1What: /sys/fs/f2fs/<disk>/gc_max_sleep_time 2Date: July 2013 3Contact: "Namjae Jeon" <namjae.jeon@samsung.com> 4Description: Controls the maximum sleep time for gc_thread. Time 5 is in milliseconds. 6 7What: /sys/fs/f2fs/<disk>/gc_min_sleep_time 8Date: July 2013 9Contact: "Namjae Jeon" <namjae.jeon@samsung.com> 10Description: Controls the minimum sleep time for gc_thread. Time 11 is in milliseconds. 12 13What: /sys/fs/f2fs/<disk>/gc_no_gc_sleep_time 14Date: July 2013 15Contact: "Namjae Jeon" <namjae.jeon@samsung.com> 16Description: Controls the default sleep time for gc_thread. Time 17 is in milliseconds. 18 19What: /sys/fs/f2fs/<disk>/gc_idle 20Date: July 2013 21Contact: "Namjae Jeon" <namjae.jeon@samsung.com> 22Description: Controls the victim selection policy for garbage collection. 23 Setting gc_idle = 0(default) will disable this option. Setting: 24 25 =========== =============================================== 26 gc_idle = 1 will select the Cost Benefit approach & setting 27 gc_idle = 2 will select the greedy approach & setting 28 gc_idle = 3 will select the age-threshold based approach. 29 =========== =============================================== 30 31What: /sys/fs/f2fs/<disk>/reclaim_segments 32Date: October 2013 33Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com> 34Description: This parameter controls the number of prefree segments to be 35 reclaimed. If the number of prefree segments is larger than 36 the number of segments in the proportion to the percentage 37 over total volume size, f2fs tries to conduct checkpoint to 38 reclaim the prefree segments to free segments. 39 By default, 5% over total # of segments. 40 41What: /sys/fs/f2fs/<disk>/main_blkaddr 42Date: November 2019 43Contact: "Ramon Pantin" <pantin@google.com> 44Description: Shows first block address of MAIN area. 45 46What: /sys/fs/f2fs/<disk>/ipu_policy 47Date: November 2013 48Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com> 49Description: Controls the in-place-update policy. 50 updates in f2fs. User can set: 51 52 ==== ================= 53 0x01 F2FS_IPU_FORCE 54 0x02 F2FS_IPU_SSR 55 0x04 F2FS_IPU_UTIL 56 0x08 F2FS_IPU_SSR_UTIL 57 0x10 F2FS_IPU_FSYNC 58 0x20 F2FS_IPU_ASYNC, 59 0x40 F2FS_IPU_NOCACHE 60 ==== ================= 61 62 Refer segment.h for details. 63 64What: /sys/fs/f2fs/<disk>/min_ipu_util 65Date: November 2013 66Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com> 67Description: Controls the FS utilization condition for the in-place-update 68 policies. It is used by F2FS_IPU_UTIL and F2FS_IPU_SSR_UTIL policies. 69 70What: /sys/fs/f2fs/<disk>/min_fsync_blocks 71Date: September 2014 72Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 73Description: Controls the dirty page count condition for the in-place-update 74 policies. 75 76What: /sys/fs/f2fs/<disk>/min_seq_blocks 77Date: August 2018 78Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 79Description: Controls the dirty page count condition for batched sequential 80 writes in writepages. 81 82What: /sys/fs/f2fs/<disk>/min_hot_blocks 83Date: March 2017 84Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 85Description: Controls the dirty page count condition for redefining hot data. 86 87What: /sys/fs/f2fs/<disk>/min_ssr_sections 88Date: October 2017 89Contact: "Chao Yu" <yuchao0@huawei.com> 90Description: Controls the free section threshold to trigger SSR allocation. 91 If this is large, SSR mode will be enabled early. 92 93What: /sys/fs/f2fs/<disk>/max_small_discards 94Date: November 2013 95Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com> 96Description: Controls the issue rate of discard commands that consist of small 97 blocks less than 2MB. The candidates to be discarded are cached until 98 checkpoint is triggered, and issued during the checkpoint. 99 By default, it is disabled with 0. 100 101What: /sys/fs/f2fs/<disk>/discard_granularity 102Date: July 2017 103Contact: "Chao Yu" <yuchao0@huawei.com> 104Description: Controls discard granularity of inner discard thread. Inner thread 105 will not issue discards with size that is smaller than granularity. 106 The unit size is one block(4KB), now only support configuring 107 in range of [1, 512]. Default value is 4(=16KB). 108 109What: /sys/fs/f2fs/<disk>/umount_discard_timeout 110Date: January 2019 111Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 112Description: Set timeout to issue discard commands during umount. 113 Default: 5 secs 114 115What: /sys/fs/f2fs/<disk>/pending_discard 116Date: November 2021 117Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 118Description: Shows the number of pending discard commands in the queue. 119 120What: /sys/fs/f2fs/<disk>/max_victim_search 121Date: January 2014 122Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com> 123Description: Controls the number of trials to find a victim segment 124 when conducting SSR and cleaning operations. The default value 125 is 4096 which covers 8GB block address range. 126 127What: /sys/fs/f2fs/<disk>/migration_granularity 128Date: October 2018 129Contact: "Chao Yu" <yuchao0@huawei.com> 130Description: Controls migration granularity of garbage collection on large 131 section, it can let GC move partial segment{s} of one section 132 in one GC cycle, so that dispersing heavy overhead GC to 133 multiple lightweight one. 134 135What: /sys/fs/f2fs/<disk>/dir_level 136Date: March 2014 137Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com> 138Description: Controls the directory level for large directory. If a 139 directory has a number of files, it can reduce the file lookup 140 latency by increasing this dir_level value. Otherwise, it 141 needs to decrease this value to reduce the space overhead. 142 The default value is 0. 143 144What: /sys/fs/f2fs/<disk>/ram_thresh 145Date: March 2014 146Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com> 147Description: Controls the memory footprint used by free nids and cached 148 nat entries. By default, 1 is set, which indicates 149 10 MB / 1 GB RAM. 150 151What: /sys/fs/f2fs/<disk>/batched_trim_sections 152Date: February 2015 153Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 154Description: Controls the trimming rate in batch mode. 155 <deprecated> 156 157What: /sys/fs/f2fs/<disk>/cp_interval 158Date: October 2015 159Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 160Description: Controls the checkpoint timing, set to 60 seconds by default. 161 162What: /sys/fs/f2fs/<disk>/idle_interval 163Date: January 2016 164Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 165Description: Controls the idle timing of system, if there is no FS operation 166 during given interval. 167 Set to 5 seconds by default. 168 169What: /sys/fs/f2fs/<disk>/discard_idle_interval 170Date: September 2018 171Contact: "Chao Yu" <yuchao0@huawei.com> 172Contact: "Sahitya Tummala" <stummala@codeaurora.org> 173Description: Controls the idle timing of discard thread given 174 this time interval. 175 Default is 5 secs. 176 177What: /sys/fs/f2fs/<disk>/gc_idle_interval 178Date: September 2018 179Contact: "Chao Yu" <yuchao0@huawei.com> 180Contact: "Sahitya Tummala" <stummala@codeaurora.org> 181Description: Controls the idle timing for gc path. Set to 5 seconds by default. 182 183What: /sys/fs/f2fs/<disk>/iostat_enable 184Date: August 2017 185Contact: "Chao Yu" <yuchao0@huawei.com> 186Description: Controls to enable/disable IO stat. 187 188What: /sys/fs/f2fs/<disk>/ra_nid_pages 189Date: October 2015 190Contact: "Chao Yu" <chao2.yu@samsung.com> 191Description: Controls the count of nid pages to be readaheaded. 192 When building free nids, F2FS reads NAT blocks ahead for 193 speed up. Default is 0. 194 195What: /sys/fs/f2fs/<disk>/dirty_nats_ratio 196Date: January 2016 197Contact: "Chao Yu" <chao2.yu@samsung.com> 198Description: Controls dirty nat entries ratio threshold, if current 199 ratio exceeds configured threshold, checkpoint will 200 be triggered for flushing dirty nat entries. 201 202What: /sys/fs/f2fs/<disk>/lifetime_write_kbytes 203Date: January 2016 204Contact: "Shuoran Liu" <liushuoran@huawei.com> 205Description: Shows total written kbytes issued to disk. 206 207What: /sys/fs/f2fs/<disk>/features 208Date: July 2017 209Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 210Description: <deprecated: should use /sys/fs/f2fs/<disk>/feature_list/ 211 Shows all enabled features in current device. 212 Supported features: 213 encryption, blkzoned, extra_attr, projquota, inode_checksum, 214 flexible_inline_xattr, quota_ino, inode_crtime, lost_found, 215 verity, sb_checksum, casefold, readonly, compression, pin_file. 216 217What: /sys/fs/f2fs/<disk>/feature_list/ 218Date: June 2021 219Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 220Description: Expand /sys/fs/f2fs/<disk>/features to meet sysfs rule. 221 Supported on-disk features: 222 encryption, block_zoned (aka blkzoned), extra_attr, 223 project_quota (aka projquota), inode_checksum, 224 flexible_inline_xattr, quota_ino, inode_crtime, lost_found, 225 verity, sb_checksum, casefold, readonly, compression. 226 Note that, pin_file is moved into /sys/fs/f2fs/features/. 227 228What: /sys/fs/f2fs/features/ 229Date: July 2017 230Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 231Description: Shows all enabled kernel features. 232 Supported features: 233 encryption, block_zoned, extra_attr, project_quota, 234 inode_checksum, flexible_inline_xattr, quota_ino, 235 inode_crtime, lost_found, verity, sb_checksum, 236 casefold, readonly, compression, test_dummy_encryption_v2, 237 atomic_write, pin_file, encrypted_casefold. 238 239What: /sys/fs/f2fs/<disk>/inject_rate 240Date: May 2016 241Contact: "Sheng Yong" <shengyong1@huawei.com> 242Description: Controls the injection rate of arbitrary faults. 243 244What: /sys/fs/f2fs/<disk>/inject_type 245Date: May 2016 246Contact: "Sheng Yong" <shengyong1@huawei.com> 247Description: Controls the injection type of arbitrary faults. 248 249What: /sys/fs/f2fs/<disk>/dirty_segments 250Date: October 2017 251Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 252Description: Shows the number of dirty segments. 253 254What: /sys/fs/f2fs/<disk>/reserved_blocks 255Date: June 2017 256Contact: "Chao Yu" <yuchao0@huawei.com> 257Description: Controls target reserved blocks in system, the threshold 258 is soft, it could exceed current available user space. 259 260What: /sys/fs/f2fs/<disk>/current_reserved_blocks 261Date: October 2017 262Contact: "Yunlong Song" <yunlong.song@huawei.com> 263Contact: "Chao Yu" <yuchao0@huawei.com> 264Description: Shows current reserved blocks in system, it may be temporarily 265 smaller than target_reserved_blocks, but will gradually 266 increase to target_reserved_blocks when more free blocks are 267 freed by user later. 268 269What: /sys/fs/f2fs/<disk>/gc_urgent 270Date: August 2017 271Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 272Description: Do background GC aggressively when set. When gc_urgent = 1, 273 background thread starts to do GC by given gc_urgent_sleep_time 274 interval. When gc_urgent = 2, F2FS will lower the bar of 275 checking idle in order to process outstanding discard commands 276 and GC a little bit aggressively. It is set to 0 by default. 277 278What: /sys/fs/f2fs/<disk>/gc_urgent_sleep_time 279Date: August 2017 280Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 281Description: Controls sleep time of GC urgent mode. Set to 500ms by default. 282 283What: /sys/fs/f2fs/<disk>/readdir_ra 284Date: November 2017 285Contact: "Sheng Yong" <shengyong1@huawei.com> 286Description: Controls readahead inode block in readdir. Enabled by default. 287 288What: /sys/fs/f2fs/<disk>/gc_pin_file_thresh 289Date: January 2018 290Contact: Jaegeuk Kim <jaegeuk@kernel.org> 291Description: This indicates how many GC can be failed for the pinned 292 file. If it exceeds this, F2FS doesn't guarantee its pinning 293 state. 2048 trials is set by default. 294 295What: /sys/fs/f2fs/<disk>/extension_list 296Date: Feburary 2018 297Contact: "Chao Yu" <yuchao0@huawei.com> 298Description: Used to control configure extension list: 299 - Query: cat /sys/fs/f2fs/<disk>/extension_list 300 - Add: echo '[h/c]extension' > /sys/fs/f2fs/<disk>/extension_list 301 - Del: echo '[h/c]!extension' > /sys/fs/f2fs/<disk>/extension_list 302 - [h] means add/del hot file extension 303 - [c] means add/del cold file extension 304 305What: /sys/fs/f2fs/<disk>/unusable 306Date April 2019 307Contact: "Daniel Rosenberg" <drosen@google.com> 308Description: If checkpoint=disable, it displays the number of blocks that 309 are unusable. 310 If checkpoint=enable it displays the number of blocks that 311 would be unusable if checkpoint=disable were to be set. 312 313What: /sys/fs/f2fs/<disk>/encoding 314Date July 2019 315Contact: "Daniel Rosenberg" <drosen@google.com> 316Description: Displays name and version of the encoding set for the filesystem. 317 If no encoding is set, displays (none) 318 319What: /sys/fs/f2fs/<disk>/free_segments 320Date: September 2019 321Contact: "Hridya Valsaraju" <hridya@google.com> 322Description: Number of free segments in disk. 323 324What: /sys/fs/f2fs/<disk>/cp_foreground_calls 325Date: September 2019 326Contact: "Hridya Valsaraju" <hridya@google.com> 327Description: Number of checkpoint operations performed on demand. Available when 328 CONFIG_F2FS_STAT_FS=y. 329 330What: /sys/fs/f2fs/<disk>/cp_background_calls 331Date: September 2019 332Contact: "Hridya Valsaraju" <hridya@google.com> 333Description: Number of checkpoint operations performed in the background to 334 free segments. Available when CONFIG_F2FS_STAT_FS=y. 335 336What: /sys/fs/f2fs/<disk>/gc_foreground_calls 337Date: September 2019 338Contact: "Hridya Valsaraju" <hridya@google.com> 339Description: Number of garbage collection operations performed on demand. 340 Available when CONFIG_F2FS_STAT_FS=y. 341 342What: /sys/fs/f2fs/<disk>/gc_background_calls 343Date: September 2019 344Contact: "Hridya Valsaraju" <hridya@google.com> 345Description: Number of garbage collection operations triggered in background. 346 Available when CONFIG_F2FS_STAT_FS=y. 347 348What: /sys/fs/f2fs/<disk>/moved_blocks_foreground 349Date: September 2019 350Contact: "Hridya Valsaraju" <hridya@google.com> 351Description: Number of blocks moved by garbage collection in foreground. 352 Available when CONFIG_F2FS_STAT_FS=y. 353 354What: /sys/fs/f2fs/<disk>/moved_blocks_background 355Date: September 2019 356Contact: "Hridya Valsaraju" <hridya@google.com> 357Description: Number of blocks moved by garbage collection in background. 358 Available when CONFIG_F2FS_STAT_FS=y. 359 360What: /sys/fs/f2fs/<disk>/avg_vblocks 361Date: September 2019 362Contact: "Hridya Valsaraju" <hridya@google.com> 363Description: Average number of valid blocks. 364 Available when CONFIG_F2FS_STAT_FS=y. 365 366What: /sys/fs/f2fs/<disk>/mounted_time_sec 367Date: February 2020 368Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 369Description: Show the mounted time in secs of this partition. 370 371What: /sys/fs/f2fs/<disk>/data_io_flag 372Date: April 2020 373Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 374Description: Give a way to attach REQ_META|FUA to data writes 375 given temperature-based bits. Now the bits indicate: 376 377 +-------------------+-------------------+ 378 | REQ_META | REQ_FUA | 379 +------+------+-----+------+------+-----+ 380 | 5 | 4 | 3 | 2 | 1 | 0 | 381 +------+------+-----+------+------+-----+ 382 | Cold | Warm | Hot | Cold | Warm | Hot | 383 +------+------+-----+------+------+-----+ 384 385What: /sys/fs/f2fs/<disk>/node_io_flag 386Date: June 2020 387Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 388Description: Give a way to attach REQ_META|FUA to node writes 389 given temperature-based bits. Now the bits indicate: 390 391 +-------------------+-------------------+ 392 | REQ_META | REQ_FUA | 393 +------+------+-----+------+------+-----+ 394 | 5 | 4 | 3 | 2 | 1 | 0 | 395 +------+------+-----+------+------+-----+ 396 | Cold | Warm | Hot | Cold | Warm | Hot | 397 +------+------+-----+------+------+-----+ 398 399What: /sys/fs/f2fs/<disk>/iostat_period_ms 400Date: April 2020 401Contact: "Daeho Jeong" <daehojeong@google.com> 402Description: Give a way to change iostat_period time. 3secs by default. 403 The new iostat trace gives stats gap given the period. 404What: /sys/fs/f2fs/<disk>/max_io_bytes 405Date: December 2020 406Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 407Description: This gives a control to limit the bio size in f2fs. 408 Default is zero, which will follow underlying block layer limit, 409 whereas, if it has a certain bytes value, f2fs won't submit a 410 bio larger than that size. 411 412What: /sys/fs/f2fs/<disk>/stat/sb_status 413Date: December 2020 414Contact: "Chao Yu" <yuchao0@huawei.com> 415Description: Show status of f2fs superblock in real time. 416 417 ====== ===================== ================================= 418 value sb status macro description 419 0x1 SBI_IS_DIRTY dirty flag for checkpoint 420 0x2 SBI_IS_CLOSE specify unmounting 421 0x4 SBI_NEED_FSCK need fsck.f2fs to fix 422 0x8 SBI_POR_DOING recovery is doing or not 423 0x10 SBI_NEED_SB_WRITE need to recover superblock 424 0x20 SBI_NEED_CP need to checkpoint 425 0x40 SBI_IS_SHUTDOWN shutdown by ioctl 426 0x80 SBI_IS_RECOVERED recovered orphan/data 427 0x100 SBI_CP_DISABLED CP was disabled last mount 428 0x200 SBI_CP_DISABLED_QUICK CP was disabled quickly 429 0x400 SBI_QUOTA_NEED_FLUSH need to flush quota info in CP 430 0x800 SBI_QUOTA_SKIP_FLUSH skip flushing quota in current CP 431 0x1000 SBI_QUOTA_NEED_REPAIR quota file may be corrupted 432 0x2000 SBI_IS_RESIZEFS resizefs is in process 433 ====== ===================== ================================= 434 435What: /sys/fs/f2fs/<disk>/ckpt_thread_ioprio 436Date: January 2021 437Contact: "Daeho Jeong" <daehojeong@google.com> 438Description: Give a way to change checkpoint merge daemon's io priority. 439 Its default value is "be,3", which means "BE" I/O class and 440 I/O priority "3". We can select the class between "rt" and "be", 441 and set the I/O priority within valid range of it. "," delimiter 442 is necessary in between I/O class and priority number. 443 444What: /sys/fs/f2fs/<disk>/ovp_segments 445Date: March 2021 446Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> 447Description: Shows the number of overprovision segments. 448 449What: /sys/fs/f2fs/<disk>/compr_written_block 450Date: March 2021 451Contact: "Daeho Jeong" <daehojeong@google.com> 452Description: Show the block count written after compression since mount. Note 453 that when the compressed blocks are deleted, this count doesn't 454 decrease. If you write "0" here, you can initialize 455 compr_written_block and compr_saved_block to "0". 456 457What: /sys/fs/f2fs/<disk>/compr_saved_block 458Date: March 2021 459Contact: "Daeho Jeong" <daehojeong@google.com> 460Description: Show the saved block count with compression since mount. Note 461 that when the compressed blocks are deleted, this count doesn't 462 decrease. If you write "0" here, you can initialize 463 compr_written_block and compr_saved_block to "0". 464 465What: /sys/fs/f2fs/<disk>/compr_new_inode 466Date: March 2021 467Contact: "Daeho Jeong" <daehojeong@google.com> 468Description: Show the count of inode newly enabled for compression since mount. 469 Note that when the compression is disabled for the files, this count 470 doesn't decrease. If you write "0" here, you can initialize 471 compr_new_inode to "0". 472 473What: /sys/fs/f2fs/<disk>/atgc_candidate_ratio 474Date: May 2021 475Contact: "Chao Yu" <yuchao0@huawei.com> 476Description: When ATGC is on, it controls candidate ratio in order to limit total 477 number of potential victim in all candidates, the value should be in 478 range of [0, 100], by default it was initialized as 20(%). 479 480What: /sys/fs/f2fs/<disk>/atgc_candidate_count 481Date: May 2021 482Contact: "Chao Yu" <yuchao0@huawei.com> 483Description: When ATGC is on, it controls candidate count in order to limit total 484 number of potential victim in all candidates, by default it was 485 initialized as 10 (sections). 486 487What: /sys/fs/f2fs/<disk>/atgc_age_weight 488Date: May 2021 489Contact: "Chao Yu" <yuchao0@huawei.com> 490Description: When ATGC is on, it controls age weight to balance weight proportion 491 in between aging and valid blocks, the value should be in range of 492 [0, 100], by default it was initialized as 60(%). 493 494What: /sys/fs/f2fs/<disk>/atgc_age_threshold 495Date: May 2021 496Contact: "Chao Yu" <yuchao0@huawei.com> 497Description: When ATGC is on, it controls age threshold to bypass GCing young 498 candidates whose age is not beyond the threshold, by default it was 499 initialized as 604800 seconds (equals to 7 days). 500 501What: /sys/fs/f2fs/<disk>/gc_reclaimed_segments 502Date: July 2021 503Contact: "Daeho Jeong" <daehojeong@google.com> 504Description: Show how many segments have been reclaimed by GC during a specific 505 GC mode (0: GC normal, 1: GC idle CB, 2: GC idle greedy, 506 3: GC idle AT, 4: GC urgent high, 5: GC urgent low) 507 You can re-initialize this value to "0". 508 509What: /sys/fs/f2fs/<disk>/gc_segment_mode 510Date: July 2021 511Contact: "Daeho Jeong" <daehojeong@google.com> 512Description: You can control for which gc mode the "gc_reclaimed_segments" node shows. 513 Refer to the description of the modes in "gc_reclaimed_segments". 514 515What: /sys/fs/f2fs/<disk>/seq_file_ra_mul 516Date: July 2021 517Contact: "Daeho Jeong" <daehojeong@google.com> 518Description: You can control the multiplier value of bdi device readahead window size 519 between 2 (default) and 256 for POSIX_FADV_SEQUENTIAL advise option. 520 521What: /sys/fs/f2fs/<disk>/max_fragment_chunk 522Date: August 2021 523Contact: "Daeho Jeong" <daehojeong@google.com> 524Description: With "mode=fragment:block" mount options, we can scatter block allocation. 525 f2fs will allocate 1..<max_fragment_chunk> blocks in a chunk and make a hole 526 in the length of 1..<max_fragment_hole> by turns. This value can be set 527 between 1..512 and the default value is 4. 528 529What: /sys/fs/f2fs/<disk>/max_fragment_hole 530Date: August 2021 531Contact: "Daeho Jeong" <daehojeong@google.com> 532Description: With "mode=fragment:block" mount options, we can scatter block allocation. 533 f2fs will allocate 1..<max_fragment_chunk> blocks in a chunk and make a hole 534 in the length of 1..<max_fragment_hole> by turns. This value can be set 535 between 1..512 and the default value is 4. 536 537What: /sys/fs/f2fs/<disk>/gc_urgent_high_remaining 538Date: December 2021 539Contact: "Daeho Jeong" <daehojeong@google.com> 540Description: You can set the trial count limit for GC urgent high mode with this value. 541 If GC thread gets to the limit, the mode will turn back to GC normal mode. 542 By default, the value is zero, which means there is no limit like before. 543