[PATCH] md: new sysfs interface for setting bits in the write-intent-bitmap

Add a new sysfs interface that allows the bitmap of an array to be dirtied. The interface is write-only, and is used as follows: echo "1000" > /sys/block/md2/md/bitmap (dirty the bit for chunk 1000 [offset 0] in the in-memory and on-disk bitmaps of array md2) echo "1000-2000" > /sys/block/md1/md/bitmap (dirty the bits for chunks 1000-2000 in md1's bitmap) This is useful, for example, in cluster environments where you may need to combine two disjoint bitmaps into one (following a server failure, after a secondary server has taken over the array). By combining the bitmaps on the two servers, a full resync can be avoided (This was discussed on the list back on March 18, 2005, "[PATCH 1/2] md bitmap bug fixes" thread). Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>

[PATCH] md: new sysfs interface for setting bits in the write-intent-bitmap
Add a new sysfs interface that allows the bitmap of an array to be dirtied. The interface is write-only, and is used as follows: echo "1000" > /sys/block/md2/md/bitmap (dirty the bit for chunk 1000 [offset 0] in the in-memory and on-disk bitmaps of array md2) echo "1000-2000" > /sys/block/md1/md/bitmap (dirty the bits for chunks 1000-2000 in md1's bitmap) This is useful, for example, in cluster environments where you may need to combine two disjoint bitmaps into one (following a server failure, after a secondary server has taken over the array). By combining the bitmaps on the two servers, a full resync can be avoided (This was discussed on the list back on March 18, 2005, "[PATCH 1/2] md bitmap bug fixes" thread). Signed-off-by: Neil Brown <neilb@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Paul Clements · Linus Torvalds
1 parent 76186dd8b7
Showing 4 changed files with 56 additions and 0 deletions Side-by-side Diff
Documentation/md.txt
drivers/md/bitmap.c
drivers/md/md.c
include/linux/raid/bitmap.h
@@ -410,6 +410,15 @@
       than sectors, this my be larger than the number of actual errors
       by a factor of the number of sectors in a page.
  
+   bitmap_set_bits
+      If the array has a write-intent bitmap, then writing to this
+      attribute can set bits in the bitmap, indicating that a resync
+      would need to check the corresponding blocks. Either individual
+      numbers or start-end pairs can be written.  Multiple numbers
+      can be separated by a space.
+      Note that the numbers are 'bit' numbers, not 'block' numbers.
+      They should be scaled by the bitmap_chunksize.
+
 Each active md device may also have attributes specific to the
 personality module that manages it.
 These are specific to the implementation of the module and could
@@ -613,6 +613,7 @@
 static inline struct page *filemap_get_page(struct bitmap *bitmap,
 					unsigned long chunk)
 {
+	if (file_page_index(chunk) >= bitmap->file_pages) return NULL;
 	return bitmap->filemap[file_page_index(chunk) - file_page_index(0)];
 }
  
@@ -739,6 +740,7 @@
 	}
  
 	page = filemap_get_page(bitmap, chunk);
+	if (!page) return;
 	bit = file_page_offset(chunk);
  
  	/* set the bit */
@@ -1320,6 +1322,18 @@
 	}
 	spin_unlock_irq(&bitmap->lock);
  
+}
+
+/* dirty the memory and file bits for bitmap chunks "s" to "e" */
+void bitmap_dirty_bits(struct bitmap *bitmap, unsigned long s, unsigned long e)
+{
+	unsigned long chunk;
+
+	for (chunk = s; chunk <= e; chunk++) {
+		sector_t sec = chunk << CHUNK_BLOCK_SHIFT(bitmap);
+		bitmap_set_memory_bits(bitmap, sec, 1);
+		bitmap_file_set_bit(bitmap, sec);
+	}
 }
  
 /*
@@ -2524,6 +2524,36 @@
 __ATTR(new_dev, S_IWUSR, null_show, new_dev_store);
  
 static ssize_t
+bitmap_store(mddev_t *mddev, const char *buf, size_t len)
+{
+	char *end;
+	unsigned long chunk, end_chunk;
+
+	if (!mddev->bitmap)
+		goto out;
+	/* buf should be <chunk> <chunk> ... or <chunk>-<chunk> ... (range) */
+	while (*buf) {
+		chunk = end_chunk = simple_strtoul(buf, &end, 0);
+		if (buf == end) break;
+		if (*end == '-') { /* range */
+			buf = end + 1;
+			end_chunk = simple_strtoul(buf, &end, 0);
+			if (buf == end) break;
+		}
+		if (*end && !isspace(*end)) break;
+		bitmap_dirty_bits(mddev->bitmap, chunk, end_chunk);
+		buf = end;
+		while (isspace(*buf)) buf++;
+	}
+	bitmap_unplug(mddev->bitmap); /* flush the bits to disk */
+out:
+	return len;
+}
+
+static struct md_sysfs_entry md_bitmap =
+__ATTR(bitmap_set_bits, S_IWUSR, null_show, bitmap_store);
+
+static ssize_t
 size_show(mddev_t *mddev, char *page)
 {
 	return sprintf(page, "%llu\n", (unsigned long long)mddev->size);
@@ -2843,6 +2873,7 @@
 	&md_sync_completed.attr,
 	&md_suspend_lo.attr,
 	&md_suspend_hi.attr,
+	&md_bitmap.attr,
 	NULL,
 };
 static struct attribute_group md_redundancy_group = {
@@ -265,6 +265,8 @@
 int  bitmap_setallbits(struct bitmap *bitmap);
 void bitmap_write_all(struct bitmap *bitmap);
  
+void bitmap_dirty_bits(struct bitmap *bitmap, unsigned long s, unsigned long e);
+
 /* these are exported */
 int bitmap_startwrite(struct bitmap *bitmap, sector_t offset,
 			unsigned long sectors, int behind);
...	...	@@ -410,6 +410,15 @@
410	410	than sectors, this my be larger than the number of actual errors
411	411	by a factor of the number of sectors in a page.
412	412
	413	+ bitmap_set_bits
	414	+ If the array has a write-intent bitmap, then writing to this
	415	+ attribute can set bits in the bitmap, indicating that a resync
	416	+ would need to check the corresponding blocks. Either individual
	417	+ numbers or start-end pairs can be written. Multiple numbers
	418	+ can be separated by a space.
	419	+ Note that the numbers are 'bit' numbers, not 'block' numbers.
	420	+ They should be scaled by the bitmap_chunksize.
	421	+
413	422	Each active md device may also have attributes specific to the
414	423	personality module that manages it.
415	424	These are specific to the implementation of the module and could
...	...	@@ -613,6 +613,7 @@
613	613	static inline struct page filemap_get_page(struct bitmap bitmap,
614	614	unsigned long chunk)
615	615	{
	616	+ if (file_page_index(chunk) >= bitmap->file_pages) return NULL;
616	617	return bitmap->filemap[file_page_index(chunk) - file_page_index(0)];
617	618	}
618	619
...	...	@@ -739,6 +740,7 @@
739	740	}
740	741
741	742	page = filemap_get_page(bitmap, chunk);
	743	+ if (!page) return;
742	744	bit = file_page_offset(chunk);
743	745
744	746	/* set the bit */
...	...	@@ -1320,6 +1322,18 @@
1320	1322	}
1321	1323	spin_unlock_irq(&bitmap->lock);
1322	1324
	1325	+}
	1326	+
	1327	+/* dirty the memory and file bits for bitmap chunks "s" to "e" */
	1328	+void bitmap_dirty_bits(struct bitmap *bitmap, unsigned long s, unsigned long e)
	1329	+{
	1330	+ unsigned long chunk;
	1331	+
	1332	+ for (chunk = s; chunk <= e; chunk++) {
	1333	+ sector_t sec = chunk << CHUNK_BLOCK_SHIFT(bitmap);
	1334	+ bitmap_set_memory_bits(bitmap, sec, 1);
	1335	+ bitmap_file_set_bit(bitmap, sec);
	1336	+ }
1323	1337	}
1324	1338
1325	1339	/*
...	...	@@ -2524,6 +2524,36 @@
2524	2524	__ATTR(new_dev, S_IWUSR, null_show, new_dev_store);
2525	2525
2526	2526	static ssize_t
	2527	+bitmap_store(mddev_t mddev, const char buf, size_t len)
	2528	+{
	2529	+ char *end;
	2530	+ unsigned long chunk, end_chunk;
	2531	+
	2532	+ if (!mddev->bitmap)
	2533	+ goto out;
	2534	+ /* buf should be <chunk> <chunk> ... or <chunk>-<chunk> ... (range) */
	2535	+ while (*buf) {
	2536	+ chunk = end_chunk = simple_strtoul(buf, &end, 0);
	2537	+ if (buf == end) break;
	2538	+ if (end == '-') { / range */
	2539	+ buf = end + 1;
	2540	+ end_chunk = simple_strtoul(buf, &end, 0);
	2541	+ if (buf == end) break;
	2542	+ }
	2543	+ if (end && !isspace(end)) break;
	2544	+ bitmap_dirty_bits(mddev->bitmap, chunk, end_chunk);
	2545	+ buf = end;
	2546	+ while (isspace(*buf)) buf++;
	2547	+ }
	2548	+ bitmap_unplug(mddev->bitmap); /* flush the bits to disk */
	2549	+out:
	2550	+ return len;
	2551	+}
	2552	+
	2553	+static struct md_sysfs_entry md_bitmap =
	2554	+__ATTR(bitmap_set_bits, S_IWUSR, null_show, bitmap_store);
	2555	+
	2556	+static ssize_t
2527	2557	size_show(mddev_t mddev, char page)
2528	2558	{
2529	2559	return sprintf(page, "%llu\n", (unsigned long long)mddev->size);
...	...	@@ -2843,6 +2873,7 @@
2843	2873	&md_sync_completed.attr,
2844	2874	&md_suspend_lo.attr,
2845	2875	&md_suspend_hi.attr,
	2876	+ &md_bitmap.attr,
2846	2877	NULL,
2847	2878	};
2848	2879	static struct attribute_group md_redundancy_group = {
...	...	@@ -265,6 +265,8 @@
265	265	int bitmap_setallbits(struct bitmap *bitmap);
266	266	void bitmap_write_all(struct bitmap *bitmap);
267	267
	268	+void bitmap_dirty_bits(struct bitmap *bitmap, unsigned long s, unsigned long e);
	269	+
268	270	/* these are exported */
269	271	int bitmap_startwrite(struct bitmap *bitmap, sector_t offset,
270	272	unsigned long sectors, int behind);