Linux-mm Archive on lore.kernel.org
 help / color / Atom feed
From: <sjpark@amazon.com>
To: <akpm@linux-foundation.org>
Cc: SeongJae Park <sjpark@amazon.de>, <acme@kernel.org>,
	<alexander.shishkin@linux.intel.com>, <amit@kernel.org>,
	<brendan.d.gregg@gmail.com>, <brendanhiggins@google.com>,
	<cai@lca.pw>, <colin.king@canonical.com>, <corbet@lwn.net>,
	<dwmw@amazon.com>, <jolsa@redhat.com>, <kirill@shutemov.name>,
	<mark.rutland@arm.com>, <mgorman@suse.de>, <minchan@kernel.org>,
	<mingo@redhat.com>, <namhyung@kernel.org>, <peterz@infradead.org>,
	<rdunlap@infradead.org>, <rostedt@goodmis.org>,
	<sj38.park@gmail.com>, <vdavydov.dev@gmail.com>,
	<linux-mm@kvack.org>, <linux-doc@vger.kernel.org>,
	<linux-kernel@vger.kernel.org>
Subject: [PATCH v4 06/11] mm/damon: Add debugfs interface
Date: Mon, 10 Feb 2020 15:51:34 +0100
Message-ID: <20200210145134.27840-1-sjpark@amazon.com> (raw)
In-Reply-To: <20200210144812.26845-1-sjpark@amazon.com>

From: SeongJae Park <sjpark@amazon.de>

This commit adds a debugfs interface for DAMON.

DAMON exports four files, ``attrs``, ``pids``, ``record``, and
``monitor_on`` under its debugfs directory, ``<debugfs>/damon/``.

Attributes
----------

Users can read and write the ``sampling interval``, ``aggregation
interval``, ``regions update interval``, and min/max number of
monitoring target regions by reading from and writing to the ``attrs``
file.  For example, below commands set those values to 5 ms, 100 ms,
1,000 ms, 10, 1000 and check it again::

    # cd <debugfs>/damon
    # echo 5000 100000 1000000 10 1000 > attrs
    # cat attrs
    5000 100000 1000000 10 1000

Target PIDs
-----------

Users can read and write the pids of current monitoring target processes
by reading from and writing to the ``pids`` file.  For example, below
commands set processes having pids 42 and 4242 as the processes to be
monitored and check it again::

    # cd <debugfs>/damon
    # echo 42 4242 > pids
    # cat pids
    42 4242

Note that setting the pids doesn't starts the monitoring.

Record
------

DAMON support direct monitoring result record feature.  The recorded
results are first written to a buffer and flushed to a file in batch.
Users can set the size of the buffer and the path to the result file by
reading from and writing to the ``record`` file.  For example, below
commands set the buffer to be 4 KiB and the result to be saved in
'/damon.data'.

    # cd <debugfs>/damon
    # echo 4096 /damon.data > pids
    # cat record
    4096 /damon.data

Turning On/Off
--------------

You can check current status, start and stop the monitoring by reading
from and writing to the ``monitor_on`` file.  Writing ``on`` to the file
starts DAMON to monitor the target processes with the attributes.
Writing ``off`` to the file stops DAMON.  DAMON also stops if every
target processes is be terminated.  Below example commands turn on, off,
and check status of DAMON::

    # cd <debugfs>/damon
    # echo on > monitor_on
    # echo off > monitor_on
    # cat monitor_on
    off

Please note that you cannot write to the ``attrs`` and ``pids`` files
while the monitoring is turned on.  If you write to the files while
DAMON is running, ``-EINVAL`` will be returned.

Signed-off-by: SeongJae Park <sjpark@amazon.de>
---
 mm/damon.c | 349 ++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 348 insertions(+), 1 deletion(-)

diff --git a/mm/damon.c b/mm/damon.c
index 450b85bef120..748cd8537fee 100644
--- a/mm/damon.c
+++ b/mm/damon.c
@@ -10,6 +10,7 @@
 #define pr_fmt(fmt) "damon: " fmt
 
 #include <linux/damon.h>
+#include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/mm.h>
@@ -41,6 +42,24 @@
 #define damon_for_each_task_safe(ctx, t, next) \
 	list_for_each_entry_safe(t, next, &(ctx)->tasks_list, list)
 
+/*
+ * For each 'sample_interval', DAMON checks whether each region is accessed or
+ * not.  It aggregates and keeps the access information (number of accesses to
+ * each region) for 'aggr_interval' and then flushes it to the result buffer if
+ * an 'aggr_interval' surpassed.  And for each 'regions_update_interval', damon
+ * checks whether the memory mapping of the target tasks has changed (e.g., by
+ * mmap() calls from the applications) and applies the changes.
+ *
+ * All time intervals are in micro-seconds.
+ */
+static struct damon_ctx damon_user_ctx = {
+	.sample_interval = 5 * 1000,
+	.aggr_interval = 100 * 1000,
+	.regions_update_interval = 1000 * 1000,
+	.min_nr_regions = 10,
+	.max_nr_regions = 1000,
+};
+
 #define LEN_RES_FILE_PATH	256
 
 /* Get a random number in [l, r) */
@@ -1040,15 +1059,343 @@ int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int,
 	return 0;
 }
 
+/*
+ * debugfs functions
+ */
+
+static ssize_t debugfs_monitor_on_read(struct file *file,
+		char __user *buf, size_t count, loff_t *ppos)
+{
+	struct damon_ctx *ctx = &damon_user_ctx;
+	char monitor_on_buf[5];
+	bool monitor_on;
+	int ret;
+
+	spin_lock(&ctx->kdamond_lock);
+	monitor_on = ctx->kdamond != NULL;
+	spin_unlock(&ctx->kdamond_lock);
+
+	ret = snprintf(monitor_on_buf, 5, monitor_on ? "on\n" : "off\n");
+
+	return simple_read_from_buffer(buf, count, ppos, monitor_on_buf, ret);
+}
+
+static ssize_t debugfs_monitor_on_write(struct file *file,
+		const char __user *buf, size_t count, loff_t *ppos)
+{
+	struct damon_ctx *ctx = &damon_user_ctx;
+	ssize_t ret;
+	bool on = false;
+	char cmdbuf[5];
+
+	ret = simple_write_to_buffer(cmdbuf, 5, ppos, buf, count);
+	if (ret < 0)
+		return ret;
+
+	if (sscanf(cmdbuf, "%s", cmdbuf) != 1)
+		return -EINVAL;
+	if (!strncmp(cmdbuf, "on", 5))
+		on = true;
+	else if (!strncmp(cmdbuf, "off", 5))
+		on = false;
+	else
+		return -EINVAL;
+
+	if (damon_turn_kdamond(ctx, on))
+		return -EINVAL;
+
+	return ret;
+}
+
+static ssize_t damon_sprint_pids(struct damon_ctx *ctx, char *buf, ssize_t len)
+{
+	char *cursor = buf;
+	struct damon_task *t;
+	int ret;
+
+	damon_for_each_task(ctx, t) {
+		ret = snprintf(cursor, len, "%lu ", t->pid);
+		cursor += ret;
+	}
+	if (cursor != buf)
+		cursor--;
+	cursor += snprintf(cursor, len, "\n");
+	return cursor - buf;
+}
+
+static ssize_t debugfs_pids_read(struct file *file,
+		char __user *buf, size_t count, loff_t *ppos)
+{
+	struct damon_ctx *ctx = &damon_user_ctx;
+	ssize_t len;
+	char pids_buf[512];
+
+	len = damon_sprint_pids(ctx, pids_buf, 512);
+
+	return simple_read_from_buffer(buf, count, ppos, pids_buf, len);
+}
+
+/*
+ * Converts a string into an array of unsigned long integers
+ *
+ * Returns an array of unsigned long integers that converted, or NULL if the
+ * input is wrong.
+ */
+static unsigned long *str_to_pids(const char *str, ssize_t len,
+				ssize_t *nr_pids)
+{
+	unsigned long *pids;
+	unsigned long pid;
+	int pos = 0, parsed, ret;
+
+	*nr_pids = 0;
+	pids = kmalloc_array(256, sizeof(unsigned long), GFP_KERNEL);
+	while (*nr_pids < 256 && pos < len) {
+		ret = sscanf(&str[pos], "%lu%n", &pid, &parsed);
+		pos += parsed;
+		if (ret != 1)
+			break;
+		pids[*nr_pids] = pid;
+		*nr_pids += 1;
+	}
+	if (*nr_pids == 0) {
+		kfree(pids);
+		pids = NULL;
+	}
+
+	return pids;
+}
+
+static ssize_t debugfs_pids_write(struct file *file,
+		const char __user *buf, size_t count, loff_t *ppos)
+{
+	struct damon_ctx *ctx = &damon_user_ctx;
+	ssize_t ret;
+	unsigned long *targets;
+	ssize_t nr_targets;
+	char pids_buf[512];
+
+	ret = simple_write_to_buffer(pids_buf, 512, ppos, buf, count);
+	if (ret < 0)
+		return ret;
+
+	targets = str_to_pids(pids_buf, ret, &nr_targets);
+
+	spin_lock(&ctx->kdamond_lock);
+	if (ctx->kdamond)
+		goto monitor_running;
+
+	damon_set_pids(ctx, targets, nr_targets);
+	spin_unlock(&ctx->kdamond_lock);
+	kfree(targets);
+
+	return ret;
+
+monitor_running:
+	spin_unlock(&ctx->kdamond_lock);
+	pr_err("%s: kdamond is running. Turn it off first.\n", __func__);
+	return -EINVAL;
+}
+
+static ssize_t debugfs_record_read(struct file *file,
+		char __user *buf, size_t count, loff_t *ppos)
+{
+	struct damon_ctx *ctx = &damon_user_ctx;
+	char record_buf[512];
+	int ret;
+
+	ret = snprintf(record_buf, 512, "%u %s\n",
+			ctx->rbuf_len, ctx->rfile_path);
+	return simple_read_from_buffer(buf, count, ppos, record_buf, ret);
+}
+
+static ssize_t debugfs_record_write(struct file *file,
+		const char __user *buf, size_t count, loff_t *ppos)
+{
+	struct damon_ctx *ctx = &damon_user_ctx;
+	char record_buf[512];
+	unsigned int rbuf_len;
+	char res_file_path[LEN_RES_FILE_PATH];
+	ssize_t ret;
+
+	if (count > 512) {
+		pr_err("record debugfs input is too large: %s\n", buf);
+		return -ENOMEM;
+	}
+
+	ret = simple_write_to_buffer(record_buf, 512, ppos, buf, count);
+	if (ret < 0)
+		return ret;
+	if (sscanf(record_buf, "%u %s",
+				&rbuf_len, res_file_path) != 2)
+		return -EINVAL;
+
+	spin_lock(&ctx->kdamond_lock);
+	if (ctx->kdamond)
+		goto monitor_running;
+
+	damon_set_recording(ctx, rbuf_len, res_file_path);
+	spin_unlock(&ctx->kdamond_lock);
+
+	return ret;
+
+monitor_running:
+	spin_unlock(&ctx->kdamond_lock);
+	pr_err("%s: kdamond is running. Turn it off first.\n", __func__);
+	return -EINVAL;
+}
+
+
+static ssize_t debugfs_attrs_read(struct file *file,
+		char __user *buf, size_t count, loff_t *ppos)
+{
+	struct damon_ctx *ctx = &damon_user_ctx;
+	char attrs_buf[256];
+	int ret;
+
+	ret = snprintf(attrs_buf, 256, "%lu %lu %lu %lu %lu\n",
+			ctx->sample_interval, ctx->aggr_interval,
+			ctx->regions_update_interval, ctx->min_nr_regions,
+			ctx->max_nr_regions);
+
+	return simple_read_from_buffer(buf, count, ppos, attrs_buf, ret);
+}
+
+static ssize_t debugfs_attrs_write(struct file *file,
+		const char __user *buf, size_t count, loff_t *ppos)
+{
+	struct damon_ctx *ctx = &damon_user_ctx;
+	unsigned long s, a, r, minr, maxr;
+	char attrs_buf[256];
+	ssize_t ret;
+
+	if (count > 256) {
+		pr_err("attributes stream is too large: %s\n", buf);
+		return -ENOMEM;
+	}
+
+	ret = simple_write_to_buffer(attrs_buf, 256, ppos, buf, count);
+	if (ret < 0)
+		return ret;
+
+	if (sscanf(attrs_buf, "%lu %lu %lu %lu %lu",
+				&s, &a, &r, &minr, &maxr) != 5)
+		return -EINVAL;
+
+	spin_lock(&ctx->kdamond_lock);
+	if (ctx->kdamond)
+		goto monitor_running;
+
+	damon_set_attrs(ctx, s, a, r, minr, maxr);
+	spin_unlock(&ctx->kdamond_lock);
+
+	return ret;
+
+monitor_running:
+	spin_unlock(&ctx->kdamond_lock);
+	pr_err("%s: kdamond is running. Turn it off first.\n", __func__);
+	return -EINVAL;
+}
+
+static const struct file_operations monitor_on_fops = {
+	.owner = THIS_MODULE,
+	.read = debugfs_monitor_on_read,
+	.write = debugfs_monitor_on_write,
+};
+
+static const struct file_operations pids_fops = {
+	.owner = THIS_MODULE,
+	.read = debugfs_pids_read,
+	.write = debugfs_pids_write,
+};
+
+static const struct file_operations record_fops = {
+	.owner = THIS_MODULE,
+	.read = debugfs_record_read,
+	.write = debugfs_record_write,
+};
+
+static const struct file_operations attrs_fops = {
+	.owner = THIS_MODULE,
+	.read = debugfs_attrs_read,
+	.write = debugfs_attrs_write,
+};
+
+static struct dentry *debugfs_root;
+
+static int __init debugfs_init(void)
+{
+	const char * const file_names[] = {"attrs", "record",
+		"pids", "monitor_on"};
+	const struct file_operations *fops[] = {&attrs_fops, &record_fops,
+		&pids_fops, &monitor_on_fops};
+	int i;
+
+	debugfs_root = debugfs_create_dir("damon", NULL);
+	if (!debugfs_root) {
+		pr_err("failed to create the debugfs dir\n");
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(file_names); i++) {
+		if (!debugfs_create_file(file_names[i], 0600, debugfs_root,
+					NULL, fops[i])) {
+			pr_err("failed to create %s file\n", file_names[i]);
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+static int __init damon_init_user_ctx(void)
+{
+	int rc;
+
+	struct damon_ctx *ctx = &damon_user_ctx;
+
+	ktime_get_coarse_ts64(&ctx->last_aggregation);
+	ctx->last_regions_update = ctx->last_aggregation;
+
+	ctx->rbuf_offset = 0;
+	rc = damon_set_recording(ctx, 1024 * 1024, "/damon.data");
+	if (rc)
+		return rc;
+
+	ctx->kdamond = NULL;
+	ctx->kdamond_stop = false;
+	spin_lock_init(&ctx->kdamond_lock);
+
+	prandom_seed_state(&ctx->rndseed, 42);
+	INIT_LIST_HEAD(&ctx->tasks_list);
+
+	ctx->sample_cb = NULL;
+	ctx->aggregate_cb = NULL;
+
+	return 0;
+}
+
 static int __init damon_init(void)
 {
+	int rc;
+
 	pr_info("init\n");
 
-	return 0;
+	rc = damon_init_user_ctx();
+	if (rc)
+		return rc;
+
+	return debugfs_init();
 }
 
 static void __exit damon_exit(void)
 {
+	damon_turn_kdamond(&damon_user_ctx, false);
+	debugfs_remove_recursive(debugfs_root);
+
+	kfree(damon_user_ctx.rbuf);
+	kfree(damon_user_ctx.rfile_path);
+
 	pr_info("exit\n");
 }
 
-- 
2.17.1



  parent reply index

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-02-10 14:48 [PATCH v4 00/11] Introduce Data Access MONitor (DAMON) sjpark
2020-02-10 14:48 ` [PATCH v4 01/11] mm: " sjpark
2020-02-10 14:48 ` [PATCH v4 02/11] mm/damon: Implement region based sampling sjpark
2020-02-10 14:48 ` [PATCH v4 03/11] mm/damon: Adaptively adjust regions sjpark
2020-02-10 14:48 ` [PATCH v4 04/11] mm/damon: Apply dynamic memory mapping changes sjpark
2020-02-10 14:50 ` [PATCH v4 05/11] mm/damon: Implement kernel space API sjpark
2020-02-12 23:21   ` kbuild test robot
2020-02-13  9:09     ` SeongJae Park
2020-02-10 14:51 ` sjpark [this message]
2020-02-10 14:52 ` [PATCH v4 07/11] mm/damon: Add a tracepoint for result writing sjpark
2020-02-10 14:52 ` [PATCH v4 08/11] tools: Add a minimal user-space tool for DAMON sjpark
2020-02-10 14:53 ` [PATCH v4 09/11] Documentation/admin-guide/mm: Add a document " sjpark
2020-02-10 14:53 ` [PATCH v4 10/11] mm/damon: Add kunit tests sjpark
2020-02-11 22:21   ` Brendan Higgins
2020-02-13 16:56   ` kbuild test robot
2020-02-14 11:19     ` SeongJae Park
2020-02-15  4:07   ` Randy Dunlap
2020-02-15  6:52     ` SeongJae Park
2020-02-10 14:54 ` [PATCH v4 11/11] MAINTAINERS: Update for DAMON sjpark

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=20200210145134.27840-1-sjpark@amazon.com \
    --to=sjpark@amazon.com \
    --cc=acme@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=amit@kernel.org \
    --cc=brendan.d.gregg@gmail.com \
    --cc=brendanhiggins@google.com \
    --cc=cai@lca.pw \
    --cc=colin.king@canonical.com \
    --cc=corbet@lwn.net \
    --cc=dwmw@amazon.com \
    --cc=jolsa@redhat.com \
    --cc=kirill@shutemov.name \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mark.rutland@arm.com \
    --cc=mgorman@suse.de \
    --cc=minchan@kernel.org \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=rdunlap@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=sj38.park@gmail.com \
    --cc=sjpark@amazon.de \
    --cc=vdavydov.dev@gmail.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

Linux-mm Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-mm/0 linux-mm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-mm linux-mm/ https://lore.kernel.org/linux-mm \
		linux-mm@kvack.org
	public-inbox-index linux-mm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kvack.linux-mm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git