mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2026-05-22 10:37:35 +03:00
Wire O_DIRECT also to Uncached I/O (#17218)
Before Direct I/O was implemented, I've implemented lighter version I called Uncached I/O. It uses normal DMU/ARC data path with some optimizations, but evicts data from caches as soon as possible and reasonable. Originally I wired it only to a primarycache property, but now completing the integration all the way up to the VFS. While Direct I/O has the lowest possible memory bandwidth usage, it also has a significant number of limitations. It require I/Os to be page aligned, does not allow speculative prefetch, etc. The Uncached I/O does not have those limitations, but instead require additional memory copy, though still one less than regular cached I/O. As such it should fill the gap in between. Considering this I've disabled annoying EINVAL errors on misaligned requests, adding a tunable for those who wants to test their applications. To pass the information between the layers I had to change a number of APIs. But as side effect upper layers can now control not only the caching, but also speculative prefetch. I haven't wired it to VFS yet, since it require looking on some OS specifics. But while there I've implemented speculative prefetch of indirect blocks for Direct I/O, controllable via all the same mechanisms. Signed-off-by: Alexander Motin <mav@FreeBSD.org> Sponsored by: iXsystems, Inc. Fixes #17027 Reviewed-by: Rob Norris <robn@despairlabs.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
This commit is contained in:
+7
-18
@@ -45,20 +45,6 @@ extern "C" {
|
||||
|
||||
#define IN_DMU_SYNC 2
|
||||
|
||||
/*
|
||||
* define flags for dbuf_read
|
||||
*/
|
||||
|
||||
#define DB_RF_MUST_SUCCEED (1 << 0)
|
||||
#define DB_RF_CANFAIL (1 << 1)
|
||||
#define DB_RF_HAVESTRUCT (1 << 2)
|
||||
#define DB_RF_NOPREFETCH (1 << 3)
|
||||
#define DB_RF_NEVERWAIT (1 << 4)
|
||||
#define DB_RF_CACHED (1 << 5)
|
||||
#define DB_RF_NO_DECRYPT (1 << 6)
|
||||
#define DB_RF_PARTIAL_FIRST (1 << 7)
|
||||
#define DB_RF_PARTIAL_MORE (1 << 8)
|
||||
|
||||
/*
|
||||
* The simplified state transition diagram for dbufs looks like:
|
||||
*
|
||||
@@ -389,12 +375,15 @@ void dbuf_rele_and_unlock(dmu_buf_impl_t *db, const void *tag,
|
||||
dmu_buf_impl_t *dbuf_find(struct objset *os, uint64_t object, uint8_t level,
|
||||
uint64_t blkid, uint64_t *hash_out);
|
||||
|
||||
int dbuf_read(dmu_buf_impl_t *db, zio_t *zio, uint32_t flags);
|
||||
int dbuf_read(dmu_buf_impl_t *db, zio_t *zio, dmu_flags_t flags);
|
||||
void dmu_buf_will_clone_or_dio(dmu_buf_t *db, dmu_tx_t *tx);
|
||||
void dmu_buf_will_not_fill(dmu_buf_t *db, dmu_tx_t *tx);
|
||||
void dmu_buf_will_fill(dmu_buf_t *db, dmu_tx_t *tx, boolean_t canfail);
|
||||
void dmu_buf_will_fill_flags(dmu_buf_t *db, dmu_tx_t *tx, boolean_t canfail,
|
||||
dmu_flags_t flags);
|
||||
boolean_t dmu_buf_fill_done(dmu_buf_t *db, dmu_tx_t *tx, boolean_t failed);
|
||||
void dbuf_assign_arcbuf(dmu_buf_impl_t *db, arc_buf_t *buf, dmu_tx_t *tx);
|
||||
void dbuf_assign_arcbuf(dmu_buf_impl_t *db, arc_buf_t *buf, dmu_tx_t *tx,
|
||||
dmu_flags_t flags);
|
||||
dbuf_dirty_record_t *dbuf_dirty(dmu_buf_impl_t *db, dmu_tx_t *tx);
|
||||
dbuf_dirty_record_t *dbuf_dirty_lightweight(dnode_t *dn, uint64_t blkid,
|
||||
dmu_tx_t *tx);
|
||||
@@ -475,10 +464,10 @@ dbuf_find_dirty_eq(dmu_buf_impl_t *db, uint64_t txg)
|
||||
#define DBUF_GET_BUFC_TYPE(_db) \
|
||||
(dbuf_is_metadata(_db) ? ARC_BUFC_METADATA : ARC_BUFC_DATA)
|
||||
|
||||
#define DBUF_IS_CACHEABLE(_db) \
|
||||
#define DBUF_IS_CACHEABLE(_db) (!(_db)->db_pending_evict && \
|
||||
((_db)->db_objset->os_primary_cache == ZFS_CACHE_ALL || \
|
||||
(dbuf_is_metadata(_db) && \
|
||||
((_db)->db_objset->os_primary_cache == ZFS_CACHE_METADATA)))
|
||||
((_db)->db_objset->os_primary_cache == ZFS_CACHE_METADATA))))
|
||||
|
||||
boolean_t dbuf_is_l2cacheable(dmu_buf_impl_t *db, blkptr_t *db_bp);
|
||||
|
||||
|
||||
Reference in New Issue
Block a user