From: Johannes Thumshirn <Johannes.Thumshirn@wdc.com>
To: "dsterba@suse.cz" <dsterba@suse.cz>
Cc: David Sterba <dsterba@suse.com>,
"linux-btrfs@vger.kernel.org" <linux-btrfs@vger.kernel.org>,
Josef Bacik <josef@toxicpanda.com>
Subject: Re: [RFC PATCH] btrfs: zoned: auto reclaim low mostly full block-groups first
Date: Tue, 21 Sep 2021 07:31:35 +0000 [thread overview]
Message-ID: <PH0PR04MB74161B892063626C4B7B32289BA19@PH0PR04MB7416.namprd04.prod.outlook.com> (raw)
In-Reply-To: 20210920155006.GN9286@suse.cz
On 20/09/2021 17:50, David Sterba wrote:
> On Tue, Sep 21, 2021 at 12:11:01AM +0900, Johannes Thumshirn wrote:
>> Currently auto reclaim of unusable zones reclaims the block-groups in the
>> order they have been added to the reclaim list.
>>
>> Sort the list so we have the block-groups with the least amount of bytes
>> to preserve at the beginning before starting the garbage collection loop.
>
> Makes sense as an optimization.
>
>> Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
>> ---
>> fs/btrfs/block-group.c | 18 ++++++++++++++++++
>> 1 file changed, 18 insertions(+)
>>
>> diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
>> index 46fdef7bbe20..d90297fb99e1 100644
>> --- a/fs/btrfs/block-group.c
>> +++ b/fs/btrfs/block-group.c
>> @@ -1,5 +1,7 @@
>> // SPDX-License-Identifier: GPL-2.0
>>
>> +#include <linux/list_sort.h>
>> +
>> #include "misc.h"
>> #include "ctree.h"
>> #include "block-group.h"
>> @@ -1486,6 +1488,21 @@ void btrfs_mark_bg_unused(struct btrfs_block_group *bg)
>> spin_unlock(&fs_info->unused_bgs_lock);
>> }
>>
>> +/*
>> + * We want block groups with a low number of used bytes to be in the beginning
>> + * of the list, so they will get reclaimed first.
>> + */
>> +static int reclaim_bgs_cmp(void *unused, const struct list_head *a,
>> + const struct list_head *b)
>> +{
>> + const struct btrfs_block_group *bg1, *bg2;
>> +
>> + bg1 = list_entry(a, struct btrfs_block_group, bg_list);
>> + bg2 = list_entry(b, struct btrfs_block_group, bg_list);
>> +
>> + return bg1->used - bg2->used;
>> +}
>> +
>> void btrfs_reclaim_bgs_work(struct work_struct *work)
>> {
>> struct btrfs_fs_info *fs_info =
>> @@ -1510,6 +1527,7 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
>> }
>>
>> spin_lock(&fs_info->unused_bgs_lock);
>> + list_sort(NULL, &fs_info->reclaim_bgs, reclaim_bgs_cmp);
>
> The sort is under a spinlock, though it's probably not a highly
> contended lock, I think we should try to move it outside. Something like
>
> lock()
> list_splice_init(&splice, &reclaim_bgs)
> unlock()
>
> list_sort(&splice);
>
> while (!list_empty(splice)) {
> }
>
> We already use splice in the again_list so it could build on top of it.
>
> OTOH, it may not be absolutelly necessary to do the sort outside of the
> lock but rather because as a matter of good programming hygiene to not
> introduce unnecessary delays due to contended lock here and there that
> could potentially cascade further.
>
I'm expecting the number of entries in the list to be in the single or two
digit range, so the sort should be rather quick.
But I agree using a spliced list looks more future proof.
prev parent reply other threads:[~2021-09-21 7:31 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-09-20 15:11 [RFC PATCH] btrfs: zoned: auto reclaim low mostly full block-groups first Johannes Thumshirn
2021-09-20 15:50 ` David Sterba
2021-09-21 7:31 ` Johannes Thumshirn [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=PH0PR04MB74161B892063626C4B7B32289BA19@PH0PR04MB7416.namprd04.prod.outlook.com \
--to=johannes.thumshirn@wdc.com \
--cc=dsterba@suse.com \
--cc=dsterba@suse.cz \
--cc=josef@toxicpanda.com \
--cc=linux-btrfs@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).