From: Johannes Thumshirn <johannes.thumshirn@wdc.com>
To: Chris Mason <clm@fb.com>, Josef Bacik <josef@toxicpanda.com>,
David Sterba <dsterba@suse.com>
Cc: Christoph Hellwig <hch@lst.de>,
Naohiro Aota <naohiro.aota@wdc.com>, Qu Wenruo <wqu@suse.com>,
Damien Le Moal <dlemoal@kernel.org>,
linux-btrfs@vger.kernel.org, linux-kernel@vger.kernel.org,
Johannes Thumshirn <johannes.thumshirn@wdc.com>
Subject: [PATCH v9 06/11] btrfs: implement RST version of scrub
Date: Thu, 14 Sep 2023 09:07:01 -0700 [thread overview]
Message-ID: <20230914-raid-stripe-tree-v9-6-15d423829637@wdc.com> (raw)
In-Reply-To: <20230914-raid-stripe-tree-v9-0-15d423829637@wdc.com>
A filesystem that uses the RAID stripe tree for logical to physical
address translation can't use the regular scrub path, that reads all
stripes and then checks if a sector is unused afterwards.
When using the RAID stripe tree, this will result in lookup errors, as the
stripe tree doesn't know the requested logical addresses.
Instead, look up stripes that are backed by the extent bitmap.
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
---
fs/btrfs/bio.c | 2 ++
fs/btrfs/raid-stripe-tree.c | 8 ++++++-
fs/btrfs/scrub.c | 53 +++++++++++++++++++++++++++++++++++++++++++++
fs/btrfs/volumes.h | 1 +
4 files changed, 63 insertions(+), 1 deletion(-)
diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
index ddbe6f8d4ea2..bdb6e3effdbb 100644
--- a/fs/btrfs/bio.c
+++ b/fs/btrfs/bio.c
@@ -663,6 +663,8 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
blk_status_t ret;
int error;
+ smap.is_scrub = !bbio->inode;
+
btrfs_bio_counter_inc_blocked(fs_info);
error = btrfs_map_block(fs_info, btrfs_op(bio), logical, &map_length,
&bioc, &smap, &mirror_num, 1);
diff --git a/fs/btrfs/raid-stripe-tree.c b/fs/btrfs/raid-stripe-tree.c
index 697a6e1fd255..63bf62c33436 100644
--- a/fs/btrfs/raid-stripe-tree.c
+++ b/fs/btrfs/raid-stripe-tree.c
@@ -334,6 +334,11 @@ int btrfs_get_raid_extent_offset(struct btrfs_fs_info *fs_info,
if (!path)
return -ENOMEM;
+ if (stripe->is_scrub) {
+ path->skip_locking = 1;
+ path->search_commit_root = 1;
+ }
+
ret = btrfs_search_slot(NULL, stripe_root, &stripe_key, path, 0, 0);
if (ret < 0)
goto free_path;
@@ -420,7 +425,8 @@ int btrfs_get_raid_extent_offset(struct btrfs_fs_info *fs_info,
out:
if (ret > 0)
ret = -ENOENT;
- if (ret && ret != -EIO) {
+ if (ret && ret != -EIO && !stripe->is_scrub) {
+
if (IS_ENABLED(CONFIG_BTRFS_DEBUG))
btrfs_print_tree(leaf, 1);
btrfs_err(fs_info,
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index f16220ce5fba..42948b66d4be 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -23,6 +23,7 @@
#include "accessors.h"
#include "file-item.h"
#include "scrub.h"
+#include "raid-stripe-tree.h"
/*
* This is only the first step towards a full-features scrub. It reads all
@@ -1634,6 +1635,53 @@ static void scrub_reset_stripe(struct scrub_stripe *stripe)
}
}
+static void scrub_submit_extent_sector_read(struct scrub_ctx *sctx,
+ struct scrub_stripe *stripe)
+{
+ struct btrfs_fs_info *fs_info = stripe->bg->fs_info;
+ struct btrfs_bio *bbio = NULL;
+ int mirror = stripe->mirror_num;
+ int i;
+
+ atomic_inc(&stripe->pending_io);
+
+ for_each_set_bit(i, &stripe->extent_sector_bitmap, stripe->nr_sectors) {
+ struct page *page = scrub_stripe_get_page(stripe, i);
+ unsigned int pgoff = scrub_stripe_get_page_offset(stripe, i);
+
+ /* The current sector cannot be merged, submit the bio. */
+ if (bbio &&
+ ((i > 0 && !test_bit(i - 1, &stripe->extent_sector_bitmap)) ||
+ bbio->bio.bi_iter.bi_size >= BTRFS_STRIPE_LEN)) {
+ ASSERT(bbio->bio.bi_iter.bi_size);
+ atomic_inc(&stripe->pending_io);
+ btrfs_submit_bio(bbio, mirror);
+ bbio = NULL;
+ }
+
+ if (!bbio) {
+ bbio = btrfs_bio_alloc(stripe->nr_sectors, REQ_OP_READ,
+ fs_info, scrub_read_endio, stripe);
+ bbio->bio.bi_iter.bi_sector = (stripe->logical +
+ (i << fs_info->sectorsize_bits)) >> SECTOR_SHIFT;
+ }
+
+ __bio_add_page(&bbio->bio, page, fs_info->sectorsize, pgoff);
+ }
+
+ if (bbio) {
+ ASSERT(bbio->bio.bi_iter.bi_size);
+ atomic_inc(&stripe->pending_io);
+ btrfs_submit_bio(bbio, mirror);
+ }
+
+ if (atomic_dec_and_test(&stripe->pending_io)) {
+ wake_up(&stripe->io_wait);
+ INIT_WORK(&stripe->work, scrub_stripe_read_repair_worker);
+ queue_work(stripe->bg->fs_info->scrub_workers, &stripe->work);
+ }
+}
+
static void scrub_submit_initial_read(struct scrub_ctx *sctx,
struct scrub_stripe *stripe)
{
@@ -1645,6 +1693,11 @@ static void scrub_submit_initial_read(struct scrub_ctx *sctx,
ASSERT(stripe->mirror_num > 0);
ASSERT(test_bit(SCRUB_STRIPE_FLAG_INITIALIZED, &stripe->state));
+ if (btrfs_need_stripe_tree_update(fs_info, stripe->bg->flags)) {
+ scrub_submit_extent_sector_read(sctx, stripe);
+ return;
+ }
+
bbio = btrfs_bio_alloc(SCRUB_STRIPE_PAGES, REQ_OP_READ, fs_info,
scrub_read_endio, stripe);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 2043aff6e966..067859de8f4c 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -393,6 +393,7 @@ struct btrfs_io_stripe {
/* Block mapping */
u64 physical;
u64 length;
+ bool is_scrub;
/* For the endio handler */
struct btrfs_io_context *bioc;
};
--
2.41.0
next prev parent reply other threads:[~2023-09-14 16:07 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-09-14 16:06 [PATCH v9 00/11] btrfs: introduce RAID stripe tree Johannes Thumshirn
2023-09-14 16:06 ` [PATCH v9 01/11] btrfs: add raid stripe tree definitions Johannes Thumshirn
2023-09-15 0:22 ` Qu Wenruo
2023-09-15 0:26 ` Qu Wenruo
2023-09-15 9:55 ` Johannes Thumshirn
2023-09-15 10:33 ` Qu Wenruo
2023-09-15 10:46 ` Johannes Thumshirn
2023-10-02 9:32 ` Johannes Thumshirn
2023-09-14 16:06 ` [PATCH v9 02/11] btrfs: read raid-stripe-tree from disk Johannes Thumshirn
2023-09-14 16:06 ` [PATCH v9 03/11] btrfs: add support for inserting raid stripe extents Johannes Thumshirn
2023-09-14 18:07 ` David Sterba
2023-09-15 10:03 ` Geert Uytterhoeven
2023-09-14 18:10 ` David Sterba
2023-09-15 0:55 ` Qu Wenruo
2023-09-19 12:13 ` Johannes Thumshirn
2023-09-14 16:06 ` [PATCH v9 04/11] btrfs: delete stripe extent on extent deletion Johannes Thumshirn
2023-09-14 16:07 ` [PATCH v9 05/11] btrfs: lookup physical address from stripe extent Johannes Thumshirn
2023-09-14 17:57 ` David Sterba
2023-09-14 16:07 ` Johannes Thumshirn [this message]
2023-09-15 0:58 ` [PATCH v9 06/11] btrfs: implement RST version of scrub Qu Wenruo
2023-09-15 14:11 ` David Sterba
2023-09-14 16:07 ` [PATCH v9 07/11] btrfs: zoned: allow zoned RAID Johannes Thumshirn
2023-09-14 17:59 ` David Sterba
2023-09-14 16:07 ` [PATCH v9 08/11] btrfs: add raid stripe tree pretty printer Johannes Thumshirn
2023-09-14 16:07 ` [PATCH v9 09/11] btrfs: announce presence of raid-stripe-tree in sysfs Johannes Thumshirn
2023-09-14 16:07 ` [PATCH v9 10/11] btrfs: add trace events for RST Johannes Thumshirn
2023-09-14 16:07 ` [PATCH v9 11/11] btrfs: add raid-stripe-tree to features enabled with debug Johannes Thumshirn
2023-09-14 18:25 ` [PATCH v9 00/11] btrfs: introduce RAID stripe tree David Sterba
2023-09-20 16:23 ` David Sterba
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=20230914-raid-stripe-tree-v9-6-15d423829637@wdc.com \
--to=johannes.thumshirn@wdc.com \
--cc=clm@fb.com \
--cc=dlemoal@kernel.org \
--cc=dsterba@suse.com \
--cc=hch@lst.de \
--cc=josef@toxicpanda.com \
--cc=linux-btrfs@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=naohiro.aota@wdc.com \
--cc=wqu@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
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).