| blob | b91e2f26b672451e687b73fb42f18bb2ebd21821 |
1 ================================================================================
2 WHAT IS Flash-Friendly File System (F2FS)?
3 ================================================================================
5 NAND flash memory-based storage devices, such as SSD, eMMC, and SD cards, have
6 been equipped on a variety systems ranging from mobile to server systems. Since
7 they are known to have different characteristics from the conventional rotating
8 disks, a file system, an upper layer to the storage device, should adapt to the
9 changes from the sketch in the design level.
11 F2FS is a file system exploiting NAND flash memory-based storage devices, which
12 is based on Log-structured File System (LFS). The design has been focused on
13 addressing the fundamental issues in LFS, which are snowball effect of wandering
14 tree and high cleaning overhead.
16 Since a NAND flash memory-based storage device shows different characteristic
17 according to its internal geometry or flash memory management scheme, namely FTL,
18 F2FS and its tools support various parameters not only for configuring on-disk
19 layout, but also for selecting allocation and cleaning algorithms.
21 The file system formatting tool, "mkfs.f2fs", is available from the following
22 git tree:
23 >> git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs-tools.git
25 For reporting bugs and sending patches, please use the following mailing list:
26 >> linux-f2fs-devel@lists.sourceforge.net
28 ================================================================================
29 BACKGROUND AND DESIGN ISSUES
30 ================================================================================
32 Log-structured File System (LFS)
33 --------------------------------
34 "A log-structured file system writes all modifications to disk sequentially in
35 a log-like structure, thereby speeding up both file writing and crash recovery.
36 The log is the only structure on disk; it contains indexing information so that
37 files can be read back from the log efficiently. In order to maintain large free
38 areas on disk for fast writing, we divide the log into segments and use a
39 segment cleaner to compress the live information from heavily fragmented
40 segments." from Rosenblum, M. and Ousterhout, J. K., 1992, "The design and
41 implementation of a log-structured file system", ACM Trans. Computer Systems
42 10, 1, 26–52.
44 Wandering Tree Problem
45 ----------------------
46 In LFS, when a file data is updated and written to the end of log, its direct
47 pointer block is updated due to the changed location. Then the indirect pointer
48 block is also updated due to the direct pointer block update. In this manner,
49 the upper index structures such as inode, inode map, and checkpoint block are
50 also updated recursively. This problem is called as wandering tree problem [1],
51 and in order to enhance the performance, it should eliminate or relax the update
52 propagation as much as possible.
54 [1] Bityutskiy, A. 2005. JFFS3 design issues. http://www.linux-mtd.infradead.org/
56 Cleaning Overhead
57 -----------------
58 Since LFS is based on out-of-place writes, it produces so many obsolete blocks
59 scattered across the whole storage. In order to serve new empty log space, it
60 needs to reclaim these obsolete blocks seamlessly to users. This job is called
61 as a cleaning process.
63 The process consists of three operations as follows.
64 1. A victim segment is selected through referencing segment usage table.
65 2. It loads parent index structures of all the data in the victim identified by
66 segment summary blocks.
67 3. It checks the cross-reference between the data and its parent index structure.
68 4. It moves valid data selectively.
70 This cleaning job may cause unexpected long delays, so the most important goal
71 is to hide the latencies to users. And also definitely, it should reduce the
72 amount of valid data to be moved, and move them quickly as well.
74 ================================================================================
75 KEY FEATURES
76 ================================================================================
78 Flash Awareness
79 ---------------
80 - Enlarge the random write area for better performance, but provide the high
81 spatial locality
82 - Align FS data structures to the operational units in FTL as best efforts
84 Wandering Tree Problem
85 ----------------------
86 - Use a term, “node”, that represents inodes as well as various pointer blocks
87 - Introduce Node Address Table (NAT) containing the locations of all the “node”
88 blocks; this will cut off the update propagation.
90 Cleaning Overhead
91 -----------------
92 - Support a background cleaning process
93 - Support greedy and cost-benefit algorithms for victim selection policies
94 - Support multi-head logs for static/dynamic hot and cold data separation
95 - Introduce adaptive logging for efficient block allocation
97 ================================================================================
98 MOUNT OPTIONS
99 ================================================================================
101 background_gc=%s Turn on/off cleaning operations, namely garbage
102 collection, triggered in background when I/O subsystem is
103 idle. If background_gc=on, it will turn on the garbage
104 collection and if background_gc=off, garbage collection
105 will be truned off.
106 Default value for this option is on. So garbage
107 collection is on by default.
108 disable_roll_forward Disable the roll-forward recovery routine
109 discard Issue discard/TRIM commands when a segment is cleaned.
110 no_heap Disable heap-style segment allocation which finds free
111 segments for data from the beginning of main area, while
112 for node from the end of main area.
113 nouser_xattr Disable Extended User Attributes. Note: xattr is enabled
114 by default if CONFIG_F2FS_FS_XATTR is selected.
115 noacl Disable POSIX Access Control List. Note: acl is enabled
116 by default if CONFIG_F2FS_FS_POSIX_ACL is selected.
117 active_logs=%u Support configuring the number of active logs. In the
118 current design, f2fs supports only 2, 4, and 6 logs.
119 Default number is 6.
120 disable_ext_identify Disable the extension list configured by mkfs, so f2fs
121 does not aware of cold files such as media files.
123 ================================================================================
124 DEBUGFS ENTRIES
125 ================================================================================
127 /sys/kernel/debug/f2fs/ contains information about all the partitions mounted as
128 f2fs. Each file shows the whole f2fs information.
130 /sys/kernel/debug/f2fs/status includes:
131 - major file system information managed by f2fs currently
132 - average SIT information about whole segments
133 - current memory footprint consumed by f2fs.
135 ================================================================================
136 USAGE
137 ================================================================================
139 1. Download userland tools and compile them.
141 2. Skip, if f2fs was compiled statically inside kernel.
142 Otherwise, insert the f2fs.ko module.
143 # insmod f2fs.ko
145 3. Create a directory trying to mount
146 # mkdir /mnt/f2fs
148 4. Format the block device, and then mount as f2fs
149 # mkfs.f2fs -l label /dev/block_device
150 # mount -t f2fs /dev/block_device /mnt/f2fs
152 Format options
153 --------------
154 -l [label] : Give a volume label, up to 512 unicode name.
155 -a [0 or 1] : Split start location of each area for heap-based allocation.
156 1 is set by default, which performs this.
157 -o [int] : Set overprovision ratio in percent over volume size.
158 5 is set by default.
159 -s [int] : Set the number of segments per section.
160 1 is set by default.
161 -z [int] : Set the number of sections per zone.
162 1 is set by default.
163 -e [str] : Set basic extension list. e.g. "mp3,gif,mov"
164 -t [0 or 1] : Disable discard command or not.
165 1 is set by default, which conducts discard.
167 ================================================================================
168 DESIGN
169 ================================================================================
171 On-disk Layout
172 --------------
174 F2FS divides the whole volume into a number of segments, each of which is fixed
175 to 2MB in size. A section is composed of consecutive segments, and a zone
176 consists of a set of sections. By default, section and zone sizes are set to one
177 segment size identically, but users can easily modify the sizes by mkfs.
179 F2FS splits the entire volume into six areas, and all the areas except superblock
180 consists of multiple segments as described below.
182 align with the zone size <-|
183 |-> align with the segment size
184 _________________________________________________________________________
185 | | | Segment | Node | Segment | |
186 | Superblock | Checkpoint | Info. | Address | Summary | Main |
187 | (SB) | (CP) | Table (SIT) | Table (NAT) | Area (SSA) | |
188 |____________|_____2______|______N______|______N______|______N_____|__N___|
189 . .
190 . .
191 . .
192 ._________________________________________.
193 |_Segment_|_..._|_Segment_|_..._|_Segment_|
194 . .
195 ._________._________
196 |_section_|__...__|_
197 . .
198 .________.
199 |__zone__|
201 - Superblock (SB)
202 : It is located at the beginning of the partition, and there exist two copies
203 to avoid file system crash. It contains basic partition information and some
204 default parameters of f2fs.
206 - Checkpoint (CP)
207 : It contains file system information, bitmaps for valid NAT/SIT sets, orphan
208 inode lists, and summary entries of current active segments.
210 - Segment Information Table (SIT)
211 : It contains segment information such as valid block count and bitmap for the
212 validity of all the blocks.
214 - Node Address Table (NAT)
215 : It is composed of a block address table for all the node blocks stored in
216 Main area.
218 - Segment Summary Area (SSA)
219 : It contains summary entries which contains the owner information of all the
220 data and node blocks stored in Main area.
222 - Main Area
223 : It contains file and directory data including their indices.
225 In order to avoid misalignment between file system and flash-based storage, F2FS
226 aligns the start block address of CP with the segment size. Also, it aligns the
227 start block address of Main area with the zone size by reserving some segments
228 in SSA area.
230 Reference the following survey for additional technical details.
231 https://wiki.linaro.org/WorkingGroups/Kernel/Projects/FlashCardSurvey
233 File System Metadata Structure
234 ------------------------------
236 F2FS adopts the checkpointing scheme to maintain file system consistency. At
237 mount time, F2FS first tries to find the last valid checkpoint data by scanning
238 CP area. In order to reduce the scanning time, F2FS uses only two copies of CP.
239 One of them always indicates the last valid data, which is called as shadow copy
240 mechanism. In addition to CP, NAT and SIT also adopt the shadow copy mechanism.
242 For file system consistency, each CP points to which NAT and SIT copies are
243 valid, as shown as below.
245 +--------+----------+---------+
246 | CP | SIT | NAT |
247 +--------+----------+---------+
248 . . . .
249 . . . .
250 . . . .
251 +-------+-------+--------+--------+--------+--------+
252 | CP #0 | CP #1 | SIT #0 | SIT #1 | NAT #0 | NAT #1 |
253 +-------+-------+--------+--------+--------+--------+
254 | ^ ^
255 | | |
256 `----------------------------------------'
258 Index Structure
259 ---------------
261 The key data structure to manage the data locations is a "node". Similar to
262 traditional file structures, F2FS has three types of node: inode, direct node,
263 indirect node. F2FS assigns 4KB to an inode block which contains 923 data block
264 indices, two direct node pointers, two indirect node pointers, and one double
265 indirect node pointer as described below. One direct node block contains 1018
266 data blocks, and one indirect node block contains also 1018 node blocks. Thus,
267 one inode block (i.e., a file) covers:
269 4KB * (923 + 2 * 1018 + 2 * 1018 * 1018 + 1018 * 1018 * 1018) := 3.94TB.
271 Inode block (4KB)
272 |- data (923)
273 |- direct node (2)
274 | `- data (1018)
275 |- indirect node (2)
276 | `- direct node (1018)
277 | `- data (1018)
278 `- double indirect node (1)
279 `- indirect node (1018)
280 `- direct node (1018)
281 `- data (1018)
283 Note that, all the node blocks are mapped by NAT which means the location of
284 each node is translated by the NAT table. In the consideration of the wandering
285 tree problem, F2FS is able to cut off the propagation of node updates caused by
286 leaf data writes.
288 Directory Structure
289 -------------------
291 A directory entry occupies 11 bytes, which consists of the following attributes.
293 - hash hash value of the file name
294 - ino inode number
295 - len the length of file name
296 - type file type such as directory, symlink, etc
298 A dentry block consists of 214 dentry slots and file names. Therein a bitmap is
299 used to represent whether each dentry is valid or not. A dentry block occupies
300 4KB with the following composition.
302 Dentry Block(4 K) = bitmap (27 bytes) + reserved (3 bytes) +
303 dentries(11 * 214 bytes) + file name (8 * 214 bytes)
305 [Bucket]
306 +--------------------------------+
307 |dentry block 1 | dentry block 2 |
308 +--------------------------------+
309 . .
310 . .
311 . [Dentry Block Structure: 4KB] .
312 +--------+----------+----------+------------+
313 | bitmap | reserved | dentries | file names |
314 +--------+----------+----------+------------+
315 [Dentry Block: 4KB] . .
316 . .
317 . .
318 +------+------+-----+------+
319 | hash | ino | len | type |
320 +------+------+-----+------+
321 [Dentry Structure: 11 bytes]
323 F2FS implements multi-level hash tables for directory structure. Each level has
324 a hash table with dedicated number of hash buckets as shown below. Note that
325 "A(2B)" means a bucket includes 2 data blocks.
327 ----------------------
328 A : bucket
329 B : block
330 N : MAX_DIR_HASH_DEPTH
331 ----------------------
333 level #0 | A(2B)
334 |
335 level #1 | A(2B) - A(2B)
336 |
337 level #2 | A(2B) - A(2B) - A(2B) - A(2B)
338 . | . . . .
339 level #N/2 | A(2B) - A(2B) - A(2B) - A(2B) - A(2B) - ... - A(2B)
340 . | . . . .
341 level #N | A(4B) - A(4B) - A(4B) - A(4B) - A(4B) - ... - A(4B)
343 The number of blocks and buckets are determined by,
345 ,- 2, if n < MAX_DIR_HASH_DEPTH / 2,
346 # of blocks in level #n = |
347 `- 4, Otherwise
349 ,- 2^n, if n < MAX_DIR_HASH_DEPTH / 2,
350 # of buckets in level #n = |
351 `- 2^((MAX_DIR_HASH_DEPTH / 2) - 1), Otherwise
353 When F2FS finds a file name in a directory, at first a hash value of the file
354 name is calculated. Then, F2FS scans the hash table in level #0 to find the
355 dentry consisting of the file name and its inode number. If not found, F2FS
356 scans the next hash table in level #1. In this way, F2FS scans hash tables in
357 each levels incrementally from 1 to N. In each levels F2FS needs to scan only
358 one bucket determined by the following equation, which shows O(log(# of files))
359 complexity.
361 bucket number to scan in level #n = (hash value) % (# of buckets in level #n)
363 In the case of file creation, F2FS finds empty consecutive slots that cover the
364 file name. F2FS searches the empty slots in the hash tables of whole levels from
365 1 to N in the same way as the lookup operation.
367 The following figure shows an example of two cases holding children.
368 --------------> Dir <--------------
369 | |
370 child child
372 child - child [hole] - child
374 child - child - child [hole] - [hole] - child
376 Case 1: Case 2:
377 Number of children = 6, Number of children = 3,
378 File size = 7 File size = 7
380 Default Block Allocation
381 ------------------------
383 At runtime, F2FS manages six active logs inside "Main" area: Hot/Warm/Cold node
384 and Hot/Warm/Cold data.
386 - Hot node contains direct node blocks of directories.
387 - Warm node contains direct node blocks except hot node blocks.
388 - Cold node contains indirect node blocks
389 - Hot data contains dentry blocks
390 - Warm data contains data blocks except hot and cold data blocks
391 - Cold data contains multimedia data or migrated data blocks
393 LFS has two schemes for free space management: threaded log and copy-and-compac-
394 tion. The copy-and-compaction scheme which is known as cleaning, is well-suited
395 for devices showing very good sequential write performance, since free segments
396 are served all the time for writing new data. However, it suffers from cleaning
397 overhead under high utilization. Contrarily, the threaded log scheme suffers
398 from random writes, but no cleaning process is needed. F2FS adopts a hybrid
399 scheme where the copy-and-compaction scheme is adopted by default, but the
400 policy is dynamically changed to the threaded log scheme according to the file
401 system status.
403 In order to align F2FS with underlying flash-based storage, F2FS allocates a
404 segment in a unit of section. F2FS expects that the section size would be the
405 same as the unit size of garbage collection in FTL. Furthermore, with respect
406 to the mapping granularity in FTL, F2FS allocates each section of the active
407 logs from different zones as much as possible, since FTL can write the data in
408 the active logs into one allocation unit according to its mapping granularity.
410 Cleaning process
411 ----------------
413 F2FS does cleaning both on demand and in the background. On-demand cleaning is
414 triggered when there are not enough free segments to serve VFS calls. Background
415 cleaner is operated by a kernel thread, and triggers the cleaning job when the
416 system is idle.
418 F2FS supports two victim selection policies: greedy and cost-benefit algorithms.
419 In the greedy algorithm, F2FS selects a victim segment having the smallest number
420 of valid blocks. In the cost-benefit algorithm, F2FS selects a victim segment
421 according to the segment age and the number of valid blocks in order to address
422 log block thrashing problem in the greedy algorithm. F2FS adopts the greedy
423 algorithm for on-demand cleaner, while background cleaner adopts cost-benefit
424 algorithm.
426 In order to identify whether the data in the victim segment are valid or not,
427 F2FS manages a bitmap. Each bit represents the validity of a block, and the
428 bitmap is composed of a bit stream covering whole blocks in main area.