提交 36a53cf3 编写于 作者: C Calvin Owens 提交者: Zheng Zengkai

brd: expose number of allocated pages in debugfs

mainline inclusion
from mainline-v5.13-rc1
commit f4be591f
category: feature
feature: brd
bugzilla: https://gitee.com/openeuler/kernel/issues/I4PMV3?from=project-issue

----------------------------------------------------------------------------

While the maximum size of each ramdisk is defined either as a module
parameter, or compile time default, it's impossible to know how many pages
have currently been allocated by each ram%d device, since they're
allocated when used and never freed.

This patch creates a new directory at this location:

/sys/kernel/debug/ramdisk_pages/

which will contain a file named "ram%d" for each instantiated ramdisk on
the system. The file is read-only, and read() will output the number of
pages currently held by that ramdisk.

We lose track how much memory a ramdisk is using as pages once used are
simply recycled but never freed.

In instances where we exhaust the size of the ramdisk with a file that
exceeds it, encounter ENOSPC and delete the file for mitigation; df would
show decrease in used and increase in available blocks but the since we
have touched all pages, the memory footprint of the ramdisk does not
reflect the blocks used/available count

...
[root@localhost ~]# mkfs.ext2 /dev/ram15
mke2fs 1.45.6 (20-Mar-2020)
Creating filesystem with 4096 1k blocks and 1024 inodes
[root@localhost ~]# mount /dev/ram15 /mnt/ram15/

[root@localhost ~]# cat
/sys/kernel/debug/ramdisk_pages/ram15
58
[root@kerneltest008.06.prn3 ~]# df /dev/ram15
Filesystem     1K-blocks  Used Available Use% Mounted on
/dev/ram15          3963    31      3728   1% /mnt/ram15
[root@kerneltest008.06.prn3 ~]# dd if=/dev/urandom of=/mnt/ram15/test2
bs=1M count=5
dd: error writing '/mnt/ram15/test2': No space left on device
4+0 records in
3+0 records out
4005888 bytes (4.0 MB, 3.8 MiB) copied, 0.0446614 s, 89.7 MB/s
[root@kerneltest008.06.prn3 ~]# df /mnt/ram15/
Filesystem     1K-blocks  Used Available Use% Mounted on
/dev/ram15          3963  3960         0 100% /mnt/ram15
[root@kerneltest008.06.prn3 ~]# cat
/sys/kernel/debug/ramdisk_pages/ram15
1024
[root@kerneltest008.06.prn3 ~]# rm /mnt/ram15/test2
rm: remove regular file '/mnt/ram15/test2'? y
[root@kerneltest008.06.prn3 /var]# df /dev/ram15
Filesystem     1K-blocks  Used Available Use% Mounted on
/dev/ram15          3963    31      3728   1% /mnt/ram15

# Acutal memory footprint
[root@kerneltest008.06.prn3 /var]# cat
/sys/kernel/debug/ramdisk_pages/ram15
1024
...

This debugfs counter will always reveal the accurate number of
permanently allocated pages to the ramdisk.
Signed-off-by: NCalvin Owens <calvinowens@fb.com>
[cleaned up the !CONFIG_DEBUG_FS case and API changes for HEAD]
Signed-off-by: NKyle McMartin <jkkm@fb.com>
[rebased]
Signed-off-by: NSaravanan D <saravanand@fb.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Conflicts:
	/drivers/block/brd.c
Signed-off-by: NWu Guanghao <wuguanghao3@huawei.com>
Reviewed-by: NJason Yan <yanaijie@huawei.com>
Signed-off-by: NZheng Zengkai <zhengzengkai@huawei.com>
上级 6385225f
...@@ -22,6 +22,7 @@ ...@@ -22,6 +22,7 @@
#include <linux/fs.h> #include <linux/fs.h>
#include <linux/slab.h> #include <linux/slab.h>
#include <linux/backing-dev.h> #include <linux/backing-dev.h>
#include <linux/debugfs.h>
#include <linux/uaccess.h> #include <linux/uaccess.h>
...@@ -48,6 +49,7 @@ struct brd_device { ...@@ -48,6 +49,7 @@ struct brd_device {
*/ */
spinlock_t brd_lock; spinlock_t brd_lock;
struct radix_tree_root brd_pages; struct radix_tree_root brd_pages;
u64 brd_nr_pages;
}; };
/* /*
...@@ -116,6 +118,8 @@ static struct page *brd_insert_page(struct brd_device *brd, sector_t sector) ...@@ -116,6 +118,8 @@ static struct page *brd_insert_page(struct brd_device *brd, sector_t sector)
page = radix_tree_lookup(&brd->brd_pages, idx); page = radix_tree_lookup(&brd->brd_pages, idx);
BUG_ON(!page); BUG_ON(!page);
BUG_ON(page->index != idx); BUG_ON(page->index != idx);
} else {
brd->brd_nr_pages++;
} }
spin_unlock(&brd->brd_lock); spin_unlock(&brd->brd_lock);
...@@ -369,11 +373,13 @@ __setup("ramdisk_size=", ramdisk_size); ...@@ -369,11 +373,13 @@ __setup("ramdisk_size=", ramdisk_size);
*/ */
static LIST_HEAD(brd_devices); static LIST_HEAD(brd_devices);
static DEFINE_MUTEX(brd_devices_mutex); static DEFINE_MUTEX(brd_devices_mutex);
static struct dentry *brd_debugfs_dir;
static struct brd_device *brd_alloc(int i) static struct brd_device *brd_alloc(int i)
{ {
struct brd_device *brd; struct brd_device *brd;
struct gendisk *disk; struct gendisk *disk;
char buf[DISK_NAME_LEN];
brd = kzalloc(sizeof(*brd), GFP_KERNEL); brd = kzalloc(sizeof(*brd), GFP_KERNEL);
if (!brd) if (!brd)
...@@ -386,6 +392,11 @@ static struct brd_device *brd_alloc(int i) ...@@ -386,6 +392,11 @@ static struct brd_device *brd_alloc(int i)
if (!brd->brd_queue) if (!brd->brd_queue)
goto out_free_dev; goto out_free_dev;
snprintf(buf, DISK_NAME_LEN, "ram%d", i);
if (!IS_ERR_OR_NULL(brd_debugfs_dir))
debugfs_create_u64(buf, 0444, brd_debugfs_dir,
&brd->brd_nr_pages);
/* This is so fdisk will align partitions on 4k, because of /* This is so fdisk will align partitions on 4k, because of
* direct_access API needing 4k alignment, returning a PFN * direct_access API needing 4k alignment, returning a PFN
* (This is only a problem on very small devices <= 4M, * (This is only a problem on very small devices <= 4M,
...@@ -401,7 +412,7 @@ static struct brd_device *brd_alloc(int i) ...@@ -401,7 +412,7 @@ static struct brd_device *brd_alloc(int i)
disk->fops = &brd_fops; disk->fops = &brd_fops;
disk->private_data = brd; disk->private_data = brd;
disk->flags = GENHD_FL_EXT_DEVT; disk->flags = GENHD_FL_EXT_DEVT;
sprintf(disk->disk_name, "ram%d", i); strlcpy(disk->disk_name, buf, DISK_NAME_LEN);
set_capacity(disk, rd_size * 2); set_capacity(disk, rd_size * 2);
/* Tell the block layer that this is not a rotational device */ /* Tell the block layer that this is not a rotational device */
...@@ -515,6 +526,8 @@ static int __init brd_init(void) ...@@ -515,6 +526,8 @@ static int __init brd_init(void)
brd_check_and_reset_par(); brd_check_and_reset_par();
brd_debugfs_dir = debugfs_create_dir("ramdisk_pages", NULL);
for (i = 0; i < rd_nr; i++) { for (i = 0; i < rd_nr; i++) {
brd = brd_alloc(i); brd = brd_alloc(i);
if (!brd) if (!brd)
...@@ -540,6 +553,8 @@ static int __init brd_init(void) ...@@ -540,6 +553,8 @@ static int __init brd_init(void)
return 0; return 0;
out_free: out_free:
debugfs_remove_recursive(brd_debugfs_dir);
list_for_each_entry_safe(brd, next, &brd_devices, brd_list) { list_for_each_entry_safe(brd, next, &brd_devices, brd_list) {
list_del(&brd->brd_list); list_del(&brd->brd_list);
brd_free(brd); brd_free(brd);
...@@ -554,6 +569,8 @@ static void __exit brd_exit(void) ...@@ -554,6 +569,8 @@ static void __exit brd_exit(void)
{ {
struct brd_device *brd, *next; struct brd_device *brd, *next;
debugfs_remove_recursive(brd_debugfs_dir);
list_for_each_entry_safe(brd, next, &brd_devices, brd_list) list_for_each_entry_safe(brd, next, &brd_devices, brd_list)
brd_del_one(brd); brd_del_one(brd);
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册