ZIL: Cleanup sync and commit handling

ZVOL:
 - Mark all ZVOL ZIL transactions as sync.  Since ZVOLs have only
one object, it makes no sense to maintain async queue and on each
commit merge it into sync. Single sync queue is just cheaper, while
it changes nothing until actual commit request arrives.
 - Remove zsd_sync_cnt and the zil_async_to_sync() calls since we
are no longer switching between sync and async queues.

ZFS:
 - Mark write transactions as sync based only on number of sync
opens (z_sync_cnt).  We can not randomly jump between sync and
async unless we want data corruptions due to writes reordering.
 - When file first opened with O_SYNC (z_sync_cnt incremented to 1)
call zil_async_to_sync() for it to preserve correct ordering between
past and future writes.
 - Drop zfs_fsyncer_key logic.  Looks like it was an optimization
for workloads heavily intermixing async writes with tons of fsyncs.
But first it was broken 8 years ago due to Linux tsd implementation
not allowing data storage between syscalls, and second, I doubt it
is safe to switch from async to sync so often and without calling
zil_async_to_sync().

 - Rename sync argument of *_log_write() into commit, now only
signalling caller's intent to call zil_commit() soon after.  It
allows WR_COPIED optimizations without extra other meanings.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: George Wilson <george.wilson@delphix.com>
Signed-off-by:	Alexander Motin <mav@FreeBSD.org>
Sponsored by:	iXsystems, Inc.
Closes #15366
This commit is contained in:
Alexander Motin
2023-10-30 17:51:56 -04:00
committed by GitHub
parent 043c6ee3b6
commit c3773de168
12 changed files with 65 additions and 82 deletions
-1
View File
@@ -575,7 +575,6 @@ typedef struct zfsdev_state {
extern void *zfsdev_get_state(minor_t minor, enum zfsdev_state_type which);
extern int zfsdev_getminor(zfs_file_t *fp, minor_t *minorp);
extern uint_t zfs_fsyncer_key;
extern uint_t zfs_allow_log_key;
#endif /* _KERNEL */
+1 -1
View File
@@ -307,7 +307,7 @@ extern void zfs_log_rename_whiteout(zilog_t *zilog, dmu_tx_t *tx,
uint64_t txtype, znode_t *sdzp, const char *sname, znode_t *tdzp,
const char *dname, znode_t *szp, znode_t *wzp);
extern void zfs_log_write(zilog_t *zilog, dmu_tx_t *tx, int txtype,
znode_t *zp, offset_t off, ssize_t len, int ioflag,
znode_t *zp, offset_t off, ssize_t len, boolean_t commit,
zil_callback_t callback, void *callback_data);
extern void zfs_log_truncate(zilog_t *zilog, dmu_tx_t *tx, int txtype,
znode_t *zp, uint64_t off, uint64_t len);
+2 -2
View File
@@ -81,9 +81,9 @@ void zvol_remove_minors_impl(const char *name);
void zvol_last_close(zvol_state_t *zv);
void zvol_insert(zvol_state_t *zv);
void zvol_log_truncate(zvol_state_t *zv, dmu_tx_t *tx, uint64_t off,
uint64_t len, boolean_t sync);
uint64_t len);
void zvol_log_write(zvol_state_t *zv, dmu_tx_t *tx, uint64_t offset,
uint64_t size, int sync);
uint64_t size, boolean_t commit);
int zvol_get_data(void *arg, uint64_t arg2, lr_write_t *lr, char *buf,
struct lwb *lwb, zio_t *zio);
int zvol_init_impl(void);