Linux-Fsdevel Archive on lore.kernel.org
 help / color / Atom feed
From: Anand Jain <anand.jain@oracle.com>
To: Naohiro Aota <naohiro.aota@wdc.com>,
	linux-btrfs@vger.kernel.org, David Sterba <dsterba@suse.com>
Cc: Chris Mason <clm@fb.com>, Josef Bacik <josef@toxicpanda.com>,
	Nikolay Borisov <nborisov@suse.com>,
	Damien Le Moal <damien.lemoal@wdc.com>,
	Matias Bjorling <Matias.Bjorling@wdc.com>,
	Johannes Thumshirn <jthumshirn@suse.de>,
	Hannes Reinecke <hare@suse.com>,
	linux-fsdevel@vger.kernel.org
Subject: Re: [PATCH v3 03/27] btrfs: Check and enable HMZONED mode
Date: Fri, 16 Aug 2019 13:46:00 +0800
Message-ID: <edcb46f5-1c3e-0b69-a2d9-66164e64b07e@oracle.com> (raw)
In-Reply-To: <20190808093038.4163421-4-naohiro.aota@wdc.com>

On 8/8/19 5:30 PM, Naohiro Aota wrote:
> HMZONED mode cannot be used together with the RAID5/6 profile for now.
> Introduce the function btrfs_check_hmzoned_mode() to check this. This
> function will also check if HMZONED flag is enabled on the file system and
> if the file system consists of zoned devices with equal zone size.
> 
> Additionally, as updates to the space cache are in-place, the space cache
> cannot be located over sequential zones and there is no guarantees that the
> device will have enough conventional zones to store this cache. Resolve
> this problem by disabling completely the space cache.  This does not
> introduces any problems with sequential block groups: all the free space is
> located after the allocation pointer and no free space before the pointer.
> There is no need to have such cache.
> 
> For the same reason, NODATACOW is also disabled.
> 
> Also INODE_MAP_CACHE is also disabled to avoid preallocation in the
> INODE_MAP_CACHE inode.

  A list of incompatibility features with zoned devices. This need better
  documentation, may be a table and its reason is better.


> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
> Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
> ---
>   fs/btrfs/ctree.h       |  3 ++
>   fs/btrfs/dev-replace.c |  8 +++++
>   fs/btrfs/disk-io.c     |  8 +++++
>   fs/btrfs/hmzoned.c     | 67 ++++++++++++++++++++++++++++++++++++++++++
>   fs/btrfs/hmzoned.h     | 18 ++++++++++++
>   fs/btrfs/super.c       |  1 +
>   fs/btrfs/volumes.c     |  5 ++++
>   7 files changed, 110 insertions(+)
> 
> diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
> index 299e11e6c554..a00ce8c4d678 100644
> --- a/fs/btrfs/ctree.h
> +++ b/fs/btrfs/ctree.h
> @@ -713,6 +713,9 @@ struct btrfs_fs_info {
>   	struct btrfs_root *uuid_root;
>   	struct btrfs_root *free_space_root;
>   
> +	/* Zone size when in HMZONED mode */
> +	u64 zone_size;
> +
>   	/* the log root tree is a directory of all the other log roots */
>   	struct btrfs_root *log_root_tree;
>   
> diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
> index 6b2e9aa83ffa..2cc3ac4d101d 100644
> --- a/fs/btrfs/dev-replace.c
> +++ b/fs/btrfs/dev-replace.c
> @@ -20,6 +20,7 @@
>   #include "rcu-string.h"
>   #include "dev-replace.h"
>   #include "sysfs.h"
> +#include "hmzoned.h"
>   
>   static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
>   				       int scrub_ret);
> @@ -201,6 +202,13 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
>   		return PTR_ERR(bdev);
>   	}
>   
> +	if (!btrfs_check_device_zone_type(fs_info, bdev)) {
> +		btrfs_err(fs_info,
> +			  "zone type of target device mismatch with the filesystem!");
> +		ret = -EINVAL;
> +		goto error;
> +	}
> +
>   	sync_blockdev(bdev);
>   
>   	devices = &fs_info->fs_devices->devices;
> diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
> index 5f7ee70b3d1a..8854ff2e5fa5 100644
> --- a/fs/btrfs/disk-io.c
> +++ b/fs/btrfs/disk-io.c
> @@ -40,6 +40,7 @@
>   #include "compression.h"
>   #include "tree-checker.h"
>   #include "ref-verify.h"
> +#include "hmzoned.h"
>   
>   #define BTRFS_SUPER_FLAG_SUPP	(BTRFS_HEADER_FLAG_WRITTEN |\
>   				 BTRFS_HEADER_FLAG_RELOC |\
> @@ -3123,6 +3124,13 @@ int open_ctree(struct super_block *sb,
>   
>   	btrfs_free_extra_devids(fs_devices, 1);
>   
> +	ret = btrfs_check_hmzoned_mode(fs_info);
> +	if (ret) {
> +		btrfs_err(fs_info, "failed to init hmzoned mode: %d",
> +				ret);
> +		goto fail_block_groups;
> +	}
> +
>   	ret = btrfs_sysfs_add_fsid(fs_devices, NULL);
>   	if (ret) {
>   		btrfs_err(fs_info, "failed to init sysfs fsid interface: %d",
> diff --git a/fs/btrfs/hmzoned.c b/fs/btrfs/hmzoned.c
> index bfd04792dd62..512674d8f488 100644
> --- a/fs/btrfs/hmzoned.c
> +++ b/fs/btrfs/hmzoned.c
> @@ -160,3 +160,70 @@ int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
>   
>   	return 0;
>   }
> +
> +int btrfs_check_hmzoned_mode(struct btrfs_fs_info *fs_info)
> +{
> +	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
> +	struct btrfs_device *device;
> +	u64 hmzoned_devices = 0;
> +	u64 nr_devices = 0;
> +	u64 zone_size = 0;
> +	int incompat_hmzoned = btrfs_fs_incompat(fs_info, HMZONED);
> +	int ret = 0;
> +
> +	/* Count zoned devices */
> +	list_for_each_entry(device, &fs_devices->devices, dev_list) {
> +		if (!device->bdev)
> +			continue;
> +		if (bdev_zoned_model(device->bdev) == BLK_ZONED_HM ||
> +		    (bdev_zoned_model(device->bdev) == BLK_ZONED_HA &&
> +		     incompat_hmzoned)) {
> +			hmzoned_devices++;
> +			if (!zone_size) {
> +				zone_size = device->zone_info->zone_size;
> +			} else if (device->zone_info->zone_size != zone_size) {
> +				btrfs_err(fs_info,
> +					  "Zoned block devices must have equal zone sizes");
> +				ret = -EINVAL;
> +				goto out;
> +			}
> +		}
> +		nr_devices++;
> +	}
> +
> +	if (!hmzoned_devices && incompat_hmzoned) {
> +		/* No zoned block device found on HMZONED FS */
> +		btrfs_err(fs_info, "HMZONED enabled file system should have zoned devices");
> +		ret = -EINVAL;
> +		goto out;


  When does the HMZONED gets enabled? I presume during mkfs. Where are
  the related btrfs-progs patches? Searching for the related btrfs-progs
  patches doesn't show up anything in the ML. Looks like I am missing
  something, nor the cover letter said anything about the progs part.

Thanks, Anand

> +	}
> +
> +	if (!hmzoned_devices && !incompat_hmzoned)
> +		goto out;
> +
> +	fs_info->zone_size = zone_size;
> +
> +	if (hmzoned_devices != nr_devices) {
> +		btrfs_err(fs_info,
> +			  "zoned devices cannot be mixed with regular devices");
> +		ret = -EINVAL;
> +		goto out;
> +	}
> +
> +	/*
> +	 * stripe_size is always aligned to BTRFS_STRIPE_LEN in
> +	 * __btrfs_alloc_chunk(). Since we want stripe_len == zone_size,
> +	 * check the alignment here.
> +	 */
> +	if (!IS_ALIGNED(zone_size, BTRFS_STRIPE_LEN)) {
> +		btrfs_err(fs_info,
> +			  "zone size is not aligned to BTRFS_STRIPE_LEN");
> +		ret = -EINVAL;
> +		goto out;
> +	}
> +
> +	btrfs_info(fs_info, "HMZONED mode enabled, zone size %llu B",
> +		   fs_info->zone_size);
> +out:
> +	return ret;
> +}
> diff --git a/fs/btrfs/hmzoned.h b/fs/btrfs/hmzoned.h
> index ffc70842135e..29cfdcabff2f 100644
> --- a/fs/btrfs/hmzoned.h
> +++ b/fs/btrfs/hmzoned.h
> @@ -9,6 +9,8 @@
>   #ifndef BTRFS_HMZONED_H
>   #define BTRFS_HMZONED_H
>   
> +#include <linux/blkdev.h>
> +
>   struct btrfs_zoned_device_info {
>   	/*
>   	 * Number of zones, zone size and types of zones if bdev is a
> @@ -25,6 +27,7 @@ int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
>   		       struct blk_zone *zone, gfp_t gfp_mask);
>   int btrfs_get_dev_zone_info(struct btrfs_device *device);
>   void btrfs_destroy_dev_zone_info(struct btrfs_device *device);
> +int btrfs_check_hmzoned_mode(struct btrfs_fs_info *fs_info);
>   
>   static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos)
>   {
> @@ -76,4 +79,19 @@ static inline void btrfs_dev_clear_zone_empty(struct btrfs_device *device,
>   	btrfs_dev_set_empty_zone_bit(device, pos, false);
>   }
>   
> +static inline bool btrfs_check_device_zone_type(struct btrfs_fs_info *fs_info,
> +						struct block_device *bdev)
> +{
> +	u64 zone_size;
> +
> +	if (btrfs_fs_incompat(fs_info, HMZONED)) {
> +		zone_size = (u64)bdev_zone_sectors(bdev) << SECTOR_SHIFT;
> +		/* Do not allow non-zoned device */
> +		return bdev_is_zoned(bdev) && fs_info->zone_size == zone_size;
> +	}
> +
> +	/* Do not allow Host Manged zoned device */
> +	return bdev_zoned_model(bdev) != BLK_ZONED_HM;
> +}
> +
>   #endif
> diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
> index 78de9d5d80c6..d7879a5a2536 100644
> --- a/fs/btrfs/super.c
> +++ b/fs/btrfs/super.c
> @@ -43,6 +43,7 @@
>   #include "free-space-cache.h"
>   #include "backref.h"
>   #include "space-info.h"
> +#include "hmzoned.h"
>   #include "tests/btrfs-tests.h"
>   
>   #include "qgroup.h"
> diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
> index 8e5a894e7bde..755b2ec1e0de 100644
> --- a/fs/btrfs/volumes.c
> +++ b/fs/btrfs/volumes.c
> @@ -2572,6 +2572,11 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
>   	if (IS_ERR(bdev))
>   		return PTR_ERR(bdev);
>   
> +	if (!btrfs_check_device_zone_type(fs_info, bdev)) {
> +		ret = -EINVAL;
> +		goto error;
> +	}
> +
>   	if (fs_devices->seeding) {
>   		seeding_dev = 1;
>   		down_write(&sb->s_umount);
> 


  reply index

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-08  9:30 [PATCH v3 00/27] btrfs zoned block device support Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 01/27] btrfs: introduce HMZONED feature flag Naohiro Aota
2019-08-16  4:49   ` Anand Jain
2019-08-08  9:30 ` [PATCH v3 02/27] btrfs: Get zone information of zoned block devices Naohiro Aota
2019-08-16  4:44   ` Anand Jain
2019-08-16 14:19     ` Damien Le Moal
2019-08-16 23:47       ` Anand Jain
2019-08-16 23:55         ` Damien Le Moal
2019-08-08  9:30 ` [PATCH v3 03/27] btrfs: Check and enable HMZONED mode Naohiro Aota
2019-08-16  5:46   ` Anand Jain [this message]
2019-08-16 14:23     ` Damien Le Moal
2019-08-16 23:56       ` Anand Jain
2019-08-17  0:05         ` Damien Le Moal
2019-08-20  5:07         ` Naohiro Aota
2019-08-20 13:05           ` David Sterba
2019-08-08  9:30 ` [PATCH v3 04/27] btrfs: disallow RAID5/6 in " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 05/27] btrfs: disallow space_cache " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 06/27] btrfs: disallow NODATACOW " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 07/27] btrfs: disable tree-log " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 08/27] btrfs: disable fallocate " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 09/27] btrfs: align device extent allocation to zone boundary Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 10/27] btrfs: do sequential extent allocation in HMZONED mode Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 11/27] btrfs: make unmirroed BGs readonly only if we have at least one writable BG Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 12/27] btrfs: ensure metadata space available on/after degraded mount in HMZONED Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 13/27] btrfs: reset zones of unused block groups Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 14/27] btrfs: limit super block locations in HMZONED mode Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 15/27] btrfs: redirty released extent buffers in sequential BGs Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 16/27] btrfs: serialize data allocation and submit IOs Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 17/27] btrfs: implement atomic compressed IO submission Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 18/27] btrfs: support direct write IO in HMZONED Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 19/27] btrfs: serialize meta IOs on HMZONED mode Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 20/27] btrfs: wait existing extents before truncating Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 21/27] btrfs: avoid async checksum/submit on HMZONED mode Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 22/27] btrfs: disallow mixed-bg in " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 23/27] btrfs: disallow inode_cache " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 24/27] btrfs: support dev-replace " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 25/27] btrfs: enable relocation " Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 26/27] btrfs: relocate block group to repair IO failure in HMZONED Naohiro Aota
2019-08-08  9:30 ` [PATCH v3 27/27] btrfs: enable to mount HMZONED incompat flag Naohiro Aota

Reply instructions:

You may reply publically 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=edcb46f5-1c3e-0b69-a2d9-66164e64b07e@oracle.com \
    --to=anand.jain@oracle.com \
    --cc=Matias.Bjorling@wdc.com \
    --cc=clm@fb.com \
    --cc=damien.lemoal@wdc.com \
    --cc=dsterba@suse.com \
    --cc=hare@suse.com \
    --cc=josef@toxicpanda.com \
    --cc=jthumshirn@suse.de \
    --cc=linux-btrfs@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=naohiro.aota@wdc.com \
    --cc=nborisov@suse.com \
    /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

Linux-Fsdevel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-fsdevel/0 linux-fsdevel/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-fsdevel linux-fsdevel/ https://lore.kernel.org/linux-fsdevel \
		linux-fsdevel@vger.kernel.org linux-fsdevel@archiver.kernel.org
	public-inbox-index linux-fsdevel


Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-fsdevel


AGPL code for this site: git clone https://public-inbox.org/ public-inbox