zhi Yong Wu
2012-10-11 14:41       ` David Sterba
2012-10-11 14:46         ` Zhi Yong Wu
2012-10-10 10:07 ` [RFC v3 02/13] vfs: introduce private radix tree structures zwu.kernel
2012-10-10 15:34   ` David Sterba
2012-10-11 13:35     ` Zhi Yong Wu
2012-10-10 10:07 ` [RFC v3 03/13] vfs: Initialize and free main data structures zwu.kernel
2012-10-10 10:07 ` [RFC v3 04/13] vfs: add function for collecting raw access info zwu.kernel
2012-10-10 10:07 ` [RFC v3 05/13] vfs: add two map arrays zwu.kernel
2012-10-10 10:07 ` [RFC v3 06/13] vfs: add hooks to enable hot data tracking zwu.kernel
2012-10-10 10:07 ` zwu.kernel [this message]
2012-10-10 10:07 ` [RFC v3 08/13] vfs: add aging function for old map info zwu.kernel
2012-10-10 10:07 ` [RFC v3 09/13] vfs: add one wq to update map info periodically zwu.kernel
2012-10-16  0:27   ` Dave Chinner
2012-10-17  6:34     ` Zhi Yong Wu
2012-10-18  2:25       ` Zheng Liu
2012-10-18  2:26         ` Zhi Yong Wu
2012-10-10 10:07 ` [RFC v3 10/13] vfs: register one memory shrinker zwu.kernel
2012-10-10 10:07 ` [RFC v3 11/13] vfs: add 3 new ioctl interfaces zwu.kernel
2012-10-15  7:48   ` Dave Chinner
2012-10-15  7:57     ` Zhi Yong Wu
2012-10-16  3:17   ` Dave Chinner
2012-10-16  4:18     ` Zhi Yong Wu
2012-10-19  8:21     ` Zhi Yong Wu
2012-10-10 10:07 ` [RFC v3 12/13] vfs: add debugfs support zwu.kernel
2012-10-10 16:53   ` David Sterba
2012-10-10 21:05   ` David Sterba
2012-10-15  7:55   ` Dave Chinner
2012-10-15  8:15     ` Zhi Yong Wu
2012-10-15  8:04   ` Dave Chinner
2012-10-15  8:47     ` Zhi Yong Wu
2012-10-10 10:07 ` [RFC v3 13/13] vfs: add documentation zwu.kernel
2012-10-15  0:35   ` Zheng Liu
2012-10-15  7:04     ` Zhi Yong Wu
2012-10-15  0:39 ` [RFC v3 00/13] vfs: hot data tracking Zheng Liu
2012-10-15  7:05   ` Zhi Yong Wu
2012-10-15 20:42 ` Dave Chinner
2012-10-17  8:57   ` Zhi Yong Wu
2012-10-18  4:29     ` Dave Chinner
2012-10-18  4:44       ` Zhi Yong Wu
2012-10-18  5:17         ` Dave Chinner
2012-10-18  5:24           ` Zhi Yong Wu
2012-10-19  8:29   ` Zhi Yong Wu
2012-10-16  0:04 ` [PATCH] xfs: add hot tracking support Dave Chinner
2012-11-07  8:38   ` Zhi Yong Wu
2012-11-08  5:13     ` Dave Chinner
2012-10-16  0:11 ` [RFC v3 00/13] vfs: hot data tracking Dave Chinner

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=1349863655-29320-8-git-send-email-zwu.kernel@gmail.com \
    --to=zwu.kernel@gmail.com \
    --cc=cmm@us.ibm.com \
    --cc=dave@jikos.cz \
    --cc=david@fromorbit.com \
    --cc=linux-btrfs@vger.kernel.org \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linuxram@linux.vnet.ibm.com \
    --cc=tytso@mit.edu \
    --cc=viro@zeniv.linux.org.uk \
    --cc=wuzhy@linux.vnet.ibm.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).