Re: [PATCH v3 1/2] btrfs: Enhance btrfs_trim_fs function to handle error better
On Wed, Aug 29, 2018 at 05:40:12PM +0300, Nikolay Borisov wrote:
>
>
> On 29.08.2018 16:53, Qu Wenruo wrote:
> >
> >
> > On 2018/8/29 下午9:43, Nikolay Borisov wrote:
> >>
> >>
> >> On 29.08.2018 08:15, Qu Wenruo wrote:
> >>> Function btrfs_trim_fs() doesn't handle errors in a consistent way, if
> >>> error happens when trimming existing block groups, it will skip the
> >>> remaining blocks and continue to trim unallocated space for each device.
> >>>
> >>> And the return value will only reflect the final error from device
> >>> trimming.
> >>>
> >>> This patch will fix such behavior by:
> >>>
> >>> 1) Recording last error from block group or device trimming
> >>>So return value will also reflect the last error during trimming.
> >>>Make developer more aware of the problem.
> >>>
> >>> 2) Continuing trimming if we can
> >>>If we failed to trim one block group or device, we could still try
> >>>next block group or device.
> >>>
> >>> 3) Report number of failures during block group and device trimming
> >>>So it would be less noisy, but still gives user a brief summary of
> >>>what's going wrong.
> >>>
> >>> Such behavior can avoid confusion for case like failure to trim the
> >>> first block group and then only unallocated space is trimmed.
> >>>
> >>> Reported-by: Chris Murphy
> >>> Signed-off-by: Qu Wenruo
> >>> ---
> >>> fs/btrfs/extent-tree.c | 57 ++
> >>> 1 file changed, 41 insertions(+), 16 deletions(-)
> >>>
> >>> diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
> >>> index de6f75f5547b..7768f206196a 100644
> >>> --- a/fs/btrfs/extent-tree.c
> >>> +++ b/fs/btrfs/extent-tree.c
> >>> @@ -10832,6 +10832,16 @@ static int btrfs_trim_free_extents(struct
> >>> btrfs_device *device,
> >>> return ret;
> >>> }
> >>>
> >>> +/*
> >>> + * Trim the whole fs, by:
> >>> + * 1) Trimming free space in each block group
> >>> + * 2) Trimming unallocated space in each device
> >>> + *
> >>> + * Will try to continue trimming even if we failed to trim one block
> >>> group or
> >>> + * device.
> >>> + * The return value will be the last error during trim.
> >>> + * Or 0 if nothing wrong happened.
> >>> + */
> >>> int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range
> >>> *range)
> >>> {
> >>> struct btrfs_block_group_cache *cache = NULL;
> >>> @@ -10842,6 +10852,10 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info,
> >>> struct fstrim_range *range)
> >>> u64 end;
> >>> u64 trimmed = 0;
> >>> u64 total_bytes = btrfs_super_total_bytes(fs_info->super_copy);
> >>> + u64 bg_failed = 0;
> >>> + u64 dev_failed = 0;
> >>> + int bg_ret = 0;
> >>> + int dev_ret = 0;
> >>> int ret = 0;
> >>>
> >>> /*
> >>> @@ -10852,7 +10866,7 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info,
> >>> struct fstrim_range *range)
> >>> else
> >>> cache = btrfs_lookup_block_group(fs_info, range->start);
> >>>
> >>> - while (cache) {
> >>> + for (; cache; cache = next_block_group(fs_info, cache)) {
> >>> if (cache->key.objectid >= (range->start + range->len)) {
> >>> btrfs_put_block_group(cache);
> >>> break;
> >>> @@ -10866,45 +10880,56 @@ int btrfs_trim_fs(struct btrfs_fs_info
> >>> *fs_info, struct fstrim_range *range)
> >>> if (!block_group_cache_done(cache)) {
> >>> ret = cache_block_group(cache, 0);
> >>> if (ret) {
> >>> - btrfs_put_block_group(cache);
> >>> - break;
> >>> + bg_failed++;
> >>> + bg_ret = ret;
> >>> + continue;
> >>> }
> >>> ret = wait_block_group_cache_done(cache);
> >>> if (ret) {
> >>> - btrfs_put_block_group(cache);
> >>> - break;
> >>> + bg_failed++;
> >>> + bg_ret = ret;
> >>> + continue;
> >>> }
> >>> }
> >>> - ret = btrfs_trim_block_group(cache,
> >>> - _trimmed,
> >>> - start,
> >>> - end,
> >>> - range->minlen);
> >>> + ret = btrfs_trim_block_group(cache, _trimmed,
> >>> + start, end, range->minlen);
> >>>
> >>> trimmed += group_trimmed;
> >>> if (ret) {
> >>> - btrfs_put_block_group(cache);
> >>> - break;
> >>> + bg_failed++;
> >>> + bg_ret = ret;
> >>> +
Re: [PATCH v3 1/2] btrfs: Enhance btrfs_trim_fs function to handle error better
On 29.08.2018 16:53, Qu Wenruo wrote:
>
>
> On 2018/8/29 下午9:43, Nikolay Borisov wrote:
>>
>>
>> On 29.08.2018 08:15, Qu Wenruo wrote:
>>> Function btrfs_trim_fs() doesn't handle errors in a consistent way, if
>>> error happens when trimming existing block groups, it will skip the
>>> remaining blocks and continue to trim unallocated space for each device.
>>>
>>> And the return value will only reflect the final error from device
>>> trimming.
>>>
>>> This patch will fix such behavior by:
>>>
>>> 1) Recording last error from block group or device trimming
>>>So return value will also reflect the last error during trimming.
>>>Make developer more aware of the problem.
>>>
>>> 2) Continuing trimming if we can
>>>If we failed to trim one block group or device, we could still try
>>>next block group or device.
>>>
>>> 3) Report number of failures during block group and device trimming
>>>So it would be less noisy, but still gives user a brief summary of
>>>what's going wrong.
>>>
>>> Such behavior can avoid confusion for case like failure to trim the
>>> first block group and then only unallocated space is trimmed.
>>>
>>> Reported-by: Chris Murphy
>>> Signed-off-by: Qu Wenruo
>>> ---
>>> fs/btrfs/extent-tree.c | 57 ++
>>> 1 file changed, 41 insertions(+), 16 deletions(-)
>>>
>>> diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
>>> index de6f75f5547b..7768f206196a 100644
>>> --- a/fs/btrfs/extent-tree.c
>>> +++ b/fs/btrfs/extent-tree.c
>>> @@ -10832,6 +10832,16 @@ static int btrfs_trim_free_extents(struct
>>> btrfs_device *device,
>>> return ret;
>>> }
>>>
>>> +/*
>>> + * Trim the whole fs, by:
>>> + * 1) Trimming free space in each block group
>>> + * 2) Trimming unallocated space in each device
>>> + *
>>> + * Will try to continue trimming even if we failed to trim one block group
>>> or
>>> + * device.
>>> + * The return value will be the last error during trim.
>>> + * Or 0 if nothing wrong happened.
>>> + */
>>> int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range
>>> *range)
>>> {
>>> struct btrfs_block_group_cache *cache = NULL;
>>> @@ -10842,6 +10852,10 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info,
>>> struct fstrim_range *range)
>>> u64 end;
>>> u64 trimmed = 0;
>>> u64 total_bytes = btrfs_super_total_bytes(fs_info->super_copy);
>>> + u64 bg_failed = 0;
>>> + u64 dev_failed = 0;
>>> + int bg_ret = 0;
>>> + int dev_ret = 0;
>>> int ret = 0;
>>>
>>> /*
>>> @@ -10852,7 +10866,7 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info,
>>> struct fstrim_range *range)
>>> else
>>> cache = btrfs_lookup_block_group(fs_info, range->start);
>>>
>>> - while (cache) {
>>> + for (; cache; cache = next_block_group(fs_info, cache)) {
>>> if (cache->key.objectid >= (range->start + range->len)) {
>>> btrfs_put_block_group(cache);
>>> break;
>>> @@ -10866,45 +10880,56 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info,
>>> struct fstrim_range *range)
>>> if (!block_group_cache_done(cache)) {
>>> ret = cache_block_group(cache, 0);
>>> if (ret) {
>>> - btrfs_put_block_group(cache);
>>> - break;
>>> + bg_failed++;
>>> + bg_ret = ret;
>>> + continue;
>>> }
>>> ret = wait_block_group_cache_done(cache);
>>> if (ret) {
>>> - btrfs_put_block_group(cache);
>>> - break;
>>> + bg_failed++;
>>> + bg_ret = ret;
>>> + continue;
>>> }
>>> }
>>> - ret = btrfs_trim_block_group(cache,
>>> -_trimmed,
>>> -start,
>>> -end,
>>> -range->minlen);
>>> + ret = btrfs_trim_block_group(cache, _trimmed,
>>> + start, end, range->minlen);
>>>
>>> trimmed += group_trimmed;
>>> if (ret) {
>>> - btrfs_put_block_group(cache);
>>> - break;
>>> + bg_failed++;
>>> + bg_ret = ret;
>>> + continue;
>>> }
>>> }
>>> -
>>> - cache = next_block_group(fs_info, cache);
>>> }
>>>
>>> + if (bg_failed)
>>> +
Re: [PATCH v3 1/2] btrfs: Enhance btrfs_trim_fs function to handle error better
On 2018/8/29 下午9:43, Nikolay Borisov wrote:
>
>
> On 29.08.2018 08:15, Qu Wenruo wrote:
>> Function btrfs_trim_fs() doesn't handle errors in a consistent way, if
>> error happens when trimming existing block groups, it will skip the
>> remaining blocks and continue to trim unallocated space for each device.
>>
>> And the return value will only reflect the final error from device
>> trimming.
>>
>> This patch will fix such behavior by:
>>
>> 1) Recording last error from block group or device trimming
>>So return value will also reflect the last error during trimming.
>>Make developer more aware of the problem.
>>
>> 2) Continuing trimming if we can
>>If we failed to trim one block group or device, we could still try
>>next block group or device.
>>
>> 3) Report number of failures during block group and device trimming
>>So it would be less noisy, but still gives user a brief summary of
>>what's going wrong.
>>
>> Such behavior can avoid confusion for case like failure to trim the
>> first block group and then only unallocated space is trimmed.
>>
>> Reported-by: Chris Murphy
>> Signed-off-by: Qu Wenruo
>> ---
>> fs/btrfs/extent-tree.c | 57 ++
>> 1 file changed, 41 insertions(+), 16 deletions(-)
>>
>> diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
>> index de6f75f5547b..7768f206196a 100644
>> --- a/fs/btrfs/extent-tree.c
>> +++ b/fs/btrfs/extent-tree.c
>> @@ -10832,6 +10832,16 @@ static int btrfs_trim_free_extents(struct
>> btrfs_device *device,
>> return ret;
>> }
>>
>> +/*
>> + * Trim the whole fs, by:
>> + * 1) Trimming free space in each block group
>> + * 2) Trimming unallocated space in each device
>> + *
>> + * Will try to continue trimming even if we failed to trim one block group
>> or
>> + * device.
>> + * The return value will be the last error during trim.
>> + * Or 0 if nothing wrong happened.
>> + */
>> int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
>> {
>> struct btrfs_block_group_cache *cache = NULL;
>> @@ -10842,6 +10852,10 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info,
>> struct fstrim_range *range)
>> u64 end;
>> u64 trimmed = 0;
>> u64 total_bytes = btrfs_super_total_bytes(fs_info->super_copy);
>> +u64 bg_failed = 0;
>> +u64 dev_failed = 0;
>> +int bg_ret = 0;
>> +int dev_ret = 0;
>> int ret = 0;
>>
>> /*
>> @@ -10852,7 +10866,7 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info,
>> struct fstrim_range *range)
>> else
>> cache = btrfs_lookup_block_group(fs_info, range->start);
>>
>> -while (cache) {
>> +for (; cache; cache = next_block_group(fs_info, cache)) {
>> if (cache->key.objectid >= (range->start + range->len)) {
>> btrfs_put_block_group(cache);
>> break;
>> @@ -10866,45 +10880,56 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info,
>> struct fstrim_range *range)
>> if (!block_group_cache_done(cache)) {
>> ret = cache_block_group(cache, 0);
>> if (ret) {
>> -btrfs_put_block_group(cache);
>> -break;
>> +bg_failed++;
>> +bg_ret = ret;
>> +continue;
>> }
>> ret = wait_block_group_cache_done(cache);
>> if (ret) {
>> -btrfs_put_block_group(cache);
>> -break;
>> +bg_failed++;
>> +bg_ret = ret;
>> +continue;
>> }
>> }
>> -ret = btrfs_trim_block_group(cache,
>> - _trimmed,
>> - start,
>> - end,
>> - range->minlen);
>> +ret = btrfs_trim_block_group(cache, _trimmed,
>> +start, end, range->minlen);
>>
>> trimmed += group_trimmed;
>> if (ret) {
>> -btrfs_put_block_group(cache);
>> -break;
>> +bg_failed++;
>> +bg_ret = ret;
>> +continue;
>> }
>> }
>> -
>> -cache = next_block_group(fs_info, cache);
>> }
>>
>> +if (bg_failed)
>> +btrfs_warn(fs_info,
>> +"failed to trim %llu block group(s), last error was %d",
>> +
Re: [PATCH v3 1/2] btrfs: Enhance btrfs_trim_fs function to handle error better
On 29.08.2018 08:15, Qu Wenruo wrote:
> Function btrfs_trim_fs() doesn't handle errors in a consistent way, if
> error happens when trimming existing block groups, it will skip the
> remaining blocks and continue to trim unallocated space for each device.
>
> And the return value will only reflect the final error from device
> trimming.
>
> This patch will fix such behavior by:
>
> 1) Recording last error from block group or device trimming
>So return value will also reflect the last error during trimming.
>Make developer more aware of the problem.
>
> 2) Continuing trimming if we can
>If we failed to trim one block group or device, we could still try
>next block group or device.
>
> 3) Report number of failures during block group and device trimming
>So it would be less noisy, but still gives user a brief summary of
>what's going wrong.
>
> Such behavior can avoid confusion for case like failure to trim the
> first block group and then only unallocated space is trimmed.
>
> Reported-by: Chris Murphy
> Signed-off-by: Qu Wenruo
> ---
> fs/btrfs/extent-tree.c | 57 ++
> 1 file changed, 41 insertions(+), 16 deletions(-)
>
> diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
> index de6f75f5547b..7768f206196a 100644
> --- a/fs/btrfs/extent-tree.c
> +++ b/fs/btrfs/extent-tree.c
> @@ -10832,6 +10832,16 @@ static int btrfs_trim_free_extents(struct
> btrfs_device *device,
> return ret;
> }
>
> +/*
> + * Trim the whole fs, by:
> + * 1) Trimming free space in each block group
> + * 2) Trimming unallocated space in each device
> + *
> + * Will try to continue trimming even if we failed to trim one block group or
> + * device.
> + * The return value will be the last error during trim.
> + * Or 0 if nothing wrong happened.
> + */
> int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
> {
> struct btrfs_block_group_cache *cache = NULL;
> @@ -10842,6 +10852,10 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info,
> struct fstrim_range *range)
> u64 end;
> u64 trimmed = 0;
> u64 total_bytes = btrfs_super_total_bytes(fs_info->super_copy);
> + u64 bg_failed = 0;
> + u64 dev_failed = 0;
> + int bg_ret = 0;
> + int dev_ret = 0;
> int ret = 0;
>
> /*
> @@ -10852,7 +10866,7 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info,
> struct fstrim_range *range)
> else
> cache = btrfs_lookup_block_group(fs_info, range->start);
>
> - while (cache) {
> + for (; cache; cache = next_block_group(fs_info, cache)) {
> if (cache->key.objectid >= (range->start + range->len)) {
> btrfs_put_block_group(cache);
> break;
> @@ -10866,45 +10880,56 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info,
> struct fstrim_range *range)
> if (!block_group_cache_done(cache)) {
> ret = cache_block_group(cache, 0);
> if (ret) {
> - btrfs_put_block_group(cache);
> - break;
> + bg_failed++;
> + bg_ret = ret;
> + continue;
> }
> ret = wait_block_group_cache_done(cache);
> if (ret) {
> - btrfs_put_block_group(cache);
> - break;
> + bg_failed++;
> + bg_ret = ret;
> + continue;
> }
> }
> - ret = btrfs_trim_block_group(cache,
> - _trimmed,
> - start,
> - end,
> - range->minlen);
> + ret = btrfs_trim_block_group(cache, _trimmed,
> + start, end, range->minlen);
>
> trimmed += group_trimmed;
> if (ret) {
> - btrfs_put_block_group(cache);
> - break;
> + bg_failed++;
> + bg_ret = ret;
> + continue;
> }
> }
> -
> - cache = next_block_group(fs_info, cache);
> }
>
> + if (bg_failed)
> + btrfs_warn(fs_info,
> + "failed to trim %llu block group(s), last error was %d",
> +bg_failed, bg_ret);
IMO this error handling strategy doesn't really bring any value. The
only thing which the
[PATCH v3 1/2] btrfs: Enhance btrfs_trim_fs function to handle error better
Function btrfs_trim_fs() doesn't handle errors in a consistent way, if
error happens when trimming existing block groups, it will skip the
remaining blocks and continue to trim unallocated space for each device.
And the return value will only reflect the final error from device
trimming.
This patch will fix such behavior by:
1) Recording last error from block group or device trimming
So return value will also reflect the last error during trimming.
Make developer more aware of the problem.
2) Continuing trimming if we can
If we failed to trim one block group or device, we could still try
next block group or device.
3) Report number of failures during block group and device trimming
So it would be less noisy, but still gives user a brief summary of
what's going wrong.
Such behavior can avoid confusion for case like failure to trim the
first block group and then only unallocated space is trimmed.
Reported-by: Chris Murphy
Signed-off-by: Qu Wenruo
---
fs/btrfs/extent-tree.c | 57 ++
1 file changed, 41 insertions(+), 16 deletions(-)
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index de6f75f5547b..7768f206196a 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -10832,6 +10832,16 @@ static int btrfs_trim_free_extents(struct btrfs_device
*device,
return ret;
}
+/*
+ * Trim the whole fs, by:
+ * 1) Trimming free space in each block group
+ * 2) Trimming unallocated space in each device
+ *
+ * Will try to continue trimming even if we failed to trim one block group or
+ * device.
+ * The return value will be the last error during trim.
+ * Or 0 if nothing wrong happened.
+ */
int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
{
struct btrfs_block_group_cache *cache = NULL;
@@ -10842,6 +10852,10 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info,
struct fstrim_range *range)
u64 end;
u64 trimmed = 0;
u64 total_bytes = btrfs_super_total_bytes(fs_info->super_copy);
+ u64 bg_failed = 0;
+ u64 dev_failed = 0;
+ int bg_ret = 0;
+ int dev_ret = 0;
int ret = 0;
/*
@@ -10852,7 +10866,7 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct
fstrim_range *range)
else
cache = btrfs_lookup_block_group(fs_info, range->start);
- while (cache) {
+ for (; cache; cache = next_block_group(fs_info, cache)) {
if (cache->key.objectid >= (range->start + range->len)) {
btrfs_put_block_group(cache);
break;
@@ -10866,45 +10880,56 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info,
struct fstrim_range *range)
if (!block_group_cache_done(cache)) {
ret = cache_block_group(cache, 0);
if (ret) {
- btrfs_put_block_group(cache);
- break;
+ bg_failed++;
+ bg_ret = ret;
+ continue;
}
ret = wait_block_group_cache_done(cache);
if (ret) {
- btrfs_put_block_group(cache);
- break;
+ bg_failed++;
+ bg_ret = ret;
+ continue;
}
}
- ret = btrfs_trim_block_group(cache,
-_trimmed,
-start,
-end,
-range->minlen);
+ ret = btrfs_trim_block_group(cache, _trimmed,
+ start, end, range->minlen);
trimmed += group_trimmed;
if (ret) {
- btrfs_put_block_group(cache);
- break;
+ bg_failed++;
+ bg_ret = ret;
+ continue;
}
}
-
- cache = next_block_group(fs_info, cache);
}
+ if (bg_failed)
+ btrfs_warn(fs_info,
+ "failed to trim %llu block group(s), last error was %d",
+ bg_failed, bg_ret);
mutex_lock(_info->fs_devices->device_list_mutex);
devices = _info->fs_devices->alloc_list;
list_for_each_entry(device, devices, dev_alloc_list) {
ret = btrfs_trim_free_extents(device, range->minlen,
