Print this page
4045 zfs write throttle & i/o scheduler performance work
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Adam Leventhal <ahl@delphix.com>
Reviewed by: Christopher Siden <christopher.siden@delphix.com>

*** 37,70 **** #include <sys/arc.h> #include <sys/ddt.h> /* * ========================================================================== - * I/O priority table - * ========================================================================== - */ - uint8_t zio_priority_table[ZIO_PRIORITY_TABLE_SIZE] = { - 0, /* ZIO_PRIORITY_NOW */ - 0, /* ZIO_PRIORITY_SYNC_READ */ - 0, /* ZIO_PRIORITY_SYNC_WRITE */ - 0, /* ZIO_PRIORITY_LOG_WRITE */ - 1, /* ZIO_PRIORITY_CACHE_FILL */ - 1, /* ZIO_PRIORITY_AGG */ - 4, /* ZIO_PRIORITY_FREE */ - 4, /* ZIO_PRIORITY_ASYNC_WRITE */ - 6, /* ZIO_PRIORITY_ASYNC_READ */ - 10, /* ZIO_PRIORITY_RESILVER */ - 20, /* ZIO_PRIORITY_SCRUB */ - 2, /* ZIO_PRIORITY_DDT_PREFETCH */ - }; - - /* - * ========================================================================== * I/O type descriptions * ========================================================================== */ ! char *zio_type_name[ZIO_TYPES] = { "zio_null", "zio_read", "zio_write", "zio_free", "zio_claim", "zio_ioctl" }; /* --- 37,50 ---- #include <sys/arc.h> #include <sys/ddt.h> /* * ========================================================================== * I/O type descriptions * ========================================================================== */ ! const char *zio_type_name[ZIO_TYPES] = { "zio_null", "zio_read", "zio_write", "zio_free", "zio_claim", "zio_ioctl" }; /*
*** 484,494 **** mutex_enter(&pio->io_lock); if (zio->io_error && !(zio->io_flags & ZIO_FLAG_DONT_PROPAGATE)) *errorp = zio_worst_error(*errorp, zio->io_error); pio->io_reexecute |= zio->io_reexecute; ASSERT3U(*countp, >, 0); ! if (--*countp == 0 && pio->io_stall == countp) { pio->io_stall = NULL; mutex_exit(&pio->io_lock); zio_execute(pio); } else { mutex_exit(&pio->io_lock); --- 464,477 ---- mutex_enter(&pio->io_lock); if (zio->io_error && !(zio->io_flags & ZIO_FLAG_DONT_PROPAGATE)) *errorp = zio_worst_error(*errorp, zio->io_error); pio->io_reexecute |= zio->io_reexecute; ASSERT3U(*countp, >, 0); ! ! (*countp)--; ! ! if (*countp == 0 && pio->io_stall == countp) { pio->io_stall = NULL; mutex_exit(&pio->io_lock); zio_execute(pio); } else { mutex_exit(&pio->io_lock);
*** 508,518 **** * ========================================================================== */ static zio_t * zio_create(zio_t *pio, spa_t *spa, uint64_t txg, const blkptr_t *bp, void *data, uint64_t size, zio_done_func_t *done, void *private, ! zio_type_t type, int priority, enum zio_flag flags, vdev_t *vd, uint64_t offset, const zbookmark_t *zb, enum zio_stage stage, enum zio_stage pipeline) { zio_t *zio; --- 491,501 ---- * ========================================================================== */ static zio_t * zio_create(zio_t *pio, spa_t *spa, uint64_t txg, const blkptr_t *bp, void *data, uint64_t size, zio_done_func_t *done, void *private, ! zio_type_t type, zio_priority_t priority, enum zio_flag flags, vdev_t *vd, uint64_t offset, const zbookmark_t *zb, enum zio_stage stage, enum zio_stage pipeline) { zio_t *zio;
*** 618,628 **** } zio_t * zio_read(zio_t *pio, spa_t *spa, const blkptr_t *bp, void *data, uint64_t size, zio_done_func_t *done, void *private, ! int priority, enum zio_flag flags, const zbookmark_t *zb) { zio_t *zio; zio = zio_create(pio, spa, BP_PHYSICAL_BIRTH(bp), bp, data, size, done, private, --- 601,611 ---- } zio_t * zio_read(zio_t *pio, spa_t *spa, const blkptr_t *bp, void *data, uint64_t size, zio_done_func_t *done, void *private, ! zio_priority_t priority, enum zio_flag flags, const zbookmark_t *zb) { zio_t *zio; zio = zio_create(pio, spa, BP_PHYSICAL_BIRTH(bp), bp, data, size, done, private,
*** 634,645 **** } zio_t * zio_write(zio_t *pio, spa_t *spa, uint64_t txg, blkptr_t *bp, void *data, uint64_t size, const zio_prop_t *zp, ! zio_done_func_t *ready, zio_done_func_t *done, void *private, ! int priority, enum zio_flag flags, const zbookmark_t *zb) { zio_t *zio; ASSERT(zp->zp_checksum >= ZIO_CHECKSUM_OFF && zp->zp_checksum < ZIO_CHECKSUM_FUNCTIONS && --- 617,629 ---- } zio_t * zio_write(zio_t *pio, spa_t *spa, uint64_t txg, blkptr_t *bp, void *data, uint64_t size, const zio_prop_t *zp, ! zio_done_func_t *ready, zio_done_func_t *physdone, zio_done_func_t *done, ! void *private, ! zio_priority_t priority, enum zio_flag flags, const zbookmark_t *zb) { zio_t *zio; ASSERT(zp->zp_checksum >= ZIO_CHECKSUM_OFF && zp->zp_checksum < ZIO_CHECKSUM_FUNCTIONS &&
*** 654,672 **** ZIO_TYPE_WRITE, priority, flags, NULL, 0, zb, ZIO_STAGE_OPEN, (flags & ZIO_FLAG_DDT_CHILD) ? ZIO_DDT_CHILD_WRITE_PIPELINE : ZIO_WRITE_PIPELINE); zio->io_ready = ready; zio->io_prop = *zp; return (zio); } zio_t * zio_rewrite(zio_t *pio, spa_t *spa, uint64_t txg, blkptr_t *bp, void *data, ! uint64_t size, zio_done_func_t *done, void *private, int priority, ! enum zio_flag flags, zbookmark_t *zb) { zio_t *zio; zio = zio_create(pio, spa, txg, bp, data, size, done, private, ZIO_TYPE_WRITE, priority, flags, NULL, 0, zb, --- 638,657 ---- ZIO_TYPE_WRITE, priority, flags, NULL, 0, zb, ZIO_STAGE_OPEN, (flags & ZIO_FLAG_DDT_CHILD) ? ZIO_DDT_CHILD_WRITE_PIPELINE : ZIO_WRITE_PIPELINE); zio->io_ready = ready; + zio->io_physdone = physdone; zio->io_prop = *zp; return (zio); } zio_t * zio_rewrite(zio_t *pio, spa_t *spa, uint64_t txg, blkptr_t *bp, void *data, ! uint64_t size, zio_done_func_t *done, void *private, ! zio_priority_t priority, enum zio_flag flags, zbookmark_t *zb) { zio_t *zio; zio = zio_create(pio, spa, txg, bp, data, size, done, private, ZIO_TYPE_WRITE, priority, flags, NULL, 0, zb,
*** 738,748 **** */ if (BP_IS_GANG(bp) || BP_GET_DEDUP(bp)) stage |= ZIO_STAGE_ISSUE_ASYNC; zio = zio_create(pio, spa, txg, bp, NULL, BP_GET_PSIZE(bp), ! NULL, NULL, ZIO_TYPE_FREE, ZIO_PRIORITY_FREE, flags, NULL, 0, NULL, ZIO_STAGE_OPEN, stage); return (zio); } --- 723,733 ---- */ if (BP_IS_GANG(bp) || BP_GET_DEDUP(bp)) stage |= ZIO_STAGE_ISSUE_ASYNC; zio = zio_create(pio, spa, txg, bp, NULL, BP_GET_PSIZE(bp), ! NULL, NULL, ZIO_TYPE_FREE, ZIO_PRIORITY_NOW, flags, NULL, 0, NULL, ZIO_STAGE_OPEN, stage); return (zio); }
*** 776,811 **** return (zio); } zio_t * zio_ioctl(zio_t *pio, spa_t *spa, vdev_t *vd, int cmd, ! zio_done_func_t *done, void *private, int priority, enum zio_flag flags) { zio_t *zio; int c; if (vd->vdev_children == 0) { zio = zio_create(pio, spa, 0, NULL, NULL, 0, done, private, ! ZIO_TYPE_IOCTL, priority, flags, vd, 0, NULL, ZIO_STAGE_OPEN, ZIO_IOCTL_PIPELINE); zio->io_cmd = cmd; } else { zio = zio_null(pio, spa, NULL, NULL, NULL, flags); for (c = 0; c < vd->vdev_children; c++) zio_nowait(zio_ioctl(zio, spa, vd->vdev_child[c], cmd, ! done, private, priority, flags)); } return (zio); } zio_t * zio_read_phys(zio_t *pio, vdev_t *vd, uint64_t offset, uint64_t size, void *data, int checksum, zio_done_func_t *done, void *private, ! int priority, enum zio_flag flags, boolean_t labels) { zio_t *zio; ASSERT(vd->vdev_children == 0); ASSERT(!labels || offset + size <= VDEV_LABEL_START_SIZE || --- 761,796 ---- return (zio); } zio_t * zio_ioctl(zio_t *pio, spa_t *spa, vdev_t *vd, int cmd, ! zio_done_func_t *done, void *private, enum zio_flag flags) { zio_t *zio; int c; if (vd->vdev_children == 0) { zio = zio_create(pio, spa, 0, NULL, NULL, 0, done, private, ! ZIO_TYPE_IOCTL, ZIO_PRIORITY_NOW, flags, vd, 0, NULL, ZIO_STAGE_OPEN, ZIO_IOCTL_PIPELINE); zio->io_cmd = cmd; } else { zio = zio_null(pio, spa, NULL, NULL, NULL, flags); for (c = 0; c < vd->vdev_children; c++) zio_nowait(zio_ioctl(zio, spa, vd->vdev_child[c], cmd, ! done, private, flags)); } return (zio); } zio_t * zio_read_phys(zio_t *pio, vdev_t *vd, uint64_t offset, uint64_t size, void *data, int checksum, zio_done_func_t *done, void *private, ! zio_priority_t priority, enum zio_flag flags, boolean_t labels) { zio_t *zio; ASSERT(vd->vdev_children == 0); ASSERT(!labels || offset + size <= VDEV_LABEL_START_SIZE ||
*** 822,832 **** } zio_t * zio_write_phys(zio_t *pio, vdev_t *vd, uint64_t offset, uint64_t size, void *data, int checksum, zio_done_func_t *done, void *private, ! int priority, enum zio_flag flags, boolean_t labels) { zio_t *zio; ASSERT(vd->vdev_children == 0); ASSERT(!labels || offset + size <= VDEV_LABEL_START_SIZE || --- 807,817 ---- } zio_t * zio_write_phys(zio_t *pio, vdev_t *vd, uint64_t offset, uint64_t size, void *data, int checksum, zio_done_func_t *done, void *private, ! zio_priority_t priority, enum zio_flag flags, boolean_t labels) { zio_t *zio; ASSERT(vd->vdev_children == 0); ASSERT(!labels || offset + size <= VDEV_LABEL_START_SIZE ||
*** 857,868 **** /* * Create a child I/O to do some work for us. */ zio_t * zio_vdev_child_io(zio_t *pio, blkptr_t *bp, vdev_t *vd, uint64_t offset, ! void *data, uint64_t size, int type, int priority, enum zio_flag flags, ! zio_done_func_t *done, void *private) { enum zio_stage pipeline = ZIO_VDEV_CHILD_PIPELINE; zio_t *zio; ASSERT(vd->vdev_parent == --- 842,853 ---- /* * Create a child I/O to do some work for us. */ zio_t * zio_vdev_child_io(zio_t *pio, blkptr_t *bp, vdev_t *vd, uint64_t offset, ! void *data, uint64_t size, int type, zio_priority_t priority, ! enum zio_flag flags, zio_done_func_t *done, void *private) { enum zio_stage pipeline = ZIO_VDEV_CHILD_PIPELINE; zio_t *zio; ASSERT(vd->vdev_parent ==
*** 893,917 **** zio = zio_create(pio, pio->io_spa, pio->io_txg, bp, data, size, done, private, type, priority, flags, vd, offset, &pio->io_bookmark, ZIO_STAGE_VDEV_IO_START >> 1, pipeline); return (zio); } zio_t * zio_vdev_delegated_io(vdev_t *vd, uint64_t offset, void *data, uint64_t size, ! int type, int priority, enum zio_flag flags, zio_done_func_t *done, void *private) { zio_t *zio; ASSERT(vd->vdev_ops->vdev_op_leaf); zio = zio_create(NULL, vd->vdev_spa, 0, NULL, data, size, done, private, type, priority, ! flags | ZIO_FLAG_CANFAIL | ZIO_FLAG_DONT_RETRY, vd, offset, NULL, ZIO_STAGE_VDEV_IO_START >> 1, ZIO_VDEV_CHILD_PIPELINE); return (zio); } --- 878,906 ---- zio = zio_create(pio, pio->io_spa, pio->io_txg, bp, data, size, done, private, type, priority, flags, vd, offset, &pio->io_bookmark, ZIO_STAGE_VDEV_IO_START >> 1, pipeline); + zio->io_physdone = pio->io_physdone; + if (vd->vdev_ops->vdev_op_leaf && zio->io_logical != NULL) + zio->io_logical->io_phys_children++; + return (zio); } zio_t * zio_vdev_delegated_io(vdev_t *vd, uint64_t offset, void *data, uint64_t size, ! int type, zio_priority_t priority, enum zio_flag flags, zio_done_func_t *done, void *private) { zio_t *zio; ASSERT(vd->vdev_ops->vdev_op_leaf); zio = zio_create(NULL, vd->vdev_spa, 0, NULL, data, size, done, private, type, priority, ! flags | ZIO_FLAG_CANFAIL | ZIO_FLAG_DONT_RETRY | ZIO_FLAG_DELEGATED, vd, offset, NULL, ZIO_STAGE_VDEV_IO_START >> 1, ZIO_VDEV_CHILD_PIPELINE); return (zio); }
*** 918,928 **** void zio_flush(zio_t *zio, vdev_t *vd) { zio_nowait(zio_ioctl(zio, zio->io_spa, vd, DKIOCFLUSHWRITECACHE, ! NULL, NULL, ZIO_PRIORITY_NOW, ZIO_FLAG_CANFAIL | ZIO_FLAG_DONT_PROPAGATE | ZIO_FLAG_DONT_RETRY)); } void zio_shrink(zio_t *zio, uint64_t size) --- 907,917 ---- void zio_flush(zio_t *zio, vdev_t *vd) { zio_nowait(zio_ioctl(zio, zio->io_spa, vd, DKIOCFLUSHWRITECACHE, ! NULL, NULL, ZIO_FLAG_CANFAIL | ZIO_FLAG_DONT_PROPAGATE | ZIO_FLAG_DONT_RETRY)); } void zio_shrink(zio_t *zio, uint64_t size)
*** 1819,1829 **** zp.zp_dedup_verify = B_FALSE; zp.zp_nopwrite = B_FALSE; zio_nowait(zio_write(zio, spa, txg, &gbh->zg_blkptr[g], (char *)pio->io_data + (pio->io_size - resid), lsize, &zp, ! zio_write_gang_member_ready, NULL, &gn->gn_child[g], pio->io_priority, ZIO_GANG_CHILD_FLAGS(pio), &pio->io_bookmark)); } /* --- 1808,1818 ---- zp.zp_dedup_verify = B_FALSE; zp.zp_nopwrite = B_FALSE; zio_nowait(zio_write(zio, spa, txg, &gbh->zg_blkptr[g], (char *)pio->io_data + (pio->io_size - resid), lsize, &zp, ! zio_write_gang_member_ready, NULL, NULL, &gn->gn_child[g], pio->io_priority, ZIO_GANG_CHILD_FLAGS(pio), &pio->io_bookmark)); } /*
*** 2196,2206 **** ddt_exit(ddt); return (ZIO_PIPELINE_CONTINUE); } dio = zio_write(zio, spa, txg, bp, zio->io_orig_data, ! zio->io_orig_size, &czp, NULL, zio_ddt_ditto_write_done, dde, zio->io_priority, ZIO_DDT_CHILD_FLAGS(zio), &zio->io_bookmark); zio_push_transform(dio, zio->io_data, zio->io_size, 0, NULL); dde->dde_lead_zio[DDT_PHYS_DITTO] = dio; --- 2185,2195 ---- ddt_exit(ddt); return (ZIO_PIPELINE_CONTINUE); } dio = zio_write(zio, spa, txg, bp, zio->io_orig_data, ! zio->io_orig_size, &czp, NULL, NULL, zio_ddt_ditto_write_done, dde, zio->io_priority, ZIO_DDT_CHILD_FLAGS(zio), &zio->io_bookmark); zio_push_transform(dio, zio->io_data, zio->io_size, 0, NULL); dde->dde_lead_zio[DDT_PHYS_DITTO] = dio;
*** 2218,2228 **** ASSERT(BP_EQUAL(bp, zio->io_bp_override)); ddt_phys_fill(ddp, bp); ddt_phys_addref(ddp); } else { cio = zio_write(zio, spa, txg, bp, zio->io_orig_data, ! zio->io_orig_size, zp, zio_ddt_child_write_ready, zio_ddt_child_write_done, dde, zio->io_priority, ZIO_DDT_CHILD_FLAGS(zio), &zio->io_bookmark); zio_push_transform(cio, zio->io_data, zio->io_size, 0, NULL); dde->dde_lead_zio[p] = cio; --- 2207,2217 ---- ASSERT(BP_EQUAL(bp, zio->io_bp_override)); ddt_phys_fill(ddp, bp); ddt_phys_addref(ddp); } else { cio = zio_write(zio, spa, txg, bp, zio->io_orig_data, ! zio->io_orig_size, zp, zio_ddt_child_write_ready, NULL, zio_ddt_child_write_done, dde, zio->io_priority, ZIO_DDT_CHILD_FLAGS(zio), &zio->io_bookmark); zio_push_transform(cio, zio->io_data, zio->io_size, 0, NULL); dde->dde_lead_zio[p] = cio;
*** 2635,2644 **** --- 2624,2640 ---- } if (zio->io_error) zio->io_pipeline = ZIO_INTERLOCK_PIPELINE; + if (vd != NULL && vd->vdev_ops->vdev_op_leaf && + zio->io_physdone != NULL) { + ASSERT(!(zio->io_flags & ZIO_FLAG_DELEGATED)); + ASSERT(zio->io_child_type == ZIO_CHILD_VDEV); + zio->io_physdone(zio->io_logical); + } + return (ZIO_PIPELINE_CONTINUE); } void zio_vdev_io_reissue(zio_t *zio)