f2fs: add a sysfs node to limit max read extent count per-inode

Quoted:
"at this time, there are still 1086911 extent nodes in this zombie
extent tree that need to be cleaned up.

crash_arm64_sprd_v8.0.3++> extent_tree.node_cnt ffffff80896cc500
  node_cnt = {
    counter = 1086911
  },
"

As reported by Xiuhong, there will be a huge number of extent nodes
in extent tree, it may potentially cause:
- slab memory fragments
- extreme long time shrink on extent tree
- low mapping efficiency

Let's add a sysfs node to limit max read extent count for each inode,
by default, value of this threshold is 10240, it can be updated
according to user's requirement.

Reported-by: Xiuhong Wang <xiuhong.wang@unisoc.com>
Closes: https://lore.kernel.org/linux-f2fs-devel/20241112110627.1314632-1-xiuhong.wang@unisoc.com/
Signed-off-by: Xiuhong Wang <xiuhong.wang@unisoc.com>
Signed-off-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
index 513296bb6f297fe0800e40643a6a76d85b80d4a9..3e1630c70d8ae70456de35a627afde1211c8882c 100644 (file)
--- a/Documentation/ABI/testing/sysfs-fs-f2fs
+++ b/Documentation/ABI/testing/sysfs-fs-f2fs
@@ -822,3 +822,9 @@ Description:        It controls the valid block ratio threshold not to trigger excessiv
                for zoned deivces. The initial value of it is 95(%). F2FS will stop the
                background GC thread from intiating GC for sections having valid blocks
                exceeding the ratio.
+
+What:          /sys/fs/f2fs/<disk>/max_read_extent_count
+Date:          November 2024
+Contact:       "Chao Yu" <chao@kernel.org>
+Description:   It controls max read extent count for per-inode, the value of threshold
+               is 10240 by default.

diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index b7a6817b44b0021a04dfb7dd9b305ba11cc06697..347b3b64783475acb7cc35bb5ab7f6067b11280a 100644 (file)
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -717,7 +717,9 @@ static void __update_extent_tree_range(struct inode *inode,
                }
 
                if (end < org_end && (type != EX_READ ||
-                               org_end - end >= F2FS_MIN_EXTENT_LEN)) {
+                       (org_end - end >= F2FS_MIN_EXTENT_LEN &&
+                       atomic_read(&et->node_cnt) <
+                                       sbi->max_read_extent_count))) {
                        if (parts) {
                                __set_extent_info(&ei,
                                        end, org_end - end,
@@ -1212,6 +1214,7 @@ void f2fs_init_extent_cache_info(struct f2fs_sb_info *sbi)
        sbi->hot_data_age_threshold = DEF_HOT_DATA_AGE_THRESHOLD;
        sbi->warm_data_age_threshold = DEF_WARM_DATA_AGE_THRESHOLD;
        sbi->last_age_weight = LAST_AGE_WEIGHT;
+       sbi->max_read_extent_count = DEF_MAX_READ_EXTENT_COUNT;
 }
 
 int __init f2fs_create_extent_cache(void)

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index b65b023a588a0e1d52bebabfb31972dd4aebea31..6f2cbf4c57402bd40497ad5c1cefd8ecff35d678 100644 (file)
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -635,6 +635,9 @@ enum {
 #define DEF_HOT_DATA_AGE_THRESHOLD     262144
 #define DEF_WARM_DATA_AGE_THRESHOLD    2621440
 
+/* default max read extent count per inode */
+#define DEF_MAX_READ_EXTENT_COUNT      10240
+
 /* extent cache type */
 enum extent_type {
        EX_READ,
@@ -1619,6 +1622,7 @@ struct f2fs_sb_info {
        /* for extent tree cache */
        struct extent_tree_info extent_tree[NR_EXTENT_CACHES];
        atomic64_t allocated_data_blocks;       /* for block age extent_cache */
+       unsigned int max_read_extent_count;     /* max read extent count per inode */
 
        /* The threshold used for hot and warm data seperation*/
        unsigned int hot_data_age_threshold;

diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index bdbf24db667bb3cd3eca44d49ccdf05f9e701b96..6b99dc49f7761a6b8ec2ecfb05d607e9d436cd45 100644 (file)
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -787,6 +787,13 @@ out:
                return count;
        }
 
+       if (!strcmp(a->attr.name, "max_read_extent_count")) {
+               if (t > UINT_MAX)
+                       return -EINVAL;
+               *ui = (unsigned int)t;
+               return count;
+       }
+
        if (!strcmp(a->attr.name, "ipu_policy")) {
                if (t >= BIT(F2FS_IPU_MAX))
                        return -EINVAL;
@@ -1052,6 +1059,8 @@ F2FS_SBI_GENERAL_RW_ATTR(revoked_atomic_block);
 F2FS_SBI_GENERAL_RW_ATTR(hot_data_age_threshold);
 F2FS_SBI_GENERAL_RW_ATTR(warm_data_age_threshold);
 F2FS_SBI_GENERAL_RW_ATTR(last_age_weight);
+/* read extent cache */
+F2FS_SBI_GENERAL_RW_ATTR(max_read_extent_count);
 #ifdef CONFIG_BLK_DEV_ZONED
 F2FS_SBI_GENERAL_RO_ATTR(unusable_blocks_per_sec);
 F2FS_SBI_GENERAL_RW_ATTR(blkzone_alloc_policy);
@@ -1242,6 +1251,7 @@ static struct attribute *f2fs_attrs[] = {
        ATTR_LIST(hot_data_age_threshold),
        ATTR_LIST(warm_data_age_threshold),
        ATTR_LIST(last_age_weight),
+       ATTR_LIST(max_read_extent_count),
        NULL,
 };
 ATTRIBUTE_GROUPS(f2fs);