* tag 'tgrabiec/row-cache-metrics-v2' of github.com:cloudius-systems/seastar-dev:
row_cache: Switch _stats.hits/misses to row granularity
row_cache: Rename num_entries() to partitions() for clarity
row_cache: Track mispopulations also at row level
row_cache: Track row insertions
row_cache: Track row hits and misses
row_cache: Make mispopulation counter also apply for continuity information
row_cache: Add partition_ prefix to current counters
misc_services: Switch to using reads_with[_no]_misses counters
row_cache: Add metrics for operations on underlying reader
row_cache: Add reader-related metrics
row_cache: Remove dead code
(cherry picked from commit b1a0e37fcb)
"This series introduces selective_token_range_sharder and uses it in repair to
generate dht::token_range belongs to a specific shard."
* tag 'asias/repair-selective_token_range_sharder-v3' of github.com:cloudius-systems/seastar-dev:
repair: Use selective_token_range_sharder
tests: Add test_selective_token_range_sharder
dht: Add selective_token_range_sharder
(cherry picked from commit 66e56511d6)
The test put a wrapping range into a non-wrapping range variable.
This was harmless at the time this test was written, but newer code
may not be as forgiving so better use a non-wrapping range as intended.
Signed-off-by: Nadav Har'El <nyh@scylladb.com>
Message-Id: <20170704103128.29689-1-nyh@scylladb.com>
(cherry picked from commit d95f908586)
"This series enables cache to keep partial partitions.
Reads no longer have to read whole partition from sstables
in order to cache the result.
The 10MB threshold for partition size in cache is lifted.
Known issues:
- There is no partial eviction yet, whole partitions are still evicted,
and partition snapshots held by active reads are not evictable at all
- Information about range continuity is not recorded if that
would require inserting a dummy entry, or if previous entry
doesn't belong to the latest snapshot
- Cache update after memtable flush happening concurrently with reads
may inhibit that reads' ability to populate cache (new issue)
- Cache update from flushed memtables has partition granularity,
so may cause latency problems with large partition
- Schema is still tracked per-partition, so after schema changes
reads may induce high latency due to whole partition needing
to be converted atomically
- Range tombstones are repeated in the stream for every range between
cache entries they cover (new issue)
- Populating scans for both small and large partitions (perf_fast_forward)
experienced a 40% reduction of throughput, CPU bound
How was this tested:
- test.py --mode release
- row_cache_stress_test -c1 -m1G
- perf_fast_forward, passes except for the test case checking range continuity population
which would require inserting a dummy entry (mentioned above)
- perf_simple_query (-c1 -m1G --duration 32):
before: 90k [ops/s] stdev: 4k [ops/s]
after: 94k [ops/s] stdev: 2k [ops/s]"
* tag 'tgrabiec/introduce-partial-cache-v8' of github.com:cloudius-systems/seastar-dev: (130 commits)
tests: row_cache: Add test_tombstone_merging_in_partial_partition test case
tests: Introduce row_cache_stress_test
utils: Add helpers for dealing with nonwrapping_range<int>
tests: simple_schema: Allow passing the tombstone to make_range_tombstone()
tests: simple_schema: Accept value by reference
tests: simple_schema: Make add_row() accept optional timestamp
tests: simple_schema: Make new_timestamp() public
tests: simple_schema: Introduce make_ckeys()
tests: simple_schema: Introduce get_value(const clustered_row&) helper
tests: simple_schema: Fix comment
tests: simple_schema: Add missing include
row_cache: Introduce evict()
tests: Add cache_streamed_mutation_test
tests: mutation_assertions: Allow expecting fragments
mutation_fragment: Implement equality check
tests: row_cache: Add test for population of random partitions
tests: row_cache: Add test for partition tombstone population
tests: row_cache: Test reading randomly populated partition
tests: row_cache: Add test_single_partition_update()
tests: row_cache: Add test_scan_with_partial_partitions
...
Runs readers, updates and eviction concurrently and verifies the
following property of reads:
- reads see all past writes
- reads see no partial writes within a single partition
[tgrabiec:
- extracted from a larger commit
- removed coupling with how cache_streamed_mutation is created (the
code went out of sync), used more stable make_reader(). it's simpler too.
- replaced false/true literals with is_continuous/is_dummy where appropraite
- dropped tests for cache::underlying (class is gone)
- reused streamed_mutation_assertions, it has better error messages
- fixed the tests to not create tombstones with missing timestamps
- relaxed range tombstone assertions to only check information relevant for the query range
- print cache on failure for improved debuggability
]
Currently readers are always using the latest snapshot. This is fine
for respecting write atomicity if partitions are fully continuous in
cache (now), but will break write atomicity once partial population is
allowed.
Consider the following case:
flush write(ck=1), write(ck=2) -> snapshot_1
cache reader 1 reads and inserts ck=1 @snapshot_1
flush write(ck=1), write(ck=2) -> snapshot_2
cache reader 2 reads and inserts ck=2 @snapshot_2
Because cache update is not atomic, it can happen that reader 2 will
complete while the partition hasn't been updated yet for snapshot_2.
In such case, after read 2 the partition would contain ck=1 from
snapshot_1 and ck=2 from snapshot_2. It will match neither of the
snapshots, and this could violate write atomicity.
To solve this problem we conceptually assign each partition key in the
ring to its current snapshot which it reflects. The update process
gradually converts entries in ring order to the new snapshot. Reads
will not be using the latest snapshot, but rather the current snapshot
for the position in the ring they are at.
There is a race between the update process and populating reads. Since
after the update all entries must reflect the new snapshot, reads
using the old snapshot cannot be allowed to insert data which can no
longer be reached by the update process. Before this patch this race
was prevented by the use of a phased_barrier, where readers would keep
phased_barrier::operation alive between starting a read of a partition
and inserting it into cache. Cache update was waiting for all prior
operations before starting the update. Any later read which was not
waited for would use the latest snapshot for reads, so the update
process didn't have to fix anything up for such reads.
After this change, later reads cannot always use the latest snapshot,
they have to use the snapshot corresponding to given entry. So it's
not enough for update() to wait for prior reads in order to prevent
stale populations. The (simple) solution implemented in this patch is
to detect the conflict and abandon population of given sub-range. In
general, reads are allowed to populate given range only if it belongs
to a single snapshot.
Note that the range here is not the whole query range. For population
of continuity, it is the range starting after the previous key and
ending after the key being inserted. When populating a partition
entry, the range is a singular range containing only the partition
key. Readers switch to new snapshots automatically as they move across
the ring. It's possible that the insertion of the partition doesn't
conflict, but continuity does. In such case the entry will be inserted
but continuity will not be set.
Currently every time cache needs to create reader for missing data it
obtains a reader which is most up to date. That reader includes writes
from later populate phases, for which update() was not yet
called. This will be problematic once we allow partitions to be
partially populated, because different parts of the partition could be
partially populated using readers using different sets of writes, and break
write atomicity.
The solution will be to always populate given partition using the same
set of writes, using reader created from the current snapshot. The
snapshot changes only on update(), with update() gradually converting
each partition to the new snapshot.
1) Reduce duplication by delegating to more general overloads
2) Improve documentation to not mention effects in terms of
population (detail) but rather write visibiliy
3) Rename clear() to invalidate() and merge with the range variant,
it has the same semantics
Currently mutation sources are free to return range tombstones
covering range which is larger than the query range. The cache
mutation source will soon become more eager about trimming such
tombstones. To cover up for such differences, allow telling the
restrictions to only care about differences relevant for given
clustering ranges.
mutation source sometimes ignore fast forwarding parameter so
this change adds assertion to check that this parameter
can be safely ignored.
Signed-off-by: Piotr Jastrzebski <piotr@scylladb.com>
This will allow expressing lack of information about certain ranges of
rows (including the static row), which will be used in cache to
determine if information in cache is complete or not.
Continuity is represented internally using flags on row entries. The
key range between two consecutive entries is continuous iff
rows_entry::continuous() is true for the later entry. The range
starting after the last entry is assumed to be continuous. The range
corresponding to the key of the entry is continuous iff
rows_entry::dummy() is false.
[tgrabiec:
- based on the following commits:
4a5bf75 - Piotr Jastrzebski : mutation_partition: introduce dummy rows_entry
773070e - Piotr Jastrzebski : mutation_partition: add continuity flag to rows_entry
- documented that partition tombstone is always complete
- require specifying the partition tombstone when creating an incomplete entry
- replaced rows_entry(dummy_tag, ...) constructor with more general
rows_entry(position_in_partition, ...)
- documented continuity semantics on mutation_partition
- fixed _static_row_cached being lost by mutation_partition copy constructors
- fixed conversion to streamed_mutation to ignore dummy entries
- fixed mutation_partition serializer to drop dummy entries
- documented semantics of continuity on mutation_partition level
- dropped assumptions that dummy entries can be only at the last position
- changed equality to ignore continuity completely, rather than
partially (it was not ignoring dummy entries, but ignoring
continuity flag)
- added printout of continuity information in mutation_partition
- fixed handling of empty entries in apply_reversibly() with regards
to continuity; we no longer can remove empty entries before
merging, since that may affect continuity of the right-hand
mutation. Added _erased flag.
- fixed mutation_partition::clustered_row() with dummy==true to not ignore the key
- fixed partition_builder to not ignore continuity
- renamed dummy_tag_t to dummy_tag. _t suffix is reserved.
- standardized all APIs on is_dummy and is_continuous bool_class:es
- replaced add_dummy_entry() with ensure_last_dummy() with safer semantics
- dropped unused remove_dummy_entry()
- simplified and inlined cache_entry::add_dummy_entry()
- fixed mutation_partition(incomplete_tag) constructor to mark all row ranges as discontinuous
]
It can happen that touch() will trigger eviction on entry to
allocating section, and drop in occupancy around insertion
will not happen. As a result, we may evict a lot without detecting that.
Extend the check to include touch() and use more reliable eviction counters.
Strategy prefers promoting oldest sstables in L0. Because sort
procedure is incorrectly sorting elements in descending order,
newest sstables will be promoted first *if and only if* L0 falls
behind (more than 32 sstables). If L0 doesn't fall behind, we'll
have all L0 sstables compacted with overlapping ones in L1.
Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
In commit c63e88d556, support was added for
fast_forward_to() in data_consume_rows(). Because an input stream's end
cannot be changed after creation, that patch ignores the specified end
byte, and uses the end of file as the end position of the stream.
As result of this, even when we want to read a specific byte range (e.g.,
in the repair code to checksum the partitions in a given range), the code
reads an entire 128K buffer around the end byte, or significantly more, with
read-ahead enabled. This causes repair to do more than 10 times the amount
of I/O it really has to do in the checksumming phase (which in the current
implementation, reads small ranges of partitions at a time).
This patch has two levels:
1. In the lower level, sstable::data_consume_rows(), which reads all
partitions in a given disk byte range, now gets another byte position,
"last_end". That can be the range's end, the end of the file, or anything
in between the two. It opens the disk stream until last_end, which means
1. we will never read-ahead beyond last_end, and 2. fast_fordward_to() is
not allowed beyond last_end.
2. In the upper level, we add to the various layers of sstable readers,
mutation readers, etc., a boolean flag mutation_reader::forwarding, which
says whether fast_forward_to() is allowed on the stream of mutations to
move the stream to a different partition range.
Note that this flag is separate from the existing boolean flag
streamed_mutation::fowarding - that one talks about skipping inside a
single partition, while the flag we are adding is about switching the
partition range being read. Most of the functions that previously
accepted streamed_mutation::forwarding now accept *also* the option
mutation_reader::forwarding. The exception are functions which are known
to read only a single partition, and not support fast_forward_to() a
different partition range.
We note that if mutation_reader::forwarding::no is requested, and
fast_forward_to() is forbidden, there is no point in reading anything
beyond the range's end, so data_consume_rows() is called with last_end as
the range's end. But if forwarding::yes is requested, we use the end of the
file as last_end, exactly like the code before this patch did.
Importantly, we note that the repair's partition reading code,
column_family::make_streaming_reader, uses mutation_reader::forwarding::no,
while the other existing reading code will use the default forwarding::yes.
In the future, we can further optimize the amount of bytes read from disk
by replacing forwarding::yes by an actual last partition that may ever be
read, and use its byte position as the last_end passed to data_consume_rows.
But we don't do this yet, and it's not a regression from the existing code,
which also opened the file input stream until the end of the file, and not
until the end of the range query. Moreover, such an improvement will not
improve of anything if the overall range is always very large, in which
case not over-reading at its end will not improve performance.
Signed-off-by: Nadav Har'El <nyh@scylladb.com>
Message-Id: <20170619152629.11703-1-nyh@scylladb.com>
