| Message ID | 20170329204815.9175-1-jaegeuk@kernel.org (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
Hi Jaegeuk, On 2017/3/30 4:48, Jaegeuk Kim wrote: > It would better split small and large IOs separately in order to get more > consecutive big writes. > > The default threshold is set to 64KB, but configurable by sysfs/min_hot_blocks. > > Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org> > --- > fs/f2fs/data.c | 9 +++++++++ > fs/f2fs/f2fs.h | 2 ++ > fs/f2fs/segment.c | 13 ++++++------- > fs/f2fs/segment.h | 1 + > fs/f2fs/super.c | 2 ++ > 5 files changed, 20 insertions(+), 7 deletions(-) > > diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c > index 090413236b27..8f36080b47c4 100644 > --- a/fs/f2fs/data.c > +++ b/fs/f2fs/data.c > @@ -1432,6 +1432,8 @@ static int __write_data_page(struct page *page, bool *submitted, > need_balance_fs = true; > else if (has_not_enough_free_secs(sbi, 0, 0)) > goto redirty_out; > + else > + set_inode_flag(inode, FI_HOT_DATA); Why here we need this, can you explain more about this? Thanks. > > err = -EAGAIN; > if (f2fs_has_inline_data(inode)) { > @@ -1457,6 +1459,7 @@ static int __write_data_page(struct page *page, bool *submitted, > if (wbc->for_reclaim) { > f2fs_submit_merged_bio_cond(sbi, inode, 0, page->index, > DATA, WRITE); > + clear_inode_flag(inode, FI_HOT_DATA); > remove_dirty_inode(inode); > submitted = NULL; > } > @@ -1511,6 +1514,12 @@ static int f2fs_write_cache_pages(struct address_space *mapping, > > pagevec_init(&pvec, 0); > > + if (get_dirty_pages(mapping->host) <= > + SM_I(F2FS_M_SB(mapping))->min_hot_blocks) > + set_inode_flag(mapping->host, FI_HOT_DATA); > + else > + clear_inode_flag(mapping->host, FI_HOT_DATA); > + > if (wbc->range_cyclic) { > writeback_index = mapping->writeback_index; /* prev offset */ > index = writeback_index; > diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h > index 5a49518ee786..32d6f674c114 100644 > --- a/fs/f2fs/f2fs.h > +++ b/fs/f2fs/f2fs.h > @@ -678,6 +678,7 @@ struct f2fs_sm_info { > unsigned int ipu_policy; /* in-place-update policy */ > unsigned int min_ipu_util; /* in-place-update threshold */ > unsigned int min_fsync_blocks; /* threshold for fsync */ > + unsigned int min_hot_blocks; /* threshold for hot block allocation */ > > /* for flush command control */ > struct flush_cmd_control *fcc_info; > @@ -1717,6 +1718,7 @@ enum { > FI_DO_DEFRAG, /* indicate defragment is running */ > FI_DIRTY_FILE, /* indicate regular/symlink has dirty pages */ > FI_NO_PREALLOC, /* indicate skipped preallocated blocks */ > + FI_HOT_DATA, /* indicate file is hot */ > }; > > static inline void __mark_inode_dirty_flag(struct inode *inode, > diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c > index b5b2a4745328..bff3f3bc7827 100644 > --- a/fs/f2fs/segment.c > +++ b/fs/f2fs/segment.c > @@ -1841,18 +1841,16 @@ static int __get_segment_type_6(struct page *page, enum page_type p_type) > if (p_type == DATA) { > struct inode *inode = page->mapping->host; > > - if (S_ISDIR(inode->i_mode)) > - return CURSEG_HOT_DATA; > - else if (is_cold_data(page) || file_is_cold(inode)) > + if (is_cold_data(page) || file_is_cold(inode)) > return CURSEG_COLD_DATA; > - else > - return CURSEG_WARM_DATA; > + if (is_inode_flag_set(inode, FI_HOT_DATA)) > + return CURSEG_HOT_DATA; > + return CURSEG_WARM_DATA; > } else { > if (IS_DNODE(page)) > return is_cold_node(page) ? CURSEG_WARM_NODE : > CURSEG_HOT_NODE; > - else > - return CURSEG_COLD_NODE; > + return CURSEG_COLD_NODE; > } > } > > @@ -2959,6 +2957,7 @@ int build_segment_manager(struct f2fs_sb_info *sbi) > sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC; > sm_info->min_ipu_util = DEF_MIN_IPU_UTIL; > sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS; > + sm_info->min_hot_blocks = DEF_MIN_HOT_BLOCKS; > > sm_info->trim_sections = DEF_BATCHED_TRIM_SECTIONS; > > diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h > index 31846b0fcb95..57e36c1ce7bd 100644 > --- a/fs/f2fs/segment.h > +++ b/fs/f2fs/segment.h > @@ -540,6 +540,7 @@ static inline int utilization(struct f2fs_sb_info *sbi) > */ > #define DEF_MIN_IPU_UTIL 70 > #define DEF_MIN_FSYNC_BLOCKS 8 > +#define DEF_MIN_HOT_BLOCKS 16 > > enum { > F2FS_IPU_FORCE, > diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c > index b4c5c6298698..2d78f3c76d18 100644 > --- a/fs/f2fs/super.c > +++ b/fs/f2fs/super.c > @@ -296,6 +296,7 @@ F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, batched_trim_sections, trim_sections); > F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy); > F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util); > F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks); > +F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_hot_blocks, min_hot_blocks); > 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); > @@ -321,6 +322,7 @@ static struct attribute *f2fs_attrs[] = { > ATTR_LIST(ipu_policy), > ATTR_LIST(min_ipu_util), > ATTR_LIST(min_fsync_blocks), > + ATTR_LIST(min_hot_blocks), > ATTR_LIST(max_victim_search), > ATTR_LIST(dir_level), > ATTR_LIST(ram_thresh), >
On 03/31, heyunlei wrote: > Hi Jaegeuk, > > On 2017/3/30 4:48, Jaegeuk Kim wrote: > > It would better split small and large IOs separately in order to get more > > consecutive big writes. > > > > The default threshold is set to 64KB, but configurable by sysfs/min_hot_blocks. > > > > Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org> > > --- > > fs/f2fs/data.c | 9 +++++++++ > > fs/f2fs/f2fs.h | 2 ++ > > fs/f2fs/segment.c | 13 ++++++------- > > fs/f2fs/segment.h | 1 + > > fs/f2fs/super.c | 2 ++ > > 5 files changed, 20 insertions(+), 7 deletions(-) > > > > diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c > > index 090413236b27..8f36080b47c4 100644 > > --- a/fs/f2fs/data.c > > +++ b/fs/f2fs/data.c > > @@ -1432,6 +1432,8 @@ static int __write_data_page(struct page *page, bool *submitted, > > need_balance_fs = true; > > else if (has_not_enough_free_secs(sbi, 0, 0)) > > goto redirty_out; > > + else > > + set_inode_flag(inode, FI_HOT_DATA); > > Why here we need this, can you explain more about this? I fixed this. Please refer the up-to-date patch that I've been testing. https://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs.git/commit/?h=dev-test&id=6976ab59090395014368296f154426c9311d69dc https://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs.git/commit/?h=dev-test&id=65f770f2ead7dfdf661b2da49af1aa814b662c93 Thanks, > > Thanks. > > > > > err = -EAGAIN; > > if (f2fs_has_inline_data(inode)) { > > @@ -1457,6 +1459,7 @@ static int __write_data_page(struct page *page, bool *submitted, > > if (wbc->for_reclaim) { > > f2fs_submit_merged_bio_cond(sbi, inode, 0, page->index, > > DATA, WRITE); > > + clear_inode_flag(inode, FI_HOT_DATA); > > remove_dirty_inode(inode); > > submitted = NULL; > > } > > @@ -1511,6 +1514,12 @@ static int f2fs_write_cache_pages(struct address_space *mapping, > > > > pagevec_init(&pvec, 0); > > > > + if (get_dirty_pages(mapping->host) <= > > + SM_I(F2FS_M_SB(mapping))->min_hot_blocks) > > + set_inode_flag(mapping->host, FI_HOT_DATA); > > + else > > + clear_inode_flag(mapping->host, FI_HOT_DATA); > > + > > if (wbc->range_cyclic) { > > writeback_index = mapping->writeback_index; /* prev offset */ > > index = writeback_index; > > diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h > > index 5a49518ee786..32d6f674c114 100644 > > --- a/fs/f2fs/f2fs.h > > +++ b/fs/f2fs/f2fs.h > > @@ -678,6 +678,7 @@ struct f2fs_sm_info { > > unsigned int ipu_policy; /* in-place-update policy */ > > unsigned int min_ipu_util; /* in-place-update threshold */ > > unsigned int min_fsync_blocks; /* threshold for fsync */ > > + unsigned int min_hot_blocks; /* threshold for hot block allocation */ > > > > /* for flush command control */ > > struct flush_cmd_control *fcc_info; > > @@ -1717,6 +1718,7 @@ enum { > > FI_DO_DEFRAG, /* indicate defragment is running */ > > FI_DIRTY_FILE, /* indicate regular/symlink has dirty pages */ > > FI_NO_PREALLOC, /* indicate skipped preallocated blocks */ > > + FI_HOT_DATA, /* indicate file is hot */ > > }; > > > > static inline void __mark_inode_dirty_flag(struct inode *inode, > > diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c > > index b5b2a4745328..bff3f3bc7827 100644 > > --- a/fs/f2fs/segment.c > > +++ b/fs/f2fs/segment.c > > @@ -1841,18 +1841,16 @@ static int __get_segment_type_6(struct page *page, enum page_type p_type) > > if (p_type == DATA) { > > struct inode *inode = page->mapping->host; > > > > - if (S_ISDIR(inode->i_mode)) > > - return CURSEG_HOT_DATA; > > - else if (is_cold_data(page) || file_is_cold(inode)) > > + if (is_cold_data(page) || file_is_cold(inode)) > > return CURSEG_COLD_DATA; > > - else > > - return CURSEG_WARM_DATA; > > + if (is_inode_flag_set(inode, FI_HOT_DATA)) > > + return CURSEG_HOT_DATA; > > + return CURSEG_WARM_DATA; > > } else { > > if (IS_DNODE(page)) > > return is_cold_node(page) ? CURSEG_WARM_NODE : > > CURSEG_HOT_NODE; > > - else > > - return CURSEG_COLD_NODE; > > + return CURSEG_COLD_NODE; > > } > > } > > > > @@ -2959,6 +2957,7 @@ int build_segment_manager(struct f2fs_sb_info *sbi) > > sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC; > > sm_info->min_ipu_util = DEF_MIN_IPU_UTIL; > > sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS; > > + sm_info->min_hot_blocks = DEF_MIN_HOT_BLOCKS; > > > > sm_info->trim_sections = DEF_BATCHED_TRIM_SECTIONS; > > > > diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h > > index 31846b0fcb95..57e36c1ce7bd 100644 > > --- a/fs/f2fs/segment.h > > +++ b/fs/f2fs/segment.h > > @@ -540,6 +540,7 @@ static inline int utilization(struct f2fs_sb_info *sbi) > > */ > > #define DEF_MIN_IPU_UTIL 70 > > #define DEF_MIN_FSYNC_BLOCKS 8 > > +#define DEF_MIN_HOT_BLOCKS 16 > > > > enum { > > F2FS_IPU_FORCE, > > diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c > > index b4c5c6298698..2d78f3c76d18 100644 > > --- a/fs/f2fs/super.c > > +++ b/fs/f2fs/super.c > > @@ -296,6 +296,7 @@ F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, batched_trim_sections, trim_sections); > > F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy); > > F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util); > > F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks); > > +F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_hot_blocks, min_hot_blocks); > > 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); > > @@ -321,6 +322,7 @@ static struct attribute *f2fs_attrs[] = { > > ATTR_LIST(ipu_policy), > > ATTR_LIST(min_ipu_util), > > ATTR_LIST(min_fsync_blocks), > > + ATTR_LIST(min_hot_blocks), > > ATTR_LIST(max_victim_search), > > ATTR_LIST(dir_level), > > ATTR_LIST(ram_thresh), > >
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 090413236b27..8f36080b47c4 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1432,6 +1432,8 @@ static int __write_data_page(struct page *page, bool *submitted, need_balance_fs = true; else if (has_not_enough_free_secs(sbi, 0, 0)) goto redirty_out; + else + set_inode_flag(inode, FI_HOT_DATA); err = -EAGAIN; if (f2fs_has_inline_data(inode)) { @@ -1457,6 +1459,7 @@ static int __write_data_page(struct page *page, bool *submitted, if (wbc->for_reclaim) { f2fs_submit_merged_bio_cond(sbi, inode, 0, page->index, DATA, WRITE); + clear_inode_flag(inode, FI_HOT_DATA); remove_dirty_inode(inode); submitted = NULL; } @@ -1511,6 +1514,12 @@ static int f2fs_write_cache_pages(struct address_space *mapping, pagevec_init(&pvec, 0); + if (get_dirty_pages(mapping->host) <= + SM_I(F2FS_M_SB(mapping))->min_hot_blocks) + set_inode_flag(mapping->host, FI_HOT_DATA); + else + clear_inode_flag(mapping->host, FI_HOT_DATA); + if (wbc->range_cyclic) { writeback_index = mapping->writeback_index; /* prev offset */ index = writeback_index; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 5a49518ee786..32d6f674c114 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -678,6 +678,7 @@ struct f2fs_sm_info { unsigned int ipu_policy; /* in-place-update policy */ unsigned int min_ipu_util; /* in-place-update threshold */ unsigned int min_fsync_blocks; /* threshold for fsync */ + unsigned int min_hot_blocks; /* threshold for hot block allocation */ /* for flush command control */ struct flush_cmd_control *fcc_info; @@ -1717,6 +1718,7 @@ enum { FI_DO_DEFRAG, /* indicate defragment is running */ FI_DIRTY_FILE, /* indicate regular/symlink has dirty pages */ FI_NO_PREALLOC, /* indicate skipped preallocated blocks */ + FI_HOT_DATA, /* indicate file is hot */ }; static inline void __mark_inode_dirty_flag(struct inode *inode, diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index b5b2a4745328..bff3f3bc7827 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -1841,18 +1841,16 @@ static int __get_segment_type_6(struct page *page, enum page_type p_type) if (p_type == DATA) { struct inode *inode = page->mapping->host; - if (S_ISDIR(inode->i_mode)) - return CURSEG_HOT_DATA; - else if (is_cold_data(page) || file_is_cold(inode)) + if (is_cold_data(page) || file_is_cold(inode)) return CURSEG_COLD_DATA; - else - return CURSEG_WARM_DATA; + if (is_inode_flag_set(inode, FI_HOT_DATA)) + return CURSEG_HOT_DATA; + return CURSEG_WARM_DATA; } else { if (IS_DNODE(page)) return is_cold_node(page) ? CURSEG_WARM_NODE : CURSEG_HOT_NODE; - else - return CURSEG_COLD_NODE; + return CURSEG_COLD_NODE; } } @@ -2959,6 +2957,7 @@ int build_segment_manager(struct f2fs_sb_info *sbi) sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC; sm_info->min_ipu_util = DEF_MIN_IPU_UTIL; sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS; + sm_info->min_hot_blocks = DEF_MIN_HOT_BLOCKS; sm_info->trim_sections = DEF_BATCHED_TRIM_SECTIONS; diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 31846b0fcb95..57e36c1ce7bd 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -540,6 +540,7 @@ static inline int utilization(struct f2fs_sb_info *sbi) */ #define DEF_MIN_IPU_UTIL 70 #define DEF_MIN_FSYNC_BLOCKS 8 +#define DEF_MIN_HOT_BLOCKS 16 enum { F2FS_IPU_FORCE, diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index b4c5c6298698..2d78f3c76d18 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -296,6 +296,7 @@ F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, batched_trim_sections, trim_sections); F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy); F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util); F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks); +F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_hot_blocks, min_hot_blocks); 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); @@ -321,6 +322,7 @@ static struct attribute *f2fs_attrs[] = { ATTR_LIST(ipu_policy), ATTR_LIST(min_ipu_util), ATTR_LIST(min_fsync_blocks), + ATTR_LIST(min_hot_blocks), ATTR_LIST(max_victim_search), ATTR_LIST(dir_level), ATTR_LIST(ram_thresh),
It would better split small and large IOs separately in order to get more consecutive big writes. The default threshold is set to 64KB, but configurable by sysfs/min_hot_blocks. Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org> --- fs/f2fs/data.c | 9 +++++++++ fs/f2fs/f2fs.h | 2 ++ fs/f2fs/segment.c | 13 ++++++------- fs/f2fs/segment.h | 1 + fs/f2fs/super.c | 2 ++ 5 files changed, 20 insertions(+), 7 deletions(-)