f2fs: introduce a batched trim
This patch introduces a batched trimming feature, which submits split discard
commands.
This is to avoid long latency due to huge trim commands.
If fstrim was triggered ranging from 0 to the end of device, we should lock
all the checkpoint-related mutexes, resulting in very long latency.
Reviewed-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index db1ff55..337204d 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -105,6 +105,10 @@
CP_DISCARD,
};
+#define DEF_BATCHED_TRIM_SECTIONS 32
+#define BATCHED_TRIM_SEGMENTS(sbi) \
+ (SM_I(sbi)->trim_sections * (sbi)->segs_per_sec)
+
struct cp_control {
int reason;
__u64 trim_start;
@@ -448,6 +452,9 @@
int nr_discards; /* # of discards in the list */
int max_discards; /* max. discards to be issued */
+ /* for batched trimming */
+ unsigned int trim_sections; /* # of sections to trim */
+
struct list_head sit_entry_set; /* sit entry set list */
unsigned int ipu_policy; /* in-place-update policy */
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 5ea57ec..9f278d1 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -1066,14 +1066,19 @@
end_segno = (end >= MAX_BLKADDR(sbi)) ? MAIN_SEGS(sbi) - 1 :
GET_SEGNO(sbi, end);
cpc.reason = CP_DISCARD;
- cpc.trim_start = start_segno;
- cpc.trim_end = end_segno;
cpc.trim_minlen = range->minlen >> sbi->log_blocksize;
/* do checkpoint to issue discard commands safely */
- mutex_lock(&sbi->gc_mutex);
- write_checkpoint(sbi, &cpc);
- mutex_unlock(&sbi->gc_mutex);
+ for (; start_segno <= end_segno; start_segno = cpc.trim_end + 1) {
+ cpc.trim_start = start_segno;
+ cpc.trim_end = min_t(unsigned int, rounddown(start_segno +
+ BATCHED_TRIM_SEGMENTS(sbi),
+ sbi->segs_per_sec) - 1, end_segno);
+
+ mutex_lock(&sbi->gc_mutex);
+ write_checkpoint(sbi, &cpc);
+ mutex_unlock(&sbi->gc_mutex);
+ }
out:
range->len = cpc.trimmed << sbi->log_blocksize;
return 0;
@@ -2127,6 +2132,8 @@
sm_info->nr_discards = 0;
sm_info->max_discards = 0;
+ sm_info->trim_sections = DEF_BATCHED_TRIM_SECTIONS;
+
INIT_LIST_HEAD(&sm_info->sit_entry_set);
if (test_opt(sbi, FLUSH_MERGE) && !f2fs_readonly(sbi->sb)) {
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 1e92c2e..f2fe666 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -195,6 +195,7 @@
F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_idle, gc_idle);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, max_small_discards, max_discards);
+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);
@@ -210,6 +211,7 @@
ATTR_LIST(gc_idle),
ATTR_LIST(reclaim_segments),
ATTR_LIST(max_small_discards),
+ ATTR_LIST(batched_trim_sections),
ATTR_LIST(ipu_policy),
ATTR_LIST(min_ipu_util),
ATTR_LIST(min_fsync_blocks),