From: Qu Wenruo <quwenruo.btrfs@gmx.com>
To: Anand Jain <anand.jain@oracle.com>, linux-btrfs@vger.kernel.org
Subject: Re: [PATCH] btrfs_progs: mkfs: match devid order to the stripe index
Date: Fri, 28 Jun 2019 14:01:42 +0800 [thread overview]
Message-ID: <fb0af2df-d4d6-4e50-33a6-f76f2a39f4f9@gmx.com> (raw)
In-Reply-To: <5d93d408-2575-f564-32ce-e6c39b3b8d17@oracle.com>
[-- Attachment #1.1: Type: text/plain, Size: 7079 bytes --]
On 2019/6/28 上午11:28, Anand Jain wrote:
> On 28/6/19 10:44 AM, Qu Wenruo wrote:
>>
>>
>> On 2019/6/28 上午10:26, Anand Jain wrote:
>>> At the time mkfs.btrfs the device id and stripe index gets reversed as
>>> shown in [1]. This patch helps to keep them in order at the time of
>>> mkfs.btrfs. And makes it easier to debug.
>>>
>>> Before:
>>> Stripe 0 is on devid 2; Stipe 1 is on devid 1;
>>>
>>> ./mkfs.btrfs -fq -draid1 -mraid1 /dev/sdb /dev/sdc && btrfs in
>>> dump-tree -d /dev/sdb | grep -A 10000 "chunk tree" | grep -B 10000
>>> "device tree" | grep -A 13 "FIRST_CHUNK_TREE CHUNK_ITEM"
>>> item 2 key (FIRST_CHUNK_TREE CHUNK_ITEM 22020096) itemoff 15975
>>> itemsize 112
>>> length 8388608 owner 2 stripe_len 65536 type SYSTEM|RAID1
>>> io_align 65536 io_width 65536 sector_size 4096
>>> num_stripes 2 sub_stripes 0
>>> stripe 0 devid 2 offset 1048576
>>> dev_uuid d9fe51c4-6e79-446d-87ee-5be3184798cd
>>> stripe 1 devid 1 offset 22020096
>>> dev_uuid 16f626ca-1a54-469b-ac7e-25623af884ab
>>> item 3 key (FIRST_CHUNK_TREE CHUNK_ITEM 30408704) itemoff 15863
>>> itemsize 112
>>> length 268435456 owner 2 stripe_len 65536 type METADATA|RAID1
>>> io_align 65536 io_width 65536 sector_size 4096
>>> num_stripes 2 sub_stripes 0
>>> stripe 0 devid 2 offset 9437184
>>> dev_uuid d9fe51c4-6e79-446d-87ee-5be3184798cd
>>> stripe 1 devid 1 offset 30408704
>>> dev_uuid 16f626ca-1a54-469b-ac7e-25623af884ab
>>> item 4 key (FIRST_CHUNK_TREE CHUNK_ITEM 298844160) itemoff 15751
>>> itemsize 112
>>> length 314572800 owner 2 stripe_len 65536 type DATA|RAID1
>>> io_align 65536 io_width 65536 sector_size 4096
>>> num_stripes 2 sub_stripes 0
>>> stripe 0 devid 2 offset 277872640
>>> dev_uuid d9fe51c4-6e79-446d-87ee-5be3184798cd
>>> stripe 1 devid 1 offset 298844160
>>> dev_uuid 16f626ca-1a54-469b-ac7e-25623af884ab
>>>
>>> After:
>>> Stripe 0 is on devid 1; Stripe 1 is on devid 2
>>>
>>> ./mkfs.btrfs -fq -draid1 -mraid1 /dev/sdb /dev/sdc && btrfs in
>>> dump-tree -d /dev/sdb | grep -A 10000 "chunk tree" | grep -B 10000
>>> "device tree" | grep -A 13 "FIRST_CHUNK_TREE CHUNK_ITEM"
>>> /dev/sdb: 8 bytes were erased at offset 0x00010040 (btrfs): 5f 42 48
>>> 52 66 53 5f 4d
>>> /dev/sdc: 8 bytes were erased at offset 0x00010040 (btrfs): 5f 42 48
>>> 52 66 53 5f 4d
>>> item 2 key (FIRST_CHUNK_TREE CHUNK_ITEM 22020096) itemoff 15975
>>> itemsize 112
>>> length 8388608 owner 2 stripe_len 65536 type SYSTEM|RAID1
>>> io_align 65536 io_width 65536 sector_size 4096
>>> num_stripes 2 sub_stripes 0
>>> stripe 0 devid 1 offset 22020096
>>> dev_uuid 6abc88fa-f42e-4f0c-9bc3-2225735e51d1
>>> stripe 1 devid 2 offset 1048576
>>> dev_uuid 73746d27-13a6-4d58-ac6b-48c90c31d94d
>>> item 3 key (FIRST_CHUNK_TREE CHUNK_ITEM 30408704) itemoff 15863
>>> itemsize 112
>>> length 268435456 owner 2 stripe_len 65536 type METADATA|RAID1
>>> io_align 65536 io_width 65536 sector_size 4096
>>> num_stripes 2 sub_stripes 0
>>> stripe 0 devid 1 offset 30408704
>>> dev_uuid 6abc88fa-f42e-4f0c-9bc3-2225735e51d1
>>> stripe 1 devid 2 offset 9437184
>>> dev_uuid 73746d27-13a6-4d58-ac6b-48c90c31d94d
>>> item 4 key (FIRST_CHUNK_TREE CHUNK_ITEM 298844160) itemoff 15751
>>> itemsize 112
>>> length 314572800 owner 2 stripe_len 65536 type DATA|RAID1
>>> io_align 65536 io_width 65536 sector_size 4096
>>> num_stripes 2 sub_stripes 0
>>> stripe 0 devid 1 offset 298844160
>>> dev_uuid 6abc88fa-f42e-4f0c-9bc3-2225735e51d1
>>> stripe 1 devid 2 offset 277872640
>>> dev_uuid 73746d27-13a6-4d58-ac6b-48c90c31d94d
>>>
>>> Signed-off-by: Anand Jain <anand.jain@oracle.com>
>>
>> Reviewed-by: Qu Wenruo <wqu@suse.com>
>>
>> But please also check the comment inlined below.
>>> ---
>>> volumes.c | 4 ++--
>>> 1 file changed, 2 insertions(+), 2 deletions(-)
>>>
>>> diff --git a/volumes.c b/volumes.c
>>> index 79d1d6a07fb7..8c8b17e814b8 100644
>>> --- a/volumes.c
>>> +++ b/volumes.c
>>> @@ -1109,7 +1109,7 @@ again:
>>> return ret;
>>> cur = cur->next;
>>> if (avail >= min_free) {
>>> - list_move_tail(&device->dev_list, &private_devs);
>>> + list_move(&device->dev_list, &private_devs);
>>
>> This is OK since current btrfs-progs chunk allocator doesn't follow the
>> kernel behavior by sorting devices with its unallocated space.
>> So it's completely devid based.
>>
>> But please keep in mind that, if we're going to unify the chunk
>> allocator behavior of kernel and btrfs-progs, the behavior will change.
>>
>> As the initial temporary chunk is always allocated on devid 1, reducing
>> its unallocated space thus reducing its priority in chunk allocator, and
>> making the devid sequence more unreliable.
>
> Right. For the debug here, I have an experimental code which disables
> the unallocated space sort in the kernel. I don't have a strong reason
> to disable the sort in the kernel so didn't send the patch.
I'd say that unallocated sort is a hidden way to prevent starvation.
The mostly common case is 3 disk RAID1. (1024M X 3)
With the unallocated space sort, we can take full use of 1.5T.
While without that, we can only use 1T, as all allocation will happen on
the first (or last) 2 devices, not utilize the remaining disk at all.
So that kernel part is very helpful to prevent starvation.
Thanks,
Qu
>
> Thanks, Anand
>
>> Thanks,
>> Qu
>>
>>> index++;
>>> if (type & BTRFS_BLOCK_GROUP_DUP)
>>> index++;
>>> @@ -1166,7 +1166,7 @@ again:
>>> /* loop over this device again if we're doing a dup group */
>>> if (!(type & BTRFS_BLOCK_GROUP_DUP) ||
>>> (index == num_stripes - 1))
>>> - list_move_tail(&device->dev_list, dev_list);
>>> + list_move(&device->dev_list, dev_list);
>>> ret = btrfs_alloc_dev_extent(trans, device, key.offset,
>>> calc_size, &dev_offset);
>>>
>>
>
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
next prev parent reply other threads:[~2019-06-28 6:02 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-06-28 2:26 [PATCH] btrfs_progs: mkfs: match devid order to the stripe index Anand Jain
2019-06-28 2:44 ` Qu Wenruo
2019-06-28 3:28 ` Anand Jain
2019-06-28 6:01 ` Qu Wenruo [this message]
2019-07-03 13:21 ` David Sterba
2019-08-27 2:02 ` Anand Jain
2019-09-02 8:01 ` Anand Jain
2019-09-02 16:22 ` David Sterba
2019-09-03 12:06 ` David Sterba
2019-09-04 11:10 ` Anand Jain
2019-09-12 17:54 ` David Sterba
2019-12-10 15:42 ` Filipe Manana
2019-12-11 1:45 ` Qu Wenruo
2019-12-11 8:58 ` Filipe Manana
2019-09-03 10:46 ` Johannes Thumshirn
2019-09-04 12:54 ` [PATCH] btrfs: misc-tests-021 fix restore overlapped on disk's stale data Anand Jain
2019-09-04 13:29 ` [PATCH Fix-title-prefix] btrfs-progs: " Anand Jain
2019-09-04 14:05 ` Johannes Thumshirn
2019-09-04 14:06 ` Nikolay Borisov
2019-09-10 7:43 ` Anand Jain
2019-09-12 17:49 ` David Sterba
2019-09-10 7:37 ` [PATCH] btrfs_progs: mkfs: match devid order to the stripe index Anand Jain
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=fb0af2df-d4d6-4e50-33a6-f76f2a39f4f9@gmx.com \
--to=quwenruo.btrfs@gmx.com \
--cc=anand.jain@oracle.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).