| Message ID | 1502199825-15218-1-git-send-email-yunlong.song@huawei.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On 2017/8/8 21:43, Yunlong Song wrote: > In this patch, we add a new sysfs interface, we can use it to gradually achieve > the reserved_blocks finally, even when reserved_blocks is initially set over > user_block_count - total_valid_block_count. This is very useful, especially when > we upgrade kernel with new reserved_blocks value, but old disk image unluckily has > user_block_count - total_valid_block_count smaller than the desired reserved_blocks. > With this patch, f2fs can try its best to reserve space and get close to the > reserved_blocks, and the current value of achieved reserved_blocks can be shown > in real time. Oh, this looks like a soft limitation in quota system, but original reserved_blocks implementation likes a hard one, so this patch changes the semantics of reserved_blocks. Actually, I doubt that it would be hard to reserve all left free space in real user scenario now, since system user's activation may depend on free space of data partition due to file creation requirement, so w/o supporting feature of uid/gid reserved block, soft reservation will block any activation of system user, such as android. Thanks, > > Signed-off-by: Yunlong Song <yunlong.song@huawei.com> > --- > Documentation/ABI/testing/sysfs-fs-f2fs | 6 ++++++ > fs/f2fs/f2fs.h | 9 +++++++-- > fs/f2fs/super.c | 4 +++- > fs/f2fs/sysfs.c | 15 ++++++++++----- > 4 files changed, 26 insertions(+), 8 deletions(-) > > diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs > index 11b7f4e..bdbb9f3 100644 > --- a/Documentation/ABI/testing/sysfs-fs-f2fs > +++ b/Documentation/ABI/testing/sysfs-fs-f2fs > @@ -151,3 +151,9 @@ Date: August 2017 > Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> > Description: > Controls sleep time of GC urgent mode > + > +What: /sys/fs/f2fs/<disk>/cur_reserved_blocks > +Date: August 2017 > +Contact: "Yunlong Song" <yunlong.song@huawei.com> > +Description: > + Shows current reserved blocks in system. > diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h > index cea329f..3b7056f 100644 > --- a/fs/f2fs/f2fs.h > +++ b/fs/f2fs/f2fs.h > @@ -1040,6 +1040,7 @@ struct f2fs_sb_info { > block_t discard_blks; /* discard command candidats */ > block_t last_valid_block_count; /* for recovery */ > block_t reserved_blocks; /* configurable reserved blocks */ > + block_t cur_reserved_blocks; /* current reserved blocks */ > > u32 s_next_generation; /* for NFS support */ > > @@ -1514,7 +1515,7 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, > > spin_lock(&sbi->stat_lock); > sbi->total_valid_block_count += (block_t)(*count); > - avail_user_block_count = sbi->user_block_count - sbi->reserved_blocks; > + avail_user_block_count = sbi->user_block_count - sbi->cur_reserved_blocks; > if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) { > diff = sbi->total_valid_block_count - avail_user_block_count; > *count -= diff; > @@ -1548,6 +1549,8 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi, > f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count); > f2fs_bug_on(sbi, inode->i_blocks < sectors); > sbi->total_valid_block_count -= (block_t)count; > + sbi->cur_reserved_blocks = min(sbi->reserved_blocks, > + sbi->cur_reserved_blocks + count); > spin_unlock(&sbi->stat_lock); > f2fs_i_blocks_write(inode, count, false, true); > } > @@ -1694,7 +1697,7 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, > spin_lock(&sbi->stat_lock); > > valid_block_count = sbi->total_valid_block_count + 1; > - if (unlikely(valid_block_count + sbi->reserved_blocks > > + if (unlikely(valid_block_count + sbi->cur_reserved_blocks > > sbi->user_block_count)) { > spin_unlock(&sbi->stat_lock); > goto enospc; > @@ -1737,6 +1740,8 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi, > > sbi->total_valid_node_count--; > sbi->total_valid_block_count--; > + sbi->cur_reserved_blocks = min(sbi->reserved_blocks, > + sbi->cur_reserved_blocks + 1); > > spin_unlock(&sbi->stat_lock); > > diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c > index 4c1bdcb..2934aa2 100644 > --- a/fs/f2fs/super.c > +++ b/fs/f2fs/super.c > @@ -957,7 +957,7 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf) > buf->f_blocks = total_count - start_count; > buf->f_bfree = user_block_count - valid_user_blocks(sbi) + ovp_count; > buf->f_bavail = user_block_count - valid_user_blocks(sbi) - > - sbi->reserved_blocks; > + sbi->cur_reserved_blocks; > > avail_node_count = sbi->total_node_count - F2FS_RESERVED_NODE_NUM; > > @@ -2411,6 +2411,8 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) > le64_to_cpu(sbi->ckpt->valid_block_count); > sbi->last_valid_block_count = sbi->total_valid_block_count; > sbi->reserved_blocks = 0; > + sbi->cur_reserved_blocks = min(sbi->reserved_blocks, > + sbi->user_block_count - sbi->total_valid_block_count); > > for (i = 0; i < NR_INODE_TYPE; i++) { > INIT_LIST_HEAD(&sbi->inode_list[i]); > diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c > index b769a3d..405c13f 100644 > --- a/fs/f2fs/sysfs.c > +++ b/fs/f2fs/sysfs.c > @@ -76,6 +76,12 @@ static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a, > BD_PART_WRITTEN(sbi))); > } > > +static ssize_t cur_reserved_blocks_show(struct f2fs_attr *a, > + struct f2fs_sb_info *sbi, char *buf) > +{ > + return snprintf(buf, PAGE_SIZE, "%u\n", sbi->cur_reserved_blocks); > +} > + > static ssize_t features_show(struct f2fs_attr *a, > struct f2fs_sb_info *sbi, char *buf) > { > @@ -143,12 +149,9 @@ static ssize_t f2fs_sbi_store(struct f2fs_attr *a, > #endif > if (a->struct_type == RESERVED_BLOCKS) { > spin_lock(&sbi->stat_lock); > - if ((unsigned long)sbi->total_valid_block_count + t > > - (unsigned long)sbi->user_block_count) { > - spin_unlock(&sbi->stat_lock); > - return -EINVAL; > - } > *ui = t; > + sbi->cur_reserved_blocks = min(t, sbi->user_block_count - > + sbi->total_valid_block_count); > spin_unlock(&sbi->stat_lock); > return count; > } > @@ -274,6 +277,7 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a, > #endif > F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes); > F2FS_GENERAL_RO_ATTR(features); > +F2FS_GENERAL_RO_ATTR(cur_reserved_blocks); > > #ifdef CONFIG_F2FS_FS_ENCRYPTION > F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO); > @@ -317,6 +321,7 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a, > ATTR_LIST(lifetime_write_kbytes), > ATTR_LIST(features), > ATTR_LIST(reserved_blocks), > + ATTR_LIST(cur_reserved_blocks), > NULL, > }; > >
I think the aim of reserved_blocks function is to leave space for f2fs and FTL, so I change it to a soft version so that it can be used to fit to the data image which does not satisfy the hard version, especially for backward compatibility when updated kernel with new default reserved_blocks set (currently it is initially set 0 as default, but can be set any value with my new patch). As for the uid/gid, does current f2fs space management design consider this issue? IMO, I think we can just ensure the reserved space for file system no matter user/system type. Whether the value of reserved_blocks is OK or not, should not be filesystem's issue. Filesystem just provide this interface, and the upper layer, such as android vold should take care of the value of reserved_blocks and make sure its value is appropriate and will not block any activation of system user, if it really happens, android should change the value dynamically, it is fine, since we make reserved_blocks to a soft version. On 2017/8/10 11:15, Chao Yu wrote: > On 2017/8/8 21:43, Yunlong Song wrote: >> In this patch, we add a new sysfs interface, we can use it to gradually achieve >> the reserved_blocks finally, even when reserved_blocks is initially set over >> user_block_count - total_valid_block_count. This is very useful, especially when >> we upgrade kernel with new reserved_blocks value, but old disk image unluckily has >> user_block_count - total_valid_block_count smaller than the desired reserved_blocks. >> With this patch, f2fs can try its best to reserve space and get close to the >> reserved_blocks, and the current value of achieved reserved_blocks can be shown >> in real time. > Oh, this looks like a soft limitation in quota system, but original > reserved_blocks implementation likes a hard one, so this patch changes the > semantics of reserved_blocks. > > Actually, I doubt that it would be hard to reserve all left free space in real > user scenario now, since system user's activation may depend on free space of > data partition due to file creation requirement, so w/o supporting feature of > uid/gid reserved block, soft reservation will block any activation of system > user, such as android. > > Thanks, > >> Signed-off-by: Yunlong Song <yunlong.song@huawei.com> >> --- >> Documentation/ABI/testing/sysfs-fs-f2fs | 6 ++++++ >> fs/f2fs/f2fs.h | 9 +++++++-- >> fs/f2fs/super.c | 4 +++- >> fs/f2fs/sysfs.c | 15 ++++++++++----- >> 4 files changed, 26 insertions(+), 8 deletions(-) >> >> diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs >> index 11b7f4e..bdbb9f3 100644 >> --- a/Documentation/ABI/testing/sysfs-fs-f2fs >> +++ b/Documentation/ABI/testing/sysfs-fs-f2fs >> @@ -151,3 +151,9 @@ Date: August 2017 >> Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> >> Description: >> Controls sleep time of GC urgent mode >> + >> +What: /sys/fs/f2fs/<disk>/cur_reserved_blocks >> +Date: August 2017 >> +Contact: "Yunlong Song" <yunlong.song@huawei.com> >> +Description: >> + Shows current reserved blocks in system. >> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h >> index cea329f..3b7056f 100644 >> --- a/fs/f2fs/f2fs.h >> +++ b/fs/f2fs/f2fs.h >> @@ -1040,6 +1040,7 @@ struct f2fs_sb_info { >> block_t discard_blks; /* discard command candidats */ >> block_t last_valid_block_count; /* for recovery */ >> block_t reserved_blocks; /* configurable reserved blocks */ >> + block_t cur_reserved_blocks; /* current reserved blocks */ >> >> u32 s_next_generation; /* for NFS support */ >> >> @@ -1514,7 +1515,7 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, >> >> spin_lock(&sbi->stat_lock); >> sbi->total_valid_block_count += (block_t)(*count); >> - avail_user_block_count = sbi->user_block_count - sbi->reserved_blocks; >> + avail_user_block_count = sbi->user_block_count - sbi->cur_reserved_blocks; >> if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) { >> diff = sbi->total_valid_block_count - avail_user_block_count; >> *count -= diff; >> @@ -1548,6 +1549,8 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi, >> f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count); >> f2fs_bug_on(sbi, inode->i_blocks < sectors); >> sbi->total_valid_block_count -= (block_t)count; >> + sbi->cur_reserved_blocks = min(sbi->reserved_blocks, >> + sbi->cur_reserved_blocks + count); >> spin_unlock(&sbi->stat_lock); >> f2fs_i_blocks_write(inode, count, false, true); >> } >> @@ -1694,7 +1697,7 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, >> spin_lock(&sbi->stat_lock); >> >> valid_block_count = sbi->total_valid_block_count + 1; >> - if (unlikely(valid_block_count + sbi->reserved_blocks > >> + if (unlikely(valid_block_count + sbi->cur_reserved_blocks > >> sbi->user_block_count)) { >> spin_unlock(&sbi->stat_lock); >> goto enospc; >> @@ -1737,6 +1740,8 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi, >> >> sbi->total_valid_node_count--; >> sbi->total_valid_block_count--; >> + sbi->cur_reserved_blocks = min(sbi->reserved_blocks, >> + sbi->cur_reserved_blocks + 1); >> >> spin_unlock(&sbi->stat_lock); >> >> diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c >> index 4c1bdcb..2934aa2 100644 >> --- a/fs/f2fs/super.c >> +++ b/fs/f2fs/super.c >> @@ -957,7 +957,7 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf) >> buf->f_blocks = total_count - start_count; >> buf->f_bfree = user_block_count - valid_user_blocks(sbi) + ovp_count; >> buf->f_bavail = user_block_count - valid_user_blocks(sbi) - >> - sbi->reserved_blocks; >> + sbi->cur_reserved_blocks; >> >> avail_node_count = sbi->total_node_count - F2FS_RESERVED_NODE_NUM; >> >> @@ -2411,6 +2411,8 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) >> le64_to_cpu(sbi->ckpt->valid_block_count); >> sbi->last_valid_block_count = sbi->total_valid_block_count; >> sbi->reserved_blocks = 0; >> + sbi->cur_reserved_blocks = min(sbi->reserved_blocks, >> + sbi->user_block_count - sbi->total_valid_block_count); >> >> for (i = 0; i < NR_INODE_TYPE; i++) { >> INIT_LIST_HEAD(&sbi->inode_list[i]); >> diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c >> index b769a3d..405c13f 100644 >> --- a/fs/f2fs/sysfs.c >> +++ b/fs/f2fs/sysfs.c >> @@ -76,6 +76,12 @@ static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a, >> BD_PART_WRITTEN(sbi))); >> } >> >> +static ssize_t cur_reserved_blocks_show(struct f2fs_attr *a, >> + struct f2fs_sb_info *sbi, char *buf) >> +{ >> + return snprintf(buf, PAGE_SIZE, "%u\n", sbi->cur_reserved_blocks); >> +} >> + >> static ssize_t features_show(struct f2fs_attr *a, >> struct f2fs_sb_info *sbi, char *buf) >> { >> @@ -143,12 +149,9 @@ static ssize_t f2fs_sbi_store(struct f2fs_attr *a, >> #endif >> if (a->struct_type == RESERVED_BLOCKS) { >> spin_lock(&sbi->stat_lock); >> - if ((unsigned long)sbi->total_valid_block_count + t > >> - (unsigned long)sbi->user_block_count) { >> - spin_unlock(&sbi->stat_lock); >> - return -EINVAL; >> - } >> *ui = t; >> + sbi->cur_reserved_blocks = min(t, sbi->user_block_count - >> + sbi->total_valid_block_count); >> spin_unlock(&sbi->stat_lock); >> return count; >> } >> @@ -274,6 +277,7 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a, >> #endif >> F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes); >> F2FS_GENERAL_RO_ATTR(features); >> +F2FS_GENERAL_RO_ATTR(cur_reserved_blocks); >> >> #ifdef CONFIG_F2FS_FS_ENCRYPTION >> F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO); >> @@ -317,6 +321,7 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a, >> ATTR_LIST(lifetime_write_kbytes), >> ATTR_LIST(features), >> ATTR_LIST(reserved_blocks), >> + ATTR_LIST(cur_reserved_blocks), >> NULL, >> }; >> >> > > . >
On 2017/8/10 11:58, Yunlong Song wrote: > I think the aim of reserved_blocks function is to leave space for f2fs > and FTL, so I change it to a > soft version so that it can be used to fit to the data image which does > not satisfy the hard version, > especially for backward compatibility when updated kernel with new > default reserved_blocks set > (currently it is initially set 0 as default, but can be set any value > with my new patch). > > As for the uid/gid, does current f2fs space management design consider > this issue? IMO, I think we Upper layer application has considered this issue, as when free space touchs the threshold, system will block any operation and give a hint to clean up user's data. So w/o uid/gid reserved block, it will be OK. But for your requirement, user free space will drop to zero, and before current reserved block number touch soft reserved block limitation, user can only do deletion, so in this time, if any system/service flow depends on file creation, could result in blocking the system. > can just ensure the reserved space for file system no matter user/system > type. Whether the value of > reserved_blocks is OK or not, should not be filesystem's issue. > Filesystem just provide this interface, > and the upper layer, such as android vold should take care of the value > of reserved_blocks and make > sure its value is appropriate and will not block any activation of > system user, if it really happens, android > should change the value dynamically, it is fine, since we make > reserved_blocks to a soft version. We can not make sure in strategy changing flow, there is no file creation dependence. Even if we can, if the reserved_blocks is not appropriate, why not setting it correctly before? Thanks, > > On 2017/8/10 11:15, Chao Yu wrote: >> On 2017/8/8 21:43, Yunlong Song wrote: >>> In this patch, we add a new sysfs interface, we can use it to gradually achieve >>> the reserved_blocks finally, even when reserved_blocks is initially set over >>> user_block_count - total_valid_block_count. This is very useful, especially when >>> we upgrade kernel with new reserved_blocks value, but old disk image unluckily has >>> user_block_count - total_valid_block_count smaller than the desired reserved_blocks. >>> With this patch, f2fs can try its best to reserve space and get close to the >>> reserved_blocks, and the current value of achieved reserved_blocks can be shown >>> in real time. >> Oh, this looks like a soft limitation in quota system, but original >> reserved_blocks implementation likes a hard one, so this patch changes the >> semantics of reserved_blocks. >> >> Actually, I doubt that it would be hard to reserve all left free space in real >> user scenario now, since system user's activation may depend on free space of >> data partition due to file creation requirement, so w/o supporting feature of >> uid/gid reserved block, soft reservation will block any activation of system >> user, such as android. >> >> Thanks, >> >>> Signed-off-by: Yunlong Song <yunlong.song@huawei.com> >>> --- >>> Documentation/ABI/testing/sysfs-fs-f2fs | 6 ++++++ >>> fs/f2fs/f2fs.h | 9 +++++++-- >>> fs/f2fs/super.c | 4 +++- >>> fs/f2fs/sysfs.c | 15 ++++++++++----- >>> 4 files changed, 26 insertions(+), 8 deletions(-) >>> >>> diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs >>> index 11b7f4e..bdbb9f3 100644 >>> --- a/Documentation/ABI/testing/sysfs-fs-f2fs >>> +++ b/Documentation/ABI/testing/sysfs-fs-f2fs >>> @@ -151,3 +151,9 @@ Date: August 2017 >>> Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> >>> Description: >>> Controls sleep time of GC urgent mode >>> + >>> +What: /sys/fs/f2fs/<disk>/cur_reserved_blocks >>> +Date: August 2017 >>> +Contact: "Yunlong Song" <yunlong.song@huawei.com> >>> +Description: >>> + Shows current reserved blocks in system. >>> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h >>> index cea329f..3b7056f 100644 >>> --- a/fs/f2fs/f2fs.h >>> +++ b/fs/f2fs/f2fs.h >>> @@ -1040,6 +1040,7 @@ struct f2fs_sb_info { >>> block_t discard_blks; /* discard command candidats */ >>> block_t last_valid_block_count; /* for recovery */ >>> block_t reserved_blocks; /* configurable reserved blocks */ >>> + block_t cur_reserved_blocks; /* current reserved blocks */ >>> >>> u32 s_next_generation; /* for NFS support */ >>> >>> @@ -1514,7 +1515,7 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, >>> >>> spin_lock(&sbi->stat_lock); >>> sbi->total_valid_block_count += (block_t)(*count); >>> - avail_user_block_count = sbi->user_block_count - sbi->reserved_blocks; >>> + avail_user_block_count = sbi->user_block_count - sbi->cur_reserved_blocks; >>> if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) { >>> diff = sbi->total_valid_block_count - avail_user_block_count; >>> *count -= diff; >>> @@ -1548,6 +1549,8 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi, >>> f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count); >>> f2fs_bug_on(sbi, inode->i_blocks < sectors); >>> sbi->total_valid_block_count -= (block_t)count; >>> + sbi->cur_reserved_blocks = min(sbi->reserved_blocks, >>> + sbi->cur_reserved_blocks + count); >>> spin_unlock(&sbi->stat_lock); >>> f2fs_i_blocks_write(inode, count, false, true); >>> } >>> @@ -1694,7 +1697,7 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, >>> spin_lock(&sbi->stat_lock); >>> >>> valid_block_count = sbi->total_valid_block_count + 1; >>> - if (unlikely(valid_block_count + sbi->reserved_blocks > >>> + if (unlikely(valid_block_count + sbi->cur_reserved_blocks > >>> sbi->user_block_count)) { >>> spin_unlock(&sbi->stat_lock); >>> goto enospc; >>> @@ -1737,6 +1740,8 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi, >>> >>> sbi->total_valid_node_count--; >>> sbi->total_valid_block_count--; >>> + sbi->cur_reserved_blocks = min(sbi->reserved_blocks, >>> + sbi->cur_reserved_blocks + 1); >>> >>> spin_unlock(&sbi->stat_lock); >>> >>> diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c >>> index 4c1bdcb..2934aa2 100644 >>> --- a/fs/f2fs/super.c >>> +++ b/fs/f2fs/super.c >>> @@ -957,7 +957,7 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf) >>> buf->f_blocks = total_count - start_count; >>> buf->f_bfree = user_block_count - valid_user_blocks(sbi) + ovp_count; >>> buf->f_bavail = user_block_count - valid_user_blocks(sbi) - >>> - sbi->reserved_blocks; >>> + sbi->cur_reserved_blocks; >>> >>> avail_node_count = sbi->total_node_count - F2FS_RESERVED_NODE_NUM; >>> >>> @@ -2411,6 +2411,8 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) >>> le64_to_cpu(sbi->ckpt->valid_block_count); >>> sbi->last_valid_block_count = sbi->total_valid_block_count; >>> sbi->reserved_blocks = 0; >>> + sbi->cur_reserved_blocks = min(sbi->reserved_blocks, >>> + sbi->user_block_count - sbi->total_valid_block_count); >>> >>> for (i = 0; i < NR_INODE_TYPE; i++) { >>> INIT_LIST_HEAD(&sbi->inode_list[i]); >>> diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c >>> index b769a3d..405c13f 100644 >>> --- a/fs/f2fs/sysfs.c >>> +++ b/fs/f2fs/sysfs.c >>> @@ -76,6 +76,12 @@ static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a, >>> BD_PART_WRITTEN(sbi))); >>> } >>> >>> +static ssize_t cur_reserved_blocks_show(struct f2fs_attr *a, >>> + struct f2fs_sb_info *sbi, char *buf) >>> +{ >>> + return snprintf(buf, PAGE_SIZE, "%u\n", sbi->cur_reserved_blocks); >>> +} >>> + >>> static ssize_t features_show(struct f2fs_attr *a, >>> struct f2fs_sb_info *sbi, char *buf) >>> { >>> @@ -143,12 +149,9 @@ static ssize_t f2fs_sbi_store(struct f2fs_attr *a, >>> #endif >>> if (a->struct_type == RESERVED_BLOCKS) { >>> spin_lock(&sbi->stat_lock); >>> - if ((unsigned long)sbi->total_valid_block_count + t > >>> - (unsigned long)sbi->user_block_count) { >>> - spin_unlock(&sbi->stat_lock); >>> - return -EINVAL; >>> - } >>> *ui = t; >>> + sbi->cur_reserved_blocks = min(t, sbi->user_block_count - >>> + sbi->total_valid_block_count); >>> spin_unlock(&sbi->stat_lock); >>> return count; >>> } >>> @@ -274,6 +277,7 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a, >>> #endif >>> F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes); >>> F2FS_GENERAL_RO_ATTR(features); >>> +F2FS_GENERAL_RO_ATTR(cur_reserved_blocks); >>> >>> #ifdef CONFIG_F2FS_FS_ENCRYPTION >>> F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO); >>> @@ -317,6 +321,7 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a, >>> ATTR_LIST(lifetime_write_kbytes), >>> ATTR_LIST(features), >>> ATTR_LIST(reserved_blocks), >>> + ATTR_LIST(cur_reserved_blocks), >>> NULL, >>> }; >>> >>> >> >> . >> >
It may block the system in such case, but so does the hard version design. In the hard version, when reserve_blocks is set to the value = user_block_count - total_valid_block_count, then the user free space can also drop to zero and has the same problem. IMO, kernel does not need to take this responsibility, it's android's responsibility. On 2017/8/10 19:26, Chao Yu wrote: > On 2017/8/10 11:58, Yunlong Song wrote: >> I think the aim of reserved_blocks function is to leave space for f2fs >> and FTL, so I change it to a >> soft version so that it can be used to fit to the data image which does >> not satisfy the hard version, >> especially for backward compatibility when updated kernel with new >> default reserved_blocks set >> (currently it is initially set 0 as default, but can be set any value >> with my new patch). >> >> As for the uid/gid, does current f2fs space management design consider >> this issue? IMO, I think we > Upper layer application has considered this issue, as when free space touchs the > threshold, system will block any operation and give a hint to clean up user's > data. So w/o uid/gid reserved block, it will be OK. But for your requirement, > user free space will drop to zero, and before current reserved block number > touch soft reserved block limitation, user can only do deletion, so in this > time, if any system/service flow depends on file creation, could result in > blocking the system. > >> can just ensure the reserved space for file system no matter user/system >> type. Whether the value of >> reserved_blocks is OK or not, should not be filesystem's issue. >> Filesystem just provide this interface, >> and the upper layer, such as android vold should take care of the value >> of reserved_blocks and make >> sure its value is appropriate and will not block any activation of >> system user, if it really happens, android >> should change the value dynamically, it is fine, since we make >> reserved_blocks to a soft version. > We can not make sure in strategy changing flow, there is no file creation > dependence. Even if we can, if the reserved_blocks is not appropriate, why not > setting it correctly before? > > Thanks, > >> On 2017/8/10 11:15, Chao Yu wrote: >>> On 2017/8/8 21:43, Yunlong Song wrote: >>>> In this patch, we add a new sysfs interface, we can use it to gradually achieve >>>> the reserved_blocks finally, even when reserved_blocks is initially set over >>>> user_block_count - total_valid_block_count. This is very useful, especially when >>>> we upgrade kernel with new reserved_blocks value, but old disk image unluckily has >>>> user_block_count - total_valid_block_count smaller than the desired reserved_blocks. >>>> With this patch, f2fs can try its best to reserve space and get close to the >>>> reserved_blocks, and the current value of achieved reserved_blocks can be shown >>>> in real time. >>> Oh, this looks like a soft limitation in quota system, but original >>> reserved_blocks implementation likes a hard one, so this patch changes the >>> semantics of reserved_blocks. >>> >>> Actually, I doubt that it would be hard to reserve all left free space in real >>> user scenario now, since system user's activation may depend on free space of >>> data partition due to file creation requirement, so w/o supporting feature of >>> uid/gid reserved block, soft reservation will block any activation of system >>> user, such as android. >>> >>> Thanks, >>> >>>> Signed-off-by: Yunlong Song <yunlong.song@huawei.com> >>>> --- >>>> Documentation/ABI/testing/sysfs-fs-f2fs | 6 ++++++ >>>> fs/f2fs/f2fs.h | 9 +++++++-- >>>> fs/f2fs/super.c | 4 +++- >>>> fs/f2fs/sysfs.c | 15 ++++++++++----- >>>> 4 files changed, 26 insertions(+), 8 deletions(-) >>>> >>>> diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs >>>> index 11b7f4e..bdbb9f3 100644 >>>> --- a/Documentation/ABI/testing/sysfs-fs-f2fs >>>> +++ b/Documentation/ABI/testing/sysfs-fs-f2fs >>>> @@ -151,3 +151,9 @@ Date: August 2017 >>>> Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> >>>> Description: >>>> Controls sleep time of GC urgent mode >>>> + >>>> +What: /sys/fs/f2fs/<disk>/cur_reserved_blocks >>>> +Date: August 2017 >>>> +Contact: "Yunlong Song" <yunlong.song@huawei.com> >>>> +Description: >>>> + Shows current reserved blocks in system. >>>> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h >>>> index cea329f..3b7056f 100644 >>>> --- a/fs/f2fs/f2fs.h >>>> +++ b/fs/f2fs/f2fs.h >>>> @@ -1040,6 +1040,7 @@ struct f2fs_sb_info { >>>> block_t discard_blks; /* discard command candidats */ >>>> block_t last_valid_block_count; /* for recovery */ >>>> block_t reserved_blocks; /* configurable reserved blocks */ >>>> + block_t cur_reserved_blocks; /* current reserved blocks */ >>>> >>>> u32 s_next_generation; /* for NFS support */ >>>> >>>> @@ -1514,7 +1515,7 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, >>>> >>>> spin_lock(&sbi->stat_lock); >>>> sbi->total_valid_block_count += (block_t)(*count); >>>> - avail_user_block_count = sbi->user_block_count - sbi->reserved_blocks; >>>> + avail_user_block_count = sbi->user_block_count - sbi->cur_reserved_blocks; >>>> if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) { >>>> diff = sbi->total_valid_block_count - avail_user_block_count; >>>> *count -= diff; >>>> @@ -1548,6 +1549,8 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi, >>>> f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count); >>>> f2fs_bug_on(sbi, inode->i_blocks < sectors); >>>> sbi->total_valid_block_count -= (block_t)count; >>>> + sbi->cur_reserved_blocks = min(sbi->reserved_blocks, >>>> + sbi->cur_reserved_blocks + count); >>>> spin_unlock(&sbi->stat_lock); >>>> f2fs_i_blocks_write(inode, count, false, true); >>>> } >>>> @@ -1694,7 +1697,7 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, >>>> spin_lock(&sbi->stat_lock); >>>> >>>> valid_block_count = sbi->total_valid_block_count + 1; >>>> - if (unlikely(valid_block_count + sbi->reserved_blocks > >>>> + if (unlikely(valid_block_count + sbi->cur_reserved_blocks > >>>> sbi->user_block_count)) { >>>> spin_unlock(&sbi->stat_lock); >>>> goto enospc; >>>> @@ -1737,6 +1740,8 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi, >>>> >>>> sbi->total_valid_node_count--; >>>> sbi->total_valid_block_count--; >>>> + sbi->cur_reserved_blocks = min(sbi->reserved_blocks, >>>> + sbi->cur_reserved_blocks + 1); >>>> >>>> spin_unlock(&sbi->stat_lock); >>>> >>>> diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c >>>> index 4c1bdcb..2934aa2 100644 >>>> --- a/fs/f2fs/super.c >>>> +++ b/fs/f2fs/super.c >>>> @@ -957,7 +957,7 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf) >>>> buf->f_blocks = total_count - start_count; >>>> buf->f_bfree = user_block_count - valid_user_blocks(sbi) + ovp_count; >>>> buf->f_bavail = user_block_count - valid_user_blocks(sbi) - >>>> - sbi->reserved_blocks; >>>> + sbi->cur_reserved_blocks; >>>> >>>> avail_node_count = sbi->total_node_count - F2FS_RESERVED_NODE_NUM; >>>> >>>> @@ -2411,6 +2411,8 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) >>>> le64_to_cpu(sbi->ckpt->valid_block_count); >>>> sbi->last_valid_block_count = sbi->total_valid_block_count; >>>> sbi->reserved_blocks = 0; >>>> + sbi->cur_reserved_blocks = min(sbi->reserved_blocks, >>>> + sbi->user_block_count - sbi->total_valid_block_count); >>>> >>>> for (i = 0; i < NR_INODE_TYPE; i++) { >>>> INIT_LIST_HEAD(&sbi->inode_list[i]); >>>> diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c >>>> index b769a3d..405c13f 100644 >>>> --- a/fs/f2fs/sysfs.c >>>> +++ b/fs/f2fs/sysfs.c >>>> @@ -76,6 +76,12 @@ static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a, >>>> BD_PART_WRITTEN(sbi))); >>>> } >>>> >>>> +static ssize_t cur_reserved_blocks_show(struct f2fs_attr *a, >>>> + struct f2fs_sb_info *sbi, char *buf) >>>> +{ >>>> + return snprintf(buf, PAGE_SIZE, "%u\n", sbi->cur_reserved_blocks); >>>> +} >>>> + >>>> static ssize_t features_show(struct f2fs_attr *a, >>>> struct f2fs_sb_info *sbi, char *buf) >>>> { >>>> @@ -143,12 +149,9 @@ static ssize_t f2fs_sbi_store(struct f2fs_attr *a, >>>> #endif >>>> if (a->struct_type == RESERVED_BLOCKS) { >>>> spin_lock(&sbi->stat_lock); >>>> - if ((unsigned long)sbi->total_valid_block_count + t > >>>> - (unsigned long)sbi->user_block_count) { >>>> - spin_unlock(&sbi->stat_lock); >>>> - return -EINVAL; >>>> - } >>>> *ui = t; >>>> + sbi->cur_reserved_blocks = min(t, sbi->user_block_count - >>>> + sbi->total_valid_block_count); >>>> spin_unlock(&sbi->stat_lock); >>>> return count; >>>> } >>>> @@ -274,6 +277,7 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a, >>>> #endif >>>> F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes); >>>> F2FS_GENERAL_RO_ATTR(features); >>>> +F2FS_GENERAL_RO_ATTR(cur_reserved_blocks); >>>> >>>> #ifdef CONFIG_F2FS_FS_ENCRYPTION >>>> F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO); >>>> @@ -317,6 +321,7 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a, >>>> ATTR_LIST(lifetime_write_kbytes), >>>> ATTR_LIST(features), >>>> ATTR_LIST(reserved_blocks), >>>> + ATTR_LIST(cur_reserved_blocks), >>>> NULL, >>>> }; >>>> >>>> >>> . >>> > > . >
On 2017/8/10 19:41, Yunlong Song wrote: > It may block the system in such case, but so does the hard version > design. In the hard version, We'd better not let soft/hard reserved_blocks to eat all left free space, at least needs to leave enough space for supporting system's activation. Thanks, > when reserve_blocks is set to the value = user_block_count - > total_valid_block_count, then > the user free space can also drop to zero and has the same problem. IMO, > kernel does not need > to take this responsibility, it's android's responsibility. > > On 2017/8/10 19:26, Chao Yu wrote: >> On 2017/8/10 11:58, Yunlong Song wrote: >>> I think the aim of reserved_blocks function is to leave space for f2fs >>> and FTL, so I change it to a >>> soft version so that it can be used to fit to the data image which does >>> not satisfy the hard version, >>> especially for backward compatibility when updated kernel with new >>> default reserved_blocks set >>> (currently it is initially set 0 as default, but can be set any value >>> with my new patch). >>> >>> As for the uid/gid, does current f2fs space management design consider >>> this issue? IMO, I think we >> Upper layer application has considered this issue, as when free space touchs the >> threshold, system will block any operation and give a hint to clean up user's >> data. So w/o uid/gid reserved block, it will be OK. But for your requirement, >> user free space will drop to zero, and before current reserved block number >> touch soft reserved block limitation, user can only do deletion, so in this >> time, if any system/service flow depends on file creation, could result in >> blocking the system. >> >>> can just ensure the reserved space for file system no matter user/system >>> type. Whether the value of >>> reserved_blocks is OK or not, should not be filesystem's issue. >>> Filesystem just provide this interface, >>> and the upper layer, such as android vold should take care of the value >>> of reserved_blocks and make >>> sure its value is appropriate and will not block any activation of >>> system user, if it really happens, android >>> should change the value dynamically, it is fine, since we make >>> reserved_blocks to a soft version. >> We can not make sure in strategy changing flow, there is no file creation >> dependence. Even if we can, if the reserved_blocks is not appropriate, why not >> setting it correctly before? >> >> Thanks, >> >>> On 2017/8/10 11:15, Chao Yu wrote: >>>> On 2017/8/8 21:43, Yunlong Song wrote: >>>>> In this patch, we add a new sysfs interface, we can use it to gradually achieve >>>>> the reserved_blocks finally, even when reserved_blocks is initially set over >>>>> user_block_count - total_valid_block_count. This is very useful, especially when >>>>> we upgrade kernel with new reserved_blocks value, but old disk image unluckily has >>>>> user_block_count - total_valid_block_count smaller than the desired reserved_blocks. >>>>> With this patch, f2fs can try its best to reserve space and get close to the >>>>> reserved_blocks, and the current value of achieved reserved_blocks can be shown >>>>> in real time. >>>> Oh, this looks like a soft limitation in quota system, but original >>>> reserved_blocks implementation likes a hard one, so this patch changes the >>>> semantics of reserved_blocks. >>>> >>>> Actually, I doubt that it would be hard to reserve all left free space in real >>>> user scenario now, since system user's activation may depend on free space of >>>> data partition due to file creation requirement, so w/o supporting feature of >>>> uid/gid reserved block, soft reservation will block any activation of system >>>> user, such as android. >>>> >>>> Thanks, >>>> >>>>> Signed-off-by: Yunlong Song <yunlong.song@huawei.com> >>>>> --- >>>>> Documentation/ABI/testing/sysfs-fs-f2fs | 6 ++++++ >>>>> fs/f2fs/f2fs.h | 9 +++++++-- >>>>> fs/f2fs/super.c | 4 +++- >>>>> fs/f2fs/sysfs.c | 15 ++++++++++----- >>>>> 4 files changed, 26 insertions(+), 8 deletions(-) >>>>> >>>>> diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs >>>>> index 11b7f4e..bdbb9f3 100644 >>>>> --- a/Documentation/ABI/testing/sysfs-fs-f2fs >>>>> +++ b/Documentation/ABI/testing/sysfs-fs-f2fs >>>>> @@ -151,3 +151,9 @@ Date: August 2017 >>>>> Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> >>>>> Description: >>>>> Controls sleep time of GC urgent mode >>>>> + >>>>> +What: /sys/fs/f2fs/<disk>/cur_reserved_blocks >>>>> +Date: August 2017 >>>>> +Contact: "Yunlong Song" <yunlong.song@huawei.com> >>>>> +Description: >>>>> + Shows current reserved blocks in system. >>>>> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h >>>>> index cea329f..3b7056f 100644 >>>>> --- a/fs/f2fs/f2fs.h >>>>> +++ b/fs/f2fs/f2fs.h >>>>> @@ -1040,6 +1040,7 @@ struct f2fs_sb_info { >>>>> block_t discard_blks; /* discard command candidats */ >>>>> block_t last_valid_block_count; /* for recovery */ >>>>> block_t reserved_blocks; /* configurable reserved blocks */ >>>>> + block_t cur_reserved_blocks; /* current reserved blocks */ >>>>> >>>>> u32 s_next_generation; /* for NFS support */ >>>>> >>>>> @@ -1514,7 +1515,7 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, >>>>> >>>>> spin_lock(&sbi->stat_lock); >>>>> sbi->total_valid_block_count += (block_t)(*count); >>>>> - avail_user_block_count = sbi->user_block_count - sbi->reserved_blocks; >>>>> + avail_user_block_count = sbi->user_block_count - sbi->cur_reserved_blocks; >>>>> if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) { >>>>> diff = sbi->total_valid_block_count - avail_user_block_count; >>>>> *count -= diff; >>>>> @@ -1548,6 +1549,8 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi, >>>>> f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count); >>>>> f2fs_bug_on(sbi, inode->i_blocks < sectors); >>>>> sbi->total_valid_block_count -= (block_t)count; >>>>> + sbi->cur_reserved_blocks = min(sbi->reserved_blocks, >>>>> + sbi->cur_reserved_blocks + count); >>>>> spin_unlock(&sbi->stat_lock); >>>>> f2fs_i_blocks_write(inode, count, false, true); >>>>> } >>>>> @@ -1694,7 +1697,7 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, >>>>> spin_lock(&sbi->stat_lock); >>>>> >>>>> valid_block_count = sbi->total_valid_block_count + 1; >>>>> - if (unlikely(valid_block_count + sbi->reserved_blocks > >>>>> + if (unlikely(valid_block_count + sbi->cur_reserved_blocks > >>>>> sbi->user_block_count)) { >>>>> spin_unlock(&sbi->stat_lock); >>>>> goto enospc; >>>>> @@ -1737,6 +1740,8 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi, >>>>> >>>>> sbi->total_valid_node_count--; >>>>> sbi->total_valid_block_count--; >>>>> + sbi->cur_reserved_blocks = min(sbi->reserved_blocks, >>>>> + sbi->cur_reserved_blocks + 1); >>>>> >>>>> spin_unlock(&sbi->stat_lock); >>>>> >>>>> diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c >>>>> index 4c1bdcb..2934aa2 100644 >>>>> --- a/fs/f2fs/super.c >>>>> +++ b/fs/f2fs/super.c >>>>> @@ -957,7 +957,7 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf) >>>>> buf->f_blocks = total_count - start_count; >>>>> buf->f_bfree = user_block_count - valid_user_blocks(sbi) + ovp_count; >>>>> buf->f_bavail = user_block_count - valid_user_blocks(sbi) - >>>>> - sbi->reserved_blocks; >>>>> + sbi->cur_reserved_blocks; >>>>> >>>>> avail_node_count = sbi->total_node_count - F2FS_RESERVED_NODE_NUM; >>>>> >>>>> @@ -2411,6 +2411,8 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) >>>>> le64_to_cpu(sbi->ckpt->valid_block_count); >>>>> sbi->last_valid_block_count = sbi->total_valid_block_count; >>>>> sbi->reserved_blocks = 0; >>>>> + sbi->cur_reserved_blocks = min(sbi->reserved_blocks, >>>>> + sbi->user_block_count - sbi->total_valid_block_count); >>>>> >>>>> for (i = 0; i < NR_INODE_TYPE; i++) { >>>>> INIT_LIST_HEAD(&sbi->inode_list[i]); >>>>> diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c >>>>> index b769a3d..405c13f 100644 >>>>> --- a/fs/f2fs/sysfs.c >>>>> +++ b/fs/f2fs/sysfs.c >>>>> @@ -76,6 +76,12 @@ static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a, >>>>> BD_PART_WRITTEN(sbi))); >>>>> } >>>>> >>>>> +static ssize_t cur_reserved_blocks_show(struct f2fs_attr *a, >>>>> + struct f2fs_sb_info *sbi, char *buf) >>>>> +{ >>>>> + return snprintf(buf, PAGE_SIZE, "%u\n", sbi->cur_reserved_blocks); >>>>> +} >>>>> + >>>>> static ssize_t features_show(struct f2fs_attr *a, >>>>> struct f2fs_sb_info *sbi, char *buf) >>>>> { >>>>> @@ -143,12 +149,9 @@ static ssize_t f2fs_sbi_store(struct f2fs_attr *a, >>>>> #endif >>>>> if (a->struct_type == RESERVED_BLOCKS) { >>>>> spin_lock(&sbi->stat_lock); >>>>> - if ((unsigned long)sbi->total_valid_block_count + t > >>>>> - (unsigned long)sbi->user_block_count) { >>>>> - spin_unlock(&sbi->stat_lock); >>>>> - return -EINVAL; >>>>> - } >>>>> *ui = t; >>>>> + sbi->cur_reserved_blocks = min(t, sbi->user_block_count - >>>>> + sbi->total_valid_block_count); >>>>> spin_unlock(&sbi->stat_lock); >>>>> return count; >>>>> } >>>>> @@ -274,6 +277,7 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a, >>>>> #endif >>>>> F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes); >>>>> F2FS_GENERAL_RO_ATTR(features); >>>>> +F2FS_GENERAL_RO_ATTR(cur_reserved_blocks); >>>>> >>>>> #ifdef CONFIG_F2FS_FS_ENCRYPTION >>>>> F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO); >>>>> @@ -317,6 +321,7 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a, >>>>> ATTR_LIST(lifetime_write_kbytes), >>>>> ATTR_LIST(features), >>>>> ATTR_LIST(reserved_blocks), >>>>> + ATTR_LIST(cur_reserved_blocks), >>>>> NULL, >>>>> }; >>>>> >>>>> >>>> . >>>> >> >> . >> >
OK, I change the initial value of cur_reserved_blocks to 0 and increase its value only in the dec_valid_block(,node)_count process, to only take up the blocks which are just obsoleted. With this change, if it is OK for system activation before, it is OK after as well. Please review the patch v2 I resent. On 2017/8/11 18:18, Chao Yu wrote: > On 2017/8/10 19:41, Yunlong Song wrote: >> It may block the system in such case, but so does the hard version >> design. In the hard version, > We'd better not let soft/hard reserved_blocks to eat all left free space, at > least needs to leave enough space for supporting system's activation. > > Thanks, > >> when reserve_blocks is set to the value = user_block_count - >> total_valid_block_count, then >> the user free space can also drop to zero and has the same problem. IMO, >> kernel does not need >> to take this responsibility, it's android's responsibility. >> >> On 2017/8/10 19:26, Chao Yu wrote: >>> On 2017/8/10 11:58, Yunlong Song wrote: >>>> I think the aim of reserved_blocks function is to leave space for f2fs >>>> and FTL, so I change it to a >>>> soft version so that it can be used to fit to the data image which does >>>> not satisfy the hard version, >>>> especially for backward compatibility when updated kernel with new >>>> default reserved_blocks set >>>> (currently it is initially set 0 as default, but can be set any value >>>> with my new patch). >>>> >>>> As for the uid/gid, does current f2fs space management design consider >>>> this issue? IMO, I think we >>> Upper layer application has considered this issue, as when free space touchs the >>> threshold, system will block any operation and give a hint to clean up user's >>> data. So w/o uid/gid reserved block, it will be OK. But for your requirement, >>> user free space will drop to zero, and before current reserved block number >>> touch soft reserved block limitation, user can only do deletion, so in this >>> time, if any system/service flow depends on file creation, could result in >>> blocking the system. >>> >>>> can just ensure the reserved space for file system no matter user/system >>>> type. Whether the value of >>>> reserved_blocks is OK or not, should not be filesystem's issue. >>>> Filesystem just provide this interface, >>>> and the upper layer, such as android vold should take care of the value >>>> of reserved_blocks and make >>>> sure its value is appropriate and will not block any activation of >>>> system user, if it really happens, android >>>> should change the value dynamically, it is fine, since we make >>>> reserved_blocks to a soft version. >>> We can not make sure in strategy changing flow, there is no file creation >>> dependence. Even if we can, if the reserved_blocks is not appropriate, why not >>> setting it correctly before? >>> >>> Thanks, >>> >>>> On 2017/8/10 11:15, Chao Yu wrote: >>>>> On 2017/8/8 21:43, Yunlong Song wrote: >>>>>> In this patch, we add a new sysfs interface, we can use it to gradually achieve >>>>>> the reserved_blocks finally, even when reserved_blocks is initially set over >>>>>> user_block_count - total_valid_block_count. This is very useful, especially when >>>>>> we upgrade kernel with new reserved_blocks value, but old disk image unluckily has >>>>>> user_block_count - total_valid_block_count smaller than the desired reserved_blocks. >>>>>> With this patch, f2fs can try its best to reserve space and get close to the >>>>>> reserved_blocks, and the current value of achieved reserved_blocks can be shown >>>>>> in real time. >>>>> Oh, this looks like a soft limitation in quota system, but original >>>>> reserved_blocks implementation likes a hard one, so this patch changes the >>>>> semantics of reserved_blocks. >>>>> >>>>> Actually, I doubt that it would be hard to reserve all left free space in real >>>>> user scenario now, since system user's activation may depend on free space of >>>>> data partition due to file creation requirement, so w/o supporting feature of >>>>> uid/gid reserved block, soft reservation will block any activation of system >>>>> user, such as android. >>>>> >>>>> Thanks, >>>>> >>>>>> Signed-off-by: Yunlong Song <yunlong.song@huawei.com> >>>>>> --- >>>>>> Documentation/ABI/testing/sysfs-fs-f2fs | 6 ++++++ >>>>>> fs/f2fs/f2fs.h | 9 +++++++-- >>>>>> fs/f2fs/super.c | 4 +++- >>>>>> fs/f2fs/sysfs.c | 15 ++++++++++----- >>>>>> 4 files changed, 26 insertions(+), 8 deletions(-) >>>>>> >>>>>> diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs >>>>>> index 11b7f4e..bdbb9f3 100644 >>>>>> --- a/Documentation/ABI/testing/sysfs-fs-f2fs >>>>>> +++ b/Documentation/ABI/testing/sysfs-fs-f2fs >>>>>> @@ -151,3 +151,9 @@ Date: August 2017 >>>>>> Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> >>>>>> Description: >>>>>> Controls sleep time of GC urgent mode >>>>>> + >>>>>> +What: /sys/fs/f2fs/<disk>/cur_reserved_blocks >>>>>> +Date: August 2017 >>>>>> +Contact: "Yunlong Song" <yunlong.song@huawei.com> >>>>>> +Description: >>>>>> + Shows current reserved blocks in system. >>>>>> diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h >>>>>> index cea329f..3b7056f 100644 >>>>>> --- a/fs/f2fs/f2fs.h >>>>>> +++ b/fs/f2fs/f2fs.h >>>>>> @@ -1040,6 +1040,7 @@ struct f2fs_sb_info { >>>>>> block_t discard_blks; /* discard command candidats */ >>>>>> block_t last_valid_block_count; /* for recovery */ >>>>>> block_t reserved_blocks; /* configurable reserved blocks */ >>>>>> + block_t cur_reserved_blocks; /* current reserved blocks */ >>>>>> >>>>>> u32 s_next_generation; /* for NFS support */ >>>>>> >>>>>> @@ -1514,7 +1515,7 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, >>>>>> >>>>>> spin_lock(&sbi->stat_lock); >>>>>> sbi->total_valid_block_count += (block_t)(*count); >>>>>> - avail_user_block_count = sbi->user_block_count - sbi->reserved_blocks; >>>>>> + avail_user_block_count = sbi->user_block_count - sbi->cur_reserved_blocks; >>>>>> if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) { >>>>>> diff = sbi->total_valid_block_count - avail_user_block_count; >>>>>> *count -= diff; >>>>>> @@ -1548,6 +1549,8 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi, >>>>>> f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count); >>>>>> f2fs_bug_on(sbi, inode->i_blocks < sectors); >>>>>> sbi->total_valid_block_count -= (block_t)count; >>>>>> + sbi->cur_reserved_blocks = min(sbi->reserved_blocks, >>>>>> + sbi->cur_reserved_blocks + count); >>>>>> spin_unlock(&sbi->stat_lock); >>>>>> f2fs_i_blocks_write(inode, count, false, true); >>>>>> } >>>>>> @@ -1694,7 +1697,7 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, >>>>>> spin_lock(&sbi->stat_lock); >>>>>> >>>>>> valid_block_count = sbi->total_valid_block_count + 1; >>>>>> - if (unlikely(valid_block_count + sbi->reserved_blocks > >>>>>> + if (unlikely(valid_block_count + sbi->cur_reserved_blocks > >>>>>> sbi->user_block_count)) { >>>>>> spin_unlock(&sbi->stat_lock); >>>>>> goto enospc; >>>>>> @@ -1737,6 +1740,8 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi, >>>>>> >>>>>> sbi->total_valid_node_count--; >>>>>> sbi->total_valid_block_count--; >>>>>> + sbi->cur_reserved_blocks = min(sbi->reserved_blocks, >>>>>> + sbi->cur_reserved_blocks + 1); >>>>>> >>>>>> spin_unlock(&sbi->stat_lock); >>>>>> >>>>>> diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c >>>>>> index 4c1bdcb..2934aa2 100644 >>>>>> --- a/fs/f2fs/super.c >>>>>> +++ b/fs/f2fs/super.c >>>>>> @@ -957,7 +957,7 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf) >>>>>> buf->f_blocks = total_count - start_count; >>>>>> buf->f_bfree = user_block_count - valid_user_blocks(sbi) + ovp_count; >>>>>> buf->f_bavail = user_block_count - valid_user_blocks(sbi) - >>>>>> - sbi->reserved_blocks; >>>>>> + sbi->cur_reserved_blocks; >>>>>> >>>>>> avail_node_count = sbi->total_node_count - F2FS_RESERVED_NODE_NUM; >>>>>> >>>>>> @@ -2411,6 +2411,8 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) >>>>>> le64_to_cpu(sbi->ckpt->valid_block_count); >>>>>> sbi->last_valid_block_count = sbi->total_valid_block_count; >>>>>> sbi->reserved_blocks = 0; >>>>>> + sbi->cur_reserved_blocks = min(sbi->reserved_blocks, >>>>>> + sbi->user_block_count - sbi->total_valid_block_count); >>>>>> >>>>>> for (i = 0; i < NR_INODE_TYPE; i++) { >>>>>> INIT_LIST_HEAD(&sbi->inode_list[i]); >>>>>> diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c >>>>>> index b769a3d..405c13f 100644 >>>>>> --- a/fs/f2fs/sysfs.c >>>>>> +++ b/fs/f2fs/sysfs.c >>>>>> @@ -76,6 +76,12 @@ static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a, >>>>>> BD_PART_WRITTEN(sbi))); >>>>>> } >>>>>> >>>>>> +static ssize_t cur_reserved_blocks_show(struct f2fs_attr *a, >>>>>> + struct f2fs_sb_info *sbi, char *buf) >>>>>> +{ >>>>>> + return snprintf(buf, PAGE_SIZE, "%u\n", sbi->cur_reserved_blocks); >>>>>> +} >>>>>> + >>>>>> static ssize_t features_show(struct f2fs_attr *a, >>>>>> struct f2fs_sb_info *sbi, char *buf) >>>>>> { >>>>>> @@ -143,12 +149,9 @@ static ssize_t f2fs_sbi_store(struct f2fs_attr *a, >>>>>> #endif >>>>>> if (a->struct_type == RESERVED_BLOCKS) { >>>>>> spin_lock(&sbi->stat_lock); >>>>>> - if ((unsigned long)sbi->total_valid_block_count + t > >>>>>> - (unsigned long)sbi->user_block_count) { >>>>>> - spin_unlock(&sbi->stat_lock); >>>>>> - return -EINVAL; >>>>>> - } >>>>>> *ui = t; >>>>>> + sbi->cur_reserved_blocks = min(t, sbi->user_block_count - >>>>>> + sbi->total_valid_block_count); >>>>>> spin_unlock(&sbi->stat_lock); >>>>>> return count; >>>>>> } >>>>>> @@ -274,6 +277,7 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a, >>>>>> #endif >>>>>> F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes); >>>>>> F2FS_GENERAL_RO_ATTR(features); >>>>>> +F2FS_GENERAL_RO_ATTR(cur_reserved_blocks); >>>>>> >>>>>> #ifdef CONFIG_F2FS_FS_ENCRYPTION >>>>>> F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO); >>>>>> @@ -317,6 +321,7 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a, >>>>>> ATTR_LIST(lifetime_write_kbytes), >>>>>> ATTR_LIST(features), >>>>>> ATTR_LIST(reserved_blocks), >>>>>> + ATTR_LIST(cur_reserved_blocks), >>>>>> NULL, >>>>>> }; >>>>>> >>>>>> >>>>> . >>>>> >>> . >>> > > . >
diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs index 11b7f4e..bdbb9f3 100644 --- a/Documentation/ABI/testing/sysfs-fs-f2fs +++ b/Documentation/ABI/testing/sysfs-fs-f2fs @@ -151,3 +151,9 @@ Date: August 2017 Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> Description: Controls sleep time of GC urgent mode + +What: /sys/fs/f2fs/<disk>/cur_reserved_blocks +Date: August 2017 +Contact: "Yunlong Song" <yunlong.song@huawei.com> +Description: + Shows current reserved blocks in system. diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index cea329f..3b7056f 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1040,6 +1040,7 @@ struct f2fs_sb_info { block_t discard_blks; /* discard command candidats */ block_t last_valid_block_count; /* for recovery */ block_t reserved_blocks; /* configurable reserved blocks */ + block_t cur_reserved_blocks; /* current reserved blocks */ u32 s_next_generation; /* for NFS support */ @@ -1514,7 +1515,7 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, spin_lock(&sbi->stat_lock); sbi->total_valid_block_count += (block_t)(*count); - avail_user_block_count = sbi->user_block_count - sbi->reserved_blocks; + avail_user_block_count = sbi->user_block_count - sbi->cur_reserved_blocks; if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) { diff = sbi->total_valid_block_count - avail_user_block_count; *count -= diff; @@ -1548,6 +1549,8 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi, f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count); f2fs_bug_on(sbi, inode->i_blocks < sectors); sbi->total_valid_block_count -= (block_t)count; + sbi->cur_reserved_blocks = min(sbi->reserved_blocks, + sbi->cur_reserved_blocks + count); spin_unlock(&sbi->stat_lock); f2fs_i_blocks_write(inode, count, false, true); } @@ -1694,7 +1697,7 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, spin_lock(&sbi->stat_lock); valid_block_count = sbi->total_valid_block_count + 1; - if (unlikely(valid_block_count + sbi->reserved_blocks > + if (unlikely(valid_block_count + sbi->cur_reserved_blocks > sbi->user_block_count)) { spin_unlock(&sbi->stat_lock); goto enospc; @@ -1737,6 +1740,8 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi, sbi->total_valid_node_count--; sbi->total_valid_block_count--; + sbi->cur_reserved_blocks = min(sbi->reserved_blocks, + sbi->cur_reserved_blocks + 1); spin_unlock(&sbi->stat_lock); diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 4c1bdcb..2934aa2 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -957,7 +957,7 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_blocks = total_count - start_count; buf->f_bfree = user_block_count - valid_user_blocks(sbi) + ovp_count; buf->f_bavail = user_block_count - valid_user_blocks(sbi) - - sbi->reserved_blocks; + sbi->cur_reserved_blocks; avail_node_count = sbi->total_node_count - F2FS_RESERVED_NODE_NUM; @@ -2411,6 +2411,8 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent) le64_to_cpu(sbi->ckpt->valid_block_count); sbi->last_valid_block_count = sbi->total_valid_block_count; sbi->reserved_blocks = 0; + sbi->cur_reserved_blocks = min(sbi->reserved_blocks, + sbi->user_block_count - sbi->total_valid_block_count); for (i = 0; i < NR_INODE_TYPE; i++) { INIT_LIST_HEAD(&sbi->inode_list[i]); diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index b769a3d..405c13f 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -76,6 +76,12 @@ static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a, BD_PART_WRITTEN(sbi))); } +static ssize_t cur_reserved_blocks_show(struct f2fs_attr *a, + struct f2fs_sb_info *sbi, char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%u\n", sbi->cur_reserved_blocks); +} + static ssize_t features_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { @@ -143,12 +149,9 @@ static ssize_t f2fs_sbi_store(struct f2fs_attr *a, #endif if (a->struct_type == RESERVED_BLOCKS) { spin_lock(&sbi->stat_lock); - if ((unsigned long)sbi->total_valid_block_count + t > - (unsigned long)sbi->user_block_count) { - spin_unlock(&sbi->stat_lock); - return -EINVAL; - } *ui = t; + sbi->cur_reserved_blocks = min(t, sbi->user_block_count - + sbi->total_valid_block_count); spin_unlock(&sbi->stat_lock); return count; } @@ -274,6 +277,7 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a, #endif F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes); F2FS_GENERAL_RO_ATTR(features); +F2FS_GENERAL_RO_ATTR(cur_reserved_blocks); #ifdef CONFIG_F2FS_FS_ENCRYPTION F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO); @@ -317,6 +321,7 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a, ATTR_LIST(lifetime_write_kbytes), ATTR_LIST(features), ATTR_LIST(reserved_blocks), + ATTR_LIST(cur_reserved_blocks), NULL, };
In this patch, we add a new sysfs interface, we can use it to gradually achieve the reserved_blocks finally, even when reserved_blocks is initially set over user_block_count - total_valid_block_count. This is very useful, especially when we upgrade kernel with new reserved_blocks value, but old disk image unluckily has user_block_count - total_valid_block_count smaller than the desired reserved_blocks. With this patch, f2fs can try its best to reserve space and get close to the reserved_blocks, and the current value of achieved reserved_blocks can be shown in real time. Signed-off-by: Yunlong Song <yunlong.song@huawei.com> --- Documentation/ABI/testing/sysfs-fs-f2fs | 6 ++++++ fs/f2fs/f2fs.h | 9 +++++++-- fs/f2fs/super.c | 4 +++- fs/f2fs/sysfs.c | 15 ++++++++++----- 4 files changed, 26 insertions(+), 8 deletions(-)