ceremonyclient/pebble/testdata/iter_histories/prefix_iteration

# Regression test for a bug discovered in #1878.
# A lazy-combined iterator triggers combined iteration during an initial
# seek-prefix-ge call. The initial seek-prefix-ge call avoids defragmenting
# fragments beyond the initial fragment [c,f). A subsequent seek-ge that seeks
# within the bounds of the initial fragment [c,f) must not fall into the
# optimization that reuses the span without reseeking the keypsan iterator,
# because the span is not defragmented.
#
# In the bug surfaced by #1878, the initial seek-prefix-ge that switched to
# combined iteration failed to record that the iterator was now in prefix mode,
# allowing the subsequent seek-ge to incorrectly reuse the existing span.

reset
----

batch commit
range-key-set a c @5 foo
----
committed 1 keys

flush
----

batch commit
range-key-set c f @5 foo
----
committed 1 keys

flush
----

batch commit
range-key-set f m @5 foo
----
committed 1 keys

flush
----

lsm
----
0.0:
  000005:[a#10,RANGEKEYSET-c#inf,RANGEKEYSET]
  000007:[c#11,RANGEKEYSET-f#inf,RANGEKEYSET]
  000009:[f#12,RANGEKEYSET-m#inf,RANGEKEYSET]

combined-iter
seek-prefix-ge d@5
seek-ge d
----
d@5: (., [d-"d\x00") @5=foo UPDATED)
d: (., [a-m) @5=foo UPDATED)

# Test that repeated SeekPrefixGEs correctly return truncated spans with
# RangeKeyChanged() -> UPDATED.

combined-iter
seek-prefix-ge c@5
seek-prefix-ge d@5
seek-ge d@7
seek-prefix-ge d@7
----
c@5: (., [c-"c\x00") @5=foo UPDATED)
d@5: (., [d-"d\x00") @5=foo UPDATED)
d@7: (., [a-m) @5=foo UPDATED)
d@7: (., [d-"d\x00") @5=foo UPDATED)

# Test a LSM with range keys fragmented within a prefix.
# This is a regression test for cockroachdb/cockroach#86102.

reset target-file-size=1
----

batch commit
range-key-set a c @1 bar
range-key-set c e @1 foo
set c@9 c@9
set c@8 c@8
set c@7 c@7
set c@6 c@6
set c@5 c@5
set c@4 c@4
set c@3 c@3
set c@2 c@2
set d@0 d@0
range-key-set y z @1 foo
set z z
----
committed 13 keys

flush
----

lsm
----
0.0:
  000005:[a#10,RANGEKEYSET-c@8#inf,RANGEKEYSET]
  000006:[c@8#13,SET-c@7#inf,RANGEKEYSET]
  000007:[c@7#14,SET-c@6#inf,RANGEKEYSET]
  000008:[c@6#15,SET-c@5#inf,RANGEKEYSET]
  000009:[c@5#16,SET-c@4#inf,RANGEKEYSET]
  000010:[c@4#17,SET-c@3#inf,RANGEKEYSET]
  000011:[c@3#18,SET-c@2#inf,RANGEKEYSET]
  000012:[c@2#19,SET-d@0#inf,RANGEKEYSET]
  000013:[d@0#20,SET-e#inf,RANGEKEYSET]
  000014:[y#21,RANGEKEYSET-z#22,SET]

# The first seek-prefix-ge y@1 converts the iterator from lazy combined iterator
# to combined iteration.
#
# The second seek-prefix-ge d@1 does not fully defragment the range key. The
# underlying range key is defragmented to [c@2,e). This incomplete
# defragmentation is still hidden from the user at this point, since the range
# key is truncated to [d,d\x00).
#
# The third seek-prefix-ge c@0 seeks to a key that falls within the
# range key currently defragmented on interleaving iterator. A previous bug
# would use this span without defragmenting the span to include the full
# span of the prefix [c,c\x00).

combined-iter
seek-prefix-ge y@1
seek-prefix-ge d@1
seek-prefix-ge c@0
----
y@1: (., [y-"y\x00") @1=foo UPDATED)
d@1: (., [d-"d\x00") @1=foo UPDATED)
c@0: (., [c-"c\x00") @1=foo UPDATED)

# Test a LSM with range keys fragmented within a prefix.
# This is a regression test for cockroachdb/cockroach#86102.

reset
----

ingest ext1
range-key-set a c@8 @1 bar
set c@9 c@9
----

ingest ext2
range-key-set c@8 e @1 bar
set c@8 c@8
set c@7 c@7
set c@6 c@6
set c@5 c@5
set c@4 c@4
set c@3 c@3
set c@2 c@2
----

ingest ext2
range-key-set y z @1 foo
set z z
----

lsm
----
6:
  000004:[a#10,RANGEKEYSET-c@8#inf,RANGEKEYSET]
  000005:[c@8#11,RANGEKEYSET-e#inf,RANGEKEYSET]
  000006:[y#12,RANGEKEYSET-z#12,SET]


# The first seek-prefix-ge y@1 converts the iterator from lazy combined iterator
# to combined iteration.
#
# The second seek-prefix-ge d@1 does not fully defragment the range key. The
# underlying range key is defragmented to [a,c@8). This incomplete
# defragmentation is still hidden from the user at this point, since the range
# key is truncated to [a,a\x00).
#
# The third seek-prefix-ge c@10 seeks to a key that falls within the
# range key currently defragmented on interleaving iterator. A previous bug
# would use this span without defragmenting the span to include the full
# span of the prefix [c,c\x00).

combined-iter
seek-prefix-ge y@1
seek-prefix-ge a@1
seek-prefix-ge c@10
----
y@1: (., [y-"y\x00") @1=foo UPDATED)
a@1: (., [a-"a\x00") @1=bar UPDATED)
c@10: (., [c-"c\x00") @1=bar UPDATED)

# Regression test for an invariant violation in the range key defragmenting
# iterator during prefix iteration. [Related to #1893]. There is a lot of
# subtlety here. Do not modify this test case without verifying that it still
# exercises the right conditions.
#
# Normally during forward iteration, if a switch to lazy-combined iteration is
# triggered, the lazy-combined iterator establishes a seek key for the range key
# iterator such that the seek key is:
#   1. greater than or equal to the key at previous iterator position.
#   2. less than or equal to the first range key with a start key greater than
#       or equal to the previous iterator position.
# These invariants are important so that the range key iterator is positioned
# appropriately after the switch to combined iteration and no range keys are
# missed.
#
# Parts of the iterator stack depend on the above invariants. For example,
# during forward iteration the BoundedIter only checks span start keys against
# iterator bounds and the configured prefix, with the expectation that the seek
# is always already greater than or equal to the lower bound. In turn, the
# DefragmentingIter indirectly relies on the same invariant, because it requires
# a consistent view of the fragments. If the BoundedIter returns a span in one
# direction, but skips it when iterating back, the defragmenting iterator will
# end up on a different fragment.
#
# This test exercises a case in which previously, during prefix iteration, it
# was possible for the switch to lazy-combined iteration to trigger using a seek
# key k, such that there exist range key fragments between the current iterator
# position and k (violating the 2nd invariant up above).
#
# The sequence of events is:
#   1. SeekPrefixGE("b@9") = 'b@4':
#      a. This seek positions the two levels, L0 and L6. The L0 iterator seeks
#         to file 000006. This file does not contain any keys with the prefix
#         "b", and the bloom filter must succeed in excluding the file. Since the
#         file contains a range deletion, SeekPrefixGE returns the level's
#         largest point key (`d#inf,RANGEDEL`) to ensure the file stays open until
#         the iterator advances past the range deletion.
#      b. In L6, the level iterator seeks to 000004 which contains a key with
#         the prefix, returning 'b@4'.
#   2. Next():
#      a. Next advances the the L6 iterator to file 000005. This file contains a
#         range key [e,f)@1=bar, which updates the lazy-combined iterator's
#         state, recording the earliest observed range key as 'e'. The L6 level
#         iterator then returns the file single point key 'c'.
#      b. The merging iterator checks whether point key 'c' is deleted by any
#         range key deletions. It is. It's deleted by L0's [c,d) range deletion.
#         The merging iterator then seeks the iterator to the tombstone's end
#         key 'd'.
#      c. After seeking, the range deletion sentinel d is at the top of the
#         heap. At this point, the merging iterator checks whether the keyspace
#         of the prefix has been exceeded, and it has. It returns nil.
#   3. Switch to combined iteration:
#      a. The Next has completed and triggered combined iteration. The only file
#         containing range keys that was observed was 000005, containing the
#         range key [e,f). The switch to combined iteration seeks the keyspan
#         iterator to 'e'. Note that the iterator never observed L0's [d,e)
#         range key that precedes [e,f) in the keyspace.
#      b. Seeking the keyspan iterator calls DefragmentingIter.SeekLT('e'),
#         which lands on the [d,e) fragment. This fragment does NOT check to see
#         if the span starts at a prefix greater than the current prefix 'b',
#         because only bounds in the direction of iteration are check.
#      c. The DefragmentingIter observes disappearing range key fragments when
#         it switches directions, as a result of (b).
#

# Use 100-bits per key to ensure the bloom filter provides total recall.
reset bloom-bits-per-key=100
----

# Ingest L6 files:
#
# 000004: b@4
# 000005: c, [e,f)@1=bar

ingest ext1
set b@4 b@4
----

ingest ext1
set c c
range-key-set e f @1 bar
----

# Ingest L0 files:
#
# 000006: a, del-range(c, d)
# 000007: [d,e)@1=bar

ingest ext2
set a a
del-range c d
----

ingest ext3
range-key-set d e @1 bar
----

lsm
----
0.0:
  000006:[a#12,SET-d#inf,RANGEDEL]
  000007:[d#13,RANGEKEYSET-e#inf,RANGEKEYSET]
6:
  000004:[b@4#10,SET-b@4#10,SET]
  000005:[c#11,SET-f#inf,RANGEKEYSET]

combined-iter
seek-prefix-ge b@9
next
----
b@4: (b@4, .)
.

# Regression test for #2151.
#
# This test consists of two SeekPrefixGEs for ascending keys, which results in
# TrySeekUsingNext()=true for the second seek. The entirety of both seeked
# prefixes is deleted by the range deletion [b-d). The iterator being used is
# created from a snapshot at sequence number #4. At that sequence number, the
# iterator observes the range deletion and all of L6's point keys, but none of
# the point keys in L5.
#
# Previously, a bug existed where the SeekPrefixGE("b@9") would cause the
# iterator to next beyond the L5 sstable. The subsequent SeekPrefixGE with
# TrySeekUsingNext would mistakenly miss the range deletion [b-d) because it had
# already proceeded beyond the file.

define snapshots=(4)
L5
  b.RANGEDEL.3:d
  b@9.SET.9:v
  c@9.SET.9:v
  d@9.SET.9:v
L6
  b@2.SET.2:v
  c@2.SET.2:v
  d@2.SET.2:v
----
5:
  000004:[b#3,RANGEDEL-d@9#9,SET]
6:
  000005:[b@2#2,SET-d@2#2,SET]

combined-iter snapshot=4
seek-prefix-ge b@9
seek-prefix-ge c@9
----
.
.