| Message ID | 15b30ab7f305a81238ec74f84a84564137f45d0a.1710906371.git.wqu@suse.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | btrfs: scrub: refine the error messages output frequency | expand |
On Wed, Mar 20, 2024 at 3:55 AM Qu Wenruo <wqu@suse.com> wrote: > > Currently scrub goes different ways to rate limits its error messages: > > - regular btrfs_err_rl_in_rcu() helper for repaired sectors and > the initial message for unrepaired sectors > > - Manually rate limits scrub_print_common_warning() > > I'd say the different rate limits could lead to cases where we only got > the "unable to fixup (regular) error" messages but the detailed report > about that corruption is ratelimited. > > To make the whole rate limit works more consistently, change the rate > limit by: > > - Always using btrfs_*_rl() helpers > > - Remove the initial "unable to fixup (regular) error" message > Since we're ensured to have at least one error message for each > unrepaired sector (before rate limit), there is no need for > a duplicated line. > > And if we hit rate limits, we will rate limit all the error messages > together, not treating different error messages differently. > > Signed-off-by: Qu Wenruo <wqu@suse.com> Reviewed-by: Filipe Manana <fdmanana@suse.com> Looks good, thanks. > --- > fs/btrfs/scrub.c | 26 ++++++++------------------ > 1 file changed, 8 insertions(+), 18 deletions(-) > > diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c > index 0d2b042d75c2..f942c9e3f121 100644 > --- a/fs/btrfs/scrub.c > +++ b/fs/btrfs/scrub.c > @@ -427,7 +427,7 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 num_bytes, > * hold all of the paths here > */ > for (i = 0; i < ipath->fspath->elem_cnt; ++i) { > - btrfs_warn_in_rcu(fs_info, > + btrfs_warn_rl_in_rcu(fs_info, > "%s at logical %llu on dev %s, physical %llu, root %llu, inode %llu, offset %llu, path: %s", > swarn->errstr, swarn->logical, > btrfs_dev_name(swarn->dev), > @@ -442,7 +442,7 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 num_bytes, > return 0; > > err: > - btrfs_warn_in_rcu(fs_info, > + btrfs_warn_rl_in_rcu(fs_info, > "%s at logical %llu on dev %s, physical %llu, root %llu, inode %llu, offset %llu: path resolving failed with ret=%d", > swarn->errstr, swarn->logical, > btrfs_dev_name(swarn->dev), > @@ -500,7 +500,7 @@ static void scrub_print_common_warning(const char *errstr, struct btrfs_device * > break; > if (ret > 0) > break; > - btrfs_warn_in_rcu(fs_info, > + btrfs_warn_rl_in_rcu(fs_info, > "%s at logical %llu on dev %s, physical %llu: metadata %s (level %d) in tree %llu", > errstr, swarn.logical, btrfs_dev_name(dev), > swarn.physical, (ref_level ? "node" : "leaf"), > @@ -508,7 +508,7 @@ static void scrub_print_common_warning(const char *errstr, struct btrfs_device * > swarn.message_printed = true; > } > if (!swarn.message_printed) > - btrfs_warn_in_rcu(fs_info, > + btrfs_warn_rl_in_rcu(fs_info, > "%s at metadata, logical %llu on dev %s physical %llu", > errstr, swarn.logical, > btrfs_dev_name(dev), swarn.physical); > @@ -527,7 +527,7 @@ static void scrub_print_common_warning(const char *errstr, struct btrfs_device * > > iterate_extent_inodes(&ctx, true, scrub_print_warning_inode, &swarn); > if (!swarn.message_printed) > - btrfs_warn_in_rcu(fs_info, > + btrfs_warn_rl_in_rcu(fs_info, > "%s at data, filename unresolved, logical %llu on dev %s physical %llu", > errstr, swarn.logical, > btrfs_dev_name(dev), swarn.physical); > @@ -846,8 +846,6 @@ static void scrub_stripe_submit_repair_read(struct scrub_stripe *stripe, > static void scrub_stripe_report_errors(struct scrub_ctx *sctx, > struct scrub_stripe *stripe) > { > - static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, > - DEFAULT_RATELIMIT_BURST); > struct btrfs_fs_info *fs_info = sctx->fs_info; > struct btrfs_device *dev = stripe->dev; > u64 stripe_physical = stripe->physical; > @@ -899,22 +897,14 @@ static void scrub_stripe_report_errors(struct scrub_ctx *sctx, > } > > /* The remaining are all for unrepaired. */ > - btrfs_err_rl_in_rcu(fs_info, > - "unable to fixup (regular) error at logical %llu on dev %s physical %llu", > - logical, btrfs_dev_name(dev), > - physical); > - > if (test_bit(sector_nr, &stripe->io_error_bitmap)) > - if (__ratelimit(&rs)) > - scrub_print_common_warning("i/o error", dev, > + scrub_print_common_warning("i/o error", dev, > logical, physical); > if (test_bit(sector_nr, &stripe->csum_error_bitmap)) > - if (__ratelimit(&rs)) > - scrub_print_common_warning("checksum error", dev, > + scrub_print_common_warning("checksum error", dev, > logical, physical); > if (test_bit(sector_nr, &stripe->meta_error_bitmap)) > - if (__ratelimit(&rs)) > - scrub_print_common_warning("header error", dev, > + scrub_print_common_warning("header error", dev, > logical, physical); > } > > -- > 2.44.0 > >
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 0d2b042d75c2..f942c9e3f121 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -427,7 +427,7 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 num_bytes, * hold all of the paths here */ for (i = 0; i < ipath->fspath->elem_cnt; ++i) { - btrfs_warn_in_rcu(fs_info, + btrfs_warn_rl_in_rcu(fs_info, "%s at logical %llu on dev %s, physical %llu, root %llu, inode %llu, offset %llu, path: %s", swarn->errstr, swarn->logical, btrfs_dev_name(swarn->dev), @@ -442,7 +442,7 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 num_bytes, return 0; err: - btrfs_warn_in_rcu(fs_info, + btrfs_warn_rl_in_rcu(fs_info, "%s at logical %llu on dev %s, physical %llu, root %llu, inode %llu, offset %llu: path resolving failed with ret=%d", swarn->errstr, swarn->logical, btrfs_dev_name(swarn->dev), @@ -500,7 +500,7 @@ static void scrub_print_common_warning(const char *errstr, struct btrfs_device * break; if (ret > 0) break; - btrfs_warn_in_rcu(fs_info, + btrfs_warn_rl_in_rcu(fs_info, "%s at logical %llu on dev %s, physical %llu: metadata %s (level %d) in tree %llu", errstr, swarn.logical, btrfs_dev_name(dev), swarn.physical, (ref_level ? "node" : "leaf"), @@ -508,7 +508,7 @@ static void scrub_print_common_warning(const char *errstr, struct btrfs_device * swarn.message_printed = true; } if (!swarn.message_printed) - btrfs_warn_in_rcu(fs_info, + btrfs_warn_rl_in_rcu(fs_info, "%s at metadata, logical %llu on dev %s physical %llu", errstr, swarn.logical, btrfs_dev_name(dev), swarn.physical); @@ -527,7 +527,7 @@ static void scrub_print_common_warning(const char *errstr, struct btrfs_device * iterate_extent_inodes(&ctx, true, scrub_print_warning_inode, &swarn); if (!swarn.message_printed) - btrfs_warn_in_rcu(fs_info, + btrfs_warn_rl_in_rcu(fs_info, "%s at data, filename unresolved, logical %llu on dev %s physical %llu", errstr, swarn.logical, btrfs_dev_name(dev), swarn.physical); @@ -846,8 +846,6 @@ static void scrub_stripe_submit_repair_read(struct scrub_stripe *stripe, static void scrub_stripe_report_errors(struct scrub_ctx *sctx, struct scrub_stripe *stripe) { - static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, - DEFAULT_RATELIMIT_BURST); struct btrfs_fs_info *fs_info = sctx->fs_info; struct btrfs_device *dev = stripe->dev; u64 stripe_physical = stripe->physical; @@ -899,22 +897,14 @@ static void scrub_stripe_report_errors(struct scrub_ctx *sctx, } /* The remaining are all for unrepaired. */ - btrfs_err_rl_in_rcu(fs_info, - "unable to fixup (regular) error at logical %llu on dev %s physical %llu", - logical, btrfs_dev_name(dev), - physical); - if (test_bit(sector_nr, &stripe->io_error_bitmap)) - if (__ratelimit(&rs)) - scrub_print_common_warning("i/o error", dev, + scrub_print_common_warning("i/o error", dev, logical, physical); if (test_bit(sector_nr, &stripe->csum_error_bitmap)) - if (__ratelimit(&rs)) - scrub_print_common_warning("checksum error", dev, + scrub_print_common_warning("checksum error", dev, logical, physical); if (test_bit(sector_nr, &stripe->meta_error_bitmap)) - if (__ratelimit(&rs)) - scrub_print_common_warning("header error", dev, + scrub_print_common_warning("header error", dev, logical, physical); }
Currently scrub goes different ways to rate limits its error messages: - regular btrfs_err_rl_in_rcu() helper for repaired sectors and the initial message for unrepaired sectors - Manually rate limits scrub_print_common_warning() I'd say the different rate limits could lead to cases where we only got the "unable to fixup (regular) error" messages but the detailed report about that corruption is ratelimited. To make the whole rate limit works more consistently, change the rate limit by: - Always using btrfs_*_rl() helpers - Remove the initial "unable to fixup (regular) error" message Since we're ensured to have at least one error message for each unrepaired sector (before rate limit), there is no need for a duplicated line. And if we hit rate limits, we will rate limit all the error messages together, not treating different error messages differently. Signed-off-by: Qu Wenruo <wqu@suse.com> --- fs/btrfs/scrub.c | 26 ++++++++------------------ 1 file changed, 8 insertions(+), 18 deletions(-)