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
balloon_compaction.c
/*
* mm/balloon_compaction.c
*
* Common interface for making balloon pages movable by compaction.
*
* Copyright (C) 2012, Red Hat, Inc. Rafael Aquini <aquini@redhat.com>
*/
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/export.h>
#include <linux/balloon_compaction.h>
/*
* balloon_page_enqueue - allocates a new page and inserts it into the balloon
* page list.
* @b_dev_info: balloon device decriptor where we will insert a new page to
*
* Driver must call it to properly allocate a new enlisted balloon page
* before definetively removing it from the guest system.
* This function returns the page address for the recently enqueued page or
* NULL in the case we fail to allocate a new page this turn.
*/
struct page *balloon_page_enqueue(struct balloon_dev_info *b_dev_info)
{
unsigned long flags;
struct page *page = alloc_page(balloon_mapping_gfp_mask() |
__GFP_NOMEMALLOC | __GFP_NORETRY);
if (!page)
return NULL;
/*
* Block others from accessing the 'page' when we get around to
* establishing additional references. We should be the only one
* holding a reference to the 'page' at this point.
*/
BUG_ON(!trylock_page(page));
spin_lock_irqsave(&b_dev_info->pages_lock, flags);
balloon_page_insert(b_dev_info, page);
__count_vm_event(BALLOON_INFLATE);
spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
unlock_page(page);
return page;
}
EXPORT_SYMBOL_GPL(balloon_page_enqueue);
/*
* balloon_page_dequeue - removes a page from balloon's page list and returns
* the its address to allow the driver release the page.
* @b_dev_info: balloon device decriptor where we will grab a page from.
*
* Driver must call it to properly de-allocate a previous enlisted balloon page
* before definetively releasing it back to the guest system.
* This function returns the page address for the recently dequeued page or
* NULL in the case we find balloon's page list temporarily empty due to
* compaction isolated pages.
*/
struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info)
{
struct page *page, *tmp;
unsigned long flags;
bool dequeued_page;
dequeued_page = false;
list_for_each_entry_safe(page, tmp, &b_dev_info->pages, lru) {
/*
* Block others from accessing the 'page' while we get around
* establishing additional references and preparing the 'page'
* to be released by the balloon driver.
*/
if (trylock_page(page)) {
#ifdef CONFIG_BALLOON_COMPACTION
if (!PagePrivate(page)) {
/* raced with isolation */
unlock_page(page);
continue;
}
#endif
spin_lock_irqsave(&b_dev_info->pages_lock, flags);
balloon_page_delete(page);
__count_vm_event(BALLOON_DEFLATE);
spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
unlock_page(page);
dequeued_page = true;
break;
}
}
if (!dequeued_page) {
/*
* If we are unable to dequeue a balloon page because the page
* list is empty and there is no isolated pages, then something
* went out of track and some balloon pages are lost.
* BUG() here, otherwise the balloon driver may get stuck into
* an infinite loop while attempting to release all its pages.
*/
spin_lock_irqsave(&b_dev_info->pages_lock, flags);
if (unlikely(list_empty(&b_dev_info->pages) &&
!b_dev_info->isolated_pages))
BUG();
spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
page = NULL;
}
return page;
}
EXPORT_SYMBOL_GPL(balloon_page_dequeue);
#ifdef CONFIG_BALLOON_COMPACTION
static inline void __isolate_balloon_page(struct page *page)
{
struct balloon_dev_info *b_dev_info = balloon_page_device(page);
unsigned long flags;
spin_lock_irqsave(&b_dev_info->pages_lock, flags);
ClearPagePrivate(page);
list_del(&page->lru);
b_dev_info->isolated_pages++;
spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
}
static inline void __putback_balloon_page(struct page *page)
{
struct balloon_dev_info *b_dev_info = balloon_page_device(page);
unsigned long flags;
spin_lock_irqsave(&b_dev_info->pages_lock, flags);
SetPagePrivate(page);
list_add(&page->lru, &b_dev_info->pages);
b_dev_info->isolated_pages--;
spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
}
/* __isolate_lru_page() counterpart for a ballooned page */
bool balloon_page_isolate(struct page *page)
{
/*
* Avoid burning cycles with pages that are yet under __free_pages(),
* or just got freed under us.
*
* In case we 'win' a race for a balloon page being freed under us and
* raise its refcount preventing __free_pages() from doing its job
* the put_page() at the end of this block will take care of
* release this page, thus avoiding a nasty leakage.
*/
if (likely(get_page_unless_zero(page))) {
/*
* As balloon pages are not isolated from LRU lists, concurrent
* compaction threads can race against page migration functions
* as well as race against the balloon driver releasing a page.
*
* In order to avoid having an already isolated balloon page
* being (wrongly) re-isolated while it is under migration,
* or to avoid attempting to isolate pages being released by
* the balloon driver, lets be sure we have the page lock
* before proceeding with the balloon page isolation steps.
*/
if (likely(trylock_page(page))) {
/*
* A ballooned page, by default, has PagePrivate set.
* Prevent concurrent compaction threads from isolating
* an already isolated balloon page by clearing it.
*/
if (balloon_page_movable(page)) {
__isolate_balloon_page(page);
unlock_page(page);
return true;
}
unlock_page(page);
}
put_page(page);
}
return false;
}
/* putback_lru_page() counterpart for a ballooned page */
void balloon_page_putback(struct page *page)
{
/*
* 'lock_page()' stabilizes the page and prevents races against
* concurrent isolation threads attempting to re-isolate it.
*/
lock_page(page);
if (__is_movable_balloon_page(page)) {
__putback_balloon_page(page);
/* drop the extra ref count taken for page isolation */
put_page(page);
} else {
WARN_ON(1);
dump_page(page, "not movable balloon page");
}
unlock_page(page);
}
/* move_to_new_page() counterpart for a ballooned page */
int balloon_page_migrate(struct page *newpage,
struct page *page, enum migrate_mode mode)
{
struct balloon_dev_info *balloon = balloon_page_device(page);
int rc = -EAGAIN;
/*
* Block others from accessing the 'newpage' when we get around to
* establishing additional references. We should be the only one
* holding a reference to the 'newpage' at this point.
*/
BUG_ON(!trylock_page(newpage));
if (WARN_ON(!__is_movable_balloon_page(page))) {
dump_page(page, "not movable balloon page");
unlock_page(newpage);
return rc;
}
if (balloon && balloon->migratepage)
rc = balloon->migratepage(balloon, newpage, page, mode);
unlock_page(newpage);
return rc;
}
#endif /* CONFIG_BALLOON_COMPACTION */
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...