/* SPDX-License-Identifier: GPL-2.0+ */ /* * Copyright (C) 2019 Oracle. All Rights Reserved. * Author: Darrick J. Wong <[email protected]> */ #ifndef __XFS_HEALTH_H__ #define __XFS_HEALTH_H__ /* * In-Core Filesystem Health Assessments * ===================================== * * We'd like to be able to summarize the current health status of the * filesystem so that the administrator knows when it's necessary to schedule * some downtime for repairs. Until then, we would also like to avoid abrupt * shutdowns due to corrupt metadata. * * The online scrub feature evaluates the health of all filesystem metadata. * When scrub detects corruption in a piece of metadata it will set the * corresponding sickness flag, and repair will clear it if successful. If * problems remain at unmount time, we can also request manual intervention by * logging a notice to run xfs_repair. * * Each health tracking group uses a pair of fields for reporting. The * "checked" field tell us if a given piece of metadata has ever been examined, * and the "sick" field tells us if that piece was found to need repairs. * Therefore we can conclude that for a given sick flag value: * * - checked && sick => metadata needs repair * - checked && !sick => metadata is ok * - !checked && sick => errors have been observed during normal operation, * but the metadata has not been checked thoroughly * - !checked && !sick => has not been examined since mount * * Evidence of health problems can be sorted into three basic categories: * * a) Primary evidence, which signals that something is defective within the * general grouping of metadata. * * b) Secondary evidence, which are side effects of primary problem but are * not themselves problems. These can be forgotten when the primary * health problems are addressed. * * c) Indirect evidence, which points to something being wrong in another * group, but we had to release resources and this is all that's left of * that state. */ struct xfs_mount; struct xfs_perag; struct xfs_inode; struct xfs_fsop_geom; struct xfs_btree_cur; struct xfs_da_args; /* Observable health issues for metadata spanning the entire filesystem. */ #define XFS_SICK_FS_COUNTERS … #define XFS_SICK_FS_UQUOTA … #define XFS_SICK_FS_GQUOTA … #define XFS_SICK_FS_PQUOTA … #define XFS_SICK_FS_QUOTACHECK … #define XFS_SICK_FS_NLINKS … /* Observable health issues for realtime volume metadata. */ #define XFS_SICK_RT_BITMAP … #define XFS_SICK_RT_SUMMARY … /* Observable health issues for AG metadata. */ #define XFS_SICK_AG_SB … #define XFS_SICK_AG_AGF … #define XFS_SICK_AG_AGFL … #define XFS_SICK_AG_AGI … #define XFS_SICK_AG_BNOBT … #define XFS_SICK_AG_CNTBT … #define XFS_SICK_AG_INOBT … #define XFS_SICK_AG_FINOBT … #define XFS_SICK_AG_RMAPBT … #define XFS_SICK_AG_REFCNTBT … #define XFS_SICK_AG_INODES … /* Observable health issues for inode metadata. */ #define XFS_SICK_INO_CORE … #define XFS_SICK_INO_BMBTD … #define XFS_SICK_INO_BMBTA … #define XFS_SICK_INO_BMBTC … #define XFS_SICK_INO_DIR … #define XFS_SICK_INO_XATTR … #define XFS_SICK_INO_SYMLINK … #define XFS_SICK_INO_PARENT … #define XFS_SICK_INO_BMBTD_ZAPPED … #define XFS_SICK_INO_BMBTA_ZAPPED … #define XFS_SICK_INO_DIR_ZAPPED … #define XFS_SICK_INO_SYMLINK_ZAPPED … /* Don't propagate sick status to ag health summary during inactivation */ #define XFS_SICK_INO_FORGET … #define XFS_SICK_INO_DIRTREE … /* Primary evidence of health problems in a given group. */ #define XFS_SICK_FS_PRIMARY … #define XFS_SICK_RT_PRIMARY … #define XFS_SICK_AG_PRIMARY … #define XFS_SICK_INO_PRIMARY … #define XFS_SICK_INO_ZAPPED … /* Secondary state related to (but not primary evidence of) health problems. */ #define XFS_SICK_FS_SECONDARY … #define XFS_SICK_RT_SECONDARY … #define XFS_SICK_AG_SECONDARY … #define XFS_SICK_INO_SECONDARY … /* Evidence of health problems elsewhere. */ #define XFS_SICK_FS_INDIRECT … #define XFS_SICK_RT_INDIRECT … #define XFS_SICK_AG_INDIRECT … #define XFS_SICK_INO_INDIRECT … /* All health masks. */ #define XFS_SICK_FS_ALL … #define XFS_SICK_RT_ALL … #define XFS_SICK_AG_ALL … #define XFS_SICK_INO_ALL … /* * These functions must be provided by the xfs implementation. Function * behavior with respect to the first argument should be as follows: * * xfs_*_mark_sick: Set the sick flags and do not set checked flags. * Runtime code should call this upon encountering * a corruption. * * xfs_*_mark_corrupt: Set the sick and checked flags simultaneously. * Fsck tools should call this when corruption is * found. * * xfs_*_mark_healthy: Clear the sick flags and set the checked flags. * Fsck tools should call this after correcting errors. * * xfs_*_measure_sickness: Return the sick and check status in the provided * out parameters. */ void xfs_fs_mark_sick(struct xfs_mount *mp, unsigned int mask); void xfs_fs_mark_corrupt(struct xfs_mount *mp, unsigned int mask); void xfs_fs_mark_healthy(struct xfs_mount *mp, unsigned int mask); void xfs_fs_measure_sickness(struct xfs_mount *mp, unsigned int *sick, unsigned int *checked); void xfs_rt_mark_sick(struct xfs_mount *mp, unsigned int mask); void xfs_rt_mark_corrupt(struct xfs_mount *mp, unsigned int mask); void xfs_rt_mark_healthy(struct xfs_mount *mp, unsigned int mask); void xfs_rt_measure_sickness(struct xfs_mount *mp, unsigned int *sick, unsigned int *checked); void xfs_agno_mark_sick(struct xfs_mount *mp, xfs_agnumber_t agno, unsigned int mask); void xfs_ag_mark_sick(struct xfs_perag *pag, unsigned int mask); void xfs_ag_mark_corrupt(struct xfs_perag *pag, unsigned int mask); void xfs_ag_mark_healthy(struct xfs_perag *pag, unsigned int mask); void xfs_ag_measure_sickness(struct xfs_perag *pag, unsigned int *sick, unsigned int *checked); void xfs_inode_mark_sick(struct xfs_inode *ip, unsigned int mask); void xfs_inode_mark_corrupt(struct xfs_inode *ip, unsigned int mask); void xfs_inode_mark_healthy(struct xfs_inode *ip, unsigned int mask); void xfs_inode_measure_sickness(struct xfs_inode *ip, unsigned int *sick, unsigned int *checked); void xfs_health_unmount(struct xfs_mount *mp); void xfs_bmap_mark_sick(struct xfs_inode *ip, int whichfork); void xfs_btree_mark_sick(struct xfs_btree_cur *cur); void xfs_dirattr_mark_sick(struct xfs_inode *ip, int whichfork); void xfs_da_mark_sick(struct xfs_da_args *args); /* Now some helpers. */ static inline bool xfs_fs_has_sickness(struct xfs_mount *mp, unsigned int mask) { … } static inline bool xfs_rt_has_sickness(struct xfs_mount *mp, unsigned int mask) { … } static inline bool xfs_ag_has_sickness(struct xfs_perag *pag, unsigned int mask) { … } static inline bool xfs_inode_has_sickness(struct xfs_inode *ip, unsigned int mask) { … } static inline bool xfs_fs_is_healthy(struct xfs_mount *mp) { … } static inline bool xfs_rt_is_healthy(struct xfs_mount *mp) { … } static inline bool xfs_ag_is_healthy(struct xfs_perag *pag) { … } static inline bool xfs_inode_is_healthy(struct xfs_inode *ip) { … } void xfs_fsop_geom_health(struct xfs_mount *mp, struct xfs_fsop_geom *geo); void xfs_ag_geom_health(struct xfs_perag *pag, struct xfs_ag_geometry *ageo); void xfs_bulkstat_health(struct xfs_inode *ip, struct xfs_bulkstat *bs); #define xfs_metadata_is_sick(error) … #endif /* __XFS_HEALTH_H__ */
Codebase Browser
linux