From: Chao Yu via Linux-f2fs-devel <linux-f2fs-devel@lists.sourceforge.net>
To: jaegeuk@kernel.org
Cc: Xiuhong Wang <xiuhong.wang@unisoc.com>,
Zhiguo Niu <zhiguo.niu@unisoc.com>,
linux-kernel@vger.kernel.org,
linux-f2fs-devel@lists.sourceforge.net
Subject: [f2fs-dev] [PATCH v2 2/2] f2fs: add a sysfs node to limit max read extent count per-inode
Date: Fri, 22 Nov 2024 14:50:05 +0800 [thread overview]
Message-ID: <20241122065005.3772987-2-chao@kernel.org> (raw)
In-Reply-To: <20241122065005.3772987-1-chao@kernel.org>
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>
---
v2:
- fix to add missing max_read_extent_count sysfs entry declaration
Documentation/ABI/testing/sysfs-fs-f2fs | 6 ++++++
fs/f2fs/extent_cache.c | 5 ++++-
fs/f2fs/f2fs.h | 4 ++++
fs/f2fs/sysfs.c | 10 ++++++++++
4 files changed, 24 insertions(+), 1 deletion(-)
diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
index 513296bb6f29..3e1630c70d8a 100644
--- 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 b7a6817b44b0..347b3b647834 100644
--- 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 b65b023a588a..6f2cbf4c5740 100644
--- 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 bdbf24db667b..6b99dc49f776 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -787,6 +787,13 @@ static ssize_t __sbi_store(struct f2fs_attr *a,
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);
--
2.40.1
_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel
WARNING: multiple messages have this Message-ID (diff)
From: Chao Yu <chao@kernel.org>
To: jaegeuk@kernel.org
Cc: linux-f2fs-devel@lists.sourceforge.net,
linux-kernel@vger.kernel.org, Chao Yu <chao@kernel.org>,
Xiuhong Wang <xiuhong.wang@unisoc.com>,
Zhiguo Niu <zhiguo.niu@unisoc.com>
Subject: [PATCH v2 2/2] f2fs: add a sysfs node to limit max read extent count per-inode
Date: Fri, 22 Nov 2024 14:50:05 +0800 [thread overview]
Message-ID: <20241122065005.3772987-2-chao@kernel.org> (raw)
In-Reply-To: <20241122065005.3772987-1-chao@kernel.org>
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>
---
v2:
- fix to add missing max_read_extent_count sysfs entry declaration
Documentation/ABI/testing/sysfs-fs-f2fs | 6 ++++++
fs/f2fs/extent_cache.c | 5 ++++-
fs/f2fs/f2fs.h | 4 ++++
fs/f2fs/sysfs.c | 10 ++++++++++
4 files changed, 24 insertions(+), 1 deletion(-)
diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
index 513296bb6f29..3e1630c70d8a 100644
--- 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 b7a6817b44b0..347b3b647834 100644
--- 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 b65b023a588a..6f2cbf4c5740 100644
--- 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 bdbf24db667b..6b99dc49f776 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -787,6 +787,13 @@ static ssize_t __sbi_store(struct f2fs_attr *a,
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);
--
2.40.1
next prev parent reply other threads:[~2024-11-22 6:50 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-11-22 6:50 [f2fs-dev] [PATCH v2 1/2] f2fs: fix to shrink read extent node in batches Chao Yu via Linux-f2fs-devel
2024-11-22 6:50 ` Chao Yu
2024-11-22 6:50 ` Chao Yu via Linux-f2fs-devel [this message]
2024-11-22 6:50 ` [PATCH v2 2/2] f2fs: add a sysfs node to limit max read extent count per-inode Chao Yu
2024-11-23 15:50 ` [f2fs-dev] [PATCH v2 1/2] f2fs: fix to shrink read extent node in batches patchwork-bot+f2fs--- via Linux-f2fs-devel
2024-11-23 15:50 ` patchwork-bot+f2fs
2024-11-25 3:11 ` [f2fs-dev] 答复: " 王秀红 (Xiuhong Wang)
2024-11-25 3:11 ` 王秀红 (Xiuhong Wang)
2024-11-25 11:13 ` [f2fs-dev] " Chao Yu via Linux-f2fs-devel
2024-11-25 11:13 ` Chao Yu
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=20241122065005.3772987-2-chao@kernel.org \
--to=linux-f2fs-devel@lists.sourceforge.net \
--cc=chao@kernel.org \
--cc=jaegeuk@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=xiuhong.wang@unisoc.com \
--cc=zhiguo.niu@unisoc.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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.