diff mbox series

[v15,41/42] btrfs: zoned: reorder log node allocation on zoned filesystem

Message ID 492da9326ecb5f888e76117983603bb502b7b589.1612434091.git.naohiro.aota@wdc.com (mailing list archive)
State New, archived
Headers show
Series btrfs: zoned block device support | expand

Commit Message

Naohiro Aota Feb. 4, 2021, 10:22 a.m. UTC
This is the 3/3 patch to enable tree-log on zoned filesystems.

The allocation order of nodes of "fs_info->log_root_tree" and nodes of
"root->log_root" is not the same as the writing order of them. So, the
writing causes unaligned write errors.

Reorder the allocation of them by delaying allocation of the root node of
"fs_info->log_root_tree," so that the node buffers can go out sequentially
to devices.

Cc: Filipe Manana <fdmanana@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
---
 fs/btrfs/disk-io.c  | 12 +++++++-----
 fs/btrfs/tree-log.c | 27 +++++++++++++++++++++------
 2 files changed, 28 insertions(+), 11 deletions(-)

Comments

Filipe Manana Feb. 4, 2021, 11:57 a.m. UTC | #1
On Thu, Feb 4, 2021 at 10:23 AM Naohiro Aota <naohiro.aota@wdc.com> wrote:
>
> This is the 3/3 patch to enable tree-log on zoned filesystems.
>
> The allocation order of nodes of "fs_info->log_root_tree" and nodes of
> "root->log_root" is not the same as the writing order of them. So, the
> writing causes unaligned write errors.
>
> Reorder the allocation of them by delaying allocation of the root node of
> "fs_info->log_root_tree," so that the node buffers can go out sequentially
> to devices.
>
> Cc: Filipe Manana <fdmanana@gmail.com>
> Reviewed-by: Josef Bacik <josef@toxicpanda.com>
> Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
> Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
> ---
>  fs/btrfs/disk-io.c  | 12 +++++++-----
>  fs/btrfs/tree-log.c | 27 +++++++++++++++++++++------
>  2 files changed, 28 insertions(+), 11 deletions(-)
>
> diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
> index 84c6650d5ef7..c2576c5fe62e 100644
> --- a/fs/btrfs/disk-io.c
> +++ b/fs/btrfs/disk-io.c
> @@ -1298,16 +1298,18 @@ int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
>                              struct btrfs_fs_info *fs_info)
>  {
>         struct btrfs_root *log_root;
> -       int ret;
>
>         log_root = alloc_log_tree(trans, fs_info);
>         if (IS_ERR(log_root))
>                 return PTR_ERR(log_root);
>
> -       ret = btrfs_alloc_log_tree_node(trans, log_root);
> -       if (ret) {
> -               btrfs_put_root(log_root);
> -               return ret;
> +       if (!btrfs_is_zoned(fs_info)) {
> +               int ret = btrfs_alloc_log_tree_node(trans, log_root);
> +
> +               if (ret) {
> +                       btrfs_put_root(log_root);
> +                       return ret;
> +               }
>         }
>
>         WARN_ON(fs_info->log_root_tree);
> diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
> index 8be3164d4c5d..7ba044bfa9b1 100644
> --- a/fs/btrfs/tree-log.c
> +++ b/fs/btrfs/tree-log.c
> @@ -3159,6 +3159,19 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
>         list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]);
>         root_log_ctx.log_transid = log_root_tree->log_transid;
>
> +       if (btrfs_is_zoned(fs_info)) {
> +               mutex_lock(&fs_info->tree_log_mutex);
> +               if (!log_root_tree->node) {

As commented in v14, the log root tree is not protected by
fs_info->tree_log_mutex anymore.
It is fs_info->tree_root->log_mutex as of 5.10.

Everything else was addressed and looks good.
Thanks.

> +                       ret = btrfs_alloc_log_tree_node(trans, log_root_tree);
> +                       if (ret) {
> +                               mutex_unlock(&fs_info->tree_log_mutex);
> +                               mutex_unlock(&log_root_tree->log_mutex);
> +                               goto out;
> +                       }
> +               }
> +               mutex_unlock(&fs_info->tree_log_mutex);
> +       }
> +
>         /*
>          * Now we are safe to update the log_root_tree because we're under the
>          * log_mutex, and we're a current writer so we're holding the commit
> @@ -3317,12 +3330,14 @@ static void free_log_tree(struct btrfs_trans_handle *trans,
>                 .process_func = process_one_buffer
>         };
>
> -       ret = walk_log_tree(trans, log, &wc);
> -       if (ret) {
> -               if (trans)
> -                       btrfs_abort_transaction(trans, ret);
> -               else
> -                       btrfs_handle_fs_error(log->fs_info, ret, NULL);
> +       if (log->node) {
> +               ret = walk_log_tree(trans, log, &wc);
> +               if (ret) {
> +                       if (trans)
> +                               btrfs_abort_transaction(trans, ret);
> +                       else
> +                               btrfs_handle_fs_error(log->fs_info, ret, NULL);
> +               }
>         }
>
>         clear_extent_bits(&log->dirty_log_pages, 0, (u64)-1,
> --
> 2.30.0
>
Johannes Thumshirn Feb. 4, 2021, 2:54 p.m. UTC | #2
On 04/02/2021 12:57, Filipe Manana wrote:
> On Thu, Feb 4, 2021 at 10:23 AM Naohiro Aota <naohiro.aota@wdc.com> wrote:
>>
>> This is the 3/3 patch to enable tree-log on zoned filesystems.
>>
>> The allocation order of nodes of "fs_info->log_root_tree" and nodes of
>> "root->log_root" is not the same as the writing order of them. So, the
>> writing causes unaligned write errors.
>>
>> Reorder the allocation of them by delaying allocation of the root node of
>> "fs_info->log_root_tree," so that the node buffers can go out sequentially
>> to devices.
>>
>> Cc: Filipe Manana <fdmanana@gmail.com>
>> Reviewed-by: Josef Bacik <josef@toxicpanda.com>
>> Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
>> Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
>> ---
>>  fs/btrfs/disk-io.c  | 12 +++++++-----
>>  fs/btrfs/tree-log.c | 27 +++++++++++++++++++++------
>>  2 files changed, 28 insertions(+), 11 deletions(-)
>>
>> diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
>> index 84c6650d5ef7..c2576c5fe62e 100644
>> --- a/fs/btrfs/disk-io.c
>> +++ b/fs/btrfs/disk-io.c
>> @@ -1298,16 +1298,18 @@ int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
>>                              struct btrfs_fs_info *fs_info)
>>  {
>>         struct btrfs_root *log_root;
>> -       int ret;
>>
>>         log_root = alloc_log_tree(trans, fs_info);
>>         if (IS_ERR(log_root))
>>                 return PTR_ERR(log_root);
>>
>> -       ret = btrfs_alloc_log_tree_node(trans, log_root);
>> -       if (ret) {
>> -               btrfs_put_root(log_root);
>> -               return ret;
>> +       if (!btrfs_is_zoned(fs_info)) {
>> +               int ret = btrfs_alloc_log_tree_node(trans, log_root);
>> +
>> +               if (ret) {
>> +                       btrfs_put_root(log_root);
>> +                       return ret;
>> +               }
>>         }
>>
>>         WARN_ON(fs_info->log_root_tree);
>> diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
>> index 8be3164d4c5d..7ba044bfa9b1 100644
>> --- a/fs/btrfs/tree-log.c
>> +++ b/fs/btrfs/tree-log.c
>> @@ -3159,6 +3159,19 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
>>         list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]);
>>         root_log_ctx.log_transid = log_root_tree->log_transid;
>>
>> +       if (btrfs_is_zoned(fs_info)) {
>> +               mutex_lock(&fs_info->tree_log_mutex);
>> +               if (!log_root_tree->node) {
> 
> As commented in v14, the log root tree is not protected by
> fs_info->tree_log_mutex anymore.
> It is fs_info->tree_root->log_mutex as of 5.10.
> 
> Everything else was addressed and looks good.
> Thanks.

David, can you add this or should we send an incremental patch?
This survived fstests -g quick run with lockdep enabled.

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 7ba044bfa9b1..36c4a60d20dc 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3160,7 +3160,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
        root_log_ctx.log_transid = log_root_tree->log_transid;
        if (btrfs_is_zoned(fs_info)) {
-               mutex_lock(&fs_info->tree_log_mutex);
+               mutex_lock(&fs_info->tree_root->log_mutex);
                if (!log_root_tree->node) {
                        ret = btrfs_alloc_log_tree_node(trans, log_root_tree);
                        if (ret) {
@@ -3169,7 +3169,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
                                goto out;
                        }
                }
-               mutex_unlock(&fs_info->tree_log_mutex);
+               mutex_unlock(&fs_info->tree_root->log_mutex);
        }
        /*
David Sterba Feb. 4, 2021, 3:48 p.m. UTC | #3
On Thu, Feb 04, 2021 at 02:54:25PM +0000, Johannes Thumshirn wrote:
> On 04/02/2021 12:57, Filipe Manana wrote:
> > On Thu, Feb 4, 2021 at 10:23 AM Naohiro Aota <naohiro.aota@wdc.com> wrote:
> >> --- a/fs/btrfs/tree-log.c
> >> +++ b/fs/btrfs/tree-log.c
> >> @@ -3159,6 +3159,19 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
> >>         list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]);
> >>         root_log_ctx.log_transid = log_root_tree->log_transid;
> >>
> >> +       if (btrfs_is_zoned(fs_info)) {
> >> +               mutex_lock(&fs_info->tree_log_mutex);
> >> +               if (!log_root_tree->node) {
> > 
> > As commented in v14, the log root tree is not protected by
> > fs_info->tree_log_mutex anymore.
> > It is fs_info->tree_root->log_mutex as of 5.10.
> > 
> > Everything else was addressed and looks good.
> > Thanks.
> 
> David, can you add this or should we send an incremental patch?
> This survived fstests -g quick run with lockdep enabled.
> 
> diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
> index 7ba044bfa9b1..36c4a60d20dc 100644
> --- a/fs/btrfs/tree-log.c
> +++ b/fs/btrfs/tree-log.c
> @@ -3160,7 +3160,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
>         root_log_ctx.log_transid = log_root_tree->log_transid;
>         if (btrfs_is_zoned(fs_info)) {
> -               mutex_lock(&fs_info->tree_log_mutex);
> +               mutex_lock(&fs_info->tree_root->log_mutex);
>                 if (!log_root_tree->node) {
>                         ret = btrfs_alloc_log_tree_node(trans, log_root_tree);
>                         if (ret) {
> @@ -3169,7 +3169,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
>                                 goto out;
>                         }
>                 }
> -               mutex_unlock(&fs_info->tree_log_mutex);
> +               mutex_unlock(&fs_info->tree_root->log_mutex);

Folded to the patch, thanks.
Johannes Thumshirn Feb. 4, 2021, 3:51 p.m. UTC | #4
On 04/02/2021 16:50, David Sterba wrote:
> On Thu, Feb 04, 2021 at 02:54:25PM +0000, Johannes Thumshirn wrote:
>> On 04/02/2021 12:57, Filipe Manana wrote:
>>> On Thu, Feb 4, 2021 at 10:23 AM Naohiro Aota <naohiro.aota@wdc.com> wrote:
>>>> --- a/fs/btrfs/tree-log.c
>>>> +++ b/fs/btrfs/tree-log.c
>>>> @@ -3159,6 +3159,19 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
>>>>         list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]);
>>>>         root_log_ctx.log_transid = log_root_tree->log_transid;
>>>>
>>>> +       if (btrfs_is_zoned(fs_info)) {
>>>> +               mutex_lock(&fs_info->tree_log_mutex);
>>>> +               if (!log_root_tree->node) {
>>>
>>> As commented in v14, the log root tree is not protected by
>>> fs_info->tree_log_mutex anymore.
>>> It is fs_info->tree_root->log_mutex as of 5.10.
>>>
>>> Everything else was addressed and looks good.
>>> Thanks.
>>
>> David, can you add this or should we send an incremental patch?
>> This survived fstests -g quick run with lockdep enabled.
>>
>> diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
>> index 7ba044bfa9b1..36c4a60d20dc 100644
>> --- a/fs/btrfs/tree-log.c
>> +++ b/fs/btrfs/tree-log.c
>> @@ -3160,7 +3160,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
>>         root_log_ctx.log_transid = log_root_tree->log_transid;
>>         if (btrfs_is_zoned(fs_info)) {
>> -               mutex_lock(&fs_info->tree_log_mutex);
>> +               mutex_lock(&fs_info->tree_root->log_mutex);
>>                 if (!log_root_tree->node) {
>>                         ret = btrfs_alloc_log_tree_node(trans, log_root_tree);
>>                         if (ret) {
>> @@ -3169,7 +3169,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
>>                                 goto out;
>>                         }
>>                 }
>> -               mutex_unlock(&fs_info->tree_log_mutex);
>> +               mutex_unlock(&fs_info->tree_root->log_mutex);
> 
> Folded to the patch, thanks.
> 

Thanks a lot
diff mbox series

Patch

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 84c6650d5ef7..c2576c5fe62e 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1298,16 +1298,18 @@  int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
 			     struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_root *log_root;
-	int ret;
 
 	log_root = alloc_log_tree(trans, fs_info);
 	if (IS_ERR(log_root))
 		return PTR_ERR(log_root);
 
-	ret = btrfs_alloc_log_tree_node(trans, log_root);
-	if (ret) {
-		btrfs_put_root(log_root);
-		return ret;
+	if (!btrfs_is_zoned(fs_info)) {
+		int ret = btrfs_alloc_log_tree_node(trans, log_root);
+
+		if (ret) {
+			btrfs_put_root(log_root);
+			return ret;
+		}
 	}
 
 	WARN_ON(fs_info->log_root_tree);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 8be3164d4c5d..7ba044bfa9b1 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3159,6 +3159,19 @@  int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]);
 	root_log_ctx.log_transid = log_root_tree->log_transid;
 
+	if (btrfs_is_zoned(fs_info)) {
+		mutex_lock(&fs_info->tree_log_mutex);
+		if (!log_root_tree->node) {
+			ret = btrfs_alloc_log_tree_node(trans, log_root_tree);
+			if (ret) {
+				mutex_unlock(&fs_info->tree_log_mutex);
+				mutex_unlock(&log_root_tree->log_mutex);
+				goto out;
+			}
+		}
+		mutex_unlock(&fs_info->tree_log_mutex);
+	}
+
 	/*
 	 * Now we are safe to update the log_root_tree because we're under the
 	 * log_mutex, and we're a current writer so we're holding the commit
@@ -3317,12 +3330,14 @@  static void free_log_tree(struct btrfs_trans_handle *trans,
 		.process_func = process_one_buffer
 	};
 
-	ret = walk_log_tree(trans, log, &wc);
-	if (ret) {
-		if (trans)
-			btrfs_abort_transaction(trans, ret);
-		else
-			btrfs_handle_fs_error(log->fs_info, ret, NULL);
+	if (log->node) {
+		ret = walk_log_tree(trans, log, &wc);
+		if (ret) {
+			if (trans)
+				btrfs_abort_transaction(trans, ret);
+			else
+				btrfs_handle_fs_error(log->fs_info, ret, NULL);
+		}
 	}
 
 	clear_extent_bits(&log->dirty_log_pages, 0, (u64)-1,