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
mm_init.c
/*
* mm_init.c - Memory initialisation verification and debugging
*
* Copyright 2008 IBM Corporation, 2008
* Author Mel Gorman <mel@csn.ul.ie>
*
*/
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/kobject.h>
#include <linux/export.h>
#include <linux/memory.h>
#include <linux/notifier.h>
#include "internal.h"
#ifdef CONFIG_DEBUG_MEMORY_INIT
int mminit_loglevel;
#ifndef SECTIONS_SHIFT
#define SECTIONS_SHIFT 0
#endif
/* The zonelists are simply reported, validation is manual. */
void mminit_verify_zonelist(void)
{
int nid;
if (mminit_loglevel < MMINIT_VERIFY)
return;
for_each_online_node(nid) {
pg_data_t *pgdat = NODE_DATA(nid);
struct zone *zone;
struct zoneref *z;
struct zonelist *zonelist;
int i, listid, zoneid;
BUG_ON(MAX_ZONELISTS > 2);
for (i = 0; i < MAX_ZONELISTS * MAX_NR_ZONES; i++) {
/* Identify the zone and nodelist */
zoneid = i % MAX_NR_ZONES;
listid = i / MAX_NR_ZONES;
zonelist = &pgdat->node_zonelists[listid];
zone = &pgdat->node_zones[zoneid];
if (!populated_zone(zone))
continue;
/* Print information about the zonelist */
printk(KERN_DEBUG "mminit::zonelist %s %d:%s = ",
listid > 0 ? "thisnode" : "general", nid,
zone->name);
/* Iterate the zonelist */
for_each_zone_zonelist(zone, z, zonelist, zoneid) {
#ifdef CONFIG_NUMA
printk(KERN_CONT "%d:%s ",
zone->node, zone->name);
#else
printk(KERN_CONT "0:%s ", zone->name);
#endif /* CONFIG_NUMA */
}
printk(KERN_CONT "\n");
}
}
}
void __init mminit_verify_pageflags_layout(void)
{
int shift, width;
unsigned long or_mask, add_mask;
shift = 8 * sizeof(unsigned long);
width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH - LAST_CPUPID_SHIFT;
mminit_dprintk(MMINIT_TRACE, "pageflags_layout_widths",
"Section %d Node %d Zone %d Lastcpupid %d Flags %d\n",
SECTIONS_WIDTH,
NODES_WIDTH,
ZONES_WIDTH,
LAST_CPUPID_WIDTH,
NR_PAGEFLAGS);
mminit_dprintk(MMINIT_TRACE, "pageflags_layout_shifts",
"Section %d Node %d Zone %d Lastcpupid %d\n",
SECTIONS_SHIFT,
NODES_SHIFT,
ZONES_SHIFT,
LAST_CPUPID_SHIFT);
mminit_dprintk(MMINIT_TRACE, "pageflags_layout_pgshifts",
"Section %lu Node %lu Zone %lu Lastcpupid %lu\n",
(unsigned long)SECTIONS_PGSHIFT,
(unsigned long)NODES_PGSHIFT,
(unsigned long)ZONES_PGSHIFT,
(unsigned long)LAST_CPUPID_PGSHIFT);
mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodezoneid",
"Node/Zone ID: %lu -> %lu\n",
(unsigned long)(ZONEID_PGOFF + ZONEID_SHIFT),
(unsigned long)ZONEID_PGOFF);
mminit_dprintk(MMINIT_TRACE, "pageflags_layout_usage",
"location: %d -> %d layout %d -> %d unused %d -> %d page-flags\n",
shift, width, width, NR_PAGEFLAGS, NR_PAGEFLAGS, 0);
#ifdef NODE_NOT_IN_PAGE_FLAGS
mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags",
"Node not in page flags");
#endif
#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags",
"Last cpupid not in page flags");
#endif
if (SECTIONS_WIDTH) {
shift -= SECTIONS_WIDTH;
BUG_ON(shift != SECTIONS_PGSHIFT);
}
if (NODES_WIDTH) {
shift -= NODES_WIDTH;
BUG_ON(shift != NODES_PGSHIFT);
}
if (ZONES_WIDTH) {
shift -= ZONES_WIDTH;
BUG_ON(shift != ZONES_PGSHIFT);
}
/* Check for bitmask overlaps */
or_mask = (ZONES_MASK << ZONES_PGSHIFT) |
(NODES_MASK << NODES_PGSHIFT) |
(SECTIONS_MASK << SECTIONS_PGSHIFT);
add_mask = (ZONES_MASK << ZONES_PGSHIFT) +
(NODES_MASK << NODES_PGSHIFT) +
(SECTIONS_MASK << SECTIONS_PGSHIFT);
BUG_ON(or_mask != add_mask);
}
void __meminit mminit_verify_page_links(struct page *page, enum zone_type zone,
unsigned long nid, unsigned long pfn)
{
BUG_ON(page_to_nid(page) != nid);
BUG_ON(page_zonenum(page) != zone);
BUG_ON(page_to_pfn(page) != pfn);
}
static __init int set_mminit_loglevel(char *str)
{
get_option(&str, &mminit_loglevel);
return 0;
}
early_param("mminit_loglevel", set_mminit_loglevel);
#endif /* CONFIG_DEBUG_MEMORY_INIT */
struct kobject *mm_kobj;
EXPORT_SYMBOL_GPL(mm_kobj);
#ifdef CONFIG_SMP
s32 vm_committed_as_batch = 32;
static void __meminit mm_compute_batch(void)
{
u64 memsized_batch;
s32 nr = num_present_cpus();
s32 batch = max_t(s32, nr*2, 32);
/* batch size set to 0.4% of (total memory/#cpus), or max int32 */
memsized_batch = min_t(u64, (totalram_pages/nr)/256, 0x7fffffff);
vm_committed_as_batch = max_t(s32, memsized_batch, batch);
}
static int __meminit mm_compute_batch_notifier(struct notifier_block *self,
unsigned long action, void *arg)
{
switch (action) {
case MEM_ONLINE:
case MEM_OFFLINE:
mm_compute_batch();
default:
break;
}
return NOTIFY_OK;
}
static struct notifier_block compute_batch_nb __meminitdata = {
.notifier_call = mm_compute_batch_notifier,
.priority = IPC_CALLBACK_PRI, /* use lowest priority */
};
static int __init mm_compute_batch_init(void)
{
mm_compute_batch();
register_hotmemory_notifier(&compute_batch_nb);
return 0;
}
__initcall(mm_compute_batch_init);
#endif
static int __init mm_sysfs_init(void)
{
mm_kobj = kobject_create_and_add("mm", kernel_kobj);
if (!mm_kobj)
return -ENOMEM;
return 0;
}
postcore_initcall(mm_sysfs_init);
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...