Revision 13212b54d18d5235fb97fbdcba8ae453fd2a3a51 authored by Zhao Lei on 12 February 2015, 06:18:17 UTC, committed by Chris Mason on 14 February 2015, 16:19:14 UTC
Btrfs will report NO_SPACE when we create and remove files for several times, and we can't write to filesystem until mount it again. Steps to reproduce: 1: Create a single-dev btrfs fs with default option 2: Write a file into it to take up most fs space 3: Delete above file 4: Wait about 100s to let chunk removed 5: goto 2 Script is like following: #!/bin/bash # Recommend 1.2G space, too large disk will make test slow DEV="/dev/sda16" MNT="/mnt/tmp" dev_size="$(lsblk -bn -o SIZE "$DEV")" || exit 2 file_size_m=$((dev_size * 75 / 100 / 1024 / 1024)) echo "Loop write ${file_size_m}M file on $((dev_size / 1024 / 1024))M dev" for ((i = 0; i < 10; i++)); do umount "$MNT" 2>/dev/null; done echo "mkfs $DEV" mkfs.btrfs -f "$DEV" >/dev/null || exit 2 echo "mount $DEV $MNT" mount "$DEV" "$MNT" || exit 2 for ((loop_i = 0; loop_i < 20; loop_i++)); do echo echo "loop $loop_i" echo "dd file..." cmd=(dd if=/dev/zero of="$MNT"/file0 bs=1M count="$file_size_m") "${cmd[@]}" 2>/dev/null || { # NO_SPACE error triggered echo "dd failed: ${cmd[*]}" exit 1 } echo "rm file..." rm -f "$MNT"/file0 || exit 2 for ((i = 0; i < 10; i++)); do df "$MNT" | tail -1 sleep 10 done done Reason: It is triggered by commit: 47ab2a6c689913db23ccae38349714edf8365e0a which is used to remove empty block groups automatically, but the reason is not in that patch. Code before works well because btrfs don't need to create and delete chunks so many times with high complexity. Above bug is caused by many reason, any of them can trigger it. Reason1: When we remove some continuous chunks but leave other chunks after, these disk space should be used by chunk-recreating, but in current code, only first create will successed. Fixed by Forrest Liu <forrestl@synology.com> in: Btrfs: fix find_free_dev_extent() malfunction in case device tree has hole Reason2: contains_pending_extent() return wrong value in calculation. Fixed by Forrest Liu <forrestl@synology.com> in: Btrfs: fix find_free_dev_extent() malfunction in case device tree has hole Reason3: btrfs_check_data_free_space() try to commit transaction and retry allocating chunk when the first allocating failed, but space_info->full is set in first allocating, and prevent second allocating in retry. Fixed in this patch by clear space_info->full in commit transaction. Tested for severial times by above script. Changelog v3->v4: use light weight int instead of atomic_t to record have_remove_bgs in transaction, suggested by: Josef Bacik <jbacik@fb.com> Changelog v2->v3: v2 fixed the bug by adding more commit-transaction, but we only need to reclaim space when we are really have no space for new chunk, noticed by: Filipe David Manana <fdmanana@gmail.com> Actually, our code already have this type of commit-and-retry, we only need to make it working with removed-bgs. v3 fixed the bug with above way. Changelog v1->v2: v1 will introduce a new bug when delete and create chunk in same disk space in same transaction, noticed by: Filipe David Manana <fdmanana@gmail.com> V2 fix this bug by commit transaction after remove block grops. Reported-by: Tsutomu Itoh <t-itoh@jp.fujitsu.com> Suggested-by: Filipe David Manana <fdmanana@gmail.com> Suggested-by: Josef Bacik <jbacik@fb.com> Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com> Signed-off-by: Chris Mason <clm@fb.com>
1 parent f55985f
hwpoison-inject.c
/* Inject a hwpoison memory failure on a arbitrary pfn */
#include <linux/module.h>
#include <linux/debugfs.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/pagemap.h>
#include <linux/hugetlb.h>
#include "internal.h"
static struct dentry *hwpoison_dir;
static int hwpoison_inject(void *data, u64 val)
{
unsigned long pfn = val;
struct page *p;
struct page *hpage;
int err;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!pfn_valid(pfn))
return -ENXIO;
p = pfn_to_page(pfn);
hpage = compound_head(p);
/*
* This implies unable to support free buddy pages.
*/
if (!get_page_unless_zero(hpage))
return 0;
if (!hwpoison_filter_enable)
goto inject;
if (!PageLRU(p) && !PageHuge(p))
shake_page(p, 0);
/*
* This implies unable to support non-LRU pages.
*/
if (!PageLRU(p) && !PageHuge(p))
return 0;
/*
* do a racy check with elevated page count, to make sure PG_hwpoison
* will only be set for the targeted owner (or on a free page).
* We temporarily take page lock for try_get_mem_cgroup_from_page().
* memory_failure() will redo the check reliably inside page lock.
*/
lock_page(hpage);
err = hwpoison_filter(hpage);
unlock_page(hpage);
if (err)
return 0;
inject:
pr_info("Injecting memory failure at pfn %#lx\n", pfn);
return memory_failure(pfn, 18, MF_COUNT_INCREASED);
}
static int hwpoison_unpoison(void *data, u64 val)
{
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
return unpoison_memory(val);
}
DEFINE_SIMPLE_ATTRIBUTE(hwpoison_fops, NULL, hwpoison_inject, "%lli\n");
DEFINE_SIMPLE_ATTRIBUTE(unpoison_fops, NULL, hwpoison_unpoison, "%lli\n");
static void pfn_inject_exit(void)
{
debugfs_remove_recursive(hwpoison_dir);
}
static int pfn_inject_init(void)
{
struct dentry *dentry;
hwpoison_dir = debugfs_create_dir("hwpoison", NULL);
if (hwpoison_dir == NULL)
return -ENOMEM;
/*
* Note that the below poison/unpoison interfaces do not involve
* hardware status change, hence do not require hardware support.
* They are mainly for testing hwpoison in software level.
*/
dentry = debugfs_create_file("corrupt-pfn", 0200, hwpoison_dir,
NULL, &hwpoison_fops);
if (!dentry)
goto fail;
dentry = debugfs_create_file("unpoison-pfn", 0200, hwpoison_dir,
NULL, &unpoison_fops);
if (!dentry)
goto fail;
dentry = debugfs_create_u32("corrupt-filter-enable", 0600,
hwpoison_dir, &hwpoison_filter_enable);
if (!dentry)
goto fail;
dentry = debugfs_create_u32("corrupt-filter-dev-major", 0600,
hwpoison_dir, &hwpoison_filter_dev_major);
if (!dentry)
goto fail;
dentry = debugfs_create_u32("corrupt-filter-dev-minor", 0600,
hwpoison_dir, &hwpoison_filter_dev_minor);
if (!dentry)
goto fail;
dentry = debugfs_create_u64("corrupt-filter-flags-mask", 0600,
hwpoison_dir, &hwpoison_filter_flags_mask);
if (!dentry)
goto fail;
dentry = debugfs_create_u64("corrupt-filter-flags-value", 0600,
hwpoison_dir, &hwpoison_filter_flags_value);
if (!dentry)
goto fail;
#ifdef CONFIG_MEMCG_SWAP
dentry = debugfs_create_u64("corrupt-filter-memcg", 0600,
hwpoison_dir, &hwpoison_filter_memcg);
if (!dentry)
goto fail;
#endif
return 0;
fail:
pfn_inject_exit();
return -ENOMEM;
}
module_init(pfn_inject_init);
module_exit(pfn_inject_exit);
MODULE_LICENSE("GPL");
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...