2018-09-12 09:16:07 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0
|
2012-11-29 12:28:09 +08:00
|
|
|
/*
|
2012-11-03 05:50:41 +08:00
|
|
|
* f2fs debugging statistics
|
|
|
|
|
*
|
|
|
|
|
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
|
|
|
|
|
* http://www.samsung.com/
|
|
|
|
|
* Copyright (c) 2012 Linux Foundation
|
|
|
|
|
* Copyright (c) 2012 Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#include <linux/fs.h>
|
|
|
|
|
#include <linux/backing-dev.h>
|
|
|
|
|
#include <linux/f2fs_fs.h>
|
|
|
|
|
#include <linux/blkdev.h>
|
|
|
|
|
#include <linux/debugfs.h>
|
|
|
|
|
#include <linux/seq_file.h>
|
|
|
|
|
|
|
|
|
|
#include "f2fs.h"
|
|
|
|
|
#include "node.h"
|
|
|
|
|
#include "segment.h"
|
|
|
|
|
#include "gc.h"
|
|
|
|
|
|
|
|
|
|
static LIST_HEAD(f2fs_stat_list);
|
2013-12-03 21:09:29 +08:00
|
|
|
static struct dentry *f2fs_debugfs_root;
|
2013-01-14 20:08:16 +08:00
|
|
|
static DEFINE_MUTEX(f2fs_stat_mutex);
|
2012-11-03 05:50:41 +08:00
|
|
|
|
2012-11-28 15:12:41 +08:00
|
|
|
static void update_general_status(struct f2fs_sb_info *sbi)
|
2012-11-03 05:50:41 +08:00
|
|
|
{
|
2013-07-12 14:47:11 +08:00
|
|
|
struct f2fs_stat_info *si = F2FS_STAT(sbi);
|
2012-11-03 05:50:41 +08:00
|
|
|
int i;
|
|
|
|
|
|
2014-08-06 22:22:50 +08:00
|
|
|
/* validation check of the segment numbers */
|
2015-09-30 17:38:48 +08:00
|
|
|
si->hit_largest = atomic64_read(&sbi->read_hit_largest);
|
|
|
|
|
si->hit_cached = atomic64_read(&sbi->read_hit_cached);
|
|
|
|
|
si->hit_rbtree = atomic64_read(&sbi->read_hit_rbtree);
|
2015-08-19 19:13:25 +08:00
|
|
|
si->hit_total = si->hit_largest + si->hit_cached + si->hit_rbtree;
|
2015-09-30 17:38:48 +08:00
|
|
|
si->total_ext = atomic64_read(&sbi->total_hit_ext);
|
2015-12-22 11:20:15 +08:00
|
|
|
si->ext_tree = atomic_read(&sbi->total_ext_tree);
|
2016-01-01 07:24:14 +08:00
|
|
|
si->zombie_tree = atomic_read(&sbi->total_zombie_tree);
|
2015-02-05 17:58:28 +08:00
|
|
|
si->ext_node = atomic_read(&sbi->total_ext_node);
|
2012-11-03 05:50:41 +08:00
|
|
|
si->ndirty_node = get_pages(sbi, F2FS_DIRTY_NODES);
|
|
|
|
|
si->ndirty_dent = get_pages(sbi, F2FS_DIRTY_DENTS);
|
|
|
|
|
si->ndirty_meta = get_pages(sbi, F2FS_DIRTY_META);
|
2015-12-17 17:14:44 +08:00
|
|
|
si->ndirty_data = get_pages(sbi, F2FS_DIRTY_DATA);
|
2017-11-14 09:46:38 +08:00
|
|
|
si->ndirty_qdata = get_pages(sbi, F2FS_DIRTY_QDATA);
|
2016-09-18 23:30:08 +08:00
|
|
|
si->ndirty_imeta = get_pages(sbi, F2FS_DIRTY_IMETA);
|
2015-12-17 17:14:44 +08:00
|
|
|
si->ndirty_dirs = sbi->ndirty_inode[DIR_INODE];
|
|
|
|
|
si->ndirty_files = sbi->ndirty_inode[FILE_INODE];
|
2017-11-16 16:59:14 +08:00
|
|
|
si->nquota_files = sbi->nquota_files;
|
2016-05-21 02:10:10 +08:00
|
|
|
si->ndirty_all = sbi->ndirty_inode[DIRTY_META];
|
2014-12-06 09:18:15 +08:00
|
|
|
si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES);
|
2016-12-29 05:55:09 +08:00
|
|
|
si->aw_cnt = atomic_read(&sbi->aw_cnt);
|
2017-03-22 17:23:45 +08:00
|
|
|
si->vw_cnt = atomic_read(&sbi->vw_cnt);
|
2016-12-29 05:55:09 +08:00
|
|
|
si->max_aw_cnt = atomic_read(&sbi->max_aw_cnt);
|
2017-03-22 17:23:45 +08:00
|
|
|
si->max_vw_cnt = atomic_read(&sbi->max_vw_cnt);
|
f2fs: don't wait writeback for datas during checkpoint
Normally, while committing checkpoint, we will wait on all pages to be
writebacked no matter the page is data or metadata, so in scenario where
there are lots of data IO being submitted with metadata, we may suffer
long latency for waiting writeback during checkpoint.
Indeed, we only care about persistence for pages with metadata, but not
pages with data, as file system consistent are only related to metadate,
so in order to avoid encountering long latency in above scenario, let's
recognize and reference metadata in submitted IOs, wait writeback only
for metadatas.
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-11-16 10:41:20 +08:00
|
|
|
si->nr_wb_cp_data = get_pages(sbi, F2FS_WB_CP_DATA);
|
|
|
|
|
si->nr_wb_data = get_pages(sbi, F2FS_WB_DATA);
|
2017-03-25 17:19:58 +08:00
|
|
|
if (SM_I(sbi) && SM_I(sbi)->fcc_info) {
|
|
|
|
|
si->nr_flushed =
|
|
|
|
|
atomic_read(&SM_I(sbi)->fcc_info->issued_flush);
|
|
|
|
|
si->nr_flushing =
|
|
|
|
|
atomic_read(&SM_I(sbi)->fcc_info->issing_flush);
|
2017-09-14 10:18:01 +08:00
|
|
|
si->flush_list_empty =
|
|
|
|
|
llist_empty(&SM_I(sbi)->fcc_info->issue_list);
|
2017-03-25 17:19:58 +08:00
|
|
|
}
|
|
|
|
|
if (SM_I(sbi) && SM_I(sbi)->dcc_info) {
|
|
|
|
|
si->nr_discarded =
|
|
|
|
|
atomic_read(&SM_I(sbi)->dcc_info->issued_discard);
|
|
|
|
|
si->nr_discarding =
|
|
|
|
|
atomic_read(&SM_I(sbi)->dcc_info->issing_discard);
|
2017-03-25 17:19:59 +08:00
|
|
|
si->nr_discard_cmd =
|
|
|
|
|
atomic_read(&SM_I(sbi)->dcc_info->discard_cmd_cnt);
|
2017-04-18 19:27:39 +08:00
|
|
|
si->undiscard_blks = SM_I(sbi)->dcc_info->undiscard_blks;
|
2017-03-25 17:19:58 +08:00
|
|
|
}
|
2012-11-03 05:50:41 +08:00
|
|
|
si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg;
|
|
|
|
|
si->rsvd_segs = reserved_segments(sbi);
|
|
|
|
|
si->overp_segs = overprovision_segments(sbi);
|
|
|
|
|
si->valid_count = valid_user_blocks(sbi);
|
2016-08-18 21:01:18 +08:00
|
|
|
si->discard_blks = discard_blocks(sbi);
|
2012-11-03 05:50:41 +08:00
|
|
|
si->valid_node_count = valid_node_count(sbi);
|
|
|
|
|
si->valid_inode_count = valid_inode_count(sbi);
|
2015-07-15 17:28:53 +08:00
|
|
|
si->inline_xattr = atomic_read(&sbi->inline_xattr);
|
2014-12-08 19:08:20 +08:00
|
|
|
si->inline_inode = atomic_read(&sbi->inline_inode);
|
|
|
|
|
si->inline_dir = atomic_read(&sbi->inline_dir);
|
2017-02-02 07:40:11 +08:00
|
|
|
si->append = sbi->im[APPEND_INO].ino_num;
|
|
|
|
|
si->update = sbi->im[UPDATE_INO].ino_num;
|
2016-05-11 10:13:50 +08:00
|
|
|
si->orphans = sbi->im[ORPHAN_INO].ino_num;
|
2012-11-03 05:50:41 +08:00
|
|
|
si->utilization = utilization(sbi);
|
|
|
|
|
|
|
|
|
|
si->free_segs = free_segments(sbi);
|
|
|
|
|
si->free_secs = free_sections(sbi);
|
|
|
|
|
si->prefree_count = prefree_segments(sbi);
|
|
|
|
|
si->dirty_count = dirty_segments(sbi);
|
2014-01-21 17:51:16 +08:00
|
|
|
si->node_pages = NODE_MAPPING(sbi)->nrpages;
|
2014-01-20 18:37:04 +08:00
|
|
|
si->meta_pages = META_MAPPING(sbi)->nrpages;
|
2012-11-03 05:50:41 +08:00
|
|
|
si->nats = NM_I(sbi)->nat_cnt;
|
2015-01-08 03:09:37 +08:00
|
|
|
si->dirty_nats = NM_I(sbi)->dirty_nat_cnt;
|
|
|
|
|
si->sits = MAIN_SEGS(sbi);
|
|
|
|
|
si->dirty_sits = SIT_I(sbi)->dirty_sentries;
|
2017-09-29 13:59:35 +08:00
|
|
|
si->free_nids = NM_I(sbi)->nid_cnt[FREE_NID];
|
2017-05-02 09:13:03 +08:00
|
|
|
si->avail_nids = NM_I(sbi)->available_nids;
|
2017-09-29 13:59:35 +08:00
|
|
|
si->alloc_nids = NM_I(sbi)->nid_cnt[PREALLOC_NID];
|
2012-11-03 05:50:41 +08:00
|
|
|
si->bg_gc = sbi->bg_gc;
|
f2fs: avoid stucking GC due to atomic write
f2fs doesn't allow abuse on atomic write class interface, so except
limiting in-mem pages' total memory usage capacity, we need to limit
atomic-write usage as well when filesystem is seriously fragmented,
otherwise we may run into infinite loop during foreground GC because
target blocks in victim segment are belong to atomic opened file for
long time.
Now, we will detect failure due to atomic write in foreground GC, if
the count exceeds threshold, we will drop all atomic written data in
cache, by this, I expect it can keep our system running safely to
prevent Dos attack.
In addition, his patch adds to show GC skip information in debugfs,
now it just shows count of skipped caused by atomic write.
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-07 20:28:54 +08:00
|
|
|
si->skipped_atomic_files[BG_GC] = sbi->skipped_atomic_files[BG_GC];
|
|
|
|
|
si->skipped_atomic_files[FG_GC] = sbi->skipped_atomic_files[FG_GC];
|
2012-11-03 05:50:41 +08:00
|
|
|
si->util_free = (int)(free_user_blocks(sbi) >> sbi->log_blocks_per_seg)
|
|
|
|
|
* 100 / (int)(sbi->user_block_count >> sbi->log_blocks_per_seg)
|
|
|
|
|
/ 2;
|
|
|
|
|
si->util_valid = (int)(written_block_count(sbi) >>
|
|
|
|
|
sbi->log_blocks_per_seg)
|
|
|
|
|
* 100 / (int)(sbi->user_block_count >> sbi->log_blocks_per_seg)
|
|
|
|
|
/ 2;
|
|
|
|
|
si->util_invalid = 50 - si->util_free - si->util_valid;
|
|
|
|
|
for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_NODE; i++) {
|
|
|
|
|
struct curseg_info *curseg = CURSEG_I(sbi, i);
|
|
|
|
|
si->curseg[i] = curseg->segno;
|
2017-04-08 06:08:17 +08:00
|
|
|
si->cursec[i] = GET_SEC_FROM_SEG(sbi, curseg->segno);
|
|
|
|
|
si->curzone[i] = GET_ZONE_FROM_SEC(sbi, si->cursec[i]);
|
2012-11-03 05:50:41 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
for (i = 0; i < 2; i++) {
|
|
|
|
|
si->segment_count[i] = sbi->segment_count[i];
|
|
|
|
|
si->block_count[i] = sbi->block_count[i];
|
|
|
|
|
}
|
2014-12-24 01:16:54 +08:00
|
|
|
|
|
|
|
|
si->inplace_count = atomic_read(&sbi->inplace_count);
|
2012-11-03 05:50:41 +08:00
|
|
|
}
|
|
|
|
|
|
2012-11-29 12:28:09 +08:00
|
|
|
/*
|
2012-11-03 05:50:41 +08:00
|
|
|
* This function calculates BDF of every segments
|
|
|
|
|
*/
|
|
|
|
|
static void update_sit_info(struct f2fs_sb_info *sbi)
|
|
|
|
|
{
|
2013-07-12 14:47:11 +08:00
|
|
|
struct f2fs_stat_info *si = F2FS_STAT(sbi);
|
2015-05-09 07:37:28 +08:00
|
|
|
unsigned long long blks_per_sec, hblks_per_sec, total_vblocks;
|
|
|
|
|
unsigned long long bimodal, dist;
|
2012-11-03 05:50:41 +08:00
|
|
|
unsigned int segno, vblocks;
|
|
|
|
|
int ndirty = 0;
|
|
|
|
|
|
|
|
|
|
bimodal = 0;
|
|
|
|
|
total_vblocks = 0;
|
2017-04-08 06:08:17 +08:00
|
|
|
blks_per_sec = BLKS_PER_SEC(sbi);
|
2012-11-03 05:50:41 +08:00
|
|
|
hblks_per_sec = blks_per_sec / 2;
|
2014-09-24 02:23:01 +08:00
|
|
|
for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) {
|
2017-04-08 05:33:22 +08:00
|
|
|
vblocks = get_valid_blocks(sbi, segno, true);
|
2012-11-03 05:50:41 +08:00
|
|
|
dist = abs(vblocks - hblks_per_sec);
|
|
|
|
|
bimodal += dist * dist;
|
|
|
|
|
|
|
|
|
|
if (vblocks > 0 && vblocks < blks_per_sec) {
|
|
|
|
|
total_vblocks += vblocks;
|
|
|
|
|
ndirty++;
|
|
|
|
|
}
|
|
|
|
|
}
|
2015-05-14 04:49:58 +08:00
|
|
|
dist = div_u64(MAIN_SECS(sbi) * hblks_per_sec * hblks_per_sec, 100);
|
2015-09-23 09:25:43 +08:00
|
|
|
si->bimodal = div64_u64(bimodal, dist);
|
2012-11-03 05:50:41 +08:00
|
|
|
if (si->dirty_count)
|
2015-05-14 04:49:58 +08:00
|
|
|
si->avg_vblocks = div_u64(total_vblocks, ndirty);
|
2012-11-03 05:50:41 +08:00
|
|
|
else
|
|
|
|
|
si->avg_vblocks = 0;
|
|
|
|
|
}
|
|
|
|
|
|
2012-11-29 12:28:09 +08:00
|
|
|
/*
|
2012-11-03 05:50:41 +08:00
|
|
|
* This function calculates memory footprint.
|
|
|
|
|
*/
|
|
|
|
|
static void update_mem_info(struct f2fs_sb_info *sbi)
|
|
|
|
|
{
|
2013-07-12 14:47:11 +08:00
|
|
|
struct f2fs_stat_info *si = F2FS_STAT(sbi);
|
2012-11-03 05:50:41 +08:00
|
|
|
unsigned npages;
|
2014-11-07 07:16:04 +08:00
|
|
|
int i;
|
2012-11-03 05:50:41 +08:00
|
|
|
|
|
|
|
|
if (si->base_mem)
|
|
|
|
|
goto get_cache;
|
|
|
|
|
|
2017-03-18 09:25:05 +08:00
|
|
|
/* build stat */
|
|
|
|
|
si->base_mem = sizeof(struct f2fs_stat_info);
|
|
|
|
|
|
|
|
|
|
/* build superblock */
|
|
|
|
|
si->base_mem += sizeof(struct f2fs_sb_info) + sbi->sb->s_blocksize;
|
2012-11-03 05:50:41 +08:00
|
|
|
si->base_mem += 2 * sizeof(struct f2fs_inode_info);
|
|
|
|
|
si->base_mem += sizeof(*sbi->ckpt);
|
|
|
|
|
|
|
|
|
|
/* build sm */
|
|
|
|
|
si->base_mem += sizeof(struct f2fs_sm_info);
|
|
|
|
|
|
|
|
|
|
/* build sit */
|
|
|
|
|
si->base_mem += sizeof(struct sit_info);
|
2014-09-24 02:23:01 +08:00
|
|
|
si->base_mem += MAIN_SEGS(sbi) * sizeof(struct seg_entry);
|
|
|
|
|
si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi));
|
2016-08-03 01:56:40 +08:00
|
|
|
si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi);
|
f2fs: fix to avoid NULL pointer dereference on se->discard_map
https://bugzilla.kernel.org/show_bug.cgi?id=200951
These is a NULL pointer dereference issue reported in bugzilla:
Hi,
in the setup there is a SATA SSD connected to a SATA-to-USB bridge.
The disc is "Samsung SSD 850 PRO 256G" which supports TRIM.
There are four partitions:
sda1: FAT /boot
sda2: F2FS /
sda3: F2FS /home
sda4: F2FS
The bridge is ASMT1153e which uses the "uas" driver.
There is no TRIM pass-through, so, when mounting it reports:
mounting with "discard" option, but the device does not support discard
The USB host is USB3.0 and UASP capable. It is the one on RK3399.
Given this everything works fine, except there is no TRIM support.
In order to enable TRIM a new UDEV rule is added [1]:
/etc/udev/rules.d/10-sata-bridge-trim.rules:
ACTION=="add|change", ATTRS{idVendor}=="174c", ATTRS{idProduct}=="55aa", SUBSYSTEM=="scsi_disk", ATTR{provisioning_mode}="unmap"
After reboot any F2FS write hangs forever and dmesg reports:
Unable to handle kernel NULL pointer dereference
Also tested on a x86_64 system: works fine even with TRIM enabled.
same disc
same bridge
different usb host controller
different cpu architecture
not root filesystem
Regards,
Vicenç.
[1] Post #5 in https://bbs.archlinux.org/viewtopic.php?id=236280
Unable to handle kernel NULL pointer dereference at virtual address 000000000000003e
Mem abort info:
ESR = 0x96000004
Exception class = DABT (current EL), IL = 32 bits
SET = 0, FnV = 0
EA = 0, S1PTW = 0
Data abort info:
ISV = 0, ISS = 0x00000004
CM = 0, WnR = 0
user pgtable: 4k pages, 48-bit VAs, pgdp = 00000000626e3122
[000000000000003e] pgd=0000000000000000
Internal error: Oops: 96000004 [#1] SMP
Modules linked in: overlay snd_soc_hdmi_codec rc_cec dw_hdmi_i2s_audio dw_hdmi_cec snd_soc_simple_card snd_soc_simple_card_utils snd_soc_rockchip_i2s rockchip_rga snd_soc_rockchip_pcm rockchipdrm videobuf2_dma_sg v4l2_mem2mem rtc_rk808 videobuf2_memops analogix_dp videobuf2_v4l2 videobuf2_common dw_hdmi dw_wdt cec rc_core videodev drm_kms_helper media drm rockchip_thermal rockchip_saradc realtek drm_panel_orientation_quirks syscopyarea sysfillrect sysimgblt fb_sys_fops dwmac_rk stmmac_platform stmmac pwm_bl squashfs loop crypto_user gpio_keys hid_kensington
CPU: 5 PID: 957 Comm: nvim Not tainted 4.19.0-rc1-1-ARCH #1
Hardware name: Sapphire-RK3399 Board (DT)
pstate: 00000005 (nzcv daif -PAN -UAO)
pc : update_sit_entry+0x304/0x4b0
lr : update_sit_entry+0x108/0x4b0
sp : ffff00000ca13bd0
x29: ffff00000ca13bd0 x28: 000000000000003e
x27: 0000000000000020 x26: 0000000000080000
x25: 0000000000000048 x24: ffff8000ebb85cf8
x23: 0000000000000253 x22: 00000000ffffffff
x21: 00000000000535f2 x20: 00000000ffffffdf
x19: ffff8000eb9e6800 x18: ffff8000eb9e6be8
x17: 0000000007ce6926 x16: 000000001c83ffa8
x15: 0000000000000000 x14: ffff8000f602df90
x13: 0000000000000006 x12: 0000000000000040
x11: 0000000000000228 x10: 0000000000000000
x9 : 0000000000000000 x8 : 0000000000000000
x7 : 00000000000535f2 x6 : ffff8000ebff3440
x5 : ffff8000ebff3440 x4 : ffff8000ebe3a6c8
x3 : 00000000ffffffff x2 : 0000000000000020
x1 : 0000000000000000 x0 : ffff8000eb9e5800
Process nvim (pid: 957, stack limit = 0x0000000063a78320)
Call trace:
update_sit_entry+0x304/0x4b0
f2fs_invalidate_blocks+0x98/0x140
truncate_node+0x90/0x400
f2fs_remove_inode_page+0xe8/0x340
f2fs_evict_inode+0x2b0/0x408
evict+0xe0/0x1e0
iput+0x160/0x260
do_unlinkat+0x214/0x298
__arm64_sys_unlinkat+0x3c/0x68
el0_svc_handler+0x94/0x118
el0_svc+0x8/0xc
Code: f9400800 b9488400 36080140 f9400f01 (387c4820)
---[ end trace a0f21a307118c477 ]---
The reason is it is possible to enable discard flag on block queue via
UDEV, but during mount, f2fs will initialize se->discard_map only if
this flag is set, once the flag is set after mount, f2fs may dereference
NULL pointer on se->discard_map.
So this patch does below changes to fix this issue:
- initialize and update se->discard_map all the time.
- don't clear DISCARD option if device has no QUEUE_FLAG_DISCARD flag
during mount.
- don't issue small discard on zoned block device.
- introduce some functions to enhance the readability.
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Tested-by: Vicente Bergas <vicencb@gmail.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-09-04 03:52:17 +08:00
|
|
|
si->base_mem += SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi);
|
2015-02-11 08:44:29 +08:00
|
|
|
si->base_mem += SIT_VBLOCK_MAP_SIZE;
|
2012-11-03 05:50:41 +08:00
|
|
|
if (sbi->segs_per_sec > 1)
|
2014-09-24 02:23:01 +08:00
|
|
|
si->base_mem += MAIN_SECS(sbi) * sizeof(struct sec_entry);
|
2012-11-03 05:50:41 +08:00
|
|
|
si->base_mem += __bitmap_size(sbi, SIT_BITMAP);
|
|
|
|
|
|
|
|
|
|
/* build free segmap */
|
|
|
|
|
si->base_mem += sizeof(struct free_segmap_info);
|
2014-09-24 02:23:01 +08:00
|
|
|
si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi));
|
|
|
|
|
si->base_mem += f2fs_bitmap_size(MAIN_SECS(sbi));
|
2012-11-03 05:50:41 +08:00
|
|
|
|
|
|
|
|
/* build curseg */
|
|
|
|
|
si->base_mem += sizeof(struct curseg_info) * NR_CURSEG_TYPE;
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
si->base_mem += PAGE_SIZE * NR_CURSEG_TYPE;
|
2012-11-03 05:50:41 +08:00
|
|
|
|
|
|
|
|
/* build dirty segmap */
|
|
|
|
|
si->base_mem += sizeof(struct dirty_seglist_info);
|
2014-09-24 02:23:01 +08:00
|
|
|
si->base_mem += NR_DIRTY_TYPE * f2fs_bitmap_size(MAIN_SEGS(sbi));
|
|
|
|
|
si->base_mem += f2fs_bitmap_size(MAIN_SECS(sbi));
|
2012-11-03 05:50:41 +08:00
|
|
|
|
2014-08-06 22:22:50 +08:00
|
|
|
/* build nm */
|
2012-11-03 05:50:41 +08:00
|
|
|
si->base_mem += sizeof(struct f2fs_nm_info);
|
|
|
|
|
si->base_mem += __bitmap_size(sbi, NAT_BITMAP);
|
2017-02-10 02:38:09 +08:00
|
|
|
si->base_mem += (NM_I(sbi)->nat_bits_blocks << F2FS_BLKSIZE_BITS);
|
2018-06-27 14:46:21 +08:00
|
|
|
si->base_mem += NM_I(sbi)->nat_blocks *
|
|
|
|
|
f2fs_bitmap_size(NAT_ENTRY_PER_BLOCK);
|
f2fs: introduce free nid bitmap
In scenario of intensively node allocation, free nids will be ran out
soon, then it needs to stop to load free nids by traversing NAT blocks,
in worse case, if NAT blocks does not be cached in memory, it generates
IOs which slows down our foreground operations.
In order to speed up node allocation, in this patch we introduce a new
free_nid_bitmap array, so there is an bitmap table for each NAT block,
Once the NAT block is loaded, related bitmap cache will be switched on,
and bitmap will be set during traversing nat entries in NAT block, later
we can query and update nid usage status in memory completely.
With such implementation, I expect performance of node allocation can be
improved in the long-term after filesystem image is mounted.
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-02-23 10:53:49 +08:00
|
|
|
si->base_mem += NM_I(sbi)->nat_blocks / 8;
|
2017-03-01 17:09:07 +08:00
|
|
|
si->base_mem += NM_I(sbi)->nat_blocks * sizeof(unsigned short);
|
2012-11-03 05:50:41 +08:00
|
|
|
|
2015-01-10 20:09:52 +08:00
|
|
|
get_cache:
|
|
|
|
|
si->cache_mem = 0;
|
|
|
|
|
|
2012-11-03 05:50:41 +08:00
|
|
|
/* build gc */
|
2015-01-10 20:09:52 +08:00
|
|
|
if (sbi->gc_thread)
|
|
|
|
|
si->cache_mem += sizeof(struct f2fs_gc_kthread);
|
|
|
|
|
|
|
|
|
|
/* build merge flush thread */
|
2017-01-10 06:13:03 +08:00
|
|
|
if (SM_I(sbi)->fcc_info)
|
2015-01-10 20:09:52 +08:00
|
|
|
si->cache_mem += sizeof(struct flush_cmd_control);
|
2017-03-25 17:19:59 +08:00
|
|
|
if (SM_I(sbi)->dcc_info) {
|
2017-01-12 06:40:24 +08:00
|
|
|
si->cache_mem += sizeof(struct discard_cmd_control);
|
2017-03-25 17:19:59 +08:00
|
|
|
si->cache_mem += sizeof(struct discard_cmd) *
|
|
|
|
|
atomic_read(&SM_I(sbi)->dcc_info->discard_cmd_cnt);
|
|
|
|
|
}
|
2012-11-03 05:50:41 +08:00
|
|
|
|
|
|
|
|
/* free nids */
|
2017-09-29 13:59:35 +08:00
|
|
|
si->cache_mem += (NM_I(sbi)->nid_cnt[FREE_NID] +
|
|
|
|
|
NM_I(sbi)->nid_cnt[PREALLOC_NID]) *
|
f2fs: split free nid list
During free nid allocation, in order to do preallocation, we will tag free
nid entry as allocated one and still leave it in free nid list, for other
allocators who want to grab free nids, it needs to traverse the free nid
list for lookup. It becomes overhead in scenario of allocating free nid
intensively by multithreads.
This patch splits free nid list to two list: {free,alloc}_nid_list, to
keep free nids and preallocated free nids separately, after that, traverse
latency will be gone, besides split nid_cnt for separate statistic.
Additionally, introduce __insert_nid_to_list and __remove_nid_from_list for
cleanup.
Signed-off-by: Chao Yu <yuchao0@huawei.com>
[Jaegeuk Kim: modify f2fs_bug_on to avoid needless branches]
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-10-12 19:28:29 +08:00
|
|
|
sizeof(struct free_nid);
|
2015-01-10 20:09:52 +08:00
|
|
|
si->cache_mem += NM_I(sbi)->nat_cnt * sizeof(struct nat_entry);
|
2015-01-11 13:37:36 +08:00
|
|
|
si->cache_mem += NM_I(sbi)->dirty_nat_cnt *
|
|
|
|
|
sizeof(struct nat_entry_set);
|
|
|
|
|
si->cache_mem += si->inmem_pages * sizeof(struct inmem_pages);
|
2017-09-29 13:59:37 +08:00
|
|
|
for (i = 0; i < MAX_INO_ENTRY; i++)
|
2014-11-18 11:18:36 +08:00
|
|
|
si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry);
|
2015-12-22 11:20:15 +08:00
|
|
|
si->cache_mem += atomic_read(&sbi->total_ext_tree) *
|
|
|
|
|
sizeof(struct extent_tree);
|
2015-02-05 17:58:28 +08:00
|
|
|
si->cache_mem += atomic_read(&sbi->total_ext_node) *
|
|
|
|
|
sizeof(struct extent_node);
|
2015-01-11 13:37:36 +08:00
|
|
|
|
|
|
|
|
si->page_mem = 0;
|
|
|
|
|
npages = NODE_MAPPING(sbi)->nrpages;
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
si->page_mem += (unsigned long long)npages << PAGE_SHIFT;
|
2015-01-11 13:37:36 +08:00
|
|
|
npages = META_MAPPING(sbi)->nrpages;
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
si->page_mem += (unsigned long long)npages << PAGE_SHIFT;
|
2012-11-03 05:50:41 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int stat_show(struct seq_file *s, void *v)
|
|
|
|
|
{
|
2013-05-14 20:06:46 +08:00
|
|
|
struct f2fs_stat_info *si;
|
2012-11-03 05:50:41 +08:00
|
|
|
int i = 0;
|
|
|
|
|
int j;
|
|
|
|
|
|
2013-01-14 20:08:16 +08:00
|
|
|
mutex_lock(&f2fs_stat_mutex);
|
2013-05-14 20:06:46 +08:00
|
|
|
list_for_each_entry(si, &f2fs_stat_list, stat_list) {
|
2012-11-03 05:50:41 +08:00
|
|
|
update_general_status(si->sbi);
|
|
|
|
|
|
2017-10-26 16:31:22 +08:00
|
|
|
seq_printf(s, "\n=====[ partition info(%pg). #%d, %s, CP: %s]=====\n",
|
2016-03-19 00:46:10 +08:00
|
|
|
si->sbi->sb->s_bdev, i++,
|
2017-10-26 16:31:22 +08:00
|
|
|
f2fs_readonly(si->sbi->sb) ? "RO": "RW",
|
|
|
|
|
f2fs_cp_error(si->sbi) ? "Error": "Good");
|
2012-12-31 13:59:09 +08:00
|
|
|
seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ",
|
|
|
|
|
si->sit_area_segs, si->nat_area_segs);
|
2012-11-03 05:50:41 +08:00
|
|
|
seq_printf(s, "[SSA: %d] [MAIN: %d",
|
|
|
|
|
si->ssa_area_segs, si->main_area_segs);
|
|
|
|
|
seq_printf(s, "(OverProv:%d Resv:%d)]\n\n",
|
|
|
|
|
si->overp_segs, si->rsvd_segs);
|
2016-08-18 21:01:18 +08:00
|
|
|
if (test_opt(si->sbi, DISCARD))
|
|
|
|
|
seq_printf(s, "Utilization: %u%% (%u valid blocks, %u discard blocks)\n",
|
|
|
|
|
si->utilization, si->valid_count, si->discard_blks);
|
|
|
|
|
else
|
|
|
|
|
seq_printf(s, "Utilization: %u%% (%u valid blocks)\n",
|
|
|
|
|
si->utilization, si->valid_count);
|
|
|
|
|
|
2012-11-03 05:50:41 +08:00
|
|
|
seq_printf(s, " - Node: %u (Inode: %u, ",
|
|
|
|
|
si->valid_node_count, si->valid_inode_count);
|
|
|
|
|
seq_printf(s, "Other: %u)\n - Data: %u\n",
|
|
|
|
|
si->valid_node_count - si->valid_inode_count,
|
|
|
|
|
si->valid_count - si->valid_node_count);
|
2015-07-15 17:28:53 +08:00
|
|
|
seq_printf(s, " - Inline_xattr Inode: %u\n",
|
|
|
|
|
si->inline_xattr);
|
2013-11-26 10:08:57 +08:00
|
|
|
seq_printf(s, " - Inline_data Inode: %u\n",
|
|
|
|
|
si->inline_inode);
|
2014-10-14 11:00:16 +08:00
|
|
|
seq_printf(s, " - Inline_dentry Inode: %u\n",
|
|
|
|
|
si->inline_dir);
|
2017-02-02 07:40:11 +08:00
|
|
|
seq_printf(s, " - Orphan/Append/Update Inode: %u, %u, %u\n",
|
|
|
|
|
si->orphans, si->append, si->update);
|
2012-11-03 05:50:41 +08:00
|
|
|
seq_printf(s, "\nMain area: %d segs, %d secs %d zones\n",
|
|
|
|
|
si->main_area_segs, si->main_area_sections,
|
|
|
|
|
si->main_area_zones);
|
|
|
|
|
seq_printf(s, " - COLD data: %d, %d, %d\n",
|
|
|
|
|
si->curseg[CURSEG_COLD_DATA],
|
|
|
|
|
si->cursec[CURSEG_COLD_DATA],
|
|
|
|
|
si->curzone[CURSEG_COLD_DATA]);
|
|
|
|
|
seq_printf(s, " - WARM data: %d, %d, %d\n",
|
|
|
|
|
si->curseg[CURSEG_WARM_DATA],
|
|
|
|
|
si->cursec[CURSEG_WARM_DATA],
|
|
|
|
|
si->curzone[CURSEG_WARM_DATA]);
|
|
|
|
|
seq_printf(s, " - HOT data: %d, %d, %d\n",
|
|
|
|
|
si->curseg[CURSEG_HOT_DATA],
|
|
|
|
|
si->cursec[CURSEG_HOT_DATA],
|
|
|
|
|
si->curzone[CURSEG_HOT_DATA]);
|
|
|
|
|
seq_printf(s, " - Dir dnode: %d, %d, %d\n",
|
|
|
|
|
si->curseg[CURSEG_HOT_NODE],
|
|
|
|
|
si->cursec[CURSEG_HOT_NODE],
|
|
|
|
|
si->curzone[CURSEG_HOT_NODE]);
|
|
|
|
|
seq_printf(s, " - File dnode: %d, %d, %d\n",
|
|
|
|
|
si->curseg[CURSEG_WARM_NODE],
|
|
|
|
|
si->cursec[CURSEG_WARM_NODE],
|
|
|
|
|
si->curzone[CURSEG_WARM_NODE]);
|
|
|
|
|
seq_printf(s, " - Indir nodes: %d, %d, %d\n",
|
|
|
|
|
si->curseg[CURSEG_COLD_NODE],
|
|
|
|
|
si->cursec[CURSEG_COLD_NODE],
|
|
|
|
|
si->curzone[CURSEG_COLD_NODE]);
|
|
|
|
|
seq_printf(s, "\n - Valid: %d\n - Dirty: %d\n",
|
|
|
|
|
si->main_area_segs - si->dirty_count -
|
|
|
|
|
si->prefree_count - si->free_segs,
|
|
|
|
|
si->dirty_count);
|
|
|
|
|
seq_printf(s, " - Prefree: %d\n - Free: %d (%d)\n\n",
|
|
|
|
|
si->prefree_count, si->free_segs, si->free_secs);
|
2016-01-10 05:45:17 +08:00
|
|
|
seq_printf(s, "CP calls: %d (BG: %d)\n",
|
|
|
|
|
si->cp_count, si->bg_cp_count);
|
2012-11-03 05:50:41 +08:00
|
|
|
seq_printf(s, "GC calls: %d (BG: %d)\n",
|
|
|
|
|
si->call_count, si->bg_gc);
|
2014-12-23 07:37:39 +08:00
|
|
|
seq_printf(s, " - data segments : %d (%d)\n",
|
|
|
|
|
si->data_segs, si->bg_data_segs);
|
|
|
|
|
seq_printf(s, " - node segments : %d (%d)\n",
|
|
|
|
|
si->node_segs, si->bg_node_segs);
|
|
|
|
|
seq_printf(s, "Try to move %d blocks (BG: %d)\n", si->tot_blks,
|
|
|
|
|
si->bg_data_blks + si->bg_node_blks);
|
|
|
|
|
seq_printf(s, " - data blocks : %d (%d)\n", si->data_blks,
|
|
|
|
|
si->bg_data_blks);
|
|
|
|
|
seq_printf(s, " - node blocks : %d (%d)\n", si->node_blks,
|
|
|
|
|
si->bg_node_blks);
|
f2fs: avoid stucking GC due to atomic write
f2fs doesn't allow abuse on atomic write class interface, so except
limiting in-mem pages' total memory usage capacity, we need to limit
atomic-write usage as well when filesystem is seriously fragmented,
otherwise we may run into infinite loop during foreground GC because
target blocks in victim segment are belong to atomic opened file for
long time.
Now, we will detect failure due to atomic write in foreground GC, if
the count exceeds threshold, we will drop all atomic written data in
cache, by this, I expect it can keep our system running safely to
prevent Dos attack.
In addition, his patch adds to show GC skip information in debugfs,
now it just shows count of skipped caused by atomic write.
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-07 20:28:54 +08:00
|
|
|
seq_printf(s, "Skipped : atomic write %llu (%llu)\n",
|
|
|
|
|
si->skipped_atomic_files[BG_GC] +
|
|
|
|
|
si->skipped_atomic_files[FG_GC],
|
|
|
|
|
si->skipped_atomic_files[BG_GC]);
|
2015-08-19 19:13:25 +08:00
|
|
|
seq_puts(s, "\nExtent Cache:\n");
|
2015-09-30 17:38:48 +08:00
|
|
|
seq_printf(s, " - Hit Count: L1-1:%llu L1-2:%llu L2:%llu\n",
|
2015-08-19 19:12:20 +08:00
|
|
|
si->hit_largest, si->hit_cached,
|
2015-08-19 19:13:25 +08:00
|
|
|
si->hit_rbtree);
|
2015-09-30 17:38:48 +08:00
|
|
|
seq_printf(s, " - Hit Ratio: %llu%% (%llu / %llu)\n",
|
2015-08-19 19:13:25 +08:00
|
|
|
!si->total_ext ? 0 :
|
2015-09-30 17:38:48 +08:00
|
|
|
div64_u64(si->hit_total * 100, si->total_ext),
|
2015-08-19 19:13:25 +08:00
|
|
|
si->hit_total, si->total_ext);
|
2016-01-01 07:24:14 +08:00
|
|
|
seq_printf(s, " - Inner Struct Count: tree: %d(%d), node: %d\n",
|
|
|
|
|
si->ext_tree, si->zombie_tree, si->ext_node);
|
2014-01-18 04:44:39 +08:00
|
|
|
seq_puts(s, "\nBalancing F2FS Async:\n");
|
2017-09-14 10:18:01 +08:00
|
|
|
seq_printf(s, " - IO (CP: %4d, Data: %4d, Flush: (%4d %4d %4d), "
|
2017-04-18 19:27:39 +08:00
|
|
|
"Discard: (%4d %4d)) cmd: %4d undiscard:%4u\n",
|
2017-01-12 02:20:04 +08:00
|
|
|
si->nr_wb_cp_data, si->nr_wb_data,
|
2017-03-25 17:19:58 +08:00
|
|
|
si->nr_flushing, si->nr_flushed,
|
2017-09-14 10:18:01 +08:00
|
|
|
si->flush_list_empty,
|
2017-03-25 17:19:59 +08:00
|
|
|
si->nr_discarding, si->nr_discarded,
|
2017-04-18 19:27:39 +08:00
|
|
|
si->nr_discard_cmd, si->undiscard_blks);
|
2017-03-22 17:23:45 +08:00
|
|
|
seq_printf(s, " - inmem: %4d, atomic IO: %4d (Max. %4d), "
|
|
|
|
|
"volatile IO: %4d (Max. %4d)\n",
|
|
|
|
|
si->inmem_pages, si->aw_cnt, si->max_aw_cnt,
|
|
|
|
|
si->vw_cnt, si->max_vw_cnt);
|
2016-10-21 10:09:57 +08:00
|
|
|
seq_printf(s, " - nodes: %4d in %4d\n",
|
2012-11-03 05:50:41 +08:00
|
|
|
si->ndirty_node, si->node_pages);
|
2016-10-21 10:09:57 +08:00
|
|
|
seq_printf(s, " - dents: %4d in dirs:%4d (%4d)\n",
|
2016-05-21 02:10:10 +08:00
|
|
|
si->ndirty_dent, si->ndirty_dirs, si->ndirty_all);
|
2016-10-21 10:09:57 +08:00
|
|
|
seq_printf(s, " - datas: %4d in files:%4d\n",
|
2015-12-17 17:14:44 +08:00
|
|
|
si->ndirty_data, si->ndirty_files);
|
2017-11-14 09:46:38 +08:00
|
|
|
seq_printf(s, " - quota datas: %4d in quota files:%4d\n",
|
|
|
|
|
si->ndirty_qdata, si->nquota_files);
|
2016-10-21 10:09:57 +08:00
|
|
|
seq_printf(s, " - meta: %4d in %4d\n",
|
2012-11-03 05:50:41 +08:00
|
|
|
si->ndirty_meta, si->meta_pages);
|
2016-10-21 10:09:57 +08:00
|
|
|
seq_printf(s, " - imeta: %4d\n",
|
2016-09-18 23:30:08 +08:00
|
|
|
si->ndirty_imeta);
|
2015-01-08 03:09:37 +08:00
|
|
|
seq_printf(s, " - NATs: %9d/%9d\n - SITs: %9d/%9d\n",
|
|
|
|
|
si->dirty_nats, si->nats, si->dirty_sits, si->sits);
|
2017-05-02 09:13:03 +08:00
|
|
|
seq_printf(s, " - free_nids: %9d/%9d\n - alloc_nids: %9d\n",
|
|
|
|
|
si->free_nids, si->avail_nids, si->alloc_nids);
|
2013-07-22 16:33:32 +08:00
|
|
|
seq_puts(s, "\nDistribution of User Blocks:");
|
|
|
|
|
seq_puts(s, " [ valid | invalid | free ]\n");
|
|
|
|
|
seq_puts(s, " [");
|
2012-11-03 05:50:41 +08:00
|
|
|
|
|
|
|
|
for (j = 0; j < si->util_valid; j++)
|
2013-07-22 16:33:32 +08:00
|
|
|
seq_putc(s, '-');
|
|
|
|
|
seq_putc(s, '|');
|
2012-11-03 05:50:41 +08:00
|
|
|
|
|
|
|
|
for (j = 0; j < si->util_invalid; j++)
|
2013-07-22 16:33:32 +08:00
|
|
|
seq_putc(s, '-');
|
|
|
|
|
seq_putc(s, '|');
|
2012-11-03 05:50:41 +08:00
|
|
|
|
|
|
|
|
for (j = 0; j < si->util_free; j++)
|
2013-07-22 16:33:32 +08:00
|
|
|
seq_putc(s, '-');
|
|
|
|
|
seq_puts(s, "]\n\n");
|
2014-12-24 01:16:54 +08:00
|
|
|
seq_printf(s, "IPU: %u blocks\n", si->inplace_count);
|
2012-11-03 05:50:41 +08:00
|
|
|
seq_printf(s, "SSR: %u blocks in %u segments\n",
|
|
|
|
|
si->block_count[SSR], si->segment_count[SSR]);
|
|
|
|
|
seq_printf(s, "LFS: %u blocks in %u segments\n",
|
|
|
|
|
si->block_count[LFS], si->segment_count[LFS]);
|
|
|
|
|
|
|
|
|
|
/* segment usage info */
|
|
|
|
|
update_sit_info(si->sbi);
|
|
|
|
|
seq_printf(s, "\nBDF: %u, avg. vblocks: %u\n",
|
|
|
|
|
si->bimodal, si->avg_vblocks);
|
|
|
|
|
|
|
|
|
|
/* memory footprint */
|
|
|
|
|
update_mem_info(si->sbi);
|
2015-09-11 14:43:52 +08:00
|
|
|
seq_printf(s, "\nMemory: %llu KB\n",
|
2015-01-11 13:37:36 +08:00
|
|
|
(si->base_mem + si->cache_mem + si->page_mem) >> 10);
|
2015-09-11 14:43:52 +08:00
|
|
|
seq_printf(s, " - static: %llu KB\n",
|
2015-01-11 13:37:36 +08:00
|
|
|
si->base_mem >> 10);
|
2015-09-11 14:43:52 +08:00
|
|
|
seq_printf(s, " - cached: %llu KB\n",
|
2015-01-11 13:37:36 +08:00
|
|
|
si->cache_mem >> 10);
|
2015-09-11 14:43:52 +08:00
|
|
|
seq_printf(s, " - paged : %llu KB\n",
|
2015-01-11 13:37:36 +08:00
|
|
|
si->page_mem >> 10);
|
2012-11-03 05:50:41 +08:00
|
|
|
}
|
2013-01-14 20:08:16 +08:00
|
|
|
mutex_unlock(&f2fs_stat_mutex);
|
2012-11-03 05:50:41 +08:00
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int stat_open(struct inode *inode, struct file *file)
|
|
|
|
|
{
|
|
|
|
|
return single_open(file, stat_show, inode->i_private);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static const struct file_operations stat_fops = {
|
2016-11-21 02:57:23 +08:00
|
|
|
.owner = THIS_MODULE,
|
2012-11-03 05:50:41 +08:00
|
|
|
.open = stat_open,
|
|
|
|
|
.read = seq_read,
|
|
|
|
|
.llseek = seq_lseek,
|
|
|
|
|
.release = single_release,
|
|
|
|
|
};
|
|
|
|
|
|
2013-01-15 18:58:47 +08:00
|
|
|
int f2fs_build_stats(struct f2fs_sb_info *sbi)
|
2012-11-03 05:50:41 +08:00
|
|
|
{
|
|
|
|
|
struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
|
|
|
|
|
struct f2fs_stat_info *si;
|
|
|
|
|
|
2017-11-30 19:28:17 +08:00
|
|
|
si = f2fs_kzalloc(sbi, sizeof(struct f2fs_stat_info), GFP_KERNEL);
|
2013-07-12 14:47:11 +08:00
|
|
|
if (!si)
|
2012-11-03 05:50:41 +08:00
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
|
|
si->all_area_segs = le32_to_cpu(raw_super->segment_count);
|
|
|
|
|
si->sit_area_segs = le32_to_cpu(raw_super->segment_count_sit);
|
|
|
|
|
si->nat_area_segs = le32_to_cpu(raw_super->segment_count_nat);
|
|
|
|
|
si->ssa_area_segs = le32_to_cpu(raw_super->segment_count_ssa);
|
|
|
|
|
si->main_area_segs = le32_to_cpu(raw_super->segment_count_main);
|
|
|
|
|
si->main_area_sections = le32_to_cpu(raw_super->section_count);
|
|
|
|
|
si->main_area_zones = si->main_area_sections /
|
|
|
|
|
le32_to_cpu(raw_super->secs_per_zone);
|
|
|
|
|
si->sbi = sbi;
|
2013-07-12 14:47:11 +08:00
|
|
|
sbi->stat_info = si;
|
2013-01-14 20:08:16 +08:00
|
|
|
|
2015-09-30 17:38:48 +08:00
|
|
|
atomic64_set(&sbi->total_hit_ext, 0);
|
|
|
|
|
atomic64_set(&sbi->read_hit_rbtree, 0);
|
|
|
|
|
atomic64_set(&sbi->read_hit_largest, 0);
|
|
|
|
|
atomic64_set(&sbi->read_hit_cached, 0);
|
2015-07-15 17:29:49 +08:00
|
|
|
|
2015-07-15 17:28:53 +08:00
|
|
|
atomic_set(&sbi->inline_xattr, 0);
|
2014-12-08 19:08:20 +08:00
|
|
|
atomic_set(&sbi->inline_inode, 0);
|
|
|
|
|
atomic_set(&sbi->inline_dir, 0);
|
2014-12-24 01:16:54 +08:00
|
|
|
atomic_set(&sbi->inplace_count, 0);
|
2014-12-08 19:08:20 +08:00
|
|
|
|
2016-12-29 05:55:09 +08:00
|
|
|
atomic_set(&sbi->aw_cnt, 0);
|
2017-03-22 17:23:45 +08:00
|
|
|
atomic_set(&sbi->vw_cnt, 0);
|
2016-12-29 05:55:09 +08:00
|
|
|
atomic_set(&sbi->max_aw_cnt, 0);
|
2017-03-22 17:23:45 +08:00
|
|
|
atomic_set(&sbi->max_vw_cnt, 0);
|
2016-12-29 05:55:09 +08:00
|
|
|
|
2013-01-14 20:08:16 +08:00
|
|
|
mutex_lock(&f2fs_stat_mutex);
|
|
|
|
|
list_add_tail(&si->stat_list, &f2fs_stat_list);
|
|
|
|
|
mutex_unlock(&f2fs_stat_mutex);
|
|
|
|
|
|
2012-11-03 05:50:41 +08:00
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void f2fs_destroy_stats(struct f2fs_sb_info *sbi)
|
|
|
|
|
{
|
2013-07-12 14:47:11 +08:00
|
|
|
struct f2fs_stat_info *si = F2FS_STAT(sbi);
|
2012-11-03 05:50:41 +08:00
|
|
|
|
2013-01-14 20:08:16 +08:00
|
|
|
mutex_lock(&f2fs_stat_mutex);
|
2012-11-03 05:50:41 +08:00
|
|
|
list_del(&si->stat_list);
|
2013-01-14 20:08:16 +08:00
|
|
|
mutex_unlock(&f2fs_stat_mutex);
|
|
|
|
|
|
2013-07-12 14:47:11 +08:00
|
|
|
kfree(si);
|
2012-11-03 05:50:41 +08:00
|
|
|
}
|
|
|
|
|
|
2015-10-29 09:13:04 +08:00
|
|
|
int __init f2fs_create_root_stats(void)
|
2013-01-15 18:58:47 +08:00
|
|
|
{
|
2013-12-03 20:11:46 +08:00
|
|
|
struct dentry *file;
|
|
|
|
|
|
2013-12-03 21:09:29 +08:00
|
|
|
f2fs_debugfs_root = debugfs_create_dir("f2fs", NULL);
|
|
|
|
|
if (!f2fs_debugfs_root)
|
2015-10-29 09:13:04 +08:00
|
|
|
return -ENOMEM;
|
2013-12-03 20:11:46 +08:00
|
|
|
|
2013-12-03 21:09:29 +08:00
|
|
|
file = debugfs_create_file("status", S_IRUGO, f2fs_debugfs_root,
|
2013-12-03 20:11:46 +08:00
|
|
|
NULL, &stat_fops);
|
2014-07-11 18:35:43 +08:00
|
|
|
if (!file) {
|
|
|
|
|
debugfs_remove(f2fs_debugfs_root);
|
|
|
|
|
f2fs_debugfs_root = NULL;
|
2015-10-29 09:13:04 +08:00
|
|
|
return -ENOMEM;
|
2014-07-11 18:35:43 +08:00
|
|
|
}
|
2015-10-29 09:13:04 +08:00
|
|
|
|
|
|
|
|
return 0;
|
2013-01-15 18:58:47 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void f2fs_destroy_root_stats(void)
|
2012-11-03 05:50:41 +08:00
|
|
|
{
|
2013-12-03 21:09:29 +08:00
|
|
|
if (!f2fs_debugfs_root)
|
2013-12-03 20:11:46 +08:00
|
|
|
return;
|
|
|
|
|
|
2013-12-03 21:09:29 +08:00
|
|
|
debugfs_remove_recursive(f2fs_debugfs_root);
|
|
|
|
|
f2fs_debugfs_root = NULL;
|
2012-11-03 05:50:41 +08:00
|
|
|
}
|
