From a1d477c24c7badc89c60955995fd84d311938486 Mon Sep 17 00:00:00 2001 From: Matthew Ahrens Date: Thu, 22 Sep 2016 09:30:13 -0700 Subject: OpenZFS 7614, 9064 - zfs device evacuation/removal OpenZFS 7614 - zfs device evacuation/removal OpenZFS 9064 - remove_mirror should wait for device removal to complete This project allows top-level vdevs to be removed from the storage pool with "zpool remove", reducing the total amount of storage in the pool. This operation copies all allocated regions of the device to be removed onto other devices, recording the mapping from old to new location. After the removal is complete, read and free operations to the removed (now "indirect") vdev must be remapped and performed at the new location on disk. The indirect mapping table is kept in memory whenever the pool is loaded, so there is minimal performance overhead when doing operations on the indirect vdev. The size of the in-memory mapping table will be reduced when its entries become "obsolete" because they are no longer used by any block pointers in the pool. An entry becomes obsolete when all the blocks that use it are freed. An entry can also become obsolete when all the snapshots that reference it are deleted, and the block pointers that reference it have been "remapped" in all filesystems/zvols (and clones). Whenever an indirect block is written, all the block pointers in it will be "remapped" to their new (concrete) locations if possible. This process can be accelerated by using the "zfs remap" command to proactively rewrite all indirect blocks that reference indirect (removed) vdevs. Note that when a device is removed, we do not verify the checksum of the data that is copied. This makes the process much faster, but if it were used on redundant vdevs (i.e. mirror or raidz vdevs), it would be possible to copy the wrong data, when we have the correct data on e.g. the other side of the mirror. At the moment, only mirrors and simple top-level vdevs can be removed and no removal is allowed if any of the top-level vdevs are raidz. Porting Notes: * Avoid zero-sized kmem_alloc() in vdev_compact_children(). The device evacuation code adds a dependency that vdev_compact_children() be able to properly empty the vdev_child array by setting it to NULL and zeroing vdev_children. Under Linux, kmem_alloc() and related functions return a sentinel pointer rather than NULL for zero-sized allocations. * Remove comment regarding "mpt" driver where zfs_remove_max_segment is initialized to SPA_MAXBLOCKSIZE. Change zfs_condense_indirect_commit_entry_delay_ticks to zfs_condense_indirect_commit_entry_delay_ms for consistency with most other tunables in which delays are specified in ms. * ZTS changes: Use set_tunable rather than mdb Use zpool sync as appropriate Use sync_pool instead of sync Kill jobs during test_removal_with_operation to allow unmount/export Don't add non-disk names such as "mirror" or "raidz" to $DISKS Use $TEST_BASE_DIR instead of /tmp Increase HZ from 100 to 1000 which is more common on Linux removal_multiple_indirection.ksh Reduce iterations in order to not time out on the code coverage builders. removal_resume_export: Functionally, the test case is correct but there exists a race where the kernel thread hasn't been fully started yet and is not visible. Wait for up to 1 second for the removal thread to be started before giving up on it. Also, increase the amount of data copied in order that the removal not finish before the export has a chance to fail. * MMP compatibility, the concept of concrete versus non-concrete devices has slightly changed the semantics of vdev_writeable(). Update mmp_random_leaf_impl() accordingly. * Updated dbuf_remap() to handle the org.zfsonlinux:large_dnode pool feature which is not supported by OpenZFS. * Added support for new vdev removal tracepoints. * Test cases removal_with_zdb and removal_condense_export have been intentionally disabled. When run manually they pass as intended, but when running in the automated test environment they produce unreliable results on the latest Fedora release. They may work better once the upstream pool import refectoring is merged into ZoL at which point they will be re-enabled. Authored by: Matthew Ahrens Reviewed-by: Alex Reece Reviewed-by: George Wilson Reviewed-by: John Kennedy Reviewed-by: Prakash Surya Reviewed by: Richard Laager Reviewed by: Tim Chase Reviewed by: Brian Behlendorf Approved by: Garrett D'Amore Ported-by: Tim Chase Signed-off-by: Tim Chase OpenZFS-issue: https://www.illumos.org/issues/7614 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/f539f1eb Closes #6900 --- module/zfs/range_tree.c | 41 +++++++---------------------------------- 1 file changed, 7 insertions(+), 34 deletions(-) (limited to 'module/zfs/range_tree.c') diff --git a/module/zfs/range_tree.c b/module/zfs/range_tree.c index 01ef463ec..baa655d39 100644 --- a/module/zfs/range_tree.c +++ b/module/zfs/range_tree.c @@ -23,7 +23,7 @@ * Use is subject to license terms. */ /* - * Copyright (c) 2013, 2014 by Delphix. All rights reserved. + * Copyright (c) 2013, 2015 by Delphix. All rights reserved. */ #include @@ -125,18 +125,6 @@ range_tree_stat_verify(range_tree_t *rt) } } -/* - * Changes out the lock used by the range tree. Useful when you are moving - * the range tree between containing structures without having to recreate - * it. Both the old and new locks must be held by the caller. - */ -void -range_tree_set_lock(range_tree_t *rt, kmutex_t *lp) -{ - ASSERT(MUTEX_HELD(rt->rt_lock) && MUTEX_HELD(lp)); - rt->rt_lock = lp; -} - static void range_tree_stat_incr(range_tree_t *rt, range_seg_t *rs) { @@ -147,7 +135,6 @@ range_tree_stat_incr(range_tree_t *rt, range_seg_t *rs) ASSERT3U(idx, <, sizeof (rt->rt_histogram) / sizeof (*rt->rt_histogram)); - ASSERT(MUTEX_HELD(rt->rt_lock)); rt->rt_histogram[idx]++; ASSERT3U(rt->rt_histogram[idx], !=, 0); } @@ -162,7 +149,6 @@ range_tree_stat_decr(range_tree_t *rt, range_seg_t *rs) ASSERT3U(idx, <, sizeof (rt->rt_histogram) / sizeof (*rt->rt_histogram)); - ASSERT(MUTEX_HELD(rt->rt_lock)); ASSERT3U(rt->rt_histogram[idx], !=, 0); rt->rt_histogram[idx]--; } @@ -184,14 +170,13 @@ range_tree_seg_compare(const void *x1, const void *x2) range_tree_t * range_tree_create_impl(range_tree_ops_t *ops, void *arg, - int (*avl_compare) (const void *, const void *), kmutex_t *lp, uint64_t gap) + int (*avl_compare) (const void *, const void *), uint64_t gap) { range_tree_t *rt = kmem_zalloc(sizeof (range_tree_t), KM_SLEEP); avl_create(&rt->rt_root, range_tree_seg_compare, sizeof (range_seg_t), offsetof(range_seg_t, rs_node)); - rt->rt_lock = lp; rt->rt_ops = ops; rt->rt_gap = gap; rt->rt_arg = arg; @@ -204,9 +189,9 @@ range_tree_create_impl(range_tree_ops_t *ops, void *arg, } range_tree_t * -range_tree_create(range_tree_ops_t *ops, void *arg, kmutex_t *lp) +range_tree_create(range_tree_ops_t *ops, void *arg) { - return (range_tree_create_impl(ops, arg, NULL, lp, 0)); + return (range_tree_create_impl(ops, arg, NULL, 0)); } void @@ -224,8 +209,6 @@ range_tree_destroy(range_tree_t *rt) void range_tree_adjust_fill(range_tree_t *rt, range_seg_t *rs, int64_t delta) { - ASSERT(MUTEX_HELD(rt->rt_lock)); - ASSERT3U(rs->rs_fill + delta, !=, 0); ASSERT3U(rs->rs_fill + delta, <=, rs->rs_end - rs->rs_start); @@ -246,7 +229,6 @@ range_tree_add_impl(void *arg, uint64_t start, uint64_t size, uint64_t fill) uint64_t bridge_size = 0; boolean_t merge_before, merge_after; - ASSERT(MUTEX_HELD(rt->rt_lock)); ASSERT3U(size, !=, 0); ASSERT3U(fill, <=, size); @@ -383,7 +365,6 @@ range_tree_remove_impl(range_tree_t *rt, uint64_t start, uint64_t size, uint64_t end = start + size; boolean_t left_over, right_over; - ASSERT(MUTEX_HELD(rt->rt_lock)); VERIFY3U(size, !=, 0); VERIFY3U(size, <=, rt->rt_space); @@ -493,8 +474,6 @@ range_tree_resize_segment(range_tree_t *rt, range_seg_t *rs, { int64_t delta = newsize - (rs->rs_end - rs->rs_start); - ASSERT(MUTEX_HELD(rt->rt_lock)); - range_tree_stat_decr(rt, rs); if (rt->rt_ops != NULL && rt->rt_ops->rtop_remove != NULL) rt->rt_ops->rtop_remove(rt, rs, rt->rt_arg); @@ -516,7 +495,6 @@ range_tree_find_impl(range_tree_t *rt, uint64_t start, uint64_t size) range_seg_t rsearch; uint64_t end = start + size; - ASSERT(MUTEX_HELD(rt->rt_lock)); VERIFY(size != 0); rsearch.rs_start = start; @@ -538,11 +516,9 @@ range_tree_verify(range_tree_t *rt, uint64_t off, uint64_t size) { range_seg_t *rs; - mutex_enter(rt->rt_lock); rs = range_tree_find(rt, off, size); if (rs != NULL) panic("freeing free block; rs=%p", (void *)rs); - mutex_exit(rt->rt_lock); } boolean_t @@ -560,6 +536,9 @@ range_tree_clear(range_tree_t *rt, uint64_t start, uint64_t size) { range_seg_t *rs; + if (size == 0) + return; + while ((rs = range_tree_find_impl(rt, start, size)) != NULL) { uint64_t free_start = MAX(rs->rs_start, start); uint64_t free_end = MIN(rs->rs_end, start + size); @@ -572,7 +551,6 @@ range_tree_swap(range_tree_t **rtsrc, range_tree_t **rtdst) { range_tree_t *rt; - ASSERT(MUTEX_HELD((*rtsrc)->rt_lock)); ASSERT0(range_tree_space(*rtdst)); ASSERT0(avl_numnodes(&(*rtdst)->rt_root)); @@ -587,8 +565,6 @@ range_tree_vacate(range_tree_t *rt, range_tree_func_t *func, void *arg) range_seg_t *rs; void *cookie = NULL; - ASSERT(MUTEX_HELD(rt->rt_lock)); - if (rt->rt_ops != NULL && rt->rt_ops->rtop_vacate != NULL) rt->rt_ops->rtop_vacate(rt, rt->rt_arg); @@ -607,8 +583,6 @@ range_tree_walk(range_tree_t *rt, range_tree_func_t *func, void *arg) { range_seg_t *rs; - ASSERT(MUTEX_HELD(rt->rt_lock)); - for (rs = avl_first(&rt->rt_root); rs; rs = AVL_NEXT(&rt->rt_root, rs)) func(arg, rs->rs_start, rs->rs_end - rs->rs_start); } @@ -616,7 +590,6 @@ range_tree_walk(range_tree_t *rt, range_tree_func_t *func, void *arg) range_seg_t * range_tree_first(range_tree_t *rt) { - ASSERT(MUTEX_HELD(rt->rt_lock)); return (avl_first(&rt->rt_root)); } -- cgit v1.2.3