Linux-Doc Archive on lore.kernel.org
 help / color / Atom feed
From: SeongJae Park <sjpark@amazon.com>
To: <akpm@linux-foundation.org>
Cc: SeongJae Park <sjpark@amazon.de>, <Jonathan.Cameron@Huawei.com>,
	<aarcange@redhat.com>, <acme@kernel.org>,
	<alexander.shishkin@linux.intel.com>, <amit@kernel.org>,
	<benh@kernel.crashing.org>, <brendan.d.gregg@gmail.com>,
	<brendanhiggins@google.com>, <cai@lca.pw>,
	<colin.king@canonical.com>, <corbet@lwn.net>, <david@redhat.com>,
	<dwmw@amazon.com>, <foersleo@amazon.de>, <irogers@google.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>, <riel@surriel.com>,
	<rientjes@google.com>, <rostedt@goodmis.org>, <rppt@kernel.org>,
	<sblbir@amazon.com>, <shakeelb@google.com>, <shuah@kernel.org>,
	<sj38.park@gmail.com>, <snu@amazon.de>, <vbabka@suse.cz>,
	<vdavydov.dev@gmail.com>, <yang.shi@linux.alibaba.com>,
	<ying.huang@intel.com>, <linux-damon@amazon.com>,
	<linux-mm@kvack.org>, <linux-doc@vger.kernel.org>,
	<linux-kernel@vger.kernel.org>
Subject: [PATCH v18 07/14] mm/damon: Implement access pattern recording
Date: Mon, 13 Jul 2020 10:41:37 +0200
Message-ID: <20200713084144.4430-8-sjpark@amazon.com> (raw)
In-Reply-To: <20200713084144.4430-1-sjpark@amazon.com>

From: SeongJae Park <sjpark@amazon.de>

This commit implements the recording feature of DAMON.  If this feature
is enabled, DAMON writes the monitored access patterns in its binary
format into a file which specified by the user.  This is already able to
be implemented by each user using the callbacks.  However, as the
recording is expected to be widely used, this commit implements the
feature in the DAMON, for more convenience.

Signed-off-by: SeongJae Park <sjpark@amazon.de>
Reviewed-by: Leonard Foerster <foersleo@amazon.de>
---
 include/linux/damon.h |  15 +++++
 mm/damon.c            | 141 +++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 153 insertions(+), 3 deletions(-)

diff --git a/include/linux/damon.h b/include/linux/damon.h
index 310d36d123b3..b0e7e31a22b3 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -72,6 +72,14 @@ struct damon_task {
  * in case of virtual memory monitoring) and applies the changes for each
  * @regions_update_interval.  All time intervals are in micro-seconds.
  *
+ * @rbuf: In-memory buffer for monitoring result recording.
+ * @rbuf_len: The length of @rbuf.
+ * @rbuf_offset: The offset for next write to @rbuf.
+ * @rfile_path: Record file path.
+ *
+ * If @rbuf, @rbuf_len, and @rfile_path are set, the monitored results are
+ * automatically stored in @rfile_path file.
+ *
  * @kdamond:		Kernel thread who does the monitoring.
  * @kdamond_stop:	Notifies whether kdamond should stop.
  * @kdamond_lock:	Mutex for the synchronizations with @kdamond.
@@ -129,6 +137,11 @@ struct damon_ctx {
 	struct timespec64 last_aggregation;
 	struct timespec64 last_regions_update;
 
+	unsigned char *rbuf;
+	unsigned int rbuf_len;
+	unsigned int rbuf_offset;
+	char *rfile_path;
+
 	struct task_struct *kdamond;
 	bool kdamond_stop;
 	struct mutex kdamond_lock;
@@ -154,6 +167,8 @@ int damon_set_pids(struct damon_ctx *ctx, int *pids, ssize_t nr_pids);
 int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int,
 		unsigned long aggr_int, unsigned long regions_update_int,
 		unsigned long min_nr_reg, unsigned long max_nr_reg);
+int damon_set_recording(struct damon_ctx *ctx,
+				unsigned int rbuf_len, char *rfile_path);
 int damon_start(struct damon_ctx *ctx);
 int damon_stop(struct damon_ctx *ctx);
 
diff --git a/mm/damon.c b/mm/damon.c
index 386780739007..55ecfab64220 100644
--- a/mm/damon.c
+++ b/mm/damon.c
@@ -58,6 +58,10 @@
 #define damon_for_each_task_safe(t, next, ctx) \
 	list_for_each_entry_safe(t, next, &(ctx)->tasks_list, list)
 
+#define MIN_RECORD_BUFFER_LEN	1024
+#define MAX_RECORD_BUFFER_LEN	(4 * 1024 * 1024)
+#define MAX_RFILE_PATH_LEN	256
+
 /* Get a random number in [l, r) */
 #define damon_rand(l, r) (l + prandom_u32() % (r - l))
 
@@ -707,16 +711,88 @@ static bool kdamond_aggregate_interval_passed(struct damon_ctx *ctx)
 }
 
 /*
- * Reset the aggregated monitoring results
+ * Flush the content in the result buffer to the result file
+ */
+static void damon_flush_rbuffer(struct damon_ctx *ctx)
+{
+	ssize_t sz;
+	loff_t pos = 0;
+	struct file *rfile;
+
+	if (!ctx->rbuf_offset)
+		return;
+
+	rfile = filp_open(ctx->rfile_path, O_CREAT | O_RDWR | O_APPEND, 0644);
+	if (IS_ERR(rfile)) {
+		pr_err("Cannot open the result file %s\n",
+				ctx->rfile_path);
+		return;
+	}
+
+	while (ctx->rbuf_offset) {
+		sz = kernel_write(rfile, ctx->rbuf, ctx->rbuf_offset, &pos);
+		if (sz < 0)
+			break;
+		ctx->rbuf_offset -= sz;
+	}
+	filp_close(rfile, NULL);
+}
+
+/*
+ * Write a data into the result buffer
+ */
+static void damon_write_rbuf(struct damon_ctx *ctx, void *data, ssize_t size)
+{
+	if (!ctx->rbuf_len || !ctx->rbuf || !ctx->rfile_path)
+		return;
+	if (ctx->rbuf_offset + size > ctx->rbuf_len)
+		damon_flush_rbuffer(ctx);
+	if (ctx->rbuf_offset + size > ctx->rbuf_len) {
+		pr_warn("%s: flush failed, or wrong size given(%u, %zu)\n",
+				__func__, ctx->rbuf_offset, size);
+		return;
+	}
+
+	memcpy(&ctx->rbuf[ctx->rbuf_offset], data, size);
+	ctx->rbuf_offset += size;
+}
+
+/*
+ * Flush the aggregated monitoring results to the result buffer
+ *
+ * Stores current tracking results to the result buffer and reset 'nr_accesses'
+ * of each region.  The format for the result buffer is as below:
+ *
+ *   <time> <number of tasks> <array of task infos>
+ *
+ *   task info: <pid> <number of regions> <array of region infos>
+ *   region info: <start address> <end address> <nr_accesses>
  */
 static void kdamond_reset_aggregated(struct damon_ctx *c)
 {
 	struct damon_task *t;
-	struct damon_region *r;
+	struct timespec64 now;
+	unsigned int nr;
+
+	ktime_get_coarse_ts64(&now);
+
+	damon_write_rbuf(c, &now, sizeof(now));
+	nr = nr_damon_tasks(c);
+	damon_write_rbuf(c, &nr, sizeof(nr));
 
 	damon_for_each_task(t, c) {
-		damon_for_each_region(r, t)
+		struct damon_region *r;
+
+		damon_write_rbuf(c, &t->pid, sizeof(t->pid));
+		nr = nr_damon_regions(t);
+		damon_write_rbuf(c, &nr, sizeof(nr));
+		damon_for_each_region(r, t) {
+			damon_write_rbuf(c, &r->ar.start, sizeof(r->ar.start));
+			damon_write_rbuf(c, &r->ar.end, sizeof(r->ar.end));
+			damon_write_rbuf(c, &r->nr_accesses,
+					sizeof(r->nr_accesses));
 			r->nr_accesses = 0;
+		}
 	}
 }
 
@@ -905,6 +981,14 @@ static bool kdamond_need_stop(struct damon_ctx *ctx)
 	return true;
 }
 
+static void kdamond_write_record_header(struct damon_ctx *ctx)
+{
+	int recfmt_ver = 1;
+
+	damon_write_rbuf(ctx, "damon_recfmt_ver", 16);
+	damon_write_rbuf(ctx, &recfmt_ver, sizeof(recfmt_ver));
+}
+
 /*
  * The monitoring daemon that runs as a kernel thread
  */
@@ -921,6 +1005,8 @@ static int kdamond_fn(void *data)
 		ctx->init_target_regions(ctx);
 	sz_limit = damon_region_sz_limit(ctx);
 
+	kdamond_write_record_header(ctx);
+
 	while (!kdamond_need_stop(ctx)) {
 		if (ctx->prepare_access_checks)
 			ctx->prepare_access_checks(ctx);
@@ -947,6 +1033,7 @@ static int kdamond_fn(void *data)
 			sz_limit = damon_region_sz_limit(ctx);
 		}
 	}
+	damon_flush_rbuffer(ctx);
 	damon_for_each_task(t, ctx) {
 		damon_for_each_region_safe(r, next, t)
 			damon_destroy_region(r);
@@ -1051,6 +1138,54 @@ int damon_set_pids(struct damon_ctx *ctx, int *pids, ssize_t nr_pids)
 	return 0;
 }
 
+/**
+ * damon_set_recording() - Set attributes for the recording.
+ * @ctx:	target kdamond context
+ * @rbuf_len:	length of the result buffer
+ * @rfile_path:	path to the monitor result files
+ *
+ * Setting 'rbuf_len' 0 disables recording.
+ *
+ * This function should not be called while the kdamond is running.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int damon_set_recording(struct damon_ctx *ctx,
+			unsigned int rbuf_len, char *rfile_path)
+{
+	size_t rfile_path_len;
+
+	if (rbuf_len && (rbuf_len > MAX_RECORD_BUFFER_LEN ||
+			rbuf_len < MIN_RECORD_BUFFER_LEN)) {
+		pr_err("result buffer size (%u) is out of [%d,%d]\n",
+				rbuf_len, MIN_RECORD_BUFFER_LEN,
+				MAX_RECORD_BUFFER_LEN);
+		return -EINVAL;
+	}
+	rfile_path_len = strnlen(rfile_path, MAX_RFILE_PATH_LEN);
+	if (rfile_path_len >= MAX_RFILE_PATH_LEN) {
+		pr_err("too long (>%d) result file path %s\n",
+				MAX_RFILE_PATH_LEN, rfile_path);
+		return -EINVAL;
+	}
+	ctx->rbuf_len = rbuf_len;
+	kfree(ctx->rbuf);
+	ctx->rbuf = NULL;
+	kfree(ctx->rfile_path);
+	ctx->rfile_path = NULL;
+
+	if (rbuf_len) {
+		ctx->rbuf = kvmalloc(rbuf_len, GFP_KERNEL);
+		if (!ctx->rbuf)
+			return -ENOMEM;
+	}
+	ctx->rfile_path = kmalloc(rfile_path_len + 1, GFP_KERNEL);
+	if (!ctx->rfile_path)
+		return -ENOMEM;
+	strncpy(ctx->rfile_path, rfile_path, rfile_path_len + 1);
+	return 0;
+}
+
 /**
  * damon_set_attrs() - Set attributes for the monitoring.
  * @ctx:		monitoring context
-- 
2.17.1


  parent reply index

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-13  8:41 [PATCH v18 00/14] Introduce Data Access MONitor (DAMON) SeongJae Park
2020-07-13  8:41 ` [PATCH v18 01/14] mm/page_ext: Export lookup_page_ext() to GPL modules SeongJae Park
2020-07-13 12:08   ` Mike Rapoport
2020-07-13 12:21     ` SeongJae Park
2020-07-13 17:19       ` Mike Rapoport
2020-07-13 17:38         ` SeongJae Park
2020-07-17  9:59           ` SeongJae Park
2020-07-13  8:41 ` [PATCH v18 02/14] mm: Introduce Data Access MONitor (DAMON) SeongJae Park
2020-07-18  2:47   ` Shakeel Butt
2020-07-18 13:31     ` SeongJae Park
2020-07-29 15:31       ` Shakeel Butt
2020-07-29 17:29         ` SeongJae Park
2020-07-13  8:41 ` [PATCH v18 03/14] mm/damon: Implement region based sampling SeongJae Park
2020-07-13  8:41 ` [PATCH v18 04/14] mm/damon: Adaptively adjust regions SeongJae Park
2020-07-13  8:41 ` [PATCH v18 05/14] mm/damon: Track dynamic monitoring target regions update SeongJae Park
2020-07-13  8:41 ` [PATCH v18 06/14] mm/damon: Implement callbacks for the virtual memory address spaces SeongJae Park
2020-07-17  0:46   ` Shakeel Butt
2020-07-17  6:53     ` SeongJae Park
2020-07-17 15:17       ` Shakeel Butt
2020-07-17 16:24         ` SeongJae Park
2020-07-18  2:23           ` Shakeel Butt
2020-07-18  2:51             ` SeongJae Park
2020-07-27  7:34   ` Greg Thelen
2020-07-27  9:02     ` SeongJae Park
2020-07-28 17:42       ` Shakeel Butt
2020-07-29  6:20         ` SeongJae Park
2020-07-13  8:41 ` SeongJae Park [this message]
2020-07-13  8:41 ` [PATCH v18 08/14] mm/damon: Add a tracepoint SeongJae Park
2020-07-13  8:41 ` [PATCH v18 09/14] mm/damon: Implement a debugfs interface SeongJae Park
2020-07-22 10:36   ` SeongJae Park
2020-07-13  8:41 ` [PATCH v18 10/14] tools: Introduce a minimal user-space tool for DAMON SeongJae Park
2020-07-13  8:41 ` [PATCH v18 11/14] Documentation: Add documents " SeongJae Park
2020-07-27  7:19   ` Greg Thelen
2020-07-27  7:38     ` SeongJae Park
2020-07-13  8:41 ` [PATCH v18 12/14] mm/damon: Add kunit tests SeongJae Park
2020-07-13  8:41 ` [PATCH v18 13/14] mm/damon: Add user space selftests SeongJae Park
2020-07-13  8:41 ` [PATCH v18 14/14] MAINTAINERS: Update for DAMON SeongJae Park

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=20200713084144.4430-8-sjpark@amazon.com \
    --to=sjpark@amazon.com \
    --cc=Jonathan.Cameron@Huawei.com \
    --cc=aarcange@redhat.com \
    --cc=acme@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=amit@kernel.org \
    --cc=benh@kernel.crashing.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=david@redhat.com \
    --cc=dwmw@amazon.com \
    --cc=foersleo@amazon.de \
    --cc=irogers@google.com \
    --cc=jolsa@redhat.com \
    --cc=kirill@shutemov.name \
    --cc=linux-damon@amazon.com \
    --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=riel@surriel.com \
    --cc=rientjes@google.com \
    --cc=rostedt@goodmis.org \
    --cc=rppt@kernel.org \
    --cc=sblbir@amazon.com \
    --cc=shakeelb@google.com \
    --cc=shuah@kernel.org \
    --cc=sj38.park@gmail.com \
    --cc=sjpark@amazon.de \
    --cc=snu@amazon.de \
    --cc=vbabka@suse.cz \
    --cc=vdavydov.dev@gmail.com \
    --cc=yang.shi@linux.alibaba.com \
    --cc=ying.huang@intel.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-Doc Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-doc/0 linux-doc/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-doc linux-doc/ https://lore.kernel.org/linux-doc \
		linux-doc@vger.kernel.org
	public-inbox-index linux-doc

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-doc


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