aboutsummaryrefslogtreecommitdiffstats
path: root/include/sys/fs
diff options
context:
space:
mode:
authorSerapheim Dimitropoulos <[email protected]>2016-12-16 14:11:29 -0800
committerBrian Behlendorf <[email protected]>2018-06-26 10:07:42 -0700
commitd2734cce68cf740e015312314415f9034c67851c (patch)
treeb7a140a3cf2a19bb7c88f2d277f3b5a33c121cea /include/sys/fs
parent88eaf610d9c7056f0946e5090cba1e6288ff2b70 (diff)
OpenZFS 9166 - zfs storage pool checkpoint
Details about the motivation of this feature and its usage can be found in this blogpost: https://sdimitro.github.io/post/zpool-checkpoint/ A lightning talk of this feature can be found here: https://www.youtube.com/watch?v=fPQA8K40jAM Implementation details can be found in big block comment of spa_checkpoint.c Side-changes that are relevant to this commit but not explained elsewhere: * renames members of "struct metaslab trees to be shorter without losing meaning * space_map_{alloc,truncate}() accept a block size as a parameter. The reason is that in the current state all space maps that we allocate through the DMU use a global tunable (space_map_blksz) which defauls to 4KB. This is ok for metaslab space maps in terms of bandwirdth since they are scattered all over the disk. But for other space maps this default is probably not what we want. Examples are device removal's vdev_obsolete_sm or vdev_chedkpoint_sm from this review. Both of these have a 1:1 relationship with each vdev and could benefit from a bigger block size. Porting notes: * The part of dsl_scan_sync() which handles async destroys has been moved into the new dsl_process_async_destroys() function. * Remove "VERIFY(!(flags & FWRITE))" in "kernel.c" so zhack can write to block device backed pools. * ZTS: * Fix get_txg() in zpool_sync_001_pos due to "checkpoint_txg". * Don't use large dd block sizes on /dev/urandom under Linux in checkpoint_capacity. * Adopt Delphix-OS's setting of 4 (spa_asize_inflation = SPA_DVAS_PER_BP + 1) for the checkpoint_capacity test to speed its attempts to fill the pool * Create the base and nested pools with sync=disabled to speed up the "setup" phase. * Clear labels in test pool between checkpoint tests to avoid duplicate pool issues. * The import_rewind_device_replaced test has been marked as "known to fail" for the reasons listed in its DISCLAIMER. * New module parameters: zfs_spa_discard_memory_limit, zfs_remove_max_bytes_pause (not documented - debugging only) vdev_max_ms_count (formerly metaslabs_per_vdev) vdev_min_ms_count Authored by: Serapheim Dimitropoulos <[email protected]> Reviewed by: Matthew Ahrens <[email protected]> Reviewed by: John Kennedy <[email protected]> Reviewed by: Dan Kimmel <[email protected]> Reviewed by: Brian Behlendorf <[email protected]> Approved by: Richard Lowe <[email protected]> Ported-by: Tim Chase <[email protected]> Signed-off-by: Tim Chase <[email protected]> OpenZFS-issue: https://illumos.org/issues/9166 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/7159fdb8 Closes #7570
Diffstat (limited to 'include/sys/fs')
-rw-r--r--include/sys/fs/zfs.h37
1 files changed, 36 insertions, 1 deletions
diff --git a/include/sys/fs/zfs.h b/include/sys/fs/zfs.h
index 870618ecb..0ee9b00bd 100644
--- a/include/sys/fs/zfs.h
+++ b/include/sys/fs/zfs.h
@@ -239,6 +239,7 @@ typedef enum {
ZPOOL_PROP_TNAME,
ZPOOL_PROP_MAXDNODESIZE,
ZPOOL_PROP_MULTIHOST,
+ ZPOOL_PROP_CHECKPOINT,
ZPOOL_NUM_PROPS
} zpool_prop_t;
@@ -616,6 +617,7 @@ typedef struct zpool_load_policy {
#define ZPOOL_CONFIG_DTL "DTL"
#define ZPOOL_CONFIG_SCAN_STATS "scan_stats" /* not stored on disk */
#define ZPOOL_CONFIG_REMOVAL_STATS "removal_stats" /* not stored on disk */
+#define ZPOOL_CONFIG_CHECKPOINT_STATS "checkpoint_stats" /* not on disk */
#define ZPOOL_CONFIG_VDEV_STATS "vdev_stats" /* not stored on disk */
#define ZPOOL_CONFIG_INDIRECT_SIZE "indirect_size" /* not stored on disk */
@@ -752,6 +754,8 @@ typedef struct zpool_load_policy {
"com.delphix:indirect_obsolete_sm"
#define VDEV_TOP_ZAP_OBSOLETE_COUNTS_ARE_PRECISE \
"com.delphix:obsolete_counts_are_precise"
+#define VDEV_TOP_ZAP_POOL_CHECKPOINT_SM \
+ "com.delphix:pool_checkpoint_sm"
/*
* This is needed in userland to report the minimum necessary device size.
@@ -861,6 +865,18 @@ typedef enum pool_scrub_cmd {
POOL_SCRUB_FLAGS_END
} pool_scrub_cmd_t;
+typedef enum {
+ CS_NONE,
+ CS_CHECKPOINT_EXISTS,
+ CS_CHECKPOINT_DISCARDING,
+ CS_NUM_STATES
+} checkpoint_state_t;
+
+typedef struct pool_checkpoint_stat {
+ uint64_t pcs_state; /* checkpoint_state_t */
+ uint64_t pcs_start_time; /* time checkpoint/discard started */
+ uint64_t pcs_space; /* checkpointed space */
+} pool_checkpoint_stat_t;
/*
* ZIO types. Needed to interpret vdev statistics below.
@@ -958,7 +974,7 @@ typedef struct vdev_stat {
uint64_t vs_scan_removing; /* removing? */
uint64_t vs_scan_processed; /* scan processed bytes */
uint64_t vs_fragmentation; /* device fragmentation */
-
+ uint64_t vs_checkpoint_space; /* checkpoint-consumed space */
} vdev_stat_t;
/*
@@ -1144,6 +1160,8 @@ typedef enum zfs_ioc {
ZFS_IOC_UNLOAD_KEY,
ZFS_IOC_CHANGE_KEY,
ZFS_IOC_REMAP,
+ ZFS_IOC_POOL_CHECKPOINT,
+ ZFS_IOC_POOL_DISCARD_CHECKPOINT,
/*
* Linux - 3/64 numbers reserved.
@@ -1167,6 +1185,22 @@ typedef enum zfs_ioc {
#define BLKZNAME _IOR(0x12, 125, char[ZFS_MAX_DATASET_NAME_LEN])
/*
+ * ZFS-specific error codes used for returning descriptive errors
+ * to the userland through zfs ioctls.
+ *
+ * The enum implicitly includes all the error codes from errno.h.
+ * New code should use and extend this enum for errors that are
+ * not described precisely by generic errno codes.
+ */
+typedef enum {
+ ZFS_ERR_CHECKPOINT_EXISTS = 1024,
+ ZFS_ERR_DISCARDING_CHECKPOINT,
+ ZFS_ERR_NO_CHECKPOINT,
+ ZFS_ERR_DEVRM_IN_PROGRESS,
+ ZFS_ERR_VDEV_TOO_BIG
+} zfs_errno_t;
+
+/*
* Internal SPA load state. Used by FMA diagnosis engine.
*/
typedef enum {
@@ -1235,6 +1269,7 @@ typedef enum {
#define ZFS_IMPORT_TEMP_NAME 0x10
#define ZFS_IMPORT_SKIP_MMP 0x20
#define ZFS_IMPORT_LOAD_KEYS 0x40
+#define ZFS_IMPORT_CHECKPOINT 0x80
/*
* Channel program argument/return nvlist keys and defaults.