| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20220127214102.2040254-1-jaegeuk@kernel.org>
Date: Thu, 27 Jan 2022 13:41:02 -0800
From: Jaegeuk Kim <jaegeuk@...nel.org>
To: linux-kernel@...r.kernel.org,
linux-f2fs-devel@...ts.sourceforge.net
Cc: Jaegeuk Kim <jaegeuk@...nel.org>
Subject: [PATCH] f2fs: add a way to limit roll forward recovery time
This adds a sysfs entry to call checkpoint during fsync() in order to avoid
long elapsed time to run roll-forward recovery when booting the device.
Signed-off-by: Jaegeuk Kim <jaegeuk@...nel.org>
---
Documentation/ABI/testing/sysfs-fs-f2fs | 6 ++++++
fs/f2fs/checkpoint.c | 1 +
fs/f2fs/f2fs.h | 3 +++
fs/f2fs/node.c | 2 ++
fs/f2fs/node.h | 3 +++
fs/f2fs/recovery.c | 3 +++
fs/f2fs/sysfs.c | 2 ++
7 files changed, 20 insertions(+)
diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
index 87d3884c90ea..ce8103f522cb 100644
--- a/Documentation/ABI/testing/sysfs-fs-f2fs
+++ b/Documentation/ABI/testing/sysfs-fs-f2fs
@@ -567,3 +567,9 @@ Contact: "Daeho Jeong" <daehojeong@...gle.com>
Description: You can set the trial count limit for GC urgent high mode with this value.
If GC thread gets to the limit, the mode will turn back to GC normal mode.
By default, the value is zero, which means there is no limit like before.
+
+What: /sys/fs/f2fs/<disk>/max_roll_forward_node_blocks
+Date: January 2022
+Contact: "Jaegeuk Kim" <jaegeuk@...nel.org>
+Description: Controls max # of node block writes to be used for roll forward
+ recovery. This can limit the roll forward recovery time.
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index deeda95688f0..57a2d9164bee 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -1543,6 +1543,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
/* update user_block_counts */
sbi->last_valid_block_count = sbi->total_valid_block_count;
percpu_counter_set(&sbi->alloc_valid_block_count, 0);
+ percpu_counter_set(&sbi->rf_node_block_count, 0);
/* Here, we have one bio having CP pack except cp pack 2 page */
f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 63c90416364b..6ddb98ff0b7c 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -913,6 +913,7 @@ struct f2fs_nm_info {
nid_t max_nid; /* maximum possible node ids */
nid_t available_nids; /* # of available node ids */
nid_t next_scan_nid; /* the next nid to be scanned */
+ nid_t max_rf_node_blocks; /* max # of nodes for recovery */
unsigned int ram_thresh; /* control the memory footprint */
unsigned int ra_nid_pages; /* # of nid pages to be readaheaded */
unsigned int dirty_nats_ratio; /* control dirty nats ratio threshold */
@@ -1684,6 +1685,8 @@ struct f2fs_sb_info {
atomic_t nr_pages[NR_COUNT_TYPE];
/* # of allocated blocks */
struct percpu_counter alloc_valid_block_count;
+ /* # of node block writes as roll forward recovery */
+ struct percpu_counter rf_node_block_count;
/* writeback control */
atomic_t wb_sync_req[META]; /* count # of WB_SYNC threads */
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 93512f8859d5..0d9883457579 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1782,6 +1782,7 @@ int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
if (!atomic || page == last_page) {
set_fsync_mark(page, 1);
+ percpu_counter_inc(&sbi->rf_node_block_count);
if (IS_INODE(page)) {
if (is_inode_flag_set(inode,
FI_DIRTY_INODE))
@@ -3218,6 +3219,7 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
nm_i->ram_thresh = DEF_RAM_THRESHOLD;
nm_i->ra_nid_pages = DEF_RA_NID_PAGES;
nm_i->dirty_nats_ratio = DEF_DIRTY_NAT_RATIO_THRESHOLD;
+ nm_i->max_rf_node_blocks = DEF_RF_NODE_BLOCKS;
INIT_RADIX_TREE(&nm_i->free_nid_root, GFP_ATOMIC);
INIT_LIST_HEAD(&nm_i->free_nid_list);
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index 18b98cf0465b..fe56fd29c0d3 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -31,6 +31,9 @@
/* control total # of nats */
#define DEF_NAT_CACHE_THRESHOLD 100000
+/* control total # of node writes used for roll-fowrad recovery */
+#define DEF_RF_NODE_BLOCKS 100
+
/* vector size for gang look-up from nat cache that consists of radix tree */
#define NATVEC_SIZE 64
#define SETVEC_SIZE 32
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 10d152cfa58d..f69b685fb2b2 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -53,9 +53,12 @@ extern struct kmem_cache *f2fs_cf_name_slab;
bool f2fs_space_for_roll_forward(struct f2fs_sb_info *sbi)
{
s64 nalloc = percpu_counter_sum_positive(&sbi->alloc_valid_block_count);
+ u32 rf_node = percpu_counter_sum_positive(&sbi->rf_node_block_count);
if (sbi->last_valid_block_count + nalloc > sbi->user_block_count)
return false;
+ if (rf_node >= NM_I(sbi)->max_rf_node_blocks)
+ return false;
return true;
}
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index 281bc0133ee6..47efcf233afd 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -732,6 +732,7 @@ F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ssr_sections, min_ssr_sections);
F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh);
F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ra_nid_pages, ra_nid_pages);
F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, dirty_nats_ratio, dirty_nats_ratio);
+F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, max_roll_forward_node_blocks, max_rf_node_blocks);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, migration_granularity, migration_granularity);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level);
@@ -855,6 +856,7 @@ static struct attribute *f2fs_attrs[] = {
ATTR_LIST(ram_thresh),
ATTR_LIST(ra_nid_pages),
ATTR_LIST(dirty_nats_ratio),
+ ATTR_LIST(max_roll_forward_node_blocks),
ATTR_LIST(cp_interval),
ATTR_LIST(idle_interval),
ATTR_LIST(discard_idle_interval),
--
2.35.0.rc0.227.g00780c9af4-goog
Powered by blists - more mailing lists