Re: [PATCH 7/8] btrfs: be more explicit about allowed flush states
On 3.12.18 г. 17:24 ч., Josef Bacik wrote:
> For FLUSH_LIMIT flushers (think evict, truncate) we can deadlock when
> running delalloc because we may be holding a tree lock. We can also
> deadlock with delayed refs rsv's that are running via the committing
> mechanism. The only safe operations for FLUSH_LIMIT is to run the
> delayed operations and to allocate chunks, everything else has the
> potential to deadlock. Future proof this by explicitly specifying the
> states that FLUSH_LIMIT is allowed to use. This will keep us from
> introducing bugs later on when adding new flush states.
>
> Signed-off-by: Josef Bacik
Reviewed-by: Nikolay Borisov
> ---
> fs/btrfs/extent-tree.c | 21 ++---
> 1 file changed, 10 insertions(+), 11 deletions(-)
>
> diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
> index 0e1a499035ac..ab9d915d9289 100644
> --- a/fs/btrfs/extent-tree.c
> +++ b/fs/btrfs/extent-tree.c
> @@ -5123,12 +5123,18 @@ void btrfs_init_async_reclaim_work(struct work_struct
> *work)
> INIT_WORK(work, btrfs_async_reclaim_metadata_space);
> }
>
> +static const enum btrfs_flush_state priority_flush_states[] = {
> + FLUSH_DELAYED_ITEMS_NR,
> + FLUSH_DELAYED_ITEMS,
> + ALLOC_CHUNK,
> +};
> +
> static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
> struct btrfs_space_info *space_info,
> struct reserve_ticket *ticket)
> {
> u64 to_reclaim;
> - int flush_state = FLUSH_DELAYED_ITEMS_NR;
> + int flush_state = 0;
>
> spin_lock(&space_info->lock);
> to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info,
> @@ -5140,7 +5146,8 @@ static void priority_reclaim_metadata_space(struct
> btrfs_fs_info *fs_info,
> spin_unlock(&space_info->lock);
>
> do {
> - flush_space(fs_info, space_info, to_reclaim, flush_state);
> + flush_space(fs_info, space_info, to_reclaim,
> + priority_flush_states[flush_state]);
> flush_state++;
> spin_lock(&space_info->lock);
> if (ticket->bytes == 0) {
> @@ -5148,15 +5155,7 @@ static void priority_reclaim_metadata_space(struct
> btrfs_fs_info *fs_info,
> return;
> }
> spin_unlock(&space_info->lock);
> -
> - /*
> - * Priority flushers can't wait on delalloc without
> - * deadlocking.
> - */
> - if (flush_state == FLUSH_DELALLOC ||
> - flush_state == FLUSH_DELALLOC_WAIT)
> - flush_state = ALLOC_CHUNK;
> - } while (flush_state < COMMIT_TRANS);
> + } while (flush_state < ARRAY_SIZE(priority_flush_states));
> }
>
> static int wait_reserve_ticket(struct btrfs_fs_info *fs_info,
>
Re: [PATCH 7/8] btrfs: be more explicit about allowed flush states
On Mon, Dec 03, 2018 at 10:24:58AM -0500, Josef Bacik wrote: > For FLUSH_LIMIT flushers (think evict, truncate) we can deadlock when > running delalloc because we may be holding a tree lock. We can also > deadlock with delayed refs rsv's that are running via the committing > mechanism. The only safe operations for FLUSH_LIMIT is to run the > delayed operations and to allocate chunks, everything else has the > potential to deadlock. Future proof this by explicitly specifying the > states that FLUSH_LIMIT is allowed to use. This will keep us from > introducing bugs later on when adding new flush states. > > Signed-off-by: Josef Bacik Reviewed-by: David Sterba
[PATCH 7/8] btrfs: be more explicit about allowed flush states
For FLUSH_LIMIT flushers (think evict, truncate) we can deadlock when
running delalloc because we may be holding a tree lock. We can also
deadlock with delayed refs rsv's that are running via the committing
mechanism. The only safe operations for FLUSH_LIMIT is to run the
delayed operations and to allocate chunks, everything else has the
potential to deadlock. Future proof this by explicitly specifying the
states that FLUSH_LIMIT is allowed to use. This will keep us from
introducing bugs later on when adding new flush states.
Signed-off-by: Josef Bacik
---
fs/btrfs/extent-tree.c | 21 ++---
1 file changed, 10 insertions(+), 11 deletions(-)
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 0e1a499035ac..ab9d915d9289 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -5123,12 +5123,18 @@ void btrfs_init_async_reclaim_work(struct work_struct
*work)
INIT_WORK(work, btrfs_async_reclaim_metadata_space);
}
+static const enum btrfs_flush_state priority_flush_states[] = {
+ FLUSH_DELAYED_ITEMS_NR,
+ FLUSH_DELAYED_ITEMS,
+ ALLOC_CHUNK,
+};
+
static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info,
struct reserve_ticket *ticket)
{
u64 to_reclaim;
- int flush_state = FLUSH_DELAYED_ITEMS_NR;
+ int flush_state = 0;
spin_lock(&space_info->lock);
to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info,
@@ -5140,7 +5146,8 @@ static void priority_reclaim_metadata_space(struct
btrfs_fs_info *fs_info,
spin_unlock(&space_info->lock);
do {
- flush_space(fs_info, space_info, to_reclaim, flush_state);
+ flush_space(fs_info, space_info, to_reclaim,
+ priority_flush_states[flush_state]);
flush_state++;
spin_lock(&space_info->lock);
if (ticket->bytes == 0) {
@@ -5148,15 +5155,7 @@ static void priority_reclaim_metadata_space(struct
btrfs_fs_info *fs_info,
return;
}
spin_unlock(&space_info->lock);
-
- /*
-* Priority flushers can't wait on delalloc without
-* deadlocking.
-*/
- if (flush_state == FLUSH_DELALLOC ||
- flush_state == FLUSH_DELALLOC_WAIT)
- flush_state = ALLOC_CHUNK;
- } while (flush_state < COMMIT_TRANS);
+ } while (flush_state < ARRAY_SIZE(priority_flush_states));
}
static int wait_reserve_ticket(struct btrfs_fs_info *fs_info,
--
2.14.3
Re: [PATCH 7/8] btrfs: be more explicit about allowed flush states
On 26.11.18 г. 14:41 ч., Nikolay Borisov wrote:
>
>
> On 21.11.18 г. 21:03 ч., Josef Bacik wrote:
>> For FLUSH_LIMIT flushers we really can only allocate chunks and flush
>> delayed inode items, everything else is problematic. I added a bunch of
>> new states and it lead to weirdness in the FLUSH_LIMIT case because I
>> forgot about how it worked. So instead explicitly declare the states
>> that are ok for flushing with FLUSH_LIMIT and use that for our state
>> machine. Then as we add new things that are safe we can just add them
>> to this list.
>
>
> Code-wise it's ok but the changelog needs rewording. At the very least
> explain the weirdness. Also in the last sentence the word 'thing' is
> better substituted with "flush states".
Case in point, you yourself mention that you have forgotten how the
FLUSH_LIMIT case works. That's why we need good changelogs so that those
details can be quickly worked out from reading the changelog.
>
>>
>> Signed-off-by: Josef Bacik
>> ---
>> fs/btrfs/extent-tree.c | 21 ++---
>> 1 file changed, 10 insertions(+), 11 deletions(-)
>>
>> diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
>> index 0e9ba77e5316..e31980d451c2 100644
>> --- a/fs/btrfs/extent-tree.c
>> +++ b/fs/btrfs/extent-tree.c
>> @@ -5112,12 +5112,18 @@ void btrfs_init_async_reclaim_work(struct
>> work_struct *work)
>> INIT_WORK(work, btrfs_async_reclaim_metadata_space);
>> }
>>
>> +static const enum btrfs_flush_state priority_flush_states[] = {
>> +FLUSH_DELAYED_ITEMS_NR,
>> +FLUSH_DELAYED_ITEMS,
>> +ALLOC_CHUNK,
>> +};
>> +
>> static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
>> struct btrfs_space_info *space_info,
>> struct reserve_ticket *ticket)
>> {
>> u64 to_reclaim;
>> -int flush_state = FLUSH_DELAYED_ITEMS_NR;
>> +int flush_state = 0;
>>
>> spin_lock(&space_info->lock);
>> to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info,
>> @@ -5129,7 +5135,8 @@ static void priority_reclaim_metadata_space(struct
>> btrfs_fs_info *fs_info,
>> spin_unlock(&space_info->lock);
>>
>> do {
>> -flush_space(fs_info, space_info, to_reclaim, flush_state);
>> +flush_space(fs_info, space_info, to_reclaim,
>> +priority_flush_states[flush_state]);
>> flush_state++;
>> spin_lock(&space_info->lock);
>> if (ticket->bytes == 0) {
>> @@ -5137,15 +5144,7 @@ static void priority_reclaim_metadata_space(struct
>> btrfs_fs_info *fs_info,
>> return;
>> }
>> spin_unlock(&space_info->lock);
>> -
>> -/*
>> - * Priority flushers can't wait on delalloc without
>> - * deadlocking.
>> - */
>> -if (flush_state == FLUSH_DELALLOC ||
>> -flush_state == FLUSH_DELALLOC_WAIT)
>> -flush_state = ALLOC_CHUNK;
>> -} while (flush_state < COMMIT_TRANS);
>> +} while (flush_state < ARRAY_SIZE(priority_flush_states));
>> }
>>
>> static int wait_reserve_ticket(struct btrfs_fs_info *fs_info,
>>
>
Re: [PATCH 7/8] btrfs: be more explicit about allowed flush states
On 21.11.18 г. 21:03 ч., Josef Bacik wrote:
> For FLUSH_LIMIT flushers we really can only allocate chunks and flush
> delayed inode items, everything else is problematic. I added a bunch of
> new states and it lead to weirdness in the FLUSH_LIMIT case because I
> forgot about how it worked. So instead explicitly declare the states
> that are ok for flushing with FLUSH_LIMIT and use that for our state
> machine. Then as we add new things that are safe we can just add them
> to this list.
Code-wise it's ok but the changelog needs rewording. At the very least
explain the weirdness. Also in the last sentence the word 'thing' is
better substituted with "flush states".
>
> Signed-off-by: Josef Bacik
> ---
> fs/btrfs/extent-tree.c | 21 ++---
> 1 file changed, 10 insertions(+), 11 deletions(-)
>
> diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
> index 0e9ba77e5316..e31980d451c2 100644
> --- a/fs/btrfs/extent-tree.c
> +++ b/fs/btrfs/extent-tree.c
> @@ -5112,12 +5112,18 @@ void btrfs_init_async_reclaim_work(struct work_struct
> *work)
> INIT_WORK(work, btrfs_async_reclaim_metadata_space);
> }
>
> +static const enum btrfs_flush_state priority_flush_states[] = {
> + FLUSH_DELAYED_ITEMS_NR,
> + FLUSH_DELAYED_ITEMS,
> + ALLOC_CHUNK,
> +};
> +
> static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
> struct btrfs_space_info *space_info,
> struct reserve_ticket *ticket)
> {
> u64 to_reclaim;
> - int flush_state = FLUSH_DELAYED_ITEMS_NR;
> + int flush_state = 0;
>
> spin_lock(&space_info->lock);
> to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info,
> @@ -5129,7 +5135,8 @@ static void priority_reclaim_metadata_space(struct
> btrfs_fs_info *fs_info,
> spin_unlock(&space_info->lock);
>
> do {
> - flush_space(fs_info, space_info, to_reclaim, flush_state);
> + flush_space(fs_info, space_info, to_reclaim,
> + priority_flush_states[flush_state]);
> flush_state++;
> spin_lock(&space_info->lock);
> if (ticket->bytes == 0) {
> @@ -5137,15 +5144,7 @@ static void priority_reclaim_metadata_space(struct
> btrfs_fs_info *fs_info,
> return;
> }
> spin_unlock(&space_info->lock);
> -
> - /*
> - * Priority flushers can't wait on delalloc without
> - * deadlocking.
> - */
> - if (flush_state == FLUSH_DELALLOC ||
> - flush_state == FLUSH_DELALLOC_WAIT)
> - flush_state = ALLOC_CHUNK;
> - } while (flush_state < COMMIT_TRANS);
> + } while (flush_state < ARRAY_SIZE(priority_flush_states));
> }
>
> static int wait_reserve_ticket(struct btrfs_fs_info *fs_info,
>
[PATCH 7/8] btrfs: be more explicit about allowed flush states
For FLUSH_LIMIT flushers we really can only allocate chunks and flush
delayed inode items, everything else is problematic. I added a bunch of
new states and it lead to weirdness in the FLUSH_LIMIT case because I
forgot about how it worked. So instead explicitly declare the states
that are ok for flushing with FLUSH_LIMIT and use that for our state
machine. Then as we add new things that are safe we can just add them
to this list.
Signed-off-by: Josef Bacik
---
fs/btrfs/extent-tree.c | 21 ++---
1 file changed, 10 insertions(+), 11 deletions(-)
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 0e9ba77e5316..e31980d451c2 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -5112,12 +5112,18 @@ void btrfs_init_async_reclaim_work(struct work_struct
*work)
INIT_WORK(work, btrfs_async_reclaim_metadata_space);
}
+static const enum btrfs_flush_state priority_flush_states[] = {
+ FLUSH_DELAYED_ITEMS_NR,
+ FLUSH_DELAYED_ITEMS,
+ ALLOC_CHUNK,
+};
+
static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info,
struct reserve_ticket *ticket)
{
u64 to_reclaim;
- int flush_state = FLUSH_DELAYED_ITEMS_NR;
+ int flush_state = 0;
spin_lock(&space_info->lock);
to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info,
@@ -5129,7 +5135,8 @@ static void priority_reclaim_metadata_space(struct
btrfs_fs_info *fs_info,
spin_unlock(&space_info->lock);
do {
- flush_space(fs_info, space_info, to_reclaim, flush_state);
+ flush_space(fs_info, space_info, to_reclaim,
+ priority_flush_states[flush_state]);
flush_state++;
spin_lock(&space_info->lock);
if (ticket->bytes == 0) {
@@ -5137,15 +5144,7 @@ static void priority_reclaim_metadata_space(struct
btrfs_fs_info *fs_info,
return;
}
spin_unlock(&space_info->lock);
-
- /*
-* Priority flushers can't wait on delalloc without
-* deadlocking.
-*/
- if (flush_state == FLUSH_DELALLOC ||
- flush_state == FLUSH_DELALLOC_WAIT)
- flush_state = ALLOC_CHUNK;
- } while (flush_state < COMMIT_TRANS);
+ } while (flush_state < ARRAY_SIZE(priority_flush_states));
}
static int wait_reserve_ticket(struct btrfs_fs_info *fs_info,
--
2.14.3
