Static class_registries hinder librarification by requiring linking with
all object files (instead of a library from which objects are linked on
demand) and reduce readability by hiding dependencies and by their
horrible syntax. Hide them behind a non-static, non-template tracing
backend registry.
Message-Id: <20181229121000.7885-1-avi@scylladb.com>
distributed_loader is a sizeable fraction of database.cc, so moving it
out reduces compile time and improves readability.
Message-Id: <20181230200926.15074-1-avi@scylladb.com>
Implementation of nodetool toppartiotion query, which samples most frequest PKs in read/write
operation over a period of time.
Content:
- data_listener classes: mechanism that interfaces with mutation readers in database and table classes,
- toppartition_query and toppartition_data_listener classes to implement toppartition-specific query (this
interfaces with data_listeners and the REST api),
- REST api for toppartitions query.
Uses Top-k structure for handling stream summary statistics (based on implementation in C*, see #2811).
What's still missing:
- JMX interface to nodetool (interface customization may be required),
- Querying #rows and #bytes (currently, only #partitions is supported).
Fixes#2811
* https://github.com/avikivity/scylla rafie_toppartitions_v7.1:
top_k: whitespace and minor fixes
top_k: map template arguments
top_k: std::list -> chunked_vector
top_k: support for appending top_k results
nodetool toppartitions: refactor table::config constructor
nodetool toppartitions: data listeners
nodetool toppartitions: add data_listeners to database/table
nodetool toppartitions: fully_qualified_cf_name
nodetool toppartitions: Toppartitions query implementation
nodetool toppartitions: Toppartitions query REST API
nodetool toppartitions: nodetool-toppartitions script
Add data_listeners member to database.
Adds data_listeners* to table::config, to be used by table methods to invoke listeners.
Install on_read() listener in table::make_reader().
Install on_write() listener in database::apply_in_memory().
Tests: Unit (release)
Signed-off-by: Rafi Einstein <rafie@scylladb.com>
Mechanism that interfaces with mutation readers in database and table classes, to
allow tracking most frequent partition keys in read and write operation.
Basic design is specified in #2811.
Tracking top #rows and #bytes will be supported in the future.
Signed-off-by: Rafi Einstein <rafie@scylladb.com>
"
=== How the the partition level repair works
- The repair master decides which ranges to work on.
- The repair master splits the ranges to sub ranges which contains around 100
partitions.
- The repair master computes the checksum of the 100 partitions and asks the
related peers to compute the checksum of the 100 partitions.
- If the checksum matches, the data in this sub range is synced.
- If the checksum mismatches, repair master fetches the data from all the peers
and sends back the merged data to peers.
=== Major problems with partition level repair
- A mismatch of a single row in any of the 100 partitions causes 100
partitions to be transferred. A single partition can be very large. Not to
mention the size of 100 partitions.
- Checksum (find the mismatch) and streaming (fix the mismatch) will read the
same data twice
=== Row level repair
Row level checksum and synchronization: detect row level mismatch and transfer
only the mismatch
=== How the row level repair works
- To solve the problem of reading data twice
Read the data only once for both checksum and synchronization between nodes.
We work on a small range which contains only a few mega bytes of rows,
We read all the rows within the small range into memory. Find the
mismatch and send the mismatch rows between peers.
We need to find a sync boundary among the nodes which contains only N bytes of
rows.
- To solve the problem of sending unnecessary data.
We need to find the mismatched rows between nodes and only send the delta.
The problem is called set reconciliation problem which is a common problem in
distributed systems.
For example:
Node1 has set1 = {row1, row2, row3}
Node2 has set2 = { row2, row3}
Node3 has set3 = {row1, row2, row4}
To repair:
Node1 fetches nothing from Node2 (set2 - set1), fetches row4 (set3 - set1) from Node3.
Node1 sends row1 and row4 (set1 + set2 + set3 - set2) to Node2
Node1 sends row3 (set1 + set2 + set3 - set3) to Node3.
=== How to implement repair with set reconciliation
- Step A: Negotiate sync boundary
class repair_sync_boundary {
dht::decorated_key pk;
position_in_partition position
}
Reads rows from disk into row buffers until the size is larger than N
bytes. Return the repair_sync_boundary of the last mutation_fragment we
read from disk. The smallest repair_sync_boundary of all nodes is
set as the current_sync_boundary.
- Step B: Get missing rows from peer nodes so that repair master contains all the rows
Request combined hashes from all nodes between last_sync_boundary and
current_sync_boundary. If the combined hashes from all nodes are identical,
data is synced, goto Step A. If not, request the full hashes from peers.
At this point, the repair master knows exactly what rows are missing. Request the
missing rows from peer nodes.
Now, local node contains all the rows.
- Step C: Send missing rows to the peer nodes
Since local node also knows what peer nodes own, it sends the missing rows to
the peer nodes.
=== How the RPC API looks like
- repair_range_start()
Step A:
- request_sync_boundary()
Step B:
- request_combined_row_hashes()
- reqeust_full_row_hashes()
- request_row_diff()
Step C:
- send_row_diff()
- repair_range_stop()
=== Performance evaluation
We created a cluster of 3 Scylla nodes on AWS using i3.xlarge instance. We
created a keyspace with a replication factor of 3 and inserted 1 billion
rows to each of the 3 nodes. Each node has 241 GiB of data.
We tested 3 cases below.
1) 0% synced: one of the node has zero data. The other two nodes have 1 billion identical rows.
Time to repair:
old = 87 min
new = 70 min (rebuild took 50 minutes)
improvement = 19.54%
2) 100% synced: all of the 3 nodes have 1 billion identical rows.
Time to repair:
old = 43 min
new = 24 min
improvement = 44.18%
3) 99.9% synced: each node has 1 billion identical rows and 1 billion * 0.1% distinct rows.
Time to repair:
old: 211 min
new: 44 min
improvement: 79.15%
Bytes sent on wire for repair:
old: tx= 162 GiB, rx = 90 GiB
new: tx= 1.15 GiB, tx = 0.57 GiB
improvement: tx = 99.29%, rx = 99.36%
It is worth noting that row level repair sends and receives exactly the
number of rows needed in theory.
In this test case, repair master needs to receives 2 million rows and
sends 4 million rows. Here are the details: Each node has 1 billion *
0.1% distinct rows, that is 1 million rows. So repair master receives 1
million rows from repair slave 1 and 1 million rows from repair slave 2.
Repair master sends 1 million rows from repair master and 1 million rows
received from repair slave 1 to repair slave 2. Repair master sends
sends 1 million rows from repair master and 1 million rows received from
repair slave 2 to repair slave 1.
In the result, we saw the rows on wire were as expected.
tx_row_nr = 1000505 + 999619 + 1001257 + 998619 (4 shards, the numbers are for each shard) = 4'000'000
rx_row_nr = 500233 + 500235 + 499559 + 499973 (4 shards, the numbers are for each shard) = 2'000'000
Fixes: #3033
Tests: dtests/repair_additional_test.py
"
* 'asias/row_level_repair_v7' of github.com:cloudius-systems/seastar-dev: (51 commits)
repair: Enable row level repair
repair: Add row_level_repair
repair: Add docs for row level repair
repair: Add repair_init_messaging_service_handler
repair: Add repair_meta
repair: Add repair_writer
repair: Add repair_reader
repair: Add repair_row
repair: Add fragment_hasher
repair: Add decorated_key_with_hash
repair: Add get_random_seed
repair: Add get_common_diff_detect_algorithm
repair: Add shard_config
repair: Add suportted_diff_detect_algorithms
repair: Add repair_stats to repair_info
repair: Introduce repair_stats
flat_mutation_reader: Add make_generating_reader
storage_service: Introduce ROW_LEVEL_REPAIR feature
messaging_service: Add RPC verbs for row level repair
repair: Export the repair logger
...
Sometimes one wants to just compile all the source files in the
projects, because for example one just moved around code or files and
there is no need to link and run anything, just check that everything
still compiles.
Since linking takes up a considerable amount of time it is worthwhile to
have a specific target that caters for such needs.
This patch introduces a ${mode}-objects target for each mode (e.g.
release-objects) that only runs the compilation step for each source
file but does not link anything.
Signed-off-by: Botond Dénes <bdenes@scylladb.com>
Message-Id: <eaad329bf22dfaa3deff43344f3e65916e2c8aaf.1545045775.git.bdenes@scylladb.com>
Validate ascii string by ORing all bytes and check if 7-th bit is 0.
Compared with original std::any_of(), which checks ascii string byte
by byte, this new approach validates input in 8 bytes and two
independent streams. Performance is much higher for normal cases,
though slightly slower when string is very short. See table below.
Speed(MB/s) of ascii string validation
+---------------+-------------+---------+
| String length | std::any_of | u64 x 2 |
+---------------+-------------+---------+
| 9 bytes | 1691 | 1635 |
+---------------+-------------+---------+
| 31 bytes | 2923 | 3181 |
+---------------+-------------+---------+
| 129 bytes | 3377 | 15110 |
+---------------+-------------+---------+
| 1039 bytes | 3357 | 31815 |
+---------------+-------------+---------+
| 16385 bytes | 3448 | 47983 |
+---------------+-------------+---------+
| 1048576 bytes | 3394 | 31391 |
+---------------+-------------+---------+
Signed-off-by: Yibo Cai <yibo.cai@arm.com>
Message-Id: <1544669646-31881-1-git-send-email-yibo.cai@arm.com>
This moves all MC-related writing code to mc/writer.cc:
- m_format_write_helpers.hh is dropped
- m_format_write_helpers_impl.hh is dropped
- sstable_writer_m is moved out of sstables.cc
sstable_writer_m is renamed to sstables::mc::writer
"
This series contains several optimizations of the MC format sstable writer, mainly:
- Avoiding output_stream when serializing into memory (e.g. a row)
- Faster serialization of primitive types when serializing into memory
I measured the improvement in throughput (frag/s) using perf_fast_forward for
datasets with a single large partition with many small rows:
- 10% for a row with a single cell of 8 bytes
- 10% for a row with a single cell of 100 bytes
- 9% for a row with a single cell of 1000 bytes
- 13% for a row with 6 cells of 100 bytes
"
* tag 'avoid-output-stream-in-sstable-writer-v2' of github.com:tgrabiec/scylla:
bytes_ostream: Optimize writing of fixed-size types
sstables: mc: Write temporary data to bytes_ostream rather than file_writer
sstables: mc: Avoid double-serialization of a range tombstone marker
sstables: file_writer: Generalize bytes& writer to accept bytes_view
sstables: Templetize write() functions on the writer
sstables: Turn m_format_write_helpers.cc into an impl header
sstables: De-futurize file_writer
bytes_ostream: Implement clear()
bytes_ostream: Make initial chunk size configurable
I need to templatize functions defined in it and want to avoid
explicit instantiations.
There is only one compilation unit in which this is used
(sstables.cc). I think in the long term we should move all those
"helpers" into sstables/mc/writer.{cc,hh} together with their only
user, the sstable_writer_m class from sstables.cc.
"
This series optimises the read path by replacing some usages of
std::vector by utils::small_vector. The motivation for this change was
an observation that memory allocation functions are pointed out by the
profiler as the ones where we spent most time and while they have a
large number of callers storage allocation for some vectors was close to
the top. The gains are not huge, since the problem is a lot of things
adding up and not a single slow thing, but we need to start with
something.
Unfortunately, the performance of boost::container::small_vector is
quite disappointing so a new implementation of a small_vector was
introduced.
perf_simple_query -c4 --duration 60, medians:
./perf_before ./perf_after diff
read 343086.80 360720.53 5.1%
Tests: unit(release, small_vector in debug)
"
* tag 'small_vector/v2.1' of https://github.com/pdziepak/scylla:
partition_slice: use small_vector for column_ids
mutation_fragment_merger: use small_vector
auth: use small_vector in resource
auth: avoid list-initialisation of vectors
idl: serialiser: add serialiser for utils::small_vector
idl: serialiser: deduplicate vector serialisers
utils: introduce small_vector
intrusive_set_external_comparator: make iterator nothrow move constructible
mutation_fragment_merger: value-initialise iterator
small_vector is a variation of std::vector<> that reserves a configurable
amount of storage internally, without the need for memory allocation.
This can bring measurable gains if the expected number of elements is
small. The drawback is that moving such small_vector is more expensive
and invalidates iterators as well as references which disqualifies it in
some cases.
"
This series of patches ensures that all the Python code base is python3 compliant
and consistent by applying the following logic:
- python3 classifier on setup.py to explicitly state our python compatibility matrix
- add UTF-8 encoding header
- correct every shebang to the same /usr/bin/env python3
- shebang is only added on scripts meant to be executed on their own (removed otherwise)
- migrate some leftover scripts from python2 to python3 with minimal QA
This work is important to prepare for a more drastic change on Python code styling
using the black formatter and the setting up of automated QA checks on Python code base.
"
* 'python3_everywhere' of https://github.com/numberly/scylla:
scylla-housekeeping: fix python3 compat and shebang
dist/ami/files/scylla_install_ami: python3 shebang
dist/docker/redhat/docker-entrypoint.py: add encoding comment
fix_system_distributed_tables.py: fix python3 compat and shebang
gen_segmented_compress_params.py: add encoding comment
idl-compiler.py: python3 shebang
scylla-gdb.py: python3 shebang
configure.py: python3 shebang
tools/scyllatop/: add / normalize python3 shebang
scripts/: add / normalize python3 shebang
dist/common/scripts: add / normalize python3 shebang
test.py: add encoding comment
setup.py: add python3 classifiers
UTF-8 string is now validated by boost::locale::conv::utf_to_utf, it
actually does string conversions which is more than necessary. As
observed on Arm server, UTF-8 validation can become bottleneck under
heavy loads.
This patch introduces a brand new SIMD implementation supporting both
NEON and SSE, as well as a naive approach to handle short strings.
The naive approach is 3x faster than boost utf_to_utf, whilst SIMD
method outperforms naive approach 3x ~ 5x on Arm and x86. Details at
https://github.com/cyb70289/utf8/.
UTF-8 unit test is added to check various corner cases.
Signed-off-by: Yibo Cai <yibo.cai@arm.com>
Message-Id: <1543978498-12123-1-git-send-email-yibo.cai@arm.com>
Fixes a build failure when only the scylla binary was selected for
building like this:
./configure.py --with scylla
In this case the rule for gen_crc_combine_table was missing, but it is
needed to build crc_combine_table.o
Message-Id: <1544010138-21282-1-git-send-email-tgrabiec@scylladb.com>
"
This is a small step in fixing issue #2347. It is mostly tests and
testing infrastructure, but it does include a fix for a case where we
were missing the filename in the malformed_sstable_exception.
"
* 'espindola/sstable-corruption-v2' of https://github.com/espindola/scylla:
Add a filename to a malformed_sstable_exception.
Try to read the full sst in broken_sst.
Convert tests to SEASTAR_THREAD_TEST_CASE.
Check the exception message.
Move some tests to broken_sstable_test.cc
"
This series attempts to solve the regressions recently discovered in
performance of multi-partition range-scans. Namely that they:
* Flood the reader concurrency semaphore's queues, trampling other
reads.
* Behave very badly when too many of them is running concurrently
(trashing).
* May deadlock if enough of them is running without a timeout.
The solution for these problems is to make inactive shard readers
evictable. This should address all three issues listed above, to varying
degrees:
* Shard readers will now not cling onto their permits for the entire
duration of the scan, which might be a lot of time.
* Will be less affected by infinite concurrency (more than the node can
handle) as each scan now can make progress by evicting inactive shard
readers belonging to other scans.
* Will not deadlock at all.
In addition to the above fix, this series also bundles two further
improvements:
* Add a mechanism to `reader_concurrecy_semaphore` to be notified of
newly inserted evictables.
* General cleanups and fixes for `multishard_combining_reader` and
`foreign_reader`.
I can unbundle these mini series and send them separately, if the
maintainers so prefer, altough considering that this series will have to
be backported to 3.0, I think this present form is better.
Fixes: #3835
"
* 'evictable-inactive-shard-readers/v7' of https://github.com/denesb/scylla: (27 commits)
tests/multishard_mutation_query_test: test stateless query too
tests/querier_cache: fail resource-based eviction test gracefully
tests/querier_cache: simplify resource-based eviction test
tests/mutation_reader_test: add test_multishard_combining_reader_next_partition
tests/mutation_reader_test: restore indentation
tests/mutation_reader_test: enrich pause-related multishard reader test
multishard_combining_reader: use pause-resume API
query::partition_slice: add clear_ranges() method
position_in_partition: add region() accessor
foreign_reader: add pause-resume API
tests/mutation_reader_test: implement the pause-resume API
query_mutations_on_all_shards(): implement pause-resume API
make_multishard_streaming_reader(): implement the pause-resume API
database: add accessors for user and streaming concurrency semaphores
reader_lifecycle_policy: extend with a pause-resume API
query_mutations_on_all_shards(): restore indentation
query_mutations_on_all_shards(): simplify the state-machine
multishard_combining_reader: use the reader lifecycle policy
multishard_combining_reader: add reader lifecycle policy
multishard_combining_reader: drop unnecessary `reader_promise` member
...
sstable_test.cc was already a bit too big and there is potential for
having a lot of tests about broken sstables.
Signed-off-by: Rafael Ávila de Espíndola <espindola@scylladb.com>
"
zlib's crc32_combine() is not very efficient. It is faster to re-combine
the buffer using crc32(). It's still substantial amount of work which
could be avoided.
This patch introduces a fast implementation of crc32_combine() which
uses a different algorithm than zlib. It also utilizes intrinsics for
carry-less multiplication instruction to perform the computation faster.
The details of the algorithm can be found in code comments.
Performance results using perf_checksum and second buffer of length 64 KiB:
zlib CRC32 combine: 38'851 ns
libdeflate CRC32: 4'797 ns
fast_crc32_combine(): 11 ns
So the new implementation is 3500x faster than zlib's, and 417x faster than
re-checksumming the buffer using libdeflate.
Tested on i7-5960X CPU @ 3.00GHz
Performance was also evaluated using sstable writer benchmark:
perf_fast_forward --populate --sstable-format=mc --data-directory /tmp/perf-mc \
--value-size=10000 --rows 1000000 --datasets small-part
It yielded 9% improvement in median frag/s (129'055 vs 117'977).
Refs #3874
"
* tag 'fast-crc32-combine-v2' of github.com:tgrabiec/scylla:
tests: perf_checksum: Test fast_crc32_combine()
tests: Rename libdeflate_test to checksum_utils_test
tests: libdeflate: Add more tests for checksum_combine()
tests: libdeflate: Check both libdeflate and default checksummers
sstables: Use fast_crc_combine() in the default checksummer
utils/gz: Add fast implementation of crc32_combine()
utils/gz: Add pre-computed polynomials
utils/gz: Import Barett reduction implementation from libdeflate
utils: Extract clmul() from crc.hh
zlib's crc32_combine() is not very efficient. It is faster to re-combine
the buffer using crc32(). It's still substantial amount of work which
could be avoided.
This patch introduces a fast implementation of crc32_combine() which
uses a different algorithm than zlib. It also utilizes intrinsics for
carry-less multiplication instruction to perform the computation faster.
The details of the algorithm can be found in code comments.
Performance results using perf_checksum and second buffer of length 64 KiB:
zlib CRC32 combine: 38'851 ns
libdeflate CRC32: 4'797 ns
fast_crc32_combine(): 11 ns
So the new implementation is 3500x faster than zlib's, and 417x faster than
re-checksumming the buffer using libdeflate.
Tested on i7-5960X CPU @ 3.00GHz
Performance was also evaluated using sstable writer benchmark:
perf_fast_forward --populate --sstable-format=mc --data-directory /tmp/perf-mc \
--value-size=10000 --rows 1000000 --datasets small-part
It yielded 9% improvement in median frag/s (129'055 vs 117'977).
gen_crc_combine_table.cc will be run during build to produce tables
with precomputed polynomials (4 x 256 x u32). The definitions will
reside in:
build/<mode>/gen/utils/gz/crc_combine_table.cc
It takes 20ms to generate on my machine.
The purpose of those polynomials will be explained in crc_combine.cc
As we are about to extend the functionality of the reader concurrency
semaphore, adding more method implementations that need to go to a .cc
file, it's time we create a dedicated file, instead of keep shoving them
into unrelated .cc files (mutation_reader.cc).
As far as I can tell the old sstable reading code required reading the
data into a contiguous buffer. The function data_consume_rows_at_once
implemented the old behavior and incrementally code was moved away
from it.
Right now the only use is in two tests. The sstables used in those
tests are already used in other tests with data_consume_rows.
Signed-off-by: Rafael Ávila de Espíndola <espindola@scylladb.com>
Message-Id: <20181127024319.18732-2-espindola@scylladb.com>
* seastar d59fcef...b924495 (2):
> build: Fix protobuf generation rules
> Merge "Restructure files" from Jesse
Includes fixup patch from Jesse:
"
Update Seastar `#include`s to reflect restructure
All Seastar header files are now prefixed with "seastar" and the
configure script reflects the new locations of files.
Signed-off-by: Jesse Haber-Kucharsky <jhaberku@scylladb.com>
Message-Id: <5d22d964a7735696fb6bb7606ed88f35dde31413.1542731639.git.jhaberku@scylladb.com>
"
"
This series adds DEFAULT UNSET and DEFAULT NULL keyword support
to INSERT JSON statement, as stated in #3909.
Tests: unit (release)
"
* 'add_json_default_unset_2' of https://github.com/psarna/scylla:
tests: add DEFAULT UNSET case to JSON cql tests
tests: split JSON part of cql query test
cql3: add DEFAULT UNSET to INSERT JSON
It achieves 2.0x speedup on intel E5 and 1.1x to 2.5x speedup on
various arm64 microarchitectures.
The algorithm cuts data into blocks of 1024 bytes and calculates crc
for each block, which is furthur divided into three subblocks of 336
bytes(42 uint64) each, and 16 remaining bytes(2 uint64).
For each iteration, three independent crc are caculated for one uint64
from each subgroup. It increases IPC(instructions per cycle) much.
After subblocks are done, three crc and remaining two uint64 are
combined using carry-less multiplication to reach the final result
for one block of 1024 bytes.
Signed-off-by: Yibo Cai <yibo.cai@arm.com>
Message-Id: <1541042759-24767-1-git-send-email-yibo.cai@arm.com>
Right now we don't have dependencies for dist/, ninja not able to detect
changes under the directory.
To update relocatable package even only change is under dist/, we need
to run create-relocatable-package.py everytime.
Signed-off-by: Takuya ASADA <syuu@scylladb.com>
To re-generate scylla version files when it removed, since these files
required for relocatable package.
Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Since debian packaging system requires source package to compress tar
file, so let's use .gz compression.
Signed-off-by: Takuya ASADA <syuu@scylladb.com>
This is a helper flat_mutation_reader that wraps another reader and
splits range tombstones over rows before emitting them.
It is used to produce the same mutation streams for both old (ka/la) and
new (mc) SSTables formats in unit tests.
Signed-off-by: Vladimir Krivopalov <vladimir@scylladb.com>
