diff options
author | Paul Dagnelie <[email protected]> | 2019-06-06 19:10:43 -0700 |
---|---|---|
committer | Brian Behlendorf <[email protected]> | 2019-06-06 19:10:43 -0700 |
commit | 893a6d62c1895f3e3eeb660b048236571995a564 (patch) | |
tree | 051154a79d6a6cc07ba4e93ed60a1b6a7f5b0763 /module/zfs/metaslab.c | |
parent | 876d76be3455ba6aa8d1567203847d8c012d05c9 (diff) |
Allow metaslab to be unloaded even when not freed from
On large systems, the memory used by loaded metaslabs can become
a concern. While range trees are a fairly efficient data structure,
on heavily fragmented pools they can still consume a significant
amount of memory. This problem is amplified when we fail to unload
metaslabs that we aren't using. Currently, we only unload a metaslab
during metaslab_sync_done; in order for that function to be called
on a given metaslab in a given txg, we have to have dirtied that
metaslab in that txg. If the dirtying was the result of an allocation,
we wouldn't be unloading it (since it wouldn't be 8 txgs since it
was selected), so in effect we only unload a metaslab during txgs
where it's being freed from.
We move the unload logic from sync_done to a new function, and
call that function on all metaslabs in a given vdev during
vdev_sync_done().
Reviewed-by: Richard Elling <[email protected]>
Reviewed-by: Brian Behlendorf <[email protected]>
Signed-off-by: Paul Dagnelie <[email protected]>
Closes #8837
Diffstat (limited to 'module/zfs/metaslab.c')
-rw-r--r-- | module/zfs/metaslab.c | 47 |
1 files changed, 25 insertions, 22 deletions
diff --git a/module/zfs/metaslab.c b/module/zfs/metaslab.c index d1d5a243f..41cbaad5f 100644 --- a/module/zfs/metaslab.c +++ b/module/zfs/metaslab.c @@ -20,7 +20,7 @@ */ /* * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved. - * Copyright (c) 2011, 2018 by Delphix. All rights reserved. + * Copyright (c) 2011, 2019 by Delphix. All rights reserved. * Copyright (c) 2013 by Saso Kiselkov. All rights reserved. * Copyright (c) 2017, Intel Corporation. */ @@ -2949,6 +2949,30 @@ metaslab_sync(metaslab_t *msp, uint64_t txg) dmu_tx_commit(tx); } +void +metaslab_potentially_unload(metaslab_t *msp, uint64_t txg) +{ + /* + * If the metaslab is loaded and we've not tried to load or allocate + * from it in 'metaslab_unload_delay' txgs, then unload it. + */ + if (msp->ms_loaded && + msp->ms_disabled == 0 && + msp->ms_selected_txg + metaslab_unload_delay < txg) { + for (int t = 1; t < TXG_CONCURRENT_STATES; t++) { + VERIFY0(range_tree_space( + msp->ms_allocating[(txg + t) & TXG_MASK])); + } + if (msp->ms_allocator != -1) { + metaslab_passivate(msp, msp->ms_weight & + ~METASLAB_ACTIVE_MASK); + } + + if (!metaslab_debug_unload) + metaslab_unload(msp); + } +} + /* * Called after a transaction group has completely synced to mark * all of the metaslab's free space as usable. @@ -3086,27 +3110,6 @@ metaslab_sync_done(metaslab_t *msp, uint64_t txg) */ metaslab_recalculate_weight_and_sort(msp); - /* - * If the metaslab is loaded and we've not tried to load or allocate - * from it in 'metaslab_unload_delay' txgs, then unload it. - */ - if (msp->ms_loaded && - msp->ms_disabled == 0 && - msp->ms_selected_txg + metaslab_unload_delay < txg) { - - for (int t = 1; t < TXG_CONCURRENT_STATES; t++) { - VERIFY0(range_tree_space( - msp->ms_allocating[(txg + t) & TXG_MASK])); - } - if (msp->ms_allocator != -1) { - metaslab_passivate(msp, msp->ms_weight & - ~METASLAB_ACTIVE_MASK); - } - - if (!metaslab_debug_unload) - metaslab_unload(msp); - } - ASSERT0(range_tree_space(msp->ms_allocating[txg & TXG_MASK])); ASSERT0(range_tree_space(msp->ms_freeing)); ASSERT0(range_tree_space(msp->ms_freed)); |