Compare commits

..

99 Commits

Author SHA1 Message Date
Jenkins
d27eb734a7 release: prepare for 2.2.2 by hagitsegev 2019-01-12 18:28:25 +02:00
Avi Kivity
e6aeb490b5 Update seastar submodule
* seastar 6f61d74...88cb58c (2):
  > reactor: disable nowait aio due to a kernel bug
  > configure.py: Enhance detection for gcc -fvisibility=hidden bug

Fixes #3996.
2018-12-17 15:57:58 +02:00
Vladimir Krivopalov
2e3b09b593 database: Capture io_priority_class by reference to avoid dangling ref.
The original reference points to a thread-local storage object that
guaranteed to outlive the continuation, but copying it make the
subsequent calls point to a local object and introduces a use-after-free
bug.

Fixes #3948

Signed-off-by: Vladimir Krivopalov <vladimir@scylladb.com>
(cherry picked from commit 68458148e7)
2018-12-02 13:32:59 +02:00
Tomasz Grabiec
92c74f4e0b utils: phased_barrier: Make advance_and_await() have strong exception guarantees
Currently, when advance_and_await() fails to allocate the new gate
object, it will throw bad_alloc and leave the phased_barrier object in
an invalid state. Calling advance_and_await() again on it will result
in undefined behavior (typically SIGSEGV) beacuse _gate will be
disengaged.

One place affected by this is table::seal_active_memtable(), which
calls _flush_barrier.advance_and_await(). If this throws, subsequent
flush attempts will SIGSEGV.

This patch rearranges the code so that advance_and_await() has strong
exception guarantees.
Message-Id: <1542645562-20932-1-git-send-email-tgrabiec@scylladb.com>

Fixes #3931.

(cherry picked from commit 57e25fa0f8)
2018-11-21 12:18:25 +02:00
Avi Kivity
89d835e9e3 tests: fix network_topology_test timing out in debug mode
In 2.2, SEASTAR_DEBUG is just DEBUG.
2018-10-21 19:04:08 +03:00
Takuya ASADA
263a740084 dist/debian: use --configfile to specify pbuilderrc
Use --configfile to specify pbuilderrc, instead of copying it to home directory.

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <20180420024624.9661-1-syuu@scylladb.com>
(cherry picked from commit 01c36556bf)
2018-10-21 18:21:18 +03:00
Avi Kivity
7f24b5319e release: prepare for 2.2.1 2018-10-19 21:16:14 +03:00
Avi Kivity
fe16c0e985 locator: fix abstract_replication_strategy::get_ranges() and friends violating sort order
get_ranges() is supposed to return ranges in sorted order. However, a35136533d
broke this and returned the range that was supposed to be last in the second
position (e.g. [0, 10, 1, 2, 3, 4, 5, 6, 7, 8, 9]). The broke cleanup, which
relied on the sort order to perform a binary search. Other users of the
get_ranges() family did not rely on the sort order.

Fixes #3872.
Message-Id: <20181019113613.1895-1-avi@scylladb.com>

(cherry picked from commit 1ce52d5432)
2018-10-19 21:16:12 +03:00
Glauber Costa
f85badaaac api: use longs instead of ints for snapshot sizes
Int types in json will be serialized to int types in C++. They will then
only be able to handle 4GB, and we tend to store more data than that.

Without this patch, listsnapshots is broken in all versions.

Fixes: #3845

Signed-off-by: Glauber Costa <glauber@scylladb.com>
Message-Id: <20181012155902.7573-1-glauber@scylladb.com>
(cherry picked from commit 98332de268)
2018-10-12 22:02:56 +03:00
Eliran Sinvani
2193d41683 cql3 : add workaround to antlr3 null dereference bug
The Antlr3 exception class has a null dereference bug that crashes
the system when trying to extract the exception message using
ANTLR_Exception<...>::displayRecognitionError(...) function. When
a parsing error occurs the CqlParser throws an exception which in
turn processesed for some special cases in scylla to generate a custom
message. The default case however, creates the message using
displayRecognitionError, causing the system to crash.
The fix is a simple workaround, making sure the pointer is not null
before the call to the function. A "proper" fix can't be implemented
because the exception class itself is implemented outside scylla
in antlr headers that resides on the host machine os.

Tested manualy 2 testcases, a typo causing scylla to crash and
a cql comment without a newline at the end also caused scylla to crash.
Ran unit tests (release).

Fixes #3740
Fixes #3764

Signed-off-by: Eliran Sinvani <eliransin@scylladb.com>
Message-Id: <cfc7e0d758d7a855d113bb7c8191b0fd7d2e8921.1538566542.git.eliransin@scylladb.com>
(cherry picked from commit 20f49566a2)
2018-10-08 11:02:16 +03:00
Avi Kivity
1e1f0c29bf utils: crc32: mark power crc32 assembly as not requiring an executable stack
The linker uses an opt-in system for non-executable stack: if all object files
opt into a non-executable stack, the binary will have a non-executable stack,
which is very desirable for security. The compiler cooperates by opting into
a non-executable stack whenever possible (always for our code).

However, we also have an assembly file (for fast power crc32 computations).
Since it doesn't opt into a non-executable stack, we get a binary with
executable stack, which Gentoo's build system rightly complains about.

Fix by adding the correct incantation to the file.

Fixes #3799.

Reported-by: Alexys Jacob <ultrabug@gmail.com>
Message-Id: <20181002151251.26383-1-avi@scylladb.com>
(cherry picked from commit aaab8a3f46)
2018-10-08 11:02:16 +03:00
Calle Wilund
84d4588b5f storage_proxy: Add missing re-throw in truncate_blocking
Iff truncation times out, we want to log it, but the exception should
not be swallowed, but re-thrown.

Fixes #3796.

Message-Id: <20181001112325.17809-1-calle@scylladb.com>
(cherry picked from commit 2996b8154f)
2018-10-08 11:02:16 +03:00
Duarte Nunes
7b43b26709 tests/aggregate_fcts_test: Add test case for wrapped types
Provide a test case which checks a type being wrapped in a
reverse_type plays no role in assignment.

Refs #3789

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20180927223201.28152-2-duarte@scylladb.com>
(cherry picked from commit 17578c3579)
2018-10-08 11:02:16 +03:00
Duarte Nunes
0ed01acf15 cql3/selection/selector: Unwrap types when validating assignment
When validating assignment between two types, it's possible one of
them is wrapped in a reverse_type, if it comes, for example, from the
type associated with a clustering column. When checking for weak
assignment the types are correctly unwrapped, but not when checking
for an exact match, which this patch fixes.

Technically, the receiver is never a reversed_type for the current
callers, but this is the morally correct implementation, as the type
being reversed or not plays no role in assignment.

Tests: unit(release)

Fixes #3789

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20180927223201.28152-1-duarte@scylladb.com>
(cherry picked from commit 5e7bb20c8a)
2018-10-08 11:02:16 +03:00
Gleb Natapov
7ce160f408 mutation_query_test: add test for result size calculation
Check that digest only and digest+data query calculate result size to be
the same.

Message-Id: <20180906153800.GK2326@scylladb.com>
(cherry picked from commit 9e438933a2)

Message-Id: <20181008075901.GC2380@scylladb.com>
2018-10-08 11:02:09 +03:00
Gleb Natapov
5017d9b46a mutation_partition: accurately account for result size in digest only queries
When measuring_output_stream is used to calculate result's element size
it incorrectly takes into account not only serialized element size, but
a placeholder that ser::qr_partition__rows/qr_partition__static_row__cells
constructors puts in the beginning. Fix it by taking starting point in a
stream before element serialization and subtracting it afterwords.

Fixes #3755

Message-Id: <20180906153609.GJ2326@scylladb.com>
(cherry picked from commit d7674288a9)
2018-10-07 18:16:19 +03:00
Gleb Natapov
50b6ab3552 mutation_partition: correctly measure static row size when doing digest calculation
The code uses incorrect output stream in case only digest is requested
and thus getting incorrect data size. Failing to correctly account
for static row size while calculating digest may cause digest mismatch
between digest and data query.

Fixes #3753.

Message-Id: <20180905131219.GD2326@scylladb.com>
(cherry picked from commit 98092353df)
2018-09-06 16:51:19 +03:00
Eliran Sinvani
b1652823aa cql3: ensure repeated values in IN clauses don't return repeated rows
When the list of values in the IN list of a single column contains
duplicates, multiple executors are activated since the assumption
is that each value in the IN list corresponds to a different partition.
this results in the same row appearing in the result number times
corresponding to the duplication of the partition value.

Added queries for the in restriction unitest and fixed with a bad result check.

Fixes #2837
Tests: Queries as in the usecase from the GitHub issue in both forms ,
prepared and plain (using python driver),Unitest.

Signed-off-by: Eliran Sinvani <eliransin@scylladb.com>
Message-Id: <ad88b7218fa55466be7bc4303dc50326a3d59733.1534322238.git.eliransin@scylladb.com>
(cherry picked from commit d734d316a6)
2018-08-26 15:51:17 +03:00
Tomasz Grabiec
02b24aec34 Merge 'Fix multi-cell static list updates in the presence of ckeys' from Duarte
Fixes a regression introduced in
9e88b60ef5, which broke the lookup for
prefetched values of lists when a clustering key is specified.

This is the code that was removed from some list operations:

 std::experimental::optional<clustering_key> row_key;
 if (!column.is_static()) {
   row_key = clustering_key::from_clustering_prefix(*params._schema, prefix);
 }
 ...
 auto&& existing_list = params.get_prefetched_list(m.key().view(), row_key, column);

Put it back, in the form of common code in the update_parameters class.

Fixes #3703

* https://github.com/duarten/scylla cql-list-fixes/v1:
  tests/cql_query_test: Test multi-cell static list updates with ckeys
  cql3/lists: Fix multi-cell static list updates in the presence of ckeys
  keys: Add factory for an empty clustering_key_prefix_view

(cherry picked from commit 6937cc2d1c)
2018-08-21 21:39:22 +01:00
Duarte Nunes
22eea4d8cf cql3/query_options: Use _value_views in prepare()
_value_views is the authoritative data structure for the
client-specified values. Indeed, the ctor called
transport::request::read_options() leaves _values completely empty.

In query_options::prepare() we were, however, using _values to
associated values to the client-specified column names, and not
_value_views. Fix this by using _value_views instead.

As for the reasons we didn't see this bug earlier, I assume it's
because very few drivers set the 0x04 query options flag, which means
column names are omitted. This is the right thing to do since most
drivers have enough information to correctly position the values.

Fixes #3688

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20180814234605.14775-1-duarte@scylladb.com>
(cherry picked from commit a4355fe7e7)
2018-08-21 21:39:22 +01:00
Tomasz Grabiec
d257f6d57c mutation_partition: Fix exception safety of row::apply_monotonically()
When emplace_back() fails, value is already moved-from into a
temporary, which breaks monotonicity expected from
apply_monotonically(). As a result, writes to that cell will be lost.

The fix is to avoid the temporary by in-place construction of
cell_and_hash. To do that, appropriate cell_and_hash constructor was
added.

Found by mutation_test.cc::test_apply_monotonically_is_monotonic with
some modifications to the random mutation generator.

Introduced in 99a3e3a.

Fixes #3678.

Message-Id: <1533816965-27328-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit 024b3c9fd9)
2018-08-21 21:39:18 +01:00
Takuya ASADA
6fca92ac3c dist/common/scripts/scylla_ec2_check: support custom NIC ifname on EC2
This is bash version of commit 88fe3c2694.

Since some AMIs using consistent network device naming, primary NIC
ifname is not 'eth0'.
But we hardcoded NIC name as 'eth0' on scylla_ec2_check, we need to add
--nic option to specify custom NIC ifname.

Fixes #3658

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <20180807231650.13697-1-syuu@scylladb.com>
2018-08-08 09:16:57 +03:00
Jesse Haber-Kucharsky
26e3917046 auth: Don't use unsupported hashing algorithms
In previous versions of Fedora, the `crypt_r` function returned
`nullptr` when a requested hashing algorithm was not supported.

This is consistent with the documentation of the function in its man
page.

As of Fedora 28, the function's behavior changes so that the encrypted
text is not `nullptr` on error, but instead the string "*0".

The info pages for `crypt_r` clarify somewhat (and contradict the man
pages):

    Some implementations return `NULL` on failure, and others return an
    _invalid_ hashed passphrase, which will begin with a `*` and will
    not be the same as SALT.

Because of this change of behavior, users running Scylla on a Fedora 28
machine which was upgraded from a previous release would not be able to
authenticate: an unsupported hashing algorithm would be selected,
producing encrypted text that did not match the entry in the table.

With this change, unsupported algorithms are correctly detected and
users should be able to continue to authenticate themselves.

Fixes #3637.

Signed-off-by: Jesse Haber-Kucharsky <jhaberku@scylladb.com>
Message-Id: <bcd708f3ec195870fa2b0d147c8910fb63db7e0e.1533322594.git.jhaberku@scylladb.com>
(cherry picked from commit fce10f2c6e)
2018-08-05 10:30:47 +03:00
Gleb Natapov
3892594a93 cache_hitrate_calculator: fix race when new table is added during calculations
The calculation consists of several parts with preemption point between
them, so a table can be added while calculation is ongoing. Do not
assume that table exists in intermediate data structure.

Fixes #3636

Message-Id: <20180801093147.GD23569@scylladb.com>
(cherry picked from commit 44a6afad8c)
2018-08-01 14:34:08 +03:00
Amos Kong
4b24439841 scylla_setup: fix conditional statement of silent mode
Commit 300af65555 introdued a problem in
conditional statement, script will always abort in silent mode, it doesn't
care about the return value.

Fixes #3485

Signed-off-by: Amos Kong <amos@scylladb.com>
Message-Id: <1c12ab04651352964a176368f8ee28f19ae43c68.1528077114.git.amos@scylladb.com>
(cherry picked from commit 364c2551c8)
2018-07-25 09:36:32 +03:00
Takuya ASADA
a02a4592d8 dist/common/scripts/scylla_setup: abort running script when one of setup failed in silent mode
Current script silently continues even one of setup fails, need to
abort.

Fixes #3433

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <20180522180355.1648-1-syuu@scylladb.com>
(cherry picked from commit 300af65555)
2018-07-25 09:36:29 +03:00
Avi Kivity
b6e1c08451 Merge "row_cache: Fix violation of continuity on concurrent eviction and population" from Tomasz
"
The problem happens under the following circumstances:

  - we have a partially populated partition in cache, with a gap in the middle

  - a read with no clustering restrictions trying to populate that gap

  - eviction of the entry for the lower bound of the gap concurrent with population

The population may incorrectly mark the range before the gap as continuous.
This may result in temporary loss of writes in that clustering range. The
problem heals by clearing cache.

Caught by row_cache_test::test_concurrent_reads_and_eviction, which has been
failing sporadically.

The problem is in ensure_population_lower_bound(), which returns true if
current clustering range covers all rows, which means that the populator has a
right to set continuity flag to true on the row it inserts. This is correct
only if the current population range actually starts since before all
clustering rows. Otherwise, we're populating since _last_row and should
consult it.

Fixes #3608.
"

* 'tgrabiec/fix-violation-of-continuity-on-concurrent-read-and-eviction' of github.com:tgrabiec/scylla:
  row_cache: Fix violation of continuity on concurrent eviction and population
  position_in_partition: Introduce is_before_all_clustered_rows()

(cherry picked from commit 31151cadd4)
2018-07-18 12:07:01 +02:00
Botond Dénes
9469afcd27 storage_proxy: use the original row limits for the final results merging
`query_partition_key_range()` does the final result merging and trimming
(if necessary) to make sure we don't send more rows to the client than
requested. This merging and trimming is done by a continuation attached
to the `query_partition_key_range_concurrent()` which does the actual
querying. The continuations captures via value the `row_limit` and
`partition_limit` fields of the `query::read_command` object of the
query. This has an unexpected consequence. The lambda object is
constructed after the call to `query_partition_key_range_concurrent()`
returns. If this call doesn't defer, any modifications done to the read
command object done by `query_partition_key_range_concurrent()` will be
visible to the lambda. This is undesirable because
`query_partition_key_range_concurrent()` updates the read command object
directly as the vnodes are traversed which in turn will result in the
lambda doing the final trimming according to a decremented `row_limits`,
which will cause the paging logic to declare the query as exhausted
prematurely because the page will not be full.
To avoid all this make a copy of the relevant limit fields before
`query_partition_key_range_concurrent()` is called and pass these copies
to the continuation, thus ensuring that the final trimming will be done
according to the original page limits.

Spotted while investigating a dtest failure on my 1865/range-scans/v2
branch. On that branch the way range scans are executed on replicas is
completely refactored. These changes appearantly reduce the number of
continuations in the read path to the point where an entire page can be
filled without deferring and thus causing the problem to surface.

Fixes #3605.

Signed-off-by: Botond Dénes <bdenes@scylladb.com>
Message-Id: <f11e80a6bf8089d49ba3c112b25a69edf1a92231.1531743940.git.bdenes@scylladb.com>
(cherry picked from commit cc4acb6e26)
2018-07-16 17:51:06 +03:00
Avi Kivity
240b9f122b Merge "Backport empty partition range scan fixes" from Botond
"
This mini-series lumps together the fix for the empty partition range
scan crash (#3564) and the two follow-up patches.
"

* 'paging-fix-backport-2.2/v1' of https://github.com/denesb/scylla:
  query_pager: use query::is_single_partition() to check for singular range
  tests/cql_query_tess: add unit test for querying empty ranges test
  query_pager: be prepared to _ranges being empty
2018-07-05 10:29:31 +03:00
Botond Dénes
cb16cd7724 query_pager: use query::is_single_partition() to check for singular range
Use query::is_single_partition() to check whether the queried ranges are
singular or not. The current method of using
`dht::partition_range::is_singular()` is incorrect, as it is possible to
build a singular range that doesn't represent a single partition.
`query::is_single_partition()` correctly checks for this so use it
instead.

Found during code-review.

Signed-off-by: Botond Dénes <bdenes@scylladb.com>
Message-Id: <f671f107e8069910a2f84b14c8d22638333d571c.1530675889.git.bdenes@scylladb.com>
(cherry picked from commit 8084ce3a8e)
2018-07-04 12:57:45 +03:00
Botond Dénes
c864d198fc tests/cql_query_tess: add unit test for querying empty ranges test
A bug was found recently (#3564) in the paging logic, where the code
assumed the queried ranges list is non-empty. This assumption is
incorrect as there can be valid (if rare) queries that can result in the
ranges list to be empty. Add a unit test that executes such a query with
paging enabled to detect any future bugs related to assumptions about
the ranges list being non-empty.

Refs: #3564
Signed-off-by: Botond Dénes <bdenes@scylladb.com>
Message-Id: <f5ba308c4014c24bb392060a7e72e7521ff021fa.1530618836.git.bdenes@scylladb.com>
(cherry picked from commit c236a96d7d)
2018-07-04 09:52:54 +03:00
Botond Dénes
25125e9c4f query_pager: be prepared to _ranges being empty
do_fetch_page() checks in the beginning whether there is a saved query
state already, meaning this is not the first page. If there is not it
checks whether the query is for a singulular partitions or a range scan
to decide whether to enable the stateful queries or not. This check
assumed that there is at least one range in _ranges which will not hold
under some circumstances. Add a check for _ranges being empty.

Fixes: #3564
Signed-off-by: Botond Dénes <bdenes@scylladb.com>
Message-Id: <cbe64473f8013967a93ef7b2104c7ca0507afac9.1530610709.git.bdenes@scylladb.com>
(cherry picked from commit 59a30f0684)
2018-07-04 09:52:54 +03:00
Shlomi Livne
faf10fe6aa release: prepare for 2.2.0
Signed-off-by: Shlomi Livne <shlomi@scylladb.com>
2018-07-01 22:40:42 +03:00
Calle Wilund
f76269cdcf sstables::compress: Ensure unqualified compressor name if possible
Fixes #3546

Both older origin and scylla writes "known" compressor names (i.e. those
in origin namespace) unqualified (i.e. LZ4Compressor).

This behaviour was not preserved in the virtualization change. But
probably should be.

Message-Id: <20180627110930.1619-1-calle@scylladb.com>
(cherry picked from commit 054514a47a)
2018-06-28 18:55:15 +03:00
Avi Kivity
a9b0ccf116 Merge "Disable sstable filtering based on min/max clustering key components" from Tomasz
"
With DateTiered and TimeWindow, there is a read optimization enabled
which excludes sstables based on overlap with recorded min/max values
of clustering key components. The problem is that it doesn't take into
account partition tombstones and static rows, which should still be
returned by the reader even if there is no overlap in the query's
clustering range. A read which returns no clustering rows can
mispopulate cache, which will appear as partition deletion or writes
to the static row being lost. Until node restart or eviction of the
partition entry.

There is also a bad interaction between cache population on read and
that optimization. When the clustering range of the query doesn't
overlap with any sstable, the reader will return no partition markers
for the read, which leads cache populator to assume there is no
partition in sstables and it will cache an empty partition. This will
cause later reads of that partition to miss prior writes to that
partition until it is evicted from cache or node is restarted.

Disable until a more elaborate fix is implemented.

Fixes #3552
Fixes #3553
"

* tag 'tgrabiec/disable-min-max-sstable-filtering-v1' of github.com:tgrabiec/scylla:
  tests: Add test for slicing a mutation source with date tiered compaction strategy
  tests: Check that database conforms to mutation source
  database: Disable sstable filtering based on min/max clustering key components

(cherry picked from commit e1efda8b0c)
2018-06-28 18:55:15 +03:00
Tomasz Grabiec
abc5941f87 flat_mutation_reader: Move field initialization to initializer list
This works around a problem of std::terminate() being called in debug
mode build if initialization of _current throws.

Backtrace:

Thread 2 "row_cache_test_" received signal SIGABRT, Aborted.
0x00007ffff17ce9fb in raise () from /lib64/libc.so.6
(gdb) bt
  #0  0x00007ffff17ce9fb in raise () from /lib64/libc.so.6
  #1  0x00007ffff17d077d in abort () from /lib64/libc.so.6
  #2  0x00007ffff5773025 in __gnu_cxx::__verbose_terminate_handler() () from /lib64/libstdc++.so.6
  #3  0x00007ffff5770c16 in ?? () from /lib64/libstdc++.so.6
  #4  0x00007ffff576fb19 in ?? () from /lib64/libstdc++.so.6
  #5  0x00007ffff5770508 in __gxx_personality_v0 () from /lib64/libstdc++.so.6
  #6  0x00007ffff3ce4ee3 in ?? () from /lib64/libgcc_s.so.1
  #7  0x00007ffff3ce570e in _Unwind_Resume () from /lib64/libgcc_s.so.1
  #8  0x0000000003633602 in reader::reader (this=0x60e0001160c0, r=...) at flat_mutation_reader.cc:214
  #9  0x0000000003655864 in std::make_unique<make_forwardable(flat_mutation_reader)::reader, flat_mutation_reader>(flat_mutation_reader &&) (__args#0=...)
    at /usr/include/c++/7/bits/unique_ptr.h:825
  #10 0x0000000003649a63 in make_flat_mutation_reader<make_forwardable(flat_mutation_reader)::reader, flat_mutation_reader>(flat_mutation_reader &&) (args#0=...)
    at flat_mutation_reader.hh:440
  #11 0x000000000363565d in make_forwardable (m=...) at flat_mutation_reader.cc:270
  #12 0x000000000303f962 in memtable::make_flat_reader (this=0x61300001d540, s=..., range=..., slice=..., pc=..., trace_state_ptr=..., fwd=..., fwd_mr=...)
    at memtable.cc:592

Message-Id: <1528792447-13336-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit 6d6b93d1e7)
2018-06-28 18:55:15 +03:00
Asias He
a152ac12af gossip: Fix tokens assignment in assassinate_endpoint
The tokens vector is defined a few lines above and is needed outsie the
if block.

Do not redefine it again in the if block, otherwise the tokens will be empty.

Found by code inspection.

Fixes #3551.

Message-Id: <c7a06375c65c950e94236571127f533e5a60cbfd.1530002177.git.asias@scylladb.com>
(cherry picked from commit c3b5a2ecd5)
2018-06-28 18:55:15 +03:00
Botond Dénes
c274fdf2ec querier: find_querier(): return end() when no querier matches the range
When none of the queriers found for the lookup key match the lookup
range `_entries.end()` should be returned as the search failed. Instead
the iterator returned from the failed `std::find_if()` is returned
which, if the find failed, will be the end iterator returned by the
previous call to `_entries.equal_range()`. This is incorrect because as
long as `equal_range()`'s end iterator is not also `_entries.end()` the
search will always return an iterator to a querier regardless of whether
any of them actually matches the read range.
Fix by returning `_entries.end()` when it is detected that no queriers
match the range.

Fixes: #3530
(cherry picked from commit 2609a17a23)
2018-06-28 18:55:15 +03:00
Botond Dénes
5b88d6b4d6 querier_cache: restructure entries storage
Currently querier_cache uses a `std::unordered_map<utils::UUID, querier>`
to store cache entries and an `std::list<meta_entry>` to store meta
information about the querier entries, like insertion order, expiry
time, etc.

All cache eviction algorithms use the meta-entry list to evict entries
in reverse insertion order (LRU order). To make this possible
meta-entries keep an iterator into the entry map so that given a
meta-entry one can easily erase the querier entry. This however poses a
problem as std::unordered_map can possibly invalidate all its iterators
when new items are inserted. This is use-after-free waiting to happen.

Another disadvantages of the current solution is that it requires the
meta-entry to use a weak pointer to the querier entry so that in case
that is removed (as a result of a successful lookup) it doesn't try to
access it. This has an impact on all cache eviction algorithms as they
have to be prepared to deal with stale meta-entries. Stale meta-entries
also unnecesarily consume memory.

To solve these problems redesign how querier_cache stores entries
completely. Instead of storing the entries in an `std::unordered_map`
and storing the meta-entries in an `std::list`, store the entries in an
`std::list` and an intrusive-map (index) for lookups. This new design
has severeal advantages over the old one:
* The entries will now be in insert order, so eviction strategies can
  work on the entry list itself, no need to involve additional data
  structures for this.
* All data related to an entry is stored in one place, no data
  duplication.
* Removing an entry automatically removes it from the index as intrusive
  containers support auto unlink. This means there is no need to store
  iterators for long terms, risking use-after-free when the container
  invalidates it's iterators.

Additional changes:
* Modify eviction strategies so that they work with the `entry`
  interface rather than the stored value directly.

Ref #3424

(cherry picked from commit 7ce7f3f0cc)
2018-06-28 18:55:15 +03:00
Botond Dénes
2d626e1cf8 tests/querier_cache: fix memory based eviction test
Do increment the key counter after inserting the first querier into the
cache. Otherwise two queriers with the same key will be inserted and
will fail the test. This problem is exposed by the changes the next
patches make to the querier-cache but will be fixed before to maintain
bisectability of the code.

Fixes: #3529
(cherry picked from commit b9d51b4c08)
2018-06-28 18:55:15 +03:00
Avi Kivity
c11bd3e1cf Merge "Do not allow compaction controller shares to grow indefinitely" from Glauber
"
We are seeing some workloads with large datasets where the compaction
controller ends up with a lot of shares. Regardless of whether or not
we'll change the algorithm, this patchset handles a more basic issue,
which is the fact that the current controller doesn't set a maximum
explicitly, so if the input is larger than the maximum it will keep
growing without bounds.

It also pushes the maximum input point of the compaction controller from
10 to 30, allowing us to err on the side of caution for the 2.2 release.
"

* 'tame-controller' of github.com:glommer/scylla:
  controller: do not increase shares of controllers for inputs higher than the maximum
  controller: adjust constants for compaction controller

(cherry picked from commit e0eb66af6b)
2018-06-20 10:58:20 +03:00
Avi Kivity
9df3df92bc Merge "Try harder to move STCS towards zero-backlog" from Glauber
"
Tests: unit (release)

Before merging the LCS controller, we merged patches that would
guarantee that LCS would move towards zero backlog - otherwise the
backlog could get too high.

We didn't do the same for STCS, our first controlled strategy. So we may
end up with a situation where there are many SSTables inducing a large
backlog, but they are not yet meeting the minimum criteria for
compaction. The backlog, then, never goes down.

This patch changes the SSTable selection criteria so that if there is
nothing to do, we'll keep pushing towards reaching a state of zero
backlog. Very similar to what we did for LCS.
"

* 'stcs-min-threshold-v4' of github.com:glommer/scylla:
  STCS: bypass min_threshold unless configure to enforce strictly
  compaction_strategy: allow the user to tell us if min_threshold has to be strict

(cherry picked from commit f0fc888381)
2018-06-18 14:21:52 +03:00
Takuya ASADA
8ad9578a6c dist/debian: add --jobs <njobs> option just like build_rpm.sh
On some build environment we may want to limit number of parallel jobs since
ninja-build runs ncpus jobs by default, it may too many since g++ eats very
huge memory.
So support --jobs <njobs> just like on rpm build script.

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <20180425205439.30053-1-syuu@scylladb.com>
(cherry picked from commit 782ebcece4)
2018-06-14 15:04:50 +03:00
Tomasz Grabiec
4cb6061a9f tests: row_cache: Reduce concurrency limit to avoid bad_alloc
The test uses random mutations. We saw it failing with bad_alloc from time to time.
Reduce concurrency to reduce memory footprint.

Message-Id: <20180611090304.16681-1-tgrabiec@scylladb.com>
(cherry picked from commit a91974af7a)
2018-06-14 13:40:00 +02:00
Tomasz Grabiec
1940e6bd95 tests: row_cache: Do not hang when only one of the readers throws
Message-Id: <20180531122729.3314-1-tgrabiec@scylladb.com>
(cherry picked from commit b5e42bc6a0)
2018-06-14 13:40:00 +02:00
Avi Kivity
044cfde5f3 database: stop using incremental selectors
There is a bug in incremental_selector for partitioned_sstable_set, so
until it is found, stop using it.

This degrades scan performance of Leveled Compaction Strategy tables.

Fixes #3513. (as a workaround)
Introduced: 2.1
Message-Id: <20180613131547.19084-1-avi@scylladb.com>

(cherry picked from commit aeffbb6732)
2018-06-13 21:04:56 +03:00
Vlad Zolotarov
262a246436 locator::ec2_multi_region_snitch: don't call for ec2_snitch::gossiper_starting()
ec2_snitch::gossiper_starting() calls for the base class (default) method
that sets _gossip_started to TRUE and thereby prevents to following
reconnectable_snitch_helper registration.

Fixes #3454

Signed-off-by: Vlad Zolotarov <vladz@scylladb.com>
Message-Id: <1528208520-28046-1-git-send-email-vladz@scylladb.com>
(cherry picked from commit 2dde372ae6)
2018-06-12 19:02:19 +03:00
Botond Dénes
799dbb4f2e forwardable reader: implement fast_forward_to(position_in_partition)
Instead of throwing std::bad_function_call. Needed by the foreign_reader
unit test. Not sure how other tests didn't hit this before as the test
is using `run_mutation_source_tests()`.

(cherry picked from commit 50b67232e5)
Fixes #3491.
2018-06-05 12:34:15 +03:00
Shlomi Livne
a2fe669dd3 dist/docker: Switch to Scylla 2.2 repository
Signed-off-by: Shlomi Livne <shlomi@scylladb.com>
Message-Id: <83b4ff801b283ade512a7035ecea9057a864dcdd.1526995747.git.shlomi@scylladb.com>
2018-06-05 12:34:15 +03:00
Avi Kivity
56de761daf Update seastar submodule
* seastar 7c6ba3a...6f61d74 (1):
  > tls: Ensure handshake always drains output before return/throw

Fixes #3461.
2018-06-05 12:34:15 +03:00
Shlomi Livne
c3187093a3 release: prepare for 2.2.rc2
Signed-off-by: Shlomi Livne <shlomi@scylladb.com>
2018-05-30 17:32:16 +03:00
Avi Kivity
111c2ecf5d Update scylla-ami submodule
* dist/ami/files/scylla-ami 49896ec...6ed71a3 (1):
  > scylla_install_ami: Update CentOS to latest version
2018-05-28 14:02:43 +03:00
Takuya ASADA
a6ecdbbba6 Revert "dist/ami: update CentOS base image to latest version"
This reverts commit 69d226625a.
Since ami-4bf3d731 is Market Place AMI, not possible to publish public AMI based on it.

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <20180523112414.27307-1-syuu@scylladb.com>
(cherry picked from commit 6b1b9f9e602c570bbc96692d30046117e7d31ea7)
2018-05-28 13:40:15 +03:00
Glauber Costa
17cc62d0b3 commitlog: don't move pointer to segment
We are currently moving the pointer we acquired to the segment inside
the lambda in which we'll handle the cycle.

The problem is, we also use that same pointer inside the exception
handler. If an exception happens we'll access it and we'll crash.

Probably #3440.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
Message-Id: <20180518125820.10726-1-glauber@scylladb.com>
(cherry picked from commit 596a525950)
2018-05-19 19:12:26 +03:00
Shlomi Livne
eb646c61ed release: prepare for 2.2.rc1
Signed-off-by: Shlomi Livne <shlomi@scylladb.com>
2018-05-16 21:31:50 +03:00
Avi Kivity
782d817e84 dist: redhat: get rid of raid0.devices_discard_performance
This parameter is not available on recent Red Hat kernels or on
non-Red Hat kernels (it was removed on 3.10.0-772.el7,
RHBZ 1455932). The presence of the parameter on kernels that don't
support it cause the module load to fail, with the result that the
storage is not available.

Fix by removing the parameter. For someone running an older Red Hat
kernel the effect will be that discard is disabled, but they can fix
that by updating the kernel. For someone running a newer kernel, the
effect will be that they can access their data.

Fixes #3437.
Message-Id: <20180516134913.6540-1-avi@scylladb.com>

(cherry picked from commit 3b8118d4e5)
2018-05-16 20:13:59 +03:00
Avi Kivity
3ed5e63e8a Update scylla-ami submodule
* dist/ami/files/scylla-ami 02b1853...49896ec (1):
  > Merge "AMI build fix" from Takuya
2018-05-16 12:37:03 +03:00
Tomasz Grabiec
d17ce46983 Update seastar submodule
Fixes #3339.

* seastar 491f994...7c6ba3a (2):
  > Merge "fix perftune.py issues with cpu-masks on big machines" from Vlad
  > Merge 'Handle Intel's NICs in a special way'  from Vlad
2018-05-16 09:37:41 +02:00
Takuya ASADA
7ca5e7e993 dist/redhat: replace scylla-libgcc72/scylla-libstdc++72 with scylla-2.2 metapackage
We have conflict between scylla-libgcc72/scylla-libstdc++72 and
scylla-libgcc73/scylla-libstdc++73, need to replace *72 package with
scylla-2.2 metapackage to prevent it.

Fixes #3373

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <20180510081246.17928-1-syuu@scylladb.com>
(cherry picked from commit 6fa3c4dcad)
2018-05-11 09:42:28 +03:00
Duarte Nunes
07b0ce27fa Merge 'Include OPTIONS with LIST ROLES' from Jesse
"
Fixes #3420.

Tests: dtest (`auth_test.py`), unit (release)
"

* 'jhk/fix_3420/v2' of https://github.com/hakuch/scylla:
  cql3: Include custom options in LIST ROLES
  auth: Query custom options from the `authenticator`
  auth: Add type alias for custom auth. options

(cherry picked from commit d49348b0e1)
2018-05-10 13:22:49 +03:00
Amnon Heiman
27be3cd242 scylla-housekeeping: support new 2018.1 path variation
Starting from 2018.1 and 2.2 there was a change in the repository path.
It was made to support multiple product (like manager and place the
enterprise in a different path).

As a result, the regular expression that look for the repository fail.

This patch change the way the path is searched, both rpm and debian
varations are combined and both options of the repository path are
unified.

See scylladb/scylla-enterprise#527

Signed-off-by: Amnon Heiman <amnon@scylladb.com>
Message-Id: <20180429151926.20431-1-amnon@scylladb.com>
(cherry picked from commit 6bf759128b)
2018-05-09 15:22:55 +03:00
Calle Wilund
abf50aafef database: Fix assert in truncate
Fixes crash in cql_tests.StorageProxyCQLTester.table_test
"avoid race condition when deleting sstable on behalf..." changed
discard_sstables behaviour to only return rp:s for sstables owned
and submitted for deletion (not all matching time stamp),
which can in some cases cause zero rp returned.
Message-Id: <20180508070003.1110-1-calle@scylladb.com>
2018-05-09 10:02:09 +01:00
Duarte Nunes
dfe5b38a43 db/view: Limit number of pending view updates
This patch adds a simple and naive mechanism to ensure a base replica
doesn't overwhelm a potentially overloaded view replica by sending too
many concurrent view updates. We add a semaphore to limit to 100 the
number of outstanding view updates. We limit globally per shard, and
not per destination view replica. We also limit statically.

Refs #2538

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20180426134457.21290-2-duarte@scylladb.com>
(cherry picked from commit 4b3562c3f5)
2018-05-08 00:46:33 +01:00
Duarte Nunes
9bdc8c25f5 db/view: Return a future when sending view updates
While we now send view mutations asynchronously in the normal view
write path, other processes interested in sending view updates, such
as streaming or view building, may wish to do it synchronously.

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
(cherry picked from commit dc44a08370)
2018-05-08 00:46:19 +01:00
Duarte Nunes
e75c55b2db db/timeout_clock: Properly scope type names
Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20180426134457.21290-1-duarte@scylladb.com>
(cherry picked from commit 2be75bdfc9)
2018-05-07 19:29:48 +01:00
Botond Dénes
756feae052 database: when dropping a table evict all relevant queriers
Queriers shouldn't outlive the table they read from as that could lead
to use-after-free problems when they are destroyed.

Fixes: #3414

Signed-off-by: Botond Dénes <bdenes@scylladb.com>
Message-Id: <3d7172cef79bb52b7097596e1d4ebba3a6ff757e.1525716986.git.bdenes@scylladb.com>
(cherry picked from commit 6f7d919470)
2018-05-07 21:20:42 +03:00
Tomasz Grabiec
202b4e6797 storage_proxy: Request schema from the coordinator in the original DC
The mutation forwarding intermediary (src_addr) may not always know
about the schema which was used by the original coordinator. I think
this may be the cause of the "Schema version ... not found" error seen
in one of the clusters which entered some pathological state:

  storage_proxy - Failed to apply mutation from 1.1.1.1#5: std::_Nested_exception<schema_version_loading_failed> (Failed to load schema version 32893223-a911-3a01-ad70-df1eb2a15db1): std::runtime_error (Schema version 32893223-a911-3a01-ad70-df1eb2a15db1 not found)

Fixes #3393.

Message-Id: <1524639030-1696-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit 423712f1fe)
2018-05-07 13:08:40 +03:00
Raphael S. Carvalho
76ac200eff database: avoid race condition when deleting sstable on behalf of cf truncate
After removal of deletion manager, caller is now responsible for properly
submitting the deletion of a shared sstable. That's because deletion manager
was responsible for holding deletion until all owners agreed on it.
Resharding for example was changed to delete the shared sstables at the end,
but truncate wasn't changed and so race condition could happen when deleting
same sstable at more than one shard in parallel. Change the operation to only
submit a shared sstable for deletion in only one owner.

Fixes dtest migration_test.TestMigration.migrate_sstable_with_schema_change_test

Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Message-Id: <20180503193427.24049-1-raphaelsc@scylladb.com>
2018-05-04 13:10:12 +01:00
Tomasz Grabiec
9aa172fe8e db: schema_tables: Treat drop of scylla_tables.version as an alter
After upgrade from 1.7 to 2.0, nodes will record a per-table schema
version which matches that on 1.7 to support the rolling upgrade. Any
later schema change (after the upgrade is done) will drop this record
from affected tables so that the per-table schema version is
recalculated. If nodes perform a schema pull (they detect schema
mismatch), then the merge will affect all tables and will wipe the
per-table schema version record from all tables, even if their schema
did not change. If then only some nodes get restarted, the restarted
nodes will load tables with the new (recalculated) per-table schema
version, while not restarted nodes will still use the 1.7 per-table
schema version. Until all nodes are restarted, writes or reads between
nodes from different groups will involve a needless exchange of schema
definition.

This will manifest in logs with repeated messages indicating schema
merge with no effect, triggered by writes:

  database - Schema version changed to 85ab46cd-771d-36c9-bc37-db6d61bfa31f
  database - Schema version changed to 85ab46cd-771d-36c9-bc37-db6d61bfa31f
  database - Schema version changed to 85ab46cd-771d-36c9-bc37-db6d61bfa31f

The sync will be performed if the receiving shard forgets the foreign
version, which happens if it doesn't process any request referencing
it for more than 1 second.

This may impact latency of writes and reads.

The fix is to treat schema changes which drop the 1.7 per-table schema
version marker as an alter, which will switch in-memory data
structures to use the new per-table schema version immediately,
without the need for a restart.

Fixes #3394

Tests:
    - dtest: schema_test.py, schema_management_test.py
    - reproduced and validated the fix with run_upgrade_tests.sh from git@github.com:tgrabiec/scylla-dtest.git
    - unit (release)

Message-Id: <1524764211-12868-1-git-send-email-tgrabiec@scylladb.com>
(cherry picked from commit b1465291cf)
2018-05-03 10:51:19 +03:00
Takuya ASADA
c4af043ef7 dist/common/scripts/scylla_raid_setup: prevent 'device or resource busy' on creating mdraid device
According to this web site, there is possibility we have race condition with
mdraid creation vs udev:
http://dev.bizo.com/2012/07/mdadm-device-or-resource-busy.html
And looks like it can happen on our AMI, too (see #2784).

To initialize RAID safely, we should wait udev events are finished before and
after mdadm executed.

Fixes #2784

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1505898196-28389-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit 4a8ed4cc6f)
2018-04-24 12:53:34 +03:00
Raphael S. Carvalho
06b25320be sstables: Fix bloom filter size after resharding by properly estimating partition count
We were feeding the total estimation partition count of an input shared
sstable to the output unshared ones.

So sstable writer thinks, *from estimation*, that each sstable created
by resharding will have the same data amount as the shared sstable they
are being created from. That's a problem because estimation is feeded to
bloom filter creation which directly influences its size.
So if we're resharding all sstables that belong to all shards, the
disk usage taken by filter components will be multiplied by the number
of shards. That becomes more of a problem with #3302.

Partition count estimation for a shard S will now be done as follow:
    //
    // TE, the total estimated partition count for a shard S, is defined as
    // TE = Sum(i = 0...N) { Ei / Si }.
    //
    // where i is an input sstable that belongs to shard S,
    //       Ei is the estimated partition count for sstable i,
    //       Si is the total number of shards that own sstable i.

Fixes #2672.
Refs #3302.

Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Message-Id: <20180423151001.9995-1-raphaelsc@scylladb.com>
(cherry picked from commit 11940ca39e)
2018-04-24 12:53:34 +03:00
Takuya ASADA
ff70d9f15c dist: Drop AmbientCapabilities from scylla-server.service for Debian 8
Debian 8 causes "Invalid argument" when we used AmbientCapabilities on systemd
unit file, so drop the line when we build .deb package for Debian 8.
For other distributions, keep using the feature.

Fixes #3344

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <20180423102041.2138-1-syuu@scylladb.com>
(cherry picked from commit 7b92c3fd3f)
2018-04-24 12:53:34 +03:00
Avi Kivity
9bbd5821a2 Update scylla-ami submodule
* dist/ami/files/scylla-ami 9b4be70...02b1853 (1):
  > scylla_install_ami: remove the host id file after scylla_setup
2018-04-24 12:53:34 +03:00
Avi Kivity
a7841f1f2e release: prepare for 2.2.rc0 2018-04-18 11:08:43 +03:00
Takuya ASADA
84859e0745 dist/debian: use ~root as HOME to place .pbuilderrc
When 'always_set_home' is specified on /etc/sudoers pbuilder won't read
.pbuilderrc from current user home directory, and we don't have a way to change
the behavor from sudo command parameter.

So let's use ~root/.pbuilderrc and switch to HOME=/root when sudo executed,
this can work both environment which does specified always_set_home and doesn't
specified.

Fixes #3366

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1523926024-3937-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit ace44784e8)
2018-04-17 09:38:43 +03:00
Avi Kivity
6b74e1f02d Update seastar submodule
* seastar bcfbe0c...491f994 (3):
  > tls: Ensure we always pass through semaphores on shutdown
  > cpu scheduler: don't penalize first group to run
  > reactor: fix sleep mode

Fixes #3350.
2018-04-14 20:44:11 +03:00
Avi Kivity
520f17b315 Point seastar submodule at scylla-seastar.git
This allows backporting seastar patches.
2018-04-14 20:43:28 +03:00
Gleb Natapov
9fe3d04f31 cql_server: fix a race between closing of a connection and notifier registration
There is a race between cql connection closure and notifier
registration. If a connection is closed before notification registration
is complete stale pointer to the connection will remain in notification
list since attempt to unregister the connection will happen to early.
The fix is to move notifier unregisteration after connection's gate
is closed which will ensure that there is no outstanding registration
request. But this means that now a connection with closed gate can be in
notifier list, so with_gate() may throw and abort a notifier loop. Fix
that by replacing with_gate() by call to is_closed();

Fixes: #3355
Tests: unit(release)

Message-Id: <20180412134744.GB22593@scylladb.com>
(cherry picked from commit 1a9aaece3e)
2018-04-12 16:57:07 +03:00
Raphael S. Carvalho
a74183eb1e sstables/compaction_manager: do not break lcs invariant by not allowing parallel compaction for it
After change to serialize compaction on compaction weight (eff62bc61e),
LCS invariant may break because parallel compaction can start, and it's
not currently supported for LCS.

The condition is that weight is deregistered right before last sstable
for a leveled compaction is sealed, so it may happen that a new compaction
starts for the same column family meanwhile that will promote a sstable to
an overlapping token range.

That leads to strategy restoring invariant when it finds the overlapping,
and that means wasted resources.
The fix is about removing a fast path check which is incorrect now because
we release weight early and also fixing a check for ongoing compaction
which prevented compaction from starting for LCS whenever weight tracker
was not empty.

Fixes #3279.

Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Message-Id: <20180410034538.30486-1-raphaelsc@scylladb.com>
(cherry picked from commit 638a647b7d)
2018-04-10 20:59:48 +03:00
Raphael S. Carvalho
e059f17bf2 database: make sure sstable is also forwarded to shard responsible for its generation
After f59f423f3c, sstable is loaded only at shards
that own it so as to reduce the sstable load overhead.

The problem is that a sstable may no longer be forwarded to a shard that needs to
be aware of its existence which would result in that sstable generation being
reallocated for a write request.
That would result in a failure as follow:
"SSTable write failed due to existence of TOC file for generation..."

This can be fixed by forwarding any sstable at load to all its owner shards
*and* the shard responsible for its generation, which is determined as follow:
s = generation % smp::count

Fixes #3273.

Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Message-Id: <20180405035245.30194-1-raphaelsc@scylladb.com>
(cherry picked from commit 30b6c9b4cd)
2018-04-05 10:58:29 +03:00
Duarte Nunes
0e8e005357 db/view: Reject view entries with non-composite, empty partition key
Empty partition keys are not supported on normal tables - they cannot
be inserted or queried (surprisingly, the rules for composite
partition keys are different: all components are then allowed to be
empty). However, the (non-composite) partition key of a view could end
up being empty if that column is: a base table regular column, a
base table clustering key column, or a base table partition key column,
part of a composite key.

Fixes #3262
Refs CASSANDRA-14345

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20180403122244.10626-1-duarte@scylladb.com>
(cherry picked from commit ec8960df45)
2018-04-03 17:20:33 +03:00
Glauber Costa
8bf6f39392 docker: default docker to overprovisioned mode.
By default, overprovisioned is not enabled on docker unless it is
explicitly set. I have come to believe that this is a mistake.

If the user is running alone in the machine, and there are no other
processes pinned anywhere - including interrupts - not running
overprovisioned is the best choice.

But everywhere else, it is not: even if a user runs 2 docker containers
in the same machine and statically partitions CPUs with --smp (but
without cpuset) the docker containers will pin themselves to the same
sets of CPU, as they are totally unaware of each other.

It is also very common, specially in some virtualized environments, for
interrupts not to be properly distributed - being particularly keen on
being delivered on CPU0, a CPU which Scylla will pin by default.

Lastly, environments like Kubernetes simply don't support pinning at the
moment.

This patch enables the overprovisioned flag if it is explicitly set -
like we did before - but also by default unless --cpuset is set.

Fixes #3336.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
Message-Id: <20180331142131.842-1-glauber@scylladb.com>
(cherry picked from commit ef84780c27)
2018-04-02 17:07:20 +03:00
Glauber Costa
04ba51986e parse and ignore background writer controller
Unused options are not exposed as command line options and will prevent
Scylla from booting when present, although they can still be pased over
YAML, for Cassandra compatibility.

That has never been a problem, but we have been adding options to i3
(and others) that are now deprecated, but were previously marked as
Used. Systems with those options may have issues upgrading.

While this problem is common to all Unused options, the likelihood for
any other unused option to appear in the command line is near zero,
except for those two - since we put them there ourselves.

There are two ways to handle this issue:

1) Mark them as Used, and just ignore them.
2) Add them explicitly to boost program options, and then ignore them.

The second option is preferred here, because we can add them as hidden
options in program_options, meaning they won't show up in the help. We
can then just print a discrete message saying that those options are,
for now on ignored.

v2: mark set as const (Botond)
v3: rebase on top of master, identation suggested by Duarte.

Signed-off-by: Glauber Costa <glauber@scylladb.com>
Message-Id: <20180329145517.8462-1-glauber@scylladb.com>
(cherry picked from commit a9ef72537f)
2018-03-29 17:57:43 +03:00
Asias He
1d5379c462 gossip: Relax generation max difference check
start node 1 2 3
shutdown node2
shutdown node1 and node3
start node1 and node3
nodetool removenode node2
clean up all scylla data on node2
bootstrap node2 as a new node

I saw node2 could not bootstrap stuck at waiting for schema information to compelte for ever:

On node1, node3

    [shard 0] gossip - received an invalid gossip generation for peer 127.0.0.2; local generation = 2, received generation = 1521779704

On node2

    [shard 0] storage_service - JOINING: waiting for schema information to complete

This is becasue in nodetool removenode operation, the generation of node1 was increased from 0 to 2.

   gossiper::advertise_removing () calls eps.get_heart_beat_state().force_newer_generation_unsafe();
   gossiper::advertise_token_removed() calls eps.get_heart_beat_state().force_newer_generation_unsafe();

Each force_newer_generation_unsafe increases the generation by 1.

Here is an example,

Before nodetool removenode:
```
curl -X GET --header "Accept: application/json" "http://127.0.0.1:10000/failure_detector/endpoints/" | python -mjson.tool
   {
   "addrs": "127.0.0.2",
   "generation": 0,
   "is_alive": false,
   "update_time": 1521778757334,
   "version": 0
   },
```

After nodetool revmoenode:
```
curl -X GET --header "Accept: application/json" "http://127.0.0.1:10000/failure_detector/endpoints/" | python -mjson.tool
 {
     "addrs": "127.0.0.2",
     "application_state": [
         {
             "application_state": 0,
             "value": "removed,146b52d5-dc94-4e35-b7d4-4f64be0d2672,1522038476246",
             "version": 214
         },
         {
             "application_state": 6,
             "value": "REMOVER,14ecc9b0-4b88-4ff3-9c96-38505fb4968a",
             "version": 153
            }
     ],
     "generation": 2,
     "is_alive": false,
     "update_time": 1521779276246,
     "version": 0
 },
```

In gossiper::apply_state_locally, we have this check:

```
if (local_generation != 0 && remote_generation > local_generation + MAX_GENERATION_DIFFERENCE) {
    // assume some peer has corrupted memory and is broadcasting an unbelievable generation about another peer (or itself)
  logger.warn("received an invalid gossip generation for peer {}; local generation = {}, received generation = {}",ep, local_generation, remote_generation);

}
```
to skip the gossip update.

To fix, we relax generation max difference check to allow the generation
of a removed node.

After this patch, the removed node bootstraps successfully.

Tests: dtest:update_cluster_layout_tests.py
Fixes #3331

Message-Id: <678fb60f6b370d3ca050c768f705a8f2fd4b1287.1522289822.git.asias@scylladb.com>
(cherry picked from commit f539e993d3)
2018-03-29 12:10:09 +03:00
Avi Kivity
cb5dc56bfd Update scylla-ami submodule
Ref #3332.
2018-03-29 10:35:54 +03:00
Duarte Nunes
b578b492cd column_family: Don't retry flushing memtable if shutdown is requested
Since we just keep retrying, this can cause Scylla to not shutdown for
a while.

The data will be safe in the commit log.

Note that this patch doesn't fix the issue when shutdown goes through
storage_service::drain_on_shutdown - more work is required to handle
that case.

Ref #3318.

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20180324140822.3743-3-duarte@scylladb.com>
(cherry picked from commit a985ea0fcb)
2018-03-26 15:26:56 +03:00
Duarte Nunes
30c950a7f6 column_family: Increase scope of exception handling when flushing a memtable
In column_family::try_flush_memtable_to_sstable, the handle_exception()
block is on the inside of the continuations to
write_memtable_to_sstable(), which, if it fails, will leave the
sstable in the compaction_backlog_tracker::_ongoing_writes map, which
will waste disk space, and that sstable will map to a dangling pointer
to a destroyed database_sstable_write_monitor, which causes a seg
fault when accessed (for example, through the backlog_controller,
which accounts the _ongoing_writes when calculating the backlog).

Fix this by increasing the scope of handle_exception().

Fixes #3315

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20180324140822.3743-2-duarte@scylladb.com>
(cherry picked from commit 50ad37d39b)
2018-03-26 15:26:54 +03:00
Duarte Nunes
f0d1e9c518 backlog_controller: Stop update timer
On database shutdown, this timer can cause use-after-free errors if
not stopped.

Refs #3315

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20180324140822.3743-1-duarte@scylladb.com>
(cherry picked from commit b7bd9b8058)
2018-03-26 15:26:52 +03:00
Avi Kivity
597aeca93d Merge "Bug fixes for access-control, and finalizing roles" from Jesse
"
This series does not add or change any features of access-control and
roles, but addresses some bugs and finalizes the switch to roles.

"auth: Wait for schema agreement" and the patch prior help avoid false
negatives for integration tests and error messages in logs.

"auth: Remove ordering dependence" fixes an important bug in `auth` that
could leave the default superuser in a corrupted state when it is first
created.

Since roles are feature-complete (to the best of the author's knowledge
as of this writing), the final patch in the series removes any warnings
about them being unimplemented.

Tests: unit (release), dtest (PENDING)
"

* 'jhk/auth_fixes/v1' of https://github.com/hakuch/scylla:
  Roles are implemented
  auth: Increase delay before background tasks start
  auth: Remove ordering dependence
  auth: Don't warn on rescheduled task
  auth: Wait for schema agreement
  Single-node clusters can agree on schema

(cherry picked from commit 999df41a49)
2018-03-26 12:37:41 +03:00
Duarte Nunes
1a94b90a4d Merge 'Grant default permissions' from Jesse
The functional change in this series is in the last patch
("auth: Grant all permissions to object creator").

The first patch addresses `const` correctness in `auth`. This change
allowed the new code added in the last patch to be written with the
correct `const` specifiers, and also some code to be removed.

The second-to-last patch addresses error-handling in the authorizer for
unsupported operations and is a prerequisite for the last patch (since
we now always grant permissions for new database objects).

Tests: unit (release)

* 'jhk/default_permissions/v3' of https://github.com/hakuch/scylla:
  auth: Grant all permissions to object creator
  auth: Unify handling for unsupported errors
  auth: Fix life-time issue with parameter
  auth: Fix `const` correctness

(cherry picked from commit 934d805b4b)
2018-03-26 12:37:35 +03:00
Avi Kivity
acdd42c7c8 Merge "Fix abort during counter table read-on-delete" from Tomasz
"
This fixes an abort in an sstable reader when querying a partition with no
clustering ranges (happens on counter table mutation with no live rows) which
also doesn't have any static columns. In such case, the
sstable_mutation_reader will setup the data_consume_context such that it only
covers the static row of the partition, knowing that there is no need to read
any clustered rows. See partition.cc::advance_to_upper_bound(). Later when
the reader is done with the range for the static row, it will try to skip to
the first clustering range (missing in this case). If clustering_ranges_walker
tells us to skip to after_all_clustering_rows(), we will hit an assert inside
continuous_data_consumer::fast_forward_to() due to attempt to skip past the
original data file range. If clustering_ranges_walker returns
before_all_clustering_rows() instead, all is fine because we're still at the
same data file position.

Fixes #3304.
"

* 'tgrabiec/fix-counter-read-no-static-columns' of github.com:scylladb/seastar-dev:
  tests: mutation_source_test: Test reads with no clustering ranges and no static columns
  tests: simple_schema: Allow creating schema with no static column
  clustering_ranges_walker: Stop after static row in case no clustering ranges

(cherry picked from commit 054854839a)
2018-03-22 18:13:29 +02:00
Takuya ASADA
bd4f658555 scripts/scylla_install_pkg: follow redirection of specified repo URL
We should follow redirection on curl, just like normal web browser does.
Fixes #3312

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1521712056-301-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit bef08087e1)
2018-03-22 12:56:58 +02:00
Vladimir Krivopalov
a983ba7aad perf_fast_forward: fix error in date formatting
Instead of 'month', 'minutes' has been used.

Signed-off-by: Vladimir Krivopalov <vladimir@scylladb.com>
Message-Id: <1e005ecaa992d8205ca44ea4eebbca4621ad9886.1521659341.git.vladimir@scylladb.com>
(cherry picked from commit 3010b637c9)
2018-03-22 12:56:56 +02:00
Duarte Nunes
0a561fc326 gms/gossiper: Synchronize endpoint state destruction
In gossiper::handle_major_state_change() we set the endpoint_state for
a particular endpoint and replicate the changes to other cores.

This is totally unsynchronized with the execution of
gossiper::evict_from_membership(), which can happen concurrently, and
can remove the very same endpoint from the map  (in all cores).

Replicating the changes to other cores in handle_major_state_change()
can interleave with replicating the changes to other cores in
evict_from_membership(), and result in an undefined final state.

Another issue happened in debug mode dtests, where a fiber executes
handle_major_state_change(), calls into the subscribers, of which
storage_service is one, and ultimately lands on
storage_service::update_peer_info(), which iterates over the
endpoint's application state with deferring points in between (to
update a system table). gossiper::evict_from_membership() was executed
concurrently by another fiber, which freed the state the first one is
iterating over.

Fixes #3299.

Signed-off-by: Duarte Nunes <duarte@scylladb.com>
Message-Id: <20180318123211.3366-1-duarte@scylladb.com>
(cherry picked from commit 810db425a5)
2018-03-18 14:54:54 +02:00
Takuya ASADA
1f10549056 dist/redhat: build only scylla, iotune
Since we don't package tests, we don't need to build them.
It reduces package building time.

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1521066363-4859-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit 1bb3531b90)
2018-03-15 10:48:36 +02:00
Takuya ASADA
c2a2560ea3 dist/debian: use 3rdparty ppa on Ubuntu 18.04
Currently Ubuntu 18.04 uses distribution provided g++ and boost, but it's easier
to maintain Scylla package to build with same version toolchain/libraries, so
switch to them.

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1521075576-12064-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit 945e6ec4f6)
2018-03-15 10:48:31 +02:00
Takuya ASADA
237e36a0b4 dist/ami: update CentOS base image to latest version
Since we requires updated version of systemd, we need to update CentOS base
image.

Fixes #3184

Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1518118694-23770-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit 69d226625a)
2018-03-15 10:47:54 +02:00
Takuya ASADA
e78c137bfc dist/redhat: switch to gcc-7.3
We have hit following bug on debug-mode binary:
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82560
Since it's fixed on gcc-7.3, we need to upgrade our gcc package.

See: https://groups.google.com/d/topic/scylladb-dev/RIdIpqMeTog/discussion
Signed-off-by: Takuya ASADA <syuu@scylladb.com>
Message-Id: <1521064473-17906-1-git-send-email-syuu@scylladb.com>
(cherry picked from commit 856dc0a636)
2018-03-15 10:39:40 +02:00
Avi Kivity
fb99a7c902 Merge "Ubuntu/Debian build error fixes" from Takuya
* 'debian-ubuntu-build-fixes-v2' of https://github.com/syuu1228/scylla:
  dist/debian: build only scylla, iotune
  dist/debian: switch to boost-1.65
  dist/debian: switch to gcc-7.3

(cherry picked from commit bb4b1f0e91)
2018-03-14 22:51:44 +02:00
2083 changed files with 31684 additions and 98666 deletions

View File

@@ -1,3 +0,0 @@
.git
build
seastar/build

View File

@@ -1,9 +1,3 @@
This is Scylla's bug tracker, to be used for reporting bugs only.
If you have a question about Scylla, and not a bug, please ask it in
our mailing-list at scylladb-dev@googlegroups.com or in our slack channel.
- [] I have read the disclaimer above, and I am reporting a suspected malfunction in Scylla.
*Installation details*
Scylla version (or git commit hash):
Cluster size:

View File

@@ -1,4 +0,0 @@
Scylla doesn't use pull-requests, please send a patch to the [mailing list](mailto:scylladb-dev@googlegroups.com) instead.
See our [contributing guidelines](../CONTRIBUTING.md) and our [Scylla development guidelines](../HACKING.md) for more information.
If you have any questions please don't hesitate to send a mail to the [dev list](mailto:scylladb-dev@googlegroups.com).

1
.gitignore vendored
View File

@@ -18,4 +18,3 @@ CMakeLists.txt.user
*.egg-info
__pycache__CMakeLists.txt.user
.gdbinit
resources

6
.gitmodules vendored
View File

@@ -6,9 +6,9 @@
path = swagger-ui
url = ../scylla-swagger-ui
ignore = dirty
[submodule "dist/ami/files/scylla-ami"]
path = dist/ami/files/scylla-ami
url = ../scylla-ami
[submodule "xxHash"]
path = xxHash
url = ../xxHash
[submodule "libdeflate"]
path = libdeflate
url = ../libdeflate

View File

@@ -138,5 +138,4 @@ target_include_directories(scylla PUBLIC
${SEASTAR_INCLUDE_DIRS}
${Boost_INCLUDE_DIRS}
xxhash
libdeflate
build/release/gen)

View File

@@ -20,13 +20,11 @@ $ git submodule update --init --recursive
Scylla depends on the system package manager for its development dependencies.
Running `./install-dependencies.sh` (as root) installs the appropriate packages based on your Linux distribution.
Running `./install_dependencies.sh` (as root) installs the appropriate packages based on your Linux distribution.
### Build system
**Note**: Compiling Scylla requires, conservatively, 2 GB of memory per native
thread, and up to 3 GB per native thread while linking. GCC >= 8.1.1. is
required.
**Note**: Compiling Scylla requires, conservatively, 2 GB of memory per native thread, and up to 3 GB per native thread while linking.
Scylla is built with [Ninja](https://ninja-build.org/), a low-level rule-based system. A Python script, `configure.py`, generates a Ninja file (`build.ninja`) based on configuration options.
@@ -45,7 +43,9 @@ The full suite of options for project configuration is available via
$ ./configure.py --help
```
The most important option is:
The most important options are:
- `--mode={release,debug,all}`: Debug mode enables [AddressSanitizer](https://github.com/google/sanitizers/wiki/AddressSanitizer) and allows for debugging with tools like GDB. Debugging builds are generally slower and generate much larger object files than release builds.
- `--{enable,disable}-dpdk`: [DPDK](http://dpdk.org/) is a set of libraries and drivers for fast packet processing. During development, it's not necessary to enable support even if it is supported by your platform.
@@ -57,29 +57,6 @@ To save time -- for instance, to avoid compiling all unit tests -- you can also
$ ninja-build build/release/tests/schema_change_test
```
You can also specify a single mode. For example
```bash
$ ninja-build release
```
Will build everytihng in release mode. The valid modes are
* Debug: Enables [AddressSanitizer](https://github.com/google/sanitizers/wiki/AddressSanitizer)
and other sanity checks. It has no optimizations, which allows for debugging with tools like
GDB. Debugging builds are generally slower and generate much larger object files than release builds.
* Release: Fewer checks and more optimizations. It still has debug info.
* Dev: No optimizations or debug info. The objective is to compile and link as fast as possible.
This is useful for the first iterations of a patch.
Note that by default unit tests binaries are stripped so they can't be used with gdb or seastar-addr2line.
To include debug information in the unit test binary, build the test binary with a `_g` suffix. For example,
```bash
$ ninja-build build/release/tests/schema_change_test_g
```
### Unit testing
Unit tests live in the `/tests` directory. Like with application source files, test sources and executables are specified manually in `configure.py` and need to be updated when changes are made.
@@ -106,7 +83,7 @@ The `-c1 -m1G` arguments limit this Seastar-based test to a single system thread
### Preparing patches
All changes to Scylla are submitted as patches to the public [mailing list](mailto:scylladb-dev@googlegroups.com). Once a patch is approved by one of the maintainers of the project, it is committed to the maintainers' copy of the repository at https://github.com/scylladb/scylla.
All changes to Scylla are submitted as patches to the public mailing list. Once a patch is approved by one of the maintainers of the project, it is committed to the maintainers' copy of the repository at https://github.com/scylladb/scylla.
Detailed instructions for formatting patches for the mailing list and advice on preparing good patches are available at the [ScyllaDB website](http://docs.scylladb.com/contribute/). There are also some guidelines that can help you make the patch review process smoother:
@@ -135,8 +112,6 @@ The usual is "Tests: unit (release)", although running debug tests is encouraged
5. When answering review comments, prefer inline quotes as they make it easier to track the conversation across multiple e-mails.
6. The Linux kernel's [Submitting Patches](https://www.kernel.org/doc/html/v4.19/process/submitting-patches.html) document offers excellent advice on how to prepare patches and patchsets for review. Since the Scylla development process is derived from the kernel's, almost all of the advice there is directly applicable.
### Finding a person to review and merge your patches
You can use the `scripts/find-maintainer` script to find a subsystem maintainer and/or reviewer for your patches. The script accepts a filename in the git source tree as an argument and outputs a list of subsystems the file belongs to and their respective maintainers and reviewers. For example, if you changed the `cql3/statements/create_view_statement.hh` file, run the script as follows:
@@ -189,29 +164,6 @@ On a development machine, one might run Scylla as
$ SCYLLA_HOME=$HOME/scylla build/release/scylla --overprovisioned --developer-mode=yes
```
To interact with scylla it is recommended to build our versions of
cqlsh and nodetool. They are available at
https://github.com/scylladb/scylla-tools-java and can be built with
```bash
$ ./install-dependencies.sh
$ ant jar
```
cqlsh should work out of the box, but nodetool depends on a running
scylla-jmx (https://github.com/scylladb/scylla-jmx). It can be build
with
```bash
$ mvn package
```
and must be started with
```bash
$ ./scripts/scylla-jmx
```
### Branches and tags
Multiple release branches are maintained on the Git repository at https://github.com/scylladb/scylla. Release 1.5, for instance, is tracked on the `branch-1.5` branch.
@@ -302,7 +254,7 @@ In this example, `10.0.0.2` will be sent up to 16 jobs and the local machine wil
When a compilation is in progress, the status of jobs on all remote machines can be visualized in the terminal with `distccmon-text` or graphically as a GTK application with `distccmon-gnome`.
One thing to keep in mind is that linking object files happens on the coordinating machine, which can be a bottleneck. See the next sections speeding up this process.
One thing to keep in mind is that linking object files happens on the coordinating machine, which can be a bottleneck. See the next section speeding up this process.
### Using the `gold` linker
@@ -312,24 +264,6 @@ Linking Scylla can be slow. The gold linker can replace GNU ld and often speeds
$ sudo alternatives --config ld
```
### Using split dwarf
With debug info enabled, most of the link time is spent copying and
relocating it. It is possible to leave most of the debug info out of
the link by writing it to a side .dwo file. This is done by passing
`-gsplit-dwarf` to gcc.
Unfortunately just `-gsplit-dwarf` would slow down `gdb` startup. To
avoid that the gold linker can be told to create an index with
`--gdb-index`.
More info at https://gcc.gnu.org/wiki/DebugFission.
Both options can be enable by passing `--split-dwarf` to configure.py.
Note that distcc is *not* compatible with it, but icecream
(https://github.com/icecc/icecream) is.
### Testing changes in Seastar with Scylla
Sometimes Scylla development is closely tied with a feature being developed in Seastar. It can be useful to compile Scylla with a particular check-out of Seastar.
@@ -343,8 +277,3 @@ $ git remote add local /home/tsmith/src/seastar
$ git remote update
$ git checkout -t local/my_local_seastar_branch
```
### Core dump debugging
Slides:
2018.11.20: https://www.slideshare.net/tomekgrabiec/scylla-core-dump-debugging-tools

View File

@@ -13,11 +13,6 @@ $ # Rejoice!
Please see [HACKING.md](HACKING.md) for detailed information on building and developing Scylla.
**Note**: GCC >= 8.1.1 is require to compile Scylla.
**Note**: See [frozen toolchain](tools/toolchain/README.md) for a way to build and run
on an older distribution.
## Running Scylla
* Run Scylla

View File

@@ -1,7 +1,6 @@
#!/bin/sh
PRODUCT=scylla
VERSION=3.1.4
VERSION=2.2.2
if test -f version
then
@@ -23,4 +22,3 @@ echo "$SCYLLA_VERSION-$SCYLLA_RELEASE"
mkdir -p build
echo "$SCYLLA_VERSION" > build/SCYLLA-VERSION-FILE
echo "$SCYLLA_RELEASE" > build/SCYLLA-RELEASE-FILE
echo "$PRODUCT" > build/SCYLLA-PRODUCT-FILE

View File

@@ -455,7 +455,7 @@
"operations":[
{
"method":"GET",
"summary":"Returns a list of sstable filenames that contain the given partition key on this node",
"summary":"Returns a list of filenames that contain the given key on this node",
"type":"array",
"items":{
"type":"string"
@@ -475,7 +475,7 @@
},
{
"name":"key",
"description":"The partition key. In a composite-key scenario, use ':' to separate the columns in the key.",
"description":"The key",
"required":true,
"allowMultiple":false,
"type":"string",
@@ -611,54 +611,6 @@
}
]
},
{
"path":"/column_family/toppartitions/{name}",
"operations":[
{
"method":"GET",
"summary":"Toppartitions query",
"type":"toppartitions_query_results",
"nickname":"toppartitions",
"produces":[
"application/json"
],
"parameters":[
{
"name":"name",
"description":"The column family name in keyspace:name format",
"required":true,
"allowMultiple":false,
"type":"string",
"paramType":"path"
},
{
"name":"duration",
"description":"Duration (in milliseconds) of monitoring operation",
"required":true,
"allowMultiple":false,
"type":"int",
"paramType":"query"
},
{
"name":"list_size",
"description":"number of the top partitions to list",
"required":false,
"allowMultiple":false,
"type":"int",
"paramType":"query"
},
{
"name":"capacity",
"description":"capacity of stream summary: determines amount of resources used in query processing",
"required":false,
"allowMultiple":false,
"type":"int",
"paramType":"query"
}
]
}
]
},
{
"path":"/column_family/metrics/memtable_columns_count/",
"operations":[
@@ -2864,44 +2816,6 @@
"description":"The column family type"
}
}
},
"toppartitions_record":{
"id":"toppartitions_record",
"description":"nodetool toppartitions query record",
"properties":{
"partition":{
"type":"string",
"description":"Partition key"
},
"count":{
"type":"long",
"description":"Number of read/write operations"
},
"error":{
"type":"long",
"description":"Indication of inaccuracy in counting PKs"
}
}
},
"toppartitions_query_results":{
"id":"toppartitions_query_results",
"description":"nodetool toppartitions query results",
"properties":{
"read":{
"type":"array",
"items":{
"type":"toppartitions_record"
},
"description":"Read results"
},
"write":{
"type":"array",
"items":{
"type":"toppartitions_record"
},
"description":"Write results"
}
}
}
}
}

View File

@@ -1,30 +0,0 @@
"/v2/config/{id}": {
"get": {
"description": "Return a config value",
"operationId": "find_config_id",
"produces": [
"application/json"
],
"tags": ["config"],
"parameters": [
{
"name": "id",
"in": "path",
"description": "ID of config to return",
"required": true,
"type": "string"
}
],
"responses": {
"200": {
"description": "Config value"
},
"default": {
"description": "unexpected error",
"schema": {
"$ref": "#/definitions/ErrorModel"
}
}
}
}
}

View File

@@ -2129,41 +2129,6 @@
]
}
]
},
{
"path":"/storage_service/view_build_statuses/{keyspace}/{view}",
"operations":[
{
"method":"GET",
"summary":"Gets the progress of a materialized view build",
"type":"array",
"items":{
"type":"mapper"
},
"nickname":"view_build_statuses",
"produces":[
"application/json"
],
"parameters":[
{
"name":"keyspace",
"description":"The keyspace",
"required":true,
"allowMultiple":false,
"type":"string",
"paramType":"path"
},
{
"name":"view",
"description":"View name",
"required":true,
"allowMultiple":false,
"type":"string",
"paramType":"path"
}
]
}
]
}
],
"models":{

View File

@@ -20,9 +20,9 @@
*/
#include "api.hh"
#include <seastar/http/file_handler.hh>
#include <seastar/http/transformers.hh>
#include <seastar/http/api_docs.hh>
#include "http/file_handler.hh"
#include "http/transformers.hh"
#include "http/api_docs.hh"
#include "storage_service.hh"
#include "commitlog.hh"
#include "gossiper.hh"
@@ -36,12 +36,9 @@
#include "endpoint_snitch.hh"
#include "compaction_manager.hh"
#include "hinted_handoff.hh"
#include <seastar/http/exception.hh>
#include "http/exception.hh"
#include "stream_manager.hh"
#include "system.hh"
#include "api/config.hh"
logging::logger apilog("api");
namespace api {
@@ -68,7 +65,6 @@ future<> set_server_init(http_context& ctx) {
rb->set_api_doc(r);
rb02->set_api_doc(r);
rb02->register_api_file(r, "swagger20_header");
set_config(rb02, ctx, r);
rb->register_function(r, "system",
"The system related API");
set_system(ctx, r);

View File

@@ -21,15 +21,13 @@
#pragma once
#include <seastar/json/json_elements.hh>
#include <type_traits>
#include "json/json_elements.hh"
#include <boost/lexical_cast.hpp>
#include <boost/algorithm/string/split.hpp>
#include <boost/algorithm/string/classification.hpp>
#include <boost/units/detail/utility.hpp>
#include "api/api-doc/utils.json.hh"
#include "utils/histogram.hh"
#include <seastar/http/exception.hh>
#include "http/exception.hh"
#include "api_init.hh"
#include "seastarx.hh"
@@ -218,42 +216,4 @@ std::vector<T> concat(std::vector<T> a, std::vector<T>&& b) {
return a;
}
template <class T, class Base = T>
class req_param {
public:
sstring name;
sstring param;
T value;
req_param(const request& req, sstring name, T default_val) : name(name) {
param = req.get_query_param(name);
if (param.empty()) {
value = default_val;
return;
}
try {
// boost::lexical_cast does not use boolalpha. Converting a
// true/false throws exceptions. We don't want that.
if constexpr (std::is_same_v<Base, bool>) {
// Cannot use boolalpha because we (probably) want to
// accept 1 and 0 as well as true and false. And True. And fAlse.
std::transform(param.begin(), param.end(), param.begin(), ::tolower);
if (param == "true" || param == "1") {
value = T(true);
} else if (param == "false" || param == "0") {
value = T(false);
} else {
throw boost::bad_lexical_cast{};
}
} else {
value = T{boost::lexical_cast<Base>(param)};
}
} catch (boost::bad_lexical_cast&) {
throw bad_param_exception(format("{} ({}): type error - should be {}", name, param, boost::units::detail::demangle(typeid(Base).name())));
}
}
operator T() const { return value; }
};
}

View File

@@ -19,9 +19,9 @@
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include "database_fwd.hh"
#include "database.hh"
#include "service/storage_proxy.hh"
#include <seastar/http/httpd.hh>
#include "http/httpd.hh"
namespace api {

View File

@@ -21,8 +21,8 @@
#include "collectd.hh"
#include "api/api-doc/collectd.json.hh"
#include <seastar/core/scollectd.hh>
#include <seastar/core/scollectd_api.hh>
#include "core/scollectd.hh"
#include "core/scollectd_api.hh"
#include "endian.h"
#include <boost/range/irange.hpp>
#include <regex>

View File

@@ -22,15 +22,11 @@
#include "column_family.hh"
#include "api/api-doc/column_family.json.hh"
#include <vector>
#include <seastar/http/exception.hh>
#include "http/exception.hh"
#include "sstables/sstables.hh"
#include "utils/estimated_histogram.hh"
#include <algorithm>
#include "db/data_listeners.hh"
extern logging::logger apilog;
namespace api {
using namespace httpd;
@@ -38,7 +34,7 @@ using namespace std;
using namespace json;
namespace cf = httpd::column_family_json;
std::tuple<sstring, sstring> parse_fully_qualified_cf_name(sstring name) {
const utils::UUID& get_uuid(const sstring& name, const database& db) {
auto pos = name.find("%3A");
size_t end;
if (pos == sstring::npos) {
@@ -50,15 +46,11 @@ std::tuple<sstring, sstring> parse_fully_qualified_cf_name(sstring name) {
} else {
end = pos + 3;
}
return std::make_tuple(name.substr(0, pos), name.substr(end));
}
const utils::UUID& get_uuid(const sstring& name, const database& db) {
auto [ks, cf] = parse_fully_qualified_cf_name(name);
try {
return db.find_uuid(ks, cf);
return db.find_uuid(name.substr(0, pos), name.substr(end));
} catch (std::out_of_range& e) {
throw bad_param_exception(format("Column family '{}:{}' not found", ks, cf));
throw bad_param_exception("Column family '" + name.substr(0, pos) + ":"
+ name.substr(end) + "' not found");
}
}
@@ -174,27 +166,27 @@ static future<json::json_return_type> get_cf_unleveled_sstables(http_context& ct
}, std::plus<int64_t>());
}
static int64_t min_partition_size(column_family& cf) {
static int64_t min_row_size(column_family& cf) {
int64_t res = INT64_MAX;
for (auto i: *cf.get_sstables() ) {
res = std::min(res, i->get_stats_metadata().estimated_partition_size.min());
res = std::min(res, i->get_stats_metadata().estimated_row_size.min());
}
return (res == INT64_MAX) ? 0 : res;
}
static int64_t max_partition_size(column_family& cf) {
static int64_t max_row_size(column_family& cf) {
int64_t res = 0;
for (auto i: *cf.get_sstables() ) {
res = std::max(i->get_stats_metadata().estimated_partition_size.max(), res);
res = std::max(i->get_stats_metadata().estimated_row_size.max(), res);
}
return res;
}
static integral_ratio_holder mean_partition_size(column_family& cf) {
static integral_ratio_holder mean_row_size(column_family& cf) {
integral_ratio_holder res;
for (auto i: *cf.get_sstables() ) {
auto c = i->get_stats_metadata().estimated_partition_size.count();
res.sub += i->get_stats_metadata().estimated_partition_size.mean() * c;
auto c = i->get_stats_metadata().estimated_row_size.count();
res.sub += i->get_stats_metadata().estimated_row_size.mean() * c;
res.total += c;
}
return res;
@@ -411,24 +403,22 @@ void set_column_family(http_context& ctx, routes& r) {
return get_cf_stats(ctx, &column_family::stats::memtable_switch_count);
});
// FIXME: this refers to partitions, not rows.
cf::get_estimated_row_size_histogram.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
utils::estimated_histogram res(0);
for (auto i: *cf.get_sstables() ) {
res.merge(i->get_stats_metadata().estimated_partition_size);
res.merge(i->get_stats_metadata().estimated_row_size);
}
return res;
},
utils::estimated_histogram_merge, utils_json::estimated_histogram());
});
// FIXME: this refers to partitions, not rows.
cf::get_estimated_row_count.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], int64_t(0), [](column_family& cf) {
uint64_t res = 0;
for (auto i: *cf.get_sstables() ) {
res += i->get_stats_metadata().estimated_partition_size.count();
res += i->get_stats_metadata().estimated_row_size.count();
}
return res;
},
@@ -439,7 +429,7 @@ void set_column_family(http_context& ctx, routes& r) {
return map_reduce_cf(ctx, req->param["name"], utils::estimated_histogram(0), [](column_family& cf) {
utils::estimated_histogram res(0);
for (auto i: *cf.get_sstables() ) {
res.merge(i->get_stats_metadata().estimated_cells_count);
res.merge(i->get_stats_metadata().estimated_column_count);
}
return res;
},
@@ -556,36 +546,30 @@ void set_column_family(http_context& ctx, routes& r) {
return sum_sstable(ctx, true);
});
// FIXME: this refers to partitions, not rows.
cf::get_min_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], INT64_MAX, min_partition_size, min_int64);
return map_reduce_cf(ctx, req->param["name"], INT64_MAX, min_row_size, min_int64);
});
// FIXME: this refers to partitions, not rows.
cf::get_all_min_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, INT64_MAX, min_partition_size, min_int64);
return map_reduce_cf(ctx, INT64_MAX, min_row_size, min_int64);
});
// FIXME: this refers to partitions, not rows.
cf::get_max_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, req->param["name"], int64_t(0), max_partition_size, max_int64);
return map_reduce_cf(ctx, req->param["name"], int64_t(0), max_row_size, max_int64);
});
// FIXME: this refers to partitions, not rows.
cf::get_all_max_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
return map_reduce_cf(ctx, int64_t(0), max_partition_size, max_int64);
return map_reduce_cf(ctx, int64_t(0), max_row_size, max_int64);
});
// FIXME: this refers to partitions, not rows.
cf::get_mean_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
// Cassandra 3.x mean values are truncated as integrals.
return map_reduce_cf(ctx, req->param["name"], integral_ratio_holder(), mean_partition_size, std::plus<integral_ratio_holder>());
return map_reduce_cf(ctx, req->param["name"], integral_ratio_holder(), mean_row_size, std::plus<integral_ratio_holder>());
});
// FIXME: this refers to partitions, not rows.
cf::get_all_mean_row_size.set(r, [&ctx] (std::unique_ptr<request> req) {
// Cassandra 3.x mean values are truncated as integrals.
return map_reduce_cf(ctx, integral_ratio_holder(), mean_partition_size, std::plus<integral_ratio_holder>());
return map_reduce_cf(ctx, integral_ratio_holder(), mean_row_size, std::plus<integral_ratio_holder>());
});
cf::get_bloom_filter_false_positives.set(r, [&ctx] (std::unique_ptr<request> req) {
@@ -921,60 +905,5 @@ void set_column_family(http_context& ctx, routes& r) {
return make_ready_future<json::json_return_type>(res);
});
});
cf::get_sstables_for_key.set(r, [&ctx](std::unique_ptr<request> req) {
auto key = req->get_query_param("key");
auto uuid = get_uuid(req->param["name"], ctx.db.local());
return ctx.db.map_reduce0([key, uuid] (database& db) {
return db.find_column_family(uuid).get_sstables_by_partition_key(key);
}, std::unordered_set<sstring>(),
[](std::unordered_set<sstring> a, std::unordered_set<sstring>&& b) mutable {
a.insert(b.begin(),b.end());
return a;
}).then([](const std::unordered_set<sstring>& res) {
return make_ready_future<json::json_return_type>(container_to_vec(res));
});
});
cf::toppartitions.set(r, [&ctx] (std::unique_ptr<request> req) {
auto name_param = req->param["name"];
auto [ks, cf] = parse_fully_qualified_cf_name(name_param);
api::req_param<std::chrono::milliseconds, unsigned> duration{*req, "duration", 1000ms};
api::req_param<unsigned> capacity(*req, "capacity", 256);
api::req_param<unsigned> list_size(*req, "list_size", 10);
apilog.info("toppartitions query: name={} duration={} list_size={} capacity={}",
name_param, duration.param, list_size.param, capacity.param);
return seastar::do_with(db::toppartitions_query(ctx.db, ks, cf, duration.value, list_size, capacity), [&ctx](auto& q) {
return q.scatter().then([&q] {
return sleep(q.duration()).then([&q] {
return q.gather(q.capacity()).then([&q] (auto topk_results) {
apilog.debug("toppartitions query: processing results");
cf::toppartitions_query_results results;
for (auto& d: topk_results.read.top(q.list_size())) {
cf::toppartitions_record r;
r.partition = sstring(d.item);
r.count = d.count;
r.error = d.error;
results.read.push(r);
}
for (auto& d: topk_results.write.top(q.list_size())) {
cf::toppartitions_record r;
r.partition = sstring(d.item);
r.count = d.count;
r.error = d.error;
results.write.push(r);
}
return make_ready_future<json::json_return_type>(results);
});
});
});
});
});
}
}

View File

@@ -24,8 +24,6 @@
#include "api.hh"
#include "api/api-doc/column_family.json.hh"
#include "database.hh"
#include <seastar/core/future-util.hh>
#include <any>
namespace api {
@@ -39,15 +37,9 @@ template<class Mapper, class I, class Reducer>
future<I> map_reduce_cf_raw(http_context& ctx, const sstring& name, I init,
Mapper mapper, Reducer reducer) {
auto uuid = get_uuid(name, ctx.db.local());
using mapper_type = std::function<std::any (database&)>;
using reducer_type = std::function<std::any (std::any, std::any)>;
return ctx.db.map_reduce0(mapper_type([mapper, uuid](database& db) {
return I(mapper(db.find_column_family(uuid)));
}), std::any(std::move(init)), reducer_type([reducer = std::move(reducer)] (std::any a, std::any b) mutable {
return I(reducer(std::any_cast<I>(std::move(a)), std::any_cast<I>(std::move(b))));
})).then([] (std::any r) {
return std::any_cast<I>(std::move(r));
});
return ctx.db.map_reduce0([mapper, uuid](database& db) {
return mapper(db.find_column_family(uuid));
}, init, reducer);
}
@@ -59,43 +51,35 @@ future<json::json_return_type> map_reduce_cf(http_context& ctx, const sstring& n
});
}
template<class Mapper, class I, class Reducer, class Result>
future<I> map_reduce_cf_raw(http_context& ctx, const sstring& name, I init,
Mapper mapper, Reducer reducer, Result result) {
auto uuid = get_uuid(name, ctx.db.local());
return ctx.db.map_reduce0([mapper, uuid](database& db) {
return mapper(db.find_column_family(uuid));
}, init, reducer);
}
template<class Mapper, class I, class Reducer, class Result>
future<json::json_return_type> map_reduce_cf(http_context& ctx, const sstring& name, I init,
Mapper mapper, Reducer reducer, Result result) {
return map_reduce_cf_raw(ctx, name, init, mapper, reducer).then([result](const I& res) mutable {
return map_reduce_cf_raw(ctx, name, init, mapper, reducer, result).then([result](const I& res) mutable {
result = res;
return make_ready_future<json::json_return_type>(result);
});
}
struct map_reduce_column_families_locally {
std::any init;
std::function<std::any (column_family&)> mapper;
std::function<std::any (std::any, std::any)> reducer;
future<std::any> operator()(database& db) const {
auto res = seastar::make_lw_shared<std::any>(init);
return do_for_each(db.get_column_families(), [res, this](const std::pair<utils::UUID, seastar::lw_shared_ptr<table>>& i) {
*res = reducer(*res.get(), mapper(*i.second.get()));
}).then([res] {
return *res;
});
}
};
template<class Mapper, class I, class Reducer>
future<I> map_reduce_cf_raw(http_context& ctx, I init,
Mapper mapper, Reducer reducer) {
using mapper_type = std::function<std::any (column_family&)>;
using reducer_type = std::function<std::any (std::any, std::any)>;
auto wrapped_mapper = mapper_type([mapper = std::move(mapper)] (column_family& cf) mutable {
return I(mapper(cf));
});
auto wrapped_reducer = reducer_type([reducer = std::move(reducer)] (std::any a, std::any b) mutable {
return I(reducer(std::any_cast<I>(std::move(a)), std::any_cast<I>(std::move(b))));
});
return ctx.db.map_reduce0(map_reduce_column_families_locally{init, std::move(wrapped_mapper), wrapped_reducer}, std::any(init), wrapped_reducer).then([] (std::any res) {
return std::any_cast<I>(std::move(res));
});
return ctx.db.map_reduce0([mapper, init, reducer](database& db) {
auto res = init;
for (auto i : db.get_column_families()) {
res = reducer(res, mapper(*i.second.get()));
}
return res;
}, init, reducer);
}

View File

@@ -22,16 +22,15 @@
#include "commitlog.hh"
#include <db/commitlog/commitlog.hh>
#include "api/api-doc/commitlog.json.hh"
#include "database.hh"
#include <vector>
namespace api {
template<typename T>
static auto acquire_cl_metric(http_context& ctx, std::function<T (db::commitlog*)> func) {
typedef T ret_type;
template<typename Func>
static auto acquire_cl_metric(http_context& ctx, Func&& func) {
typedef std::result_of_t<Func(db::commitlog *)> ret_type;
return ctx.db.map_reduce0([func = std::move(func)](database& db) {
return ctx.db.map_reduce0([func = std::forward<Func>(func)](database& db) {
if (db.commitlog() == nullptr) {
return make_ready_future<ret_type>();
}
@@ -64,15 +63,15 @@ void set_commitlog(http_context& ctx, routes& r) {
});
httpd::commitlog_json::get_completed_tasks.set(r, [&ctx](std::unique_ptr<request> req) {
return acquire_cl_metric<uint64_t>(ctx, std::bind(&db::commitlog::get_completed_tasks, std::placeholders::_1));
return acquire_cl_metric(ctx, std::bind(&db::commitlog::get_completed_tasks, std::placeholders::_1));
});
httpd::commitlog_json::get_pending_tasks.set(r, [&ctx](std::unique_ptr<request> req) {
return acquire_cl_metric<uint64_t>(ctx, std::bind(&db::commitlog::get_pending_tasks, std::placeholders::_1));
return acquire_cl_metric(ctx, std::bind(&db::commitlog::get_pending_tasks, std::placeholders::_1));
});
httpd::commitlog_json::get_total_commit_log_size.set(r, [&ctx](std::unique_ptr<request> req) {
return acquire_cl_metric<uint64_t>(ctx, std::bind(&db::commitlog::get_total_size, std::placeholders::_1));
return acquire_cl_metric(ctx, std::bind(&db::commitlog::get_total_size, std::placeholders::_1));
});
}

View File

@@ -47,8 +47,8 @@ void set_compaction_manager(http_context& ctx, routes& r) {
for (const auto& c : cm.get_compactions()) {
cm::summary s;
s.ks = c->ks_name;
s.cf = c->cf_name;
s.ks = c->ks;
s.cf = c->cf;
s.unit = "keys";
s.task_type = sstables::compaction_name(c->type);
s.completed = c->total_keys_written;
@@ -103,37 +103,29 @@ void set_compaction_manager(http_context& ctx, routes& r) {
});
cm::get_compaction_history.set(r, [] (std::unique_ptr<request> req) {
std::function<future<>(output_stream<char>&&)> f = [](output_stream<char>&& s) {
return do_with(output_stream<char>(std::move(s)), true, [] (output_stream<char>& s, bool& first){
return s.write("[").then([&s, &first] {
return db::system_keyspace::get_compaction_history([&s, &first](const db::system_keyspace::compaction_history_entry& entry) mutable {
cm::history h;
h.id = entry.id.to_sstring();
h.ks = std::move(entry.ks);
h.cf = std::move(entry.cf);
h.compacted_at = entry.compacted_at;
h.bytes_in = entry.bytes_in;
h.bytes_out = entry.bytes_out;
for (auto it : entry.rows_merged) {
httpd::compaction_manager_json::row_merged e;
e.key = it.first;
e.value = it.second;
h.rows_merged.push(std::move(e));
}
auto fut = first ? make_ready_future<>() : s.write(", ");
first = false;
return fut.then([&s, h = std::move(h)] {
return formatter::write(s, h);
});
}).then([&s] {
return s.write("]").then([&s] {
return s.close();
});
});
});
});
};
return make_ready_future<json::json_return_type>(std::move(f));
return db::system_keyspace::get_compaction_history().then([] (std::vector<db::system_keyspace::compaction_history_entry> history) {
std::vector<cm::history> res;
res.reserve(history.size());
for (auto& entry : history) {
cm::history h;
h.id = entry.id.to_sstring();
h.ks = std::move(entry.ks);
h.cf = std::move(entry.cf);
h.compacted_at = entry.compacted_at;
h.bytes_in = entry.bytes_in;
h.bytes_out = entry.bytes_out;
for (auto it : entry.rows_merged) {
httpd::compaction_manager_json::row_merged e;
e.key = it.first;
e.value = it.second;
h.rows_merged.push(std::move(e));
}
res.push_back(std::move(h));
}
return make_ready_future<json::json_return_type>(res);
});
});
cm::get_compaction_info.set(r, [] (std::unique_ptr<request> req) {

View File

@@ -1,113 +0,0 @@
/*
* Copyright 2018 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "api/config.hh"
#include "api/api-doc/config.json.hh"
#include "db/config.hh"
#include "database.hh"
#include <sstream>
#include <boost/algorithm/string/replace.hpp>
namespace api {
template<class T>
json::json_return_type get_json_return_type(const T& val) {
return json::json_return_type(val);
}
/*
* As commented on db::seed_provider_type is not used
* and probably never will.
*
* Just in case, we will return its name
*/
template<>
json::json_return_type get_json_return_type(const db::seed_provider_type& val) {
return json::json_return_type(val.class_name);
}
std::string format_type(const std::string& type) {
if (type == "int") {
return "integer";
}
return type;
}
future<> get_config_swagger_entry(const std::string& name, const std::string& description, const std::string& type, bool& first, output_stream<char>& os) {
std::stringstream ss;
if (first) {
first=false;
} else {
ss <<',';
};
ss << "\"/config/" << name <<"\": {"
"\"get\": {"
"\"description\": \"" << boost::replace_all_copy(boost::replace_all_copy(boost::replace_all_copy(description,"\n","\\n"),"\"", "''"), "\t", " ") <<"\","
"\"operationId\": \"find_config_"<< name <<"\","
"\"produces\": ["
"\"application/json\""
"],"
"\"tags\": [\"config\"],"
"\"parameters\": ["
"],"
"\"responses\": {"
"\"200\": {"
"\"description\": \"Config value\","
"\"schema\": {"
"\"type\": \"" << format_type(type) << "\""
"}"
"},"
"\"default\": {"
"\"description\": \"unexpected error\","
"\"schema\": {"
"\"$ref\": \"#/definitions/ErrorModel\""
"}"
"}"
"}"
"}"
"}";
return os.write(ss.str());
}
namespace cs = httpd::config_json;
#define _get_config_value(name, type, deflt, status, desc, ...) if (id == #name) {return get_json_return_type(ctx.db.local().get_config().name());}
#define _get_config_description(name, type, deflt, status, desc, ...) f = f.then([&os, &first] {return get_config_swagger_entry(#name, desc, #type, first, os);});
void set_config(std::shared_ptr < api_registry_builder20 > rb, http_context& ctx, routes& r) {
rb->register_function(r, [] (output_stream<char>& os) {
return do_with(true, [&os] (bool& first) {
auto f = make_ready_future();
_make_config_values(_get_config_description)
return f;
});
});
cs::find_config_id.set(r, [&ctx] (const_req r) {
auto id = r.param["id"];
_make_config_values(_get_config_value)
throw bad_param_exception(sstring("No such config entry: ") + id);
});
}
}

View File

@@ -1,30 +0,0 @@
/*
* Copyright (C) 2018 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include "api.hh"
#include <seastar/http/api_docs.hh>
namespace api {
void set_config(std::shared_ptr<api_registry_builder20> rb, http_context& ctx, routes& r);
}

View File

@@ -23,7 +23,7 @@
#include "api/lsa.hh"
#include "api/api.hh"
#include <seastar/http/exception.hh>
#include "http/exception.hh"
#include "utils/logalloc.hh"
#include "log.hh"

View File

@@ -21,7 +21,7 @@
#include "messaging_service.hh"
#include "message/messaging_service.hh"
#include <seastar/rpc/rpc_types.hh>
#include "rpc/rpc_types.hh"
#include "api/api-doc/messaging_service.json.hh"
#include <iostream>
#include <sstream>
@@ -139,7 +139,7 @@ void set_messaging_service(http_context& ctx, routes& r) {
messaging_verb v = i; // for type safety we use messaging_verb values
auto idx = static_cast<uint32_t>(v);
if (idx >= map->size()) {
throw std::runtime_error(format("verb index out of bounds: {:d}, map size: {:d}", idx, map->size()));
throw std::runtime_error(sprint("verb index out of bounds: %lu, map size: %lu", idx, map->size()));
}
if ((*map)[idx] > 0) {
c.count = (*map)[idx];

View File

@@ -26,7 +26,6 @@
#include "service/storage_service.hh"
#include "db/config.hh"
#include "utils/histogram.hh"
#include "database.hh"
namespace api {

View File

@@ -28,17 +28,13 @@
#include <db/commitlog/commitlog.hh>
#include <gms/gossiper.hh>
#include <db/system_keyspace.hh>
#include <seastar/http/exception.hh>
#include "http/exception.hh"
#include "repair/repair.hh"
#include "locator/snitch_base.hh"
#include "column_family.hh"
#include "log.hh"
#include "release.hh"
#include "sstables/compaction_manager.hh"
#include "sstables/sstables.hh"
#include "database.hh"
sstables::sstable::version_types get_highest_supported_format();
namespace api {
@@ -76,36 +72,21 @@ static std::vector<ss::token_range> describe_ring(const sstring& keyspace) {
}
void set_storage_service(http_context& ctx, routes& r) {
using ks_cf_func = std::function<future<json::json_return_type>(std::unique_ptr<request>, sstring, std::vector<sstring>)>;
auto wrap_ks_cf = [&ctx](ks_cf_func f) {
return [&ctx, f = std::move(f)](std::unique_ptr<request> req) {
auto keyspace = validate_keyspace(ctx, req->param);
auto column_families = split_cf(req->get_query_param("cf"));
if (column_families.empty()) {
column_families = map_keys(ctx.db.local().find_keyspace(keyspace).metadata().get()->cf_meta_data());
}
return f(std::move(req), std::move(keyspace), std::move(column_families));
};
};
ss::local_hostid.set(r, [](std::unique_ptr<request> req) {
return db::system_keyspace::get_local_host_id().then([](const utils::UUID& id) {
return make_ready_future<json::json_return_type>(id.to_sstring());
});
});
ss::get_tokens.set(r, [] (std::unique_ptr<request> req) {
return make_ready_future<json::json_return_type>(stream_range_as_array(service::get_local_storage_service().get_token_metadata().sorted_tokens(), [](const dht::token& i) {
return boost::lexical_cast<std::string>(i);
}));
ss::get_tokens.set(r, [] (const_req req) {
auto tokens = service::get_local_storage_service().get_token_metadata().sorted_tokens();
return container_to_vec(tokens);
});
ss::get_node_tokens.set(r, [] (std::unique_ptr<request> req) {
gms::inet_address addr(req->param["endpoint"]);
return make_ready_future<json::json_return_type>(stream_range_as_array(service::get_local_storage_service().get_token_metadata().get_tokens(addr), [](const dht::token& i) {
return boost::lexical_cast<std::string>(i);
}));
ss::get_node_tokens.set(r, [] (const_req req) {
gms::inet_address addr(req.param["endpoint"]);
auto tokens = service::get_local_storage_service().get_token_metadata().get_tokens(addr);
return container_to_vec(tokens);
});
ss::get_commitlog.set(r, [&ctx](const_req req) {
@@ -126,7 +107,11 @@ void set_storage_service(http_context& ctx, routes& r) {
});
ss::get_moving_nodes.set(r, [](const_req req) {
auto points = service::get_local_storage_service().get_token_metadata().get_moving_endpoints();
std::unordered_set<sstring> addr;
for (auto i: points) {
addr.insert(boost::lexical_cast<std::string>(i.second));
}
return container_to_vec(addr);
});
@@ -316,44 +301,24 @@ void set_storage_service(http_context& ctx, routes& r) {
});
});
ss::scrub.set(r, wrap_ks_cf([&ctx](std::unique_ptr<request> req, sstring keyspace, std::vector<sstring> column_families) {
// TODO: respect this
ss::scrub.set(r, [&ctx](std::unique_ptr<request> req) {
//TBD
unimplemented();
auto keyspace = validate_keyspace(ctx, req->param);
auto column_family = req->get_query_param("cf");
auto disable_snapshot = req->get_query_param("disable_snapshot");
auto skip_corrupted = req->get_query_param("skip_corrupted");
return make_ready_future<json::json_return_type>(json_void());
});
auto f = make_ready_future<>();
if (!req_param<bool>(*req, "disable_snapshot", false)) {
auto tag = format("pre-scrub-{:d}", db_clock::now().time_since_epoch().count());
f = parallel_for_each(column_families, [keyspace, tag](sstring cf) {
return service::get_local_storage_service().take_column_family_snapshot(keyspace, cf, tag);
});
}
return f.then([&ctx, keyspace, column_families] {
return ctx.db.invoke_on_all([=] (database& db) {
return do_for_each(column_families, [=, &db](sstring cfname) {
auto& cm = db.get_compaction_manager();
auto& cf = db.find_column_family(keyspace, cfname);
return cm.perform_sstable_scrub(&cf);
});
});
}).then([]{
return make_ready_future<json::json_return_type>(0);
});
}));
ss::upgrade_sstables.set(r, wrap_ks_cf([&ctx](std::unique_ptr<request> req, sstring keyspace, std::vector<sstring> column_families) {
bool exclude_current_version = req_param<bool>(*req, "exclude_current_version", false);
return ctx.db.invoke_on_all([=] (database& db) {
return do_for_each(column_families, [=, &db](sstring cfname) {
auto& cm = db.get_compaction_manager();
auto& cf = db.find_column_family(keyspace, cfname);
return cm.perform_sstable_upgrade(&cf, exclude_current_version);
});
}).then([]{
return make_ready_future<json::json_return_type>(0);
});
}));
ss::upgrade_sstables.set(r, [&ctx](std::unique_ptr<request> req) {
//TBD
unimplemented();
auto keyspace = validate_keyspace(ctx, req->param);
auto column_family = req->get_query_param("cf");
auto exclude_current_version = req->get_query_param("exclude_current_version");
return make_ready_future<json::json_return_type>(json_void());
});
ss::force_keyspace_flush.set(r, [&ctx](std::unique_ptr<request> req) {
auto keyspace = validate_keyspace(ctx, req->param);
@@ -491,7 +456,7 @@ void set_storage_service(http_context& ctx, routes& r) {
return service::get_storage_service().map_reduce(adder<service::storage_service::drain_progress>(), [] (auto& ss) {
return ss.get_drain_progress();
}).then([] (auto&& progress) {
auto progress_str = format("Drained {}/{} ColumnFamilies", progress.remaining_cfs, progress.total_cfs);
auto progress_str = sprint("Drained %s/%s ColumnFamilies", progress.remaining_cfs, progress.total_cfs);
return make_ready_future<json::json_return_type>(std::move(progress_str));
});
});
@@ -702,11 +667,7 @@ void set_storage_service(http_context& ctx, routes& r) {
auto coordinator = std::hash<sstring>()(cf) % smp::count;
return service::get_storage_service().invoke_on(coordinator, [ks = std::move(ks), cf = std::move(cf)] (service::storage_service& s) {
return s.load_new_sstables(ks, cf);
}).then_wrapped([] (auto&& f) {
if (f.failed()) {
auto msg = fmt::format("Failed to load new sstables: {}", f.get_exception());
return make_exception_future<json::json_return_type>(httpd::server_error_exception(msg));
}
}).then([] {
return make_ready_future<json::json_return_type>(json_void());
});
});
@@ -740,7 +701,7 @@ void set_storage_service(http_context& ctx, routes& r) {
} catch (std::out_of_range& e) {
throw httpd::bad_param_exception(e.what());
} catch (std::invalid_argument&){
throw httpd::bad_param_exception(format("Bad format in a probability value: \"{}\"", probability.c_str()));
throw httpd::bad_param_exception(sprint("Bad format in a probability value: \"%s\"", probability.c_str()));
}
});
});
@@ -776,7 +737,7 @@ void set_storage_service(http_context& ctx, routes& r) {
return make_ready_future<json::json_return_type>(json_void());
});
} catch (...) {
throw httpd::bad_param_exception(format("Bad format value: "));
throw httpd::bad_param_exception(sprint("Bad format value: "));
}
});
@@ -891,15 +852,6 @@ void set_storage_service(http_context& ctx, routes& r) {
return make_ready_future<json::json_return_type>(map_to_key_value(ownership, res));
});
});
ss::view_build_statuses.set(r, [&ctx] (std::unique_ptr<request> req) {
auto keyspace = validate_keyspace(ctx, req->param);
auto view = req->param["view"];
return service::get_local_storage_service().view_build_statuses(std::move(keyspace), std::move(view)).then([] (std::unordered_map<sstring, sstring> status) {
std::vector<storage_service_json::mapper> res;
return make_ready_future<json::json_return_type>(map_to_key_value(std::move(status), res));
});
});
}
}

View File

@@ -22,7 +22,7 @@
#include "api/api-doc/system.json.hh"
#include "api/api.hh"
#include <seastar/http/exception.hh>
#include "http/exception.hh"
#include "log.hh"
namespace api {

View File

@@ -1,261 +0,0 @@
/*
* Copyright (C) 2018 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "atomic_cell.hh"
#include "atomic_cell_or_collection.hh"
#include "types.hh"
#include "types/collection.hh"
/// LSA mirator for cells with irrelevant type
///
///
const data::type_imr_descriptor& no_type_imr_descriptor() {
static thread_local data::type_imr_descriptor state(data::type_info::make_variable_size());
return state;
}
atomic_cell atomic_cell::make_dead(api::timestamp_type timestamp, gc_clock::time_point deletion_time) {
auto& imr_data = no_type_imr_descriptor();
return atomic_cell(
imr_data.type_info(),
imr_object_type::make(data::cell::make_dead(timestamp, deletion_time), &imr_data.lsa_migrator())
);
}
atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, bytes_view value, atomic_cell::collection_member cm) {
auto& imr_data = type.imr_state();
return atomic_cell(
imr_data.type_info(),
imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, bool(cm)), &imr_data.lsa_migrator())
);
}
atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, ser::buffer_view<bytes_ostream::fragment_iterator> value, atomic_cell::collection_member cm) {
auto& imr_data = type.imr_state();
return atomic_cell(
imr_data.type_info(),
imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, bool(cm)), &imr_data.lsa_migrator())
);
}
atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, const fragmented_temporary_buffer::view& value, collection_member cm)
{
auto& imr_data = type.imr_state();
return atomic_cell(
imr_data.type_info(),
imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, bool(cm)), &imr_data.lsa_migrator())
);
}
atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, bytes_view value,
gc_clock::time_point expiry, gc_clock::duration ttl, atomic_cell::collection_member cm) {
auto& imr_data = type.imr_state();
return atomic_cell(
imr_data.type_info(),
imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, expiry, ttl, bool(cm)), &imr_data.lsa_migrator())
);
}
atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, ser::buffer_view<bytes_ostream::fragment_iterator> value,
gc_clock::time_point expiry, gc_clock::duration ttl, atomic_cell::collection_member cm) {
auto& imr_data = type.imr_state();
return atomic_cell(
imr_data.type_info(),
imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, expiry, ttl, bool(cm)), &imr_data.lsa_migrator())
);
}
atomic_cell atomic_cell::make_live(const abstract_type& type, api::timestamp_type timestamp, const fragmented_temporary_buffer::view& value,
gc_clock::time_point expiry, gc_clock::duration ttl, collection_member cm)
{
auto& imr_data = type.imr_state();
return atomic_cell(
imr_data.type_info(),
imr_object_type::make(data::cell::make_live(imr_data.type_info(), timestamp, value, expiry, ttl, bool(cm)), &imr_data.lsa_migrator())
);
}
atomic_cell atomic_cell::make_live_counter_update(api::timestamp_type timestamp, int64_t value) {
auto& imr_data = no_type_imr_descriptor();
return atomic_cell(
imr_data.type_info(),
imr_object_type::make(data::cell::make_live_counter_update(timestamp, value), &imr_data.lsa_migrator())
);
}
atomic_cell atomic_cell::make_live_uninitialized(const abstract_type& type, api::timestamp_type timestamp, size_t size) {
auto& imr_data = no_type_imr_descriptor();
return atomic_cell(
imr_data.type_info(),
imr_object_type::make(data::cell::make_live_uninitialized(imr_data.type_info(), timestamp, size), &imr_data.lsa_migrator())
);
}
static imr::utils::object<data::cell::structure> copy_cell(const data::type_imr_descriptor& imr_data, const uint8_t* ptr)
{
using imr_object_type = imr::utils::object<data::cell::structure>;
// If the cell doesn't own any memory it is trivial and can be copied with
// memcpy.
auto f = data::cell::structure::get_member<data::cell::tags::flags>(ptr);
if (!f.template get<data::cell::tags::external_data>()) {
data::cell::context ctx(f, imr_data.type_info());
// XXX: We may be better off storing the total cell size in memory. Measure!
auto size = data::cell::structure::serialized_object_size(ptr, ctx);
return imr_object_type::make_raw(size, [&] (uint8_t* dst) noexcept {
std::copy_n(ptr, size, dst);
}, &imr_data.lsa_migrator());
}
return imr_object_type::make(data::cell::copy_fn(imr_data.type_info(), ptr), &imr_data.lsa_migrator());
}
atomic_cell::atomic_cell(const abstract_type& type, atomic_cell_view other)
: atomic_cell(type.imr_state().type_info(),
copy_cell(type.imr_state(), other._view.raw_pointer()))
{ }
atomic_cell_or_collection atomic_cell_or_collection::copy(const abstract_type& type) const {
if (!_data.get()) {
return atomic_cell_or_collection();
}
auto& imr_data = type.imr_state();
return atomic_cell_or_collection(
copy_cell(imr_data, _data.get())
);
}
atomic_cell_or_collection::atomic_cell_or_collection(const abstract_type& type, atomic_cell_view acv)
: _data(copy_cell(type.imr_state(), acv._view.raw_pointer()))
{
}
static collection_mutation_view get_collection_mutation_view(const uint8_t* ptr)
{
auto f = data::cell::structure::get_member<data::cell::tags::flags>(ptr);
auto ti = data::type_info::make_collection();
data::cell::context ctx(f, ti);
auto view = data::cell::structure::get_member<data::cell::tags::cell>(ptr).as<data::cell::tags::collection>(ctx);
auto dv = data::cell::variable_value::make_view(view, f.get<data::cell::tags::external_data>());
return collection_mutation_view { dv };
}
collection_mutation_view atomic_cell_or_collection::as_collection_mutation() const {
return get_collection_mutation_view(_data.get());
}
collection_mutation::collection_mutation(const collection_type_impl& type, collection_mutation_view v)
: _data(imr_object_type::make(data::cell::make_collection(v.data), &type.imr_state().lsa_migrator()))
{
}
collection_mutation::collection_mutation(const collection_type_impl& type, bytes_view v)
: _data(imr_object_type::make(data::cell::make_collection(v), &type.imr_state().lsa_migrator()))
{
}
collection_mutation::operator collection_mutation_view() const
{
return get_collection_mutation_view(_data.get());
}
bool atomic_cell_or_collection::equals(const abstract_type& type, const atomic_cell_or_collection& other) const
{
auto ptr_a = _data.get();
auto ptr_b = other._data.get();
if (!ptr_a || !ptr_b) {
return !ptr_a && !ptr_b;
}
if (type.is_atomic()) {
auto a = atomic_cell_view::from_bytes(type.imr_state().type_info(), _data);
auto b = atomic_cell_view::from_bytes(type.imr_state().type_info(), other._data);
if (a.timestamp() != b.timestamp()) {
return false;
}
if (a.is_live() != b.is_live()) {
return false;
}
if (a.is_live()) {
if (a.is_counter_update() != b.is_counter_update()) {
return false;
}
if (a.is_counter_update()) {
return a.counter_update_value() == b.counter_update_value();
}
if (a.is_live_and_has_ttl() != b.is_live_and_has_ttl()) {
return false;
}
if (a.is_live_and_has_ttl()) {
if (a.ttl() != b.ttl() || a.expiry() != b.expiry()) {
return false;
}
}
return a.value() == b.value();
}
return a.deletion_time() == b.deletion_time();
} else {
return as_collection_mutation().data == other.as_collection_mutation().data;
}
}
size_t atomic_cell_or_collection::external_memory_usage(const abstract_type& t) const
{
if (!_data.get()) {
return 0;
}
auto ctx = data::cell::context(_data.get(), t.imr_state().type_info());
auto view = data::cell::structure::make_view(_data.get(), ctx);
auto flags = view.get<data::cell::tags::flags>();
size_t external_value_size = 0;
if (flags.get<data::cell::tags::external_data>()) {
if (flags.get<data::cell::tags::collection>()) {
external_value_size = get_collection_mutation_view(_data.get()).data.size_bytes();
} else {
auto cell_view = data::cell::atomic_cell_view(t.imr_state().type_info(), view);
external_value_size = cell_view.value_size();
}
// Add overhead of chunk headers. The last one is a special case.
external_value_size += (external_value_size - 1) / data::cell::maximum_external_chunk_length * data::cell::external_chunk_overhead;
external_value_size += data::cell::external_last_chunk_overhead;
}
return data::cell::structure::serialized_object_size(_data.get(), ctx)
+ imr_object_type::size_overhead + external_value_size;
}
std::ostream& operator<<(std::ostream& os, const atomic_cell_or_collection::printer& p) {
if (!p._cell._data.get()) {
return os << "{ null atomic_cell_or_collection }";
}
using dc = data::cell;
os << "{ ";
if (dc::structure::get_member<dc::tags::flags>(p._cell._data.get()).get<dc::tags::collection>()) {
os << "collection ";
auto cmv = p._cell.as_collection_mutation();
os << to_hex(cmv.data.linearize());
} else {
os << p._cell.as_atomic_cell(p._cdef);
}
return os << " }";
}

View File

@@ -26,55 +26,193 @@
#include "tombstone.hh"
#include "gc_clock.hh"
#include "utils/managed_bytes.hh"
#include <seastar/net//byteorder.hh>
#include "net/byteorder.hh"
#include <cstdint>
#include <iosfwd>
#include <seastar/util/gcc6-concepts.hh>
#include "data/cell.hh"
#include "data/schema_info.hh"
#include "imr/utils.hh"
#include "utils/fragmented_temporary_buffer.hh"
#include "serializer.hh"
template<typename T, typename Input>
static inline
void set_field(Input& v, unsigned offset, T val) {
reinterpret_cast<net::packed<T>*>(v.begin() + offset)->raw = net::hton(val);
}
class abstract_type;
class collection_type_impl;
template<typename T>
static inline
T get_field(const bytes_view& v, unsigned offset) {
return net::ntoh(*reinterpret_cast<const net::packed<T>*>(v.begin() + offset));
}
using atomic_cell_value_view = data::value_view;
using atomic_cell_value_mutable_view = data::value_mutable_view;
class atomic_cell_or_collection;
/// View of an atomic cell
template<mutable_view is_mutable>
class basic_atomic_cell_view {
protected:
data::cell::basic_atomic_cell_view<is_mutable> _view;
friend class atomic_cell;
/*
* Represents atomic cell layout. Works on serialized form.
*
* Layout:
*
* <live> := <int8_t:flags><int64_t:timestamp>(<int32_t:expiry><int32_t:ttl>)?<value>
* <dead> := <int8_t: 0><int64_t:timestamp><int32_t:deletion_time>
*/
class atomic_cell_type final {
private:
static constexpr int8_t LIVE_FLAG = 0x01;
static constexpr int8_t EXPIRY_FLAG = 0x02; // When present, expiry field is present. Set only for live cells
static constexpr int8_t COUNTER_UPDATE_FLAG = 0x08; // Cell is a counter update.
static constexpr int8_t COUNTER_IN_PLACE_REVERT = 0x10;
static constexpr unsigned flags_size = 1;
static constexpr unsigned timestamp_offset = flags_size;
static constexpr unsigned timestamp_size = 8;
static constexpr unsigned expiry_offset = timestamp_offset + timestamp_size;
static constexpr unsigned expiry_size = 4;
static constexpr unsigned deletion_time_offset = timestamp_offset + timestamp_size;
static constexpr unsigned deletion_time_size = 4;
static constexpr unsigned ttl_offset = expiry_offset + expiry_size;
static constexpr unsigned ttl_size = 4;
friend class counter_cell_builder;
private:
static bool is_counter_update(bytes_view cell) {
return cell[0] & COUNTER_UPDATE_FLAG;
}
static bool is_counter_in_place_revert_set(bytes_view cell) {
return cell[0] & COUNTER_IN_PLACE_REVERT;
}
template<typename BytesContainer>
static void set_counter_in_place_revert(BytesContainer& cell, bool flag) {
cell[0] = (cell[0] & ~COUNTER_IN_PLACE_REVERT) | (flag * COUNTER_IN_PLACE_REVERT);
}
static bool is_live(const bytes_view& cell) {
return cell[0] & LIVE_FLAG;
}
static bool is_live_and_has_ttl(const bytes_view& cell) {
return cell[0] & EXPIRY_FLAG;
}
static bool is_dead(const bytes_view& cell) {
return !is_live(cell);
}
// Can be called on live and dead cells
static api::timestamp_type timestamp(const bytes_view& cell) {
return get_field<api::timestamp_type>(cell, timestamp_offset);
}
template<typename BytesContainer>
static void set_timestamp(BytesContainer& cell, api::timestamp_type ts) {
set_field(cell, timestamp_offset, ts);
}
// Can be called on live cells only
private:
template<typename BytesView>
static BytesView do_get_value(BytesView cell) {
auto expiry_field_size = bool(cell[0] & EXPIRY_FLAG) * (expiry_size + ttl_size);
auto value_offset = flags_size + timestamp_size + expiry_field_size;
cell.remove_prefix(value_offset);
return cell;
}
public:
using pointer_type = std::conditional_t<is_mutable == mutable_view::no, const uint8_t*, uint8_t*>;
static bytes_view value(bytes_view cell) {
return do_get_value(cell);
}
static bytes_mutable_view value(bytes_mutable_view cell) {
return do_get_value(cell);
}
// Can be called on live counter update cells only
static int64_t counter_update_value(bytes_view cell) {
return get_field<int64_t>(cell, flags_size + timestamp_size);
}
// Can be called only when is_dead() is true.
static gc_clock::time_point deletion_time(const bytes_view& cell) {
assert(is_dead(cell));
return gc_clock::time_point(gc_clock::duration(
get_field<int32_t>(cell, deletion_time_offset)));
}
// Can be called only when is_live_and_has_ttl() is true.
static gc_clock::time_point expiry(const bytes_view& cell) {
assert(is_live_and_has_ttl(cell));
auto expiry = get_field<int32_t>(cell, expiry_offset);
return gc_clock::time_point(gc_clock::duration(expiry));
}
// Can be called only when is_live_and_has_ttl() is true.
static gc_clock::duration ttl(const bytes_view& cell) {
assert(is_live_and_has_ttl(cell));
return gc_clock::duration(get_field<int32_t>(cell, ttl_offset));
}
static managed_bytes make_dead(api::timestamp_type timestamp, gc_clock::time_point deletion_time) {
managed_bytes b(managed_bytes::initialized_later(), flags_size + timestamp_size + deletion_time_size);
b[0] = 0;
set_field(b, timestamp_offset, timestamp);
set_field(b, deletion_time_offset, deletion_time.time_since_epoch().count());
return b;
}
static managed_bytes make_live(api::timestamp_type timestamp, bytes_view value) {
auto value_offset = flags_size + timestamp_size;
managed_bytes b(managed_bytes::initialized_later(), value_offset + value.size());
b[0] = LIVE_FLAG;
set_field(b, timestamp_offset, timestamp);
std::copy_n(value.begin(), value.size(), b.begin() + value_offset);
return b;
}
static managed_bytes make_live_counter_update(api::timestamp_type timestamp, int64_t value) {
auto value_offset = flags_size + timestamp_size;
managed_bytes b(managed_bytes::initialized_later(), value_offset + sizeof(value));
b[0] = LIVE_FLAG | COUNTER_UPDATE_FLAG;
set_field(b, timestamp_offset, timestamp);
set_field(b, value_offset, value);
return b;
}
static managed_bytes make_live(api::timestamp_type timestamp, bytes_view value, gc_clock::time_point expiry, gc_clock::duration ttl) {
auto value_offset = flags_size + timestamp_size + expiry_size + ttl_size;
managed_bytes b(managed_bytes::initialized_later(), value_offset + value.size());
b[0] = EXPIRY_FLAG | LIVE_FLAG;
set_field(b, timestamp_offset, timestamp);
set_field(b, expiry_offset, expiry.time_since_epoch().count());
set_field(b, ttl_offset, ttl.count());
std::copy_n(value.begin(), value.size(), b.begin() + value_offset);
return b;
}
// make_live_from_serializer() is intended for users that need to serialise
// some object or objects to the format used in atomic_cell::value().
// With just make_live() the patter would look like follows:
// 1. allocate a buffer and write to it serialised objects
// 2. pass that buffer to make_live()
// 3. make_live() needs to prepend some metadata to the cell value so it
// allocates a new buffer and copies the content of the original one
//
// The allocation and copy of a buffer can be avoided.
// make_live_from_serializer() allows the user code to specify the timestamp
// and size of the cell value as well as provide the serialiser function
// object, which would write the serialised value of the cell to the buffer
// given to it by make_live_from_serializer().
template<typename Serializer>
GCC6_CONCEPT(requires requires(Serializer serializer, bytes::iterator it) {
serializer(it);
})
static managed_bytes make_live_from_serializer(api::timestamp_type timestamp, size_t size, Serializer&& serializer) {
auto value_offset = flags_size + timestamp_size;
managed_bytes b(managed_bytes::initialized_later(), value_offset + size);
b[0] = LIVE_FLAG;
set_field(b, timestamp_offset, timestamp);
serializer(b.begin() + value_offset);
return b;
}
template<typename ByteContainer>
friend class atomic_cell_base;
friend class atomic_cell;
};
template<typename ByteContainer>
class atomic_cell_base {
protected:
explicit basic_atomic_cell_view(data::cell::basic_atomic_cell_view<is_mutable> v)
: _view(std::move(v)) { }
basic_atomic_cell_view(const data::type_info& ti, pointer_type ptr)
: _view(data::cell::make_atomic_cell_view(ti, ptr))
{ }
ByteContainer _data;
protected:
atomic_cell_base(ByteContainer&& data) : _data(std::forward<ByteContainer>(data)) { }
friend class atomic_cell_or_collection;
public:
operator basic_atomic_cell_view<mutable_view::no>() const noexcept {
return basic_atomic_cell_view<mutable_view::no>(_view);
}
void swap(basic_atomic_cell_view& other) noexcept {
using std::swap;
swap(_view, other._view);
}
bool is_counter_update() const {
return _view.is_counter_update();
return atomic_cell_type::is_counter_update(_data);
}
bool is_counter_in_place_revert_set() const {
return atomic_cell_type::is_counter_in_place_revert_set(_data);
}
bool is_live() const {
return _view.is_live();
return atomic_cell_type::is_live(_data);
}
bool is_live(tombstone t, bool is_counter) const {
return is_live() && !is_covered_by(t, is_counter);
@@ -83,140 +221,122 @@ public:
return is_live() && !is_covered_by(t, is_counter) && !has_expired(now);
}
bool is_live_and_has_ttl() const {
return _view.is_expiring();
return atomic_cell_type::is_live_and_has_ttl(_data);
}
bool is_dead(gc_clock::time_point now) const {
return !is_live() || has_expired(now);
return atomic_cell_type::is_dead(_data) || has_expired(now);
}
bool is_covered_by(tombstone t, bool is_counter) const {
return timestamp() <= t.timestamp || (is_counter && t.timestamp != api::missing_timestamp);
}
// Can be called on live and dead cells
api::timestamp_type timestamp() const {
return _view.timestamp();
return atomic_cell_type::timestamp(_data);
}
void set_timestamp(api::timestamp_type ts) {
_view.set_timestamp(ts);
atomic_cell_type::set_timestamp(_data, ts);
}
// Can be called on live cells only
data::basic_value_view<is_mutable> value() const {
return _view.value();
}
// Can be called on live cells only
size_t value_size() const {
return _view.value_size();
}
bool is_value_fragmented() const {
return _view.is_value_fragmented();
auto value() const {
return atomic_cell_type::value(_data);
}
// Can be called on live counter update cells only
int64_t counter_update_value() const {
return _view.counter_update_value();
return atomic_cell_type::counter_update_value(_data);
}
// Can be called only when is_dead(gc_clock::time_point)
gc_clock::time_point deletion_time() const {
return !is_live() ? _view.deletion_time() : expiry() - ttl();
return !is_live() ? atomic_cell_type::deletion_time(_data) : expiry() - ttl();
}
// Can be called only when is_live_and_has_ttl()
gc_clock::time_point expiry() const {
return _view.expiry();
return atomic_cell_type::expiry(_data);
}
// Can be called only when is_live_and_has_ttl()
gc_clock::duration ttl() const {
return _view.ttl();
return atomic_cell_type::ttl(_data);
}
// Can be called on live and dead cells
bool has_expired(gc_clock::time_point now) const {
return is_live_and_has_ttl() && expiry() <= now;
}
bytes_view serialize() const {
return _view.serialize();
return _data;
}
void set_counter_in_place_revert(bool flag) {
atomic_cell_type::set_counter_in_place_revert(_data, flag);
}
};
class atomic_cell_view final : public basic_atomic_cell_view<mutable_view::no> {
atomic_cell_view(const data::type_info& ti, const uint8_t* data)
: basic_atomic_cell_view<mutable_view::no>(ti, data) {}
template<mutable_view is_mutable>
atomic_cell_view(data::cell::basic_atomic_cell_view<is_mutable> view)
: basic_atomic_cell_view<mutable_view::no>(view) { }
friend class atomic_cell;
class atomic_cell_view final : public atomic_cell_base<bytes_view> {
atomic_cell_view(bytes_view data) : atomic_cell_base(std::move(data)) {}
public:
static atomic_cell_view from_bytes(const data::type_info& ti, const imr::utils::object<data::cell::structure>& data) {
return atomic_cell_view(ti, data.get());
}
static atomic_cell_view from_bytes(const data::type_info& ti, bytes_view bv) {
return atomic_cell_view(ti, reinterpret_cast<const uint8_t*>(bv.begin()));
}
static atomic_cell_view from_bytes(bytes_view data) { return atomic_cell_view(data); }
friend class atomic_cell;
friend std::ostream& operator<<(std::ostream& os, const atomic_cell_view& acv);
};
class atomic_cell_mutable_view final : public basic_atomic_cell_view<mutable_view::yes> {
atomic_cell_mutable_view(const data::type_info& ti, uint8_t* data)
: basic_atomic_cell_view<mutable_view::yes>(ti, data) {}
class atomic_cell_mutable_view final : public atomic_cell_base<bytes_mutable_view> {
atomic_cell_mutable_view(bytes_mutable_view data) : atomic_cell_base(std::move(data)) {}
public:
static atomic_cell_mutable_view from_bytes(const data::type_info& ti, imr::utils::object<data::cell::structure>& data) {
return atomic_cell_mutable_view(ti, data.get());
}
static atomic_cell_mutable_view from_bytes(bytes_mutable_view data) { return atomic_cell_mutable_view(data); }
friend class atomic_cell;
};
using atomic_cell_ref = atomic_cell_mutable_view;
class atomic_cell final : public basic_atomic_cell_view<mutable_view::yes> {
using imr_object_type = imr::utils::object<data::cell::structure>;
imr_object_type _data;
atomic_cell(const data::type_info& ti, imr::utils::object<data::cell::structure>&& data)
: basic_atomic_cell_view<mutable_view::yes>(ti, data.get()), _data(std::move(data)) {}
class atomic_cell_ref final : public atomic_cell_base<managed_bytes&> {
public:
class collection_member_tag;
using collection_member = bool_class<collection_member_tag>;
atomic_cell_ref(managed_bytes& buf) : atomic_cell_base(buf) {}
};
class atomic_cell final : public atomic_cell_base<managed_bytes> {
atomic_cell(managed_bytes b) : atomic_cell_base(std::move(b)) {}
public:
atomic_cell(const atomic_cell&) = default;
atomic_cell(atomic_cell&&) = default;
atomic_cell& operator=(const atomic_cell&) = delete;
atomic_cell& operator=(const atomic_cell&) = default;
atomic_cell& operator=(atomic_cell&&) = default;
void swap(atomic_cell& other) noexcept {
basic_atomic_cell_view<mutable_view::yes>::swap(other);
_data.swap(other._data);
static atomic_cell from_bytes(managed_bytes b) {
return atomic_cell(std::move(b));
}
operator atomic_cell_view() const { return atomic_cell_view(_view); }
atomic_cell(const abstract_type& t, atomic_cell_view other);
static atomic_cell make_dead(api::timestamp_type timestamp, gc_clock::time_point deletion_time);
static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, bytes_view value,
collection_member = collection_member::no);
static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, ser::buffer_view<bytes_ostream::fragment_iterator> value,
collection_member = collection_member::no);
static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, const fragmented_temporary_buffer::view& value,
collection_member = collection_member::no);
static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, const bytes& value,
collection_member cm = collection_member::no) {
return make_live(type, timestamp, bytes_view(value), cm);
atomic_cell(atomic_cell_view other) : atomic_cell_base(managed_bytes{other._data}) {}
operator atomic_cell_view() const {
return atomic_cell_view(_data);
}
static atomic_cell make_live_counter_update(api::timestamp_type timestamp, int64_t value);
static atomic_cell make_live(const abstract_type&, api::timestamp_type timestamp, bytes_view value,
gc_clock::time_point expiry, gc_clock::duration ttl, collection_member = collection_member::no);
static atomic_cell make_live(const abstract_type&, api::timestamp_type timestamp, ser::buffer_view<bytes_ostream::fragment_iterator> value,
gc_clock::time_point expiry, gc_clock::duration ttl, collection_member = collection_member::no);
static atomic_cell make_live(const abstract_type&, api::timestamp_type timestamp, const fragmented_temporary_buffer::view& value,
gc_clock::time_point expiry, gc_clock::duration ttl, collection_member = collection_member::no);
static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, const bytes& value,
gc_clock::time_point expiry, gc_clock::duration ttl, collection_member cm = collection_member::no)
static atomic_cell make_dead(api::timestamp_type timestamp, gc_clock::time_point deletion_time) {
return atomic_cell_type::make_dead(timestamp, deletion_time);
}
static atomic_cell make_live(api::timestamp_type timestamp, bytes_view value) {
return atomic_cell_type::make_live(timestamp, value);
}
static atomic_cell make_live(api::timestamp_type timestamp, const bytes& value) {
return make_live(timestamp, bytes_view(value));
}
static atomic_cell make_live_counter_update(api::timestamp_type timestamp, int64_t value) {
return atomic_cell_type::make_live_counter_update(timestamp, value);
}
static atomic_cell make_live(api::timestamp_type timestamp, bytes_view value,
gc_clock::time_point expiry, gc_clock::duration ttl)
{
return make_live(type, timestamp, bytes_view(value), expiry, ttl, cm);
return atomic_cell_type::make_live(timestamp, value, expiry, ttl);
}
static atomic_cell make_live(const abstract_type& type, api::timestamp_type timestamp, bytes_view value, ttl_opt ttl, collection_member cm = collection_member::no) {
static atomic_cell make_live(api::timestamp_type timestamp, const bytes& value,
gc_clock::time_point expiry, gc_clock::duration ttl)
{
return make_live(timestamp, bytes_view(value), expiry, ttl);
}
static atomic_cell make_live(api::timestamp_type timestamp, bytes_view value, ttl_opt ttl) {
if (!ttl) {
return make_live(type, timestamp, value, cm);
return atomic_cell_type::make_live(timestamp, value);
} else {
return make_live(type, timestamp, value, gc_clock::now() + *ttl, *ttl, cm);
return atomic_cell_type::make_live(timestamp, value, gc_clock::now() + *ttl, *ttl);
}
}
static atomic_cell make_live_uninitialized(const abstract_type& type, api::timestamp_type timestamp, size_t size);
template<typename Serializer>
static atomic_cell make_live_from_serializer(api::timestamp_type timestamp, size_t size, Serializer&& serializer) {
return atomic_cell_type::make_live_from_serializer(timestamp, size, std::forward<Serializer>(serializer));
}
friend class atomic_cell_or_collection;
friend std::ostream& operator<<(std::ostream& os, const atomic_cell& ac);
};
@@ -230,24 +350,33 @@ class collection_mutation_view;
// list: tbd, probably ugly
class collection_mutation {
public:
using imr_object_type = imr::utils::object<data::cell::structure>;
imr_object_type _data;
managed_bytes data;
collection_mutation() {}
collection_mutation(const collection_type_impl&, collection_mutation_view v);
collection_mutation(const collection_type_impl&, bytes_view bv);
collection_mutation(managed_bytes b) : data(std::move(b)) {}
collection_mutation(collection_mutation_view v);
operator collection_mutation_view() const;
};
class collection_mutation_view {
public:
atomic_cell_value_view data;
bytes_view data;
bytes_view serialize() const { return data; }
static collection_mutation_view from_bytes(bytes_view v) { return { v }; }
};
inline
collection_mutation::collection_mutation(collection_mutation_view v)
: data(v.data) {
}
inline
collection_mutation::operator collection_mutation_view() const {
return { data };
}
class column_definition;
int compare_atomic_cell_for_merge(atomic_cell_view left, atomic_cell_view right);
void merge_column(const abstract_type& def,
void merge_column(const column_definition& def,
atomic_cell_or_collection& old,
const atomic_cell_or_collection& neww);

View File

@@ -24,7 +24,6 @@
// Not part of atomic_cell.hh to avoid cyclic dependency between types.hh and atomic_cell.hh
#include "types.hh"
#include "types/collection.hh"
#include "atomic_cell.hh"
#include "atomic_cell_or_collection.hh"
#include "hashing.hh"
@@ -34,15 +33,12 @@ template<>
struct appending_hash<collection_mutation_view> {
template<typename Hasher>
void operator()(Hasher& h, collection_mutation_view cell, const column_definition& cdef) const {
cell.data.with_linearized([&] (bytes_view cell_bv) {
auto ctype = static_pointer_cast<const collection_type_impl>(cdef.type);
auto m_view = ctype->deserialize_mutation_form(cell_bv);
auto m_view = collection_type_impl::deserialize_mutation_form(cell);
::feed_hash(h, m_view.tomb);
for (auto&& key_and_value : m_view.cells) {
::feed_hash(h, key_and_value.first);
::feed_hash(h, key_and_value.second, cdef);
}
});
}
};
@@ -54,9 +50,7 @@ struct appending_hash<atomic_cell_view> {
feed_hash(h, cell.timestamp());
if (cell.is_live()) {
if (cdef.is_counter()) {
counter_cell_view::with_linearized(cell, [&] (counter_cell_view ccv) {
::feed_hash(h, ccv);
});
::feed_hash(h, counter_cell_view(cell));
return;
}
if (cell.is_live_and_has_ttl()) {
@@ -91,9 +85,9 @@ struct appending_hash<atomic_cell_or_collection> {
template<typename Hasher>
void operator()(Hasher& h, const atomic_cell_or_collection& c, const column_definition& cdef) const {
if (cdef.is_atomic()) {
feed_hash(h, c.as_atomic_cell(cdef), cdef);
feed_hash(h, c.as_atomic_cell(), cdef);
} else {
feed_hash(h, c.as_collection_mutation(), cdef);
}
}
};
};

View File

@@ -25,68 +25,42 @@
#include "schema.hh"
#include "hashing.hh"
#include "imr/utils.hh"
// A variant type that can hold either an atomic_cell, or a serialized collection.
// Which type is stored is determined by the schema.
// Has an "empty" state.
// Objects moved-from are left in an empty state.
class atomic_cell_or_collection final {
// FIXME: This has made us lose small-buffer optimisation. Unfortunately,
// due to the changed cell format it would be less effective now, anyway.
// Measure the actual impact because any attempts to fix this will become
// irrelevant once rows are converted to the IMR as well, so maybe we can
// live with this like that.
using imr_object_type = imr::utils::object<data::cell::structure>;
imr_object_type _data;
managed_bytes _data;
private:
atomic_cell_or_collection(imr::utils::object<data::cell::structure>&& data) : _data(std::move(data)) {}
atomic_cell_or_collection(managed_bytes&& data) : _data(std::move(data)) {}
public:
atomic_cell_or_collection() = default;
atomic_cell_or_collection(atomic_cell_or_collection&&) = default;
atomic_cell_or_collection(const atomic_cell_or_collection&) = delete;
atomic_cell_or_collection& operator=(atomic_cell_or_collection&&) = default;
atomic_cell_or_collection& operator=(const atomic_cell_or_collection&) = delete;
atomic_cell_or_collection(atomic_cell ac) : _data(std::move(ac._data)) {}
atomic_cell_or_collection(const abstract_type& at, atomic_cell_view acv);
static atomic_cell_or_collection from_atomic_cell(atomic_cell data) { return { std::move(data._data) }; }
atomic_cell_view as_atomic_cell(const column_definition& cdef) const { return atomic_cell_view::from_bytes(cdef.type->imr_state().type_info(), _data); }
atomic_cell_ref as_atomic_cell_ref(const column_definition& cdef) { return atomic_cell_mutable_view::from_bytes(cdef.type->imr_state().type_info(), _data); }
atomic_cell_mutable_view as_mutable_atomic_cell(const column_definition& cdef) { return atomic_cell_mutable_view::from_bytes(cdef.type->imr_state().type_info(), _data); }
atomic_cell_or_collection(collection_mutation cm) : _data(std::move(cm._data)) { }
atomic_cell_or_collection copy(const abstract_type&) const;
atomic_cell_view as_atomic_cell() const { return atomic_cell_view::from_bytes(_data); }
atomic_cell_ref as_atomic_cell_ref() { return { _data }; }
atomic_cell_mutable_view as_mutable_atomic_cell() { return atomic_cell_mutable_view::from_bytes(_data); }
atomic_cell_or_collection(collection_mutation cm) : _data(std::move(cm.data)) {}
explicit operator bool() const {
return bool(_data);
return !_data.empty();
}
static constexpr bool can_use_mutable_view() {
return true;
bool can_use_mutable_view() const {
return !_data.is_fragmented();
}
void swap(atomic_cell_or_collection& other) noexcept {
_data.swap(other._data);
static atomic_cell_or_collection from_collection_mutation(collection_mutation data) {
return std::move(data.data);
}
static atomic_cell_or_collection from_collection_mutation(collection_mutation data) { return std::move(data._data); }
collection_mutation_view as_collection_mutation() const;
bytes_view serialize() const;
bool equals(const abstract_type& type, const atomic_cell_or_collection& other) const;
size_t external_memory_usage(const abstract_type&) const;
class printer {
const column_definition& _cdef;
const atomic_cell_or_collection& _cell;
public:
printer(const column_definition& cdef, const atomic_cell_or_collection& cell)
: _cdef(cdef), _cell(cell) { }
printer(const printer&) = delete;
printer(printer&&) = delete;
friend std::ostream& operator<<(std::ostream&, const printer&);
};
friend std::ostream& operator<<(std::ostream&, const printer&);
collection_mutation_view as_collection_mutation() const {
return collection_mutation_view{_data};
}
bytes_view serialize() const {
return _data;
}
bool operator==(const atomic_cell_or_collection& other) const {
return _data == other._data;
}
size_t external_memory_usage() const {
return _data.external_memory_usage();
}
friend std::ostream& operator<<(std::ostream&, const atomic_cell_or_collection&);
};
namespace std {
inline void swap(atomic_cell_or_collection& a, atomic_cell_or_collection& b) noexcept
{
a.swap(b);
}
}

View File

@@ -72,19 +72,19 @@ public:
return make_ready_future<authenticated_user>(anonymous_user());
}
virtual future<> create(std::string_view, const authentication_options& options) const override {
virtual future<> create(stdx::string_view, const authentication_options& options) const override {
return make_ready_future();
}
virtual future<> alter(std::string_view, const authentication_options& options) const override {
virtual future<> alter(stdx::string_view, const authentication_options& options) const override {
return make_ready_future();
}
virtual future<> drop(std::string_view) const override {
virtual future<> drop(stdx::string_view) const override {
return make_ready_future();
}
virtual future<custom_options> query_custom_options(std::string_view role_name) const override {
virtual future<custom_options> query_custom_options(stdx::string_view role_name) const override {
return make_ready_future<custom_options>();
}

View File

@@ -23,6 +23,7 @@
#include "auth/authorizer.hh"
#include "exceptions/exceptions.hh"
#include "stdx.hh"
namespace cql3 {
class query_processor;
@@ -57,12 +58,12 @@ public:
return make_ready_future<permission_set>(permissions::ALL);
}
virtual future<> grant(std::string_view, permission_set, const resource&) const override {
virtual future<> grant(stdx::string_view, permission_set, const resource&) const override {
return make_exception_future<>(
unsupported_authorization_operation("GRANT operation is not supported by AllowAllAuthorizer"));
}
virtual future<> revoke(std::string_view, permission_set, const resource&) const override {
virtual future<> revoke(stdx::string_view, permission_set, const resource&) const override {
return make_exception_future<>(
unsupported_authorization_operation("REVOKE operation is not supported by AllowAllAuthorizer"));
}
@@ -73,7 +74,7 @@ public:
"LIST PERMISSIONS operation is not supported by AllowAllAuthorizer"));
}
virtual future<> revoke_all(std::string_view) const override {
virtual future<> revoke_all(stdx::string_view) const override {
return make_exception_future(
unsupported_authorization_operation("REVOKE operation is not supported by AllowAllAuthorizer"));
}

View File

@@ -45,7 +45,7 @@
namespace auth {
authenticated_user::authenticated_user(std::string_view name)
authenticated_user::authenticated_user(stdx::string_view name)
: name(sstring(name)) {
}

View File

@@ -41,7 +41,7 @@
#pragma once
#include <string_view>
#include <experimental/string_view>
#include <functional>
#include <iosfwd>
#include <optional>
@@ -49,6 +49,7 @@
#include <seastar/core/sstring.hh>
#include "seastarx.hh"
#include "stdx.hh"
namespace auth {
@@ -66,7 +67,7 @@ public:
/// An anonymous user.
///
authenticated_user() = default;
explicit authenticated_user(std::string_view name);
explicit authenticated_user(stdx::string_view name);
};
///

View File

@@ -57,7 +57,7 @@ inline bool any_authentication_options(const authentication_options& aos) noexce
class unsupported_authentication_option : public std::invalid_argument {
public:
explicit unsupported_authentication_option(authentication_option k)
: std::invalid_argument(format("The {} option is not supported.", k)) {
: std::invalid_argument(sprint("The %s option is not supported.", k)) {
}
};

View File

@@ -45,6 +45,7 @@
#include "auth/common.hh"
#include "auth/password_authenticator.hh"
#include "cql3/query_processor.hh"
#include "db/config.hh"
#include "utils/class_registrator.hh"
const sstring auth::authenticator::USERNAME_KEY("username");

View File

@@ -41,7 +41,7 @@
#pragma once
#include <string_view>
#include <experimental/string_view>
#include <memory>
#include <set>
#include <stdexcept>
@@ -55,10 +55,10 @@
#include "auth/authentication_options.hh"
#include "auth/resource.hh"
#include "auth/sasl_challenge.hh"
#include "bytes.hh"
#include "enum_set.hh"
#include "exceptions/exceptions.hh"
#include "stdx.hh"
namespace db {
class config;
@@ -122,7 +122,7 @@ public:
///
/// The options provided must be a subset of `supported_options()`.
///
virtual future<> create(std::string_view role_name, const authentication_options& options) const = 0;
virtual future<> create(stdx::string_view role_name, const authentication_options& options) const = 0;
///
/// Alter the authentication record of an existing user.
@@ -131,25 +131,39 @@ public:
///
/// Callers must ensure that the specification of `alterable_options()` is adhered to.
///
virtual future<> alter(std::string_view role_name, const authentication_options& options) const = 0;
virtual future<> alter(stdx::string_view role_name, const authentication_options& options) const = 0;
///
/// Delete the authentication record for a user. This will disallow the user from logging in.
///
virtual future<> drop(std::string_view role_name) const = 0;
virtual future<> drop(stdx::string_view role_name) const = 0;
///
/// Query for custom options (those corresponding to \ref authentication_options::options).
///
/// If no options are set the result is an empty container.
///
virtual future<custom_options> query_custom_options(std::string_view role_name) const = 0;
virtual future<custom_options> query_custom_options(stdx::string_view role_name) const = 0;
///
/// System resources used internally as part of the implementation. These are made inaccessible to users.
///
virtual const resource_set& protected_resources() const = 0;
///
/// A stateful SASL challenge which supports many authentication schemes (depending on the implementation).
///
class sasl_challenge {
public:
virtual ~sasl_challenge() = default;
virtual bytes evaluate_response(bytes_view client_response) = 0;
virtual bool is_complete() const = 0;
virtual future<authenticated_user> get_authenticated_user() const = 0;
};
virtual ::shared_ptr<sasl_challenge> new_sasl_challenge() const = 0;
};

View File

@@ -41,7 +41,7 @@
#pragma once
#include <string_view>
#include <experimental/string_view>
#include <functional>
#include <optional>
#include <stdexcept>
@@ -54,6 +54,7 @@
#include "auth/permission.hh"
#include "auth/resource.hh"
#include "seastarx.hh"
#include "stdx.hh"
namespace auth {
@@ -116,14 +117,14 @@ public:
///
/// \throws \ref unsupported_authorization_operation if granting permissions is not supported.
///
virtual future<> grant(std::string_view role_name, permission_set, const resource&) const = 0;
virtual future<> grant(stdx::string_view role_name, permission_set, const resource&) const = 0;
///
/// Revoke a set of permissions from a role for a particular \ref resource.
///
/// \throws \ref unsupported_authorization_operation if revoking permissions is not supported.
///
virtual future<> revoke(std::string_view role_name, permission_set, const resource&) const = 0;
virtual future<> revoke(stdx::string_view role_name, permission_set, const resource&) const = 0;
///
/// Query for all directly granted permissions.
@@ -137,7 +138,7 @@ public:
///
/// \throws \ref unsupported_authorization_operation if revoking permissions is not supported.
///
virtual future<> revoke_all(std::string_view role_name) const = 0;
virtual future<> revoke_all(stdx::string_view role_name) const = 0;
///
/// Revoke all permissions granted to any role for a particular resource.

View File

@@ -28,7 +28,6 @@
#include "database.hh"
#include "schema_builder.hh"
#include "service/migration_manager.hh"
#include "timeout_config.hh"
namespace auth {
@@ -48,9 +47,9 @@ future<> do_after_system_ready(seastar::abort_source& as, seastar::noncopyable_f
struct empty_state { };
return delay_until_system_ready(as).then([&as, func = std::move(func)] () mutable {
return exponential_backoff_retry::do_until_value(1s, 1min, as, [func = std::move(func)] {
return func().then_wrapped([] (auto&& f) -> std::optional<empty_state> {
return func().then_wrapped([] (auto&& f) -> stdx::optional<empty_state> {
if (f.failed()) {
auth_log.debug("Auth task failed with error, rescheduling: {}", f.get_exception());
auth_log.info("Auth task failed with error, rescheduling: {}", f.get_exception());
return { };
}
return { empty_state() };
@@ -60,14 +59,16 @@ future<> do_after_system_ready(seastar::abort_source& as, seastar::noncopyable_f
}
future<> create_metadata_table_if_missing(
std::string_view table_name,
stdx::string_view table_name,
cql3::query_processor& qp,
std::string_view cql,
stdx::string_view cql,
::service::migration_manager& mm) {
static auto ignore_existing = [] (seastar::noncopyable_function<future<>()> func) {
return futurize_apply(std::move(func)).handle_exception_type([] (exceptions::already_exists_exception& ignored) { });
};
auto& db = qp.db();
auto& db = qp.db().local();
if (db.has_schema(meta::AUTH_KS, sstring(table_name))) {
return make_ready_future<>();
}
auto parsed_statement = static_pointer_cast<cql3::statements::raw::cf_statement>(
cql3::query_processor::parse_statement(cql));
@@ -76,36 +77,21 @@ future<> create_metadata_table_if_missing(
auto statement = static_pointer_cast<cql3::statements::create_table_statement>(
parsed_statement->prepare(db, qp.get_cql_stats())->statement);
const auto schema = statement->get_cf_meta_data(qp.db());
const auto schema = statement->get_cf_meta_data(qp.db().local());
const auto uuid = generate_legacy_id(schema->ks_name(), schema->cf_name());
schema_builder b(schema);
b.set_uuid(uuid);
schema_ptr table = b.build();
return ignore_existing([&mm, table = std::move(table)] () {
return mm.announce_new_column_family(table, false);
});
return mm.announce_new_column_family(b.build(), false);
}
future<> wait_for_schema_agreement(::service::migration_manager& mm, const database& db, seastar::abort_source& as) {
future<> wait_for_schema_agreement(::service::migration_manager& mm, const database& db) {
static const auto pause = [] { return sleep(std::chrono::milliseconds(500)); };
return do_until([&db, &as] {
as.check();
return db.get_version() != database::empty_version;
}, pause).then([&mm, &as] {
return do_until([&mm, &as] {
as.check();
return mm.have_schema_agreement();
}, pause);
return do_until([&db] { return db.get_version() != database::empty_version; }, pause).then([&mm] {
return do_until([&mm] { return mm.have_schema_agreement(); }, pause);
});
}
const timeout_config& internal_distributed_timeout_config() noexcept {
static const auto t = 5s;
static const timeout_config tc{t, t, t, t, t, t, t};
return tc;
}
}

View File

@@ -22,7 +22,7 @@
#pragma once
#include <chrono>
#include <string_view>
#include <experimental/string_view>
#include <seastar/core/future.hh>
#include <seastar/core/abort_source.hh>
@@ -38,7 +38,6 @@
using namespace std::chrono_literals;
class database;
class timeout_config;
namespace service {
class migration_manager;
@@ -76,16 +75,11 @@ inline future<> delay_until_system_ready(seastar::abort_source& as) {
future<> do_after_system_ready(seastar::abort_source& as, seastar::noncopyable_function<future<>()> func);
future<> create_metadata_table_if_missing(
std::string_view table_name,
stdx::string_view table_name,
cql3::query_processor&,
std::string_view cql,
stdx::string_view cql,
::service::migration_manager&);
future<> wait_for_schema_agreement(::service::migration_manager&, const database&, seastar::abort_source&);
///
/// Time-outs for internal, non-local CQL queries.
///
const timeout_config& internal_distributed_timeout_config() noexcept;
future<> wait_for_schema_agreement(::service::migration_manager&, const database&);
}

View File

@@ -61,7 +61,6 @@ extern "C" {
#include "cql3/untyped_result_set.hh"
#include "exceptions/exceptions.hh"
#include "log.hh"
#include "database.hh"
namespace auth {
@@ -95,16 +94,15 @@ default_authorizer::~default_authorizer() {
static const sstring legacy_table_name{"permissions"};
bool default_authorizer::legacy_metadata_exists() const {
return _qp.db().has_schema(meta::AUTH_KS, legacy_table_name);
return _qp.db().local().has_schema(meta::AUTH_KS, legacy_table_name);
}
future<bool> default_authorizer::any_granted() const {
static const sstring query = format("SELECT * FROM {}.{} LIMIT 1", meta::AUTH_KS, PERMISSIONS_CF);
static const sstring query = sprint("SELECT * FROM %s.%s LIMIT 1", meta::AUTH_KS, PERMISSIONS_CF);
return _qp.process(
query,
db::consistency_level::LOCAL_ONE,
infinite_timeout_config,
{},
true).then([this](::shared_ptr<cql3::untyped_result_set> results) {
return !results->empty();
@@ -113,12 +111,11 @@ future<bool> default_authorizer::any_granted() const {
future<> default_authorizer::migrate_legacy_metadata() const {
alogger.info("Starting migration of legacy permissions metadata.");
static const sstring query = format("SELECT * FROM {}.{}", meta::AUTH_KS, legacy_table_name);
static const sstring query = sprint("SELECT * FROM %s.%s", meta::AUTH_KS, legacy_table_name);
return _qp.process(
query,
db::consistency_level::LOCAL_ONE,
infinite_timeout_config).then([this](::shared_ptr<cql3::untyped_result_set> results) {
db::consistency_level::LOCAL_ONE).then([this](::shared_ptr<cql3::untyped_result_set> results) {
return do_for_each(*results, [this](const cql3::untyped_result_set_row& row) {
return do_with(
row.get_as<sstring>("username"),
@@ -161,7 +158,7 @@ future<> default_authorizer::start() {
_migration_manager).then([this] {
_finished = do_after_system_ready(_as, [this] {
return async([this] {
wait_for_schema_agreement(_migration_manager, _qp.db(), _as).get0();
wait_for_schema_agreement(_migration_manager, _qp.db().local()).get0();
if (legacy_metadata_exists()) {
if (!any_granted().get0()) {
@@ -179,7 +176,7 @@ future<> default_authorizer::start() {
future<> default_authorizer::stop() {
_as.request_abort();
return _finished.handle_exception_type([](const sleep_aborted&) {}).handle_exception_type([](const abort_requested_exception&) {});
return _finished.handle_exception_type([](const sleep_aborted&) {});
}
future<permission_set>
@@ -188,7 +185,8 @@ default_authorizer::authorize(const role_or_anonymous& maybe_role, const resourc
return make_ready_future<permission_set>(permissions::NONE);
}
static const sstring query = format("SELECT {} FROM {}.{} WHERE {} = ? AND {} = ?",
static const sstring query = sprint(
"SELECT %s FROM %s.%s WHERE %s = ? AND %s = ?",
PERMISSIONS_NAME,
meta::AUTH_KS,
PERMISSIONS_CF,
@@ -198,7 +196,6 @@ default_authorizer::authorize(const role_or_anonymous& maybe_role, const resourc
return _qp.process(
query,
db::consistency_level::LOCAL_ONE,
infinite_timeout_config,
{*maybe_role.name, r.name()}).then([](::shared_ptr<cql3::untyped_result_set> results) {
if (results->empty()) {
return permissions::NONE;
@@ -210,12 +207,13 @@ default_authorizer::authorize(const role_or_anonymous& maybe_role, const resourc
future<>
default_authorizer::modify(
std::string_view role_name,
stdx::string_view role_name,
permission_set set,
const resource& resource,
std::string_view op) const {
stdx::string_view op) const {
return do_with(
format("UPDATE {}.{} SET {} = {} {} ? WHERE {} = ? AND {} = ?",
sprint(
"UPDATE %s.%s SET %s = %s %s ? WHERE %s = ? AND %s = ?",
meta::AUTH_KS,
PERMISSIONS_CF,
PERMISSIONS_NAME,
@@ -227,22 +225,22 @@ default_authorizer::modify(
return _qp.process(
query,
db::consistency_level::ONE,
internal_distributed_timeout_config(),
{permissions::to_strings(set), sstring(role_name), resource.name()}).discard_result();
});
}
future<> default_authorizer::grant(std::string_view role_name, permission_set set, const resource& resource) const {
future<> default_authorizer::grant(stdx::string_view role_name, permission_set set, const resource& resource) const {
return modify(role_name, std::move(set), resource, "+");
}
future<> default_authorizer::revoke(std::string_view role_name, permission_set set, const resource& resource) const {
future<> default_authorizer::revoke(stdx::string_view role_name, permission_set set, const resource& resource) const {
return modify(role_name, std::move(set), resource, "-");
}
future<std::vector<permission_details>> default_authorizer::list_all() const {
static const sstring query = format("SELECT {}, {}, {} FROM {}.{}",
static const sstring query = sprint(
"SELECT %s, %s, %s FROM %s.%s",
ROLE_NAME,
RESOURCE_NAME,
PERMISSIONS_NAME,
@@ -252,7 +250,6 @@ future<std::vector<permission_details>> default_authorizer::list_all() const {
return _qp.process(
query,
db::consistency_level::ONE,
internal_distributed_timeout_config(),
{},
true).then([](::shared_ptr<cql3::untyped_result_set> results) {
std::vector<permission_details> all_details;
@@ -270,8 +267,9 @@ future<std::vector<permission_details>> default_authorizer::list_all() const {
});
}
future<> default_authorizer::revoke_all(std::string_view role_name) const {
static const sstring query = format("DELETE FROM {}.{} WHERE {} = ?",
future<> default_authorizer::revoke_all(stdx::string_view role_name) const {
static const sstring query = sprint(
"DELETE FROM %s.%s WHERE %s = ?",
meta::AUTH_KS,
PERMISSIONS_CF,
ROLE_NAME);
@@ -279,7 +277,6 @@ future<> default_authorizer::revoke_all(std::string_view role_name) const {
return _qp.process(
query,
db::consistency_level::ONE,
internal_distributed_timeout_config(),
{sstring(role_name)}).discard_result().handle_exception([role_name](auto ep) {
try {
std::rethrow_exception(ep);
@@ -290,7 +287,8 @@ future<> default_authorizer::revoke_all(std::string_view role_name) const {
}
future<> default_authorizer::revoke_all(const resource& resource) const {
static const sstring query = format("SELECT {} FROM {}.{} WHERE {} = ? ALLOW FILTERING",
static const sstring query = sprint(
"SELECT %s FROM %s.%s WHERE %s = ? ALLOW FILTERING",
ROLE_NAME,
meta::AUTH_KS,
PERMISSIONS_CF,
@@ -299,7 +297,6 @@ future<> default_authorizer::revoke_all(const resource& resource) const {
return _qp.process(
query,
db::consistency_level::LOCAL_ONE,
infinite_timeout_config,
{resource.name()}).then_wrapped([this, resource](future<::shared_ptr<cql3::untyped_result_set>> f) {
try {
auto res = f.get0();
@@ -307,7 +304,8 @@ future<> default_authorizer::revoke_all(const resource& resource) const {
res->begin(),
res->end(),
[this, res, resource](const cql3::untyped_result_set::row& r) {
static const sstring query = format("DELETE FROM {}.{} WHERE {} = ? AND {} = ?",
static const sstring query = sprint(
"DELETE FROM %s.%s WHERE %s = ? AND %s = ?",
meta::AUTH_KS,
PERMISSIONS_CF,
ROLE_NAME,
@@ -316,7 +314,6 @@ future<> default_authorizer::revoke_all(const resource& resource) const {
return _qp.process(
query,
db::consistency_level::LOCAL_ONE,
infinite_timeout_config,
{r.get_as<sstring>(ROLE_NAME), resource.name()}).discard_result().handle_exception(
[resource](auto ep) {
try {

View File

@@ -77,13 +77,13 @@ public:
virtual future<permission_set> authorize(const role_or_anonymous&, const resource&) const override;
virtual future<> grant(std::string_view, permission_set, const resource&) const override;
virtual future<> grant(stdx::string_view, permission_set, const resource&) const override;
virtual future<> revoke( std::string_view, permission_set, const resource&) const override;
virtual future<> revoke( stdx::string_view, permission_set, const resource&) const override;
virtual future<std::vector<permission_details>> list_all() const override;
virtual future<> revoke_all(std::string_view) const override;
virtual future<> revoke_all(stdx::string_view) const override;
virtual future<> revoke_all(const resource&) const override;
@@ -96,7 +96,7 @@ private:
future<> migrate_legacy_metadata() const;
future<> modify(std::string_view, permission_set, const resource&, std::string_view) const;
future<> modify(stdx::string_view, permission_set, const resource&, stdx::string_view) const;
};
} /* namespace auth */

View File

@@ -41,24 +41,25 @@
#include "auth/password_authenticator.hh"
extern "C" {
#include <crypt.h>
#include <unistd.h>
}
#include <algorithm>
#include <chrono>
#include <random>
#include <string_view>
#include <optional>
#include <boost/algorithm/cxx11/all_of.hpp>
#include <seastar/core/reactor.hh>
#include "auth/authenticated_user.hh"
#include "auth/common.hh"
#include "auth/passwords.hh"
#include "auth/roles-metadata.hh"
#include "cql3/untyped_result_set.hh"
#include "log.hh"
#include "service/migration_manager.hh"
#include "utils/class_registrator.hh"
#include "database.hh"
namespace auth {
@@ -81,8 +82,6 @@ static const class_registrator<
cql3::query_processor&,
::service::migration_manager&> password_auth_reg("org.apache.cassandra.auth.PasswordAuthenticator");
static thread_local auto rng_for_salt = std::default_random_engine(std::random_device{}());
password_authenticator::~password_authenticator() {
}
@@ -92,11 +91,84 @@ password_authenticator::password_authenticator(cql3::query_processor& qp, ::serv
, _stopped(make_ready_future<>()) {
}
static bool has_salted_hash(const cql3::untyped_result_set_row& row) {
return !row.get_or<sstring>(SALTED_HASH, "").empty();
// TODO: blowfish
// Origin uses Java bcrypt library, i.e. blowfish salt
// generation and hashing, which is arguably a "better"
// password hash than sha/md5 versions usually available in
// crypt_r. Otoh, glibc 2.7+ uses a modified sha512 algo
// which should be the same order of safe, so the only
// real issue should be salted hash compatibility with
// origin if importing system tables from there.
//
// Since bcrypt/blowfish is _not_ (afaict) not available
// as a dev package/lib on most linux distros, we'd have to
// copy and compile for example OWL crypto
// (http://cvsweb.openwall.com/cgi/cvsweb.cgi/Owl/packages/glibc/crypt_blowfish/)
// to be fully bit-compatible.
//
// Until we decide this is needed, let's just use crypt_r,
// and some old-fashioned random salt generation.
static constexpr size_t rand_bytes = 16;
static thread_local crypt_data tlcrypt = { 0, };
static sstring hashpw(const sstring& pass, const sstring& salt) {
auto res = crypt_r(pass.c_str(), salt.c_str(), &tlcrypt);
if (res == nullptr) {
throw std::system_error(errno, std::system_category());
}
return res;
}
static const sstring update_row_query = format("UPDATE {} SET {} = ? WHERE {} = ?",
static bool checkpw(const sstring& pass, const sstring& salted_hash) {
auto tmp = hashpw(pass, salted_hash);
return tmp == salted_hash;
}
static sstring gensalt() {
static sstring prefix;
std::random_device rd;
std::default_random_engine e1(rd());
std::uniform_int_distribution<char> dist;
sstring valid_salt = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789./";
sstring input(rand_bytes, 0);
for (char&c : input) {
c = valid_salt[dist(e1) % valid_salt.size()];
}
sstring salt;
if (!prefix.empty()) {
return prefix + input;
}
// Try in order:
// blowfish 2011 fix, blowfish, sha512, sha256, md5
for (sstring pfx : { "$2y$", "$2a$", "$6$", "$5$", "$1$" }) {
salt = pfx + input;
const char* e = crypt_r("fisk", salt.c_str(), &tlcrypt);
if (e && (e[0] != '*')) {
prefix = pfx;
return salt;
}
}
throw std::runtime_error("Could not initialize hashing algorithm");
}
static sstring hashpw(const sstring& pass) {
return hashpw(pass, gensalt());
}
static bool has_salted_hash(const cql3::untyped_result_set_row& row) {
return utf8_type->deserialize(row.get_blob(SALTED_HASH)) != data_value::make_null(utf8_type);
}
static const sstring update_row_query = sprint(
"UPDATE %s SET %s = ? WHERE %s = ?",
meta::roles_table::qualified_name(),
SALTED_HASH,
meta::roles_table::role_col_name);
@@ -104,17 +176,16 @@ static const sstring update_row_query = format("UPDATE {} SET {} = ? WHERE {} =
static const sstring legacy_table_name{"credentials"};
bool password_authenticator::legacy_metadata_exists() const {
return _qp.db().has_schema(meta::AUTH_KS, legacy_table_name);
return _qp.db().local().has_schema(meta::AUTH_KS, legacy_table_name);
}
future<> password_authenticator::migrate_legacy_metadata() const {
plogger.info("Starting migration of legacy authentication metadata.");
static const sstring query = format("SELECT * FROM {}.{}", meta::AUTH_KS, legacy_table_name);
static const sstring query = sprint("SELECT * FROM %s.%s", meta::AUTH_KS, legacy_table_name);
return _qp.process(
query,
db::consistency_level::QUORUM,
internal_distributed_timeout_config()).then([this](::shared_ptr<cql3::untyped_result_set> results) {
db::consistency_level::QUORUM).then([this](::shared_ptr<cql3::untyped_result_set> results) {
return do_for_each(*results, [this](const cql3::untyped_result_set_row& row) {
auto username = row.get_as<sstring>("username");
auto salted_hash = row.get_as<sstring>(SALTED_HASH);
@@ -122,7 +193,6 @@ future<> password_authenticator::migrate_legacy_metadata() const {
return _qp.process(
update_row_query,
consistency_for_user(username),
internal_distributed_timeout_config(),
{std::move(salted_hash), username}).discard_result();
}).finally([results] {});
}).then([] {
@@ -139,8 +209,7 @@ future<> password_authenticator::create_default_if_missing() const {
return _qp.process(
update_row_query,
db::consistency_level::QUORUM,
internal_distributed_timeout_config(),
{passwords::hash(DEFAULT_USER_PASSWORD, rng_for_salt), DEFAULT_USER_NAME}).then([](auto&&) {
{hashpw(DEFAULT_USER_PASSWORD), DEFAULT_USER_NAME}).then([](auto&&) {
plogger.info("Created default superuser authentication record.");
});
}
@@ -151,6 +220,8 @@ future<> password_authenticator::create_default_if_missing() const {
future<> password_authenticator::start() {
return once_among_shards([this] {
gensalt(); // do this once to determine usable hashing
auto f = create_metadata_table_if_missing(
meta::roles_table::name,
_qp,
@@ -159,7 +230,7 @@ future<> password_authenticator::start() {
_stopped = do_after_system_ready(_as, [this] {
return async([this] {
wait_for_schema_agreement(_migration_manager, _qp.db(), _as).get0();
wait_for_schema_agreement(_migration_manager, _qp.db().local()).get0();
if (any_nondefault_role_row_satisfies(_qp, &has_salted_hash).get0()) {
if (legacy_metadata_exists()) {
@@ -184,10 +255,10 @@ future<> password_authenticator::start() {
future<> password_authenticator::stop() {
_as.request_abort();
return _stopped.handle_exception_type([] (const sleep_aborted&) { }).handle_exception_type([](const abort_requested_exception&) {});
return _stopped.handle_exception_type([] (const sleep_aborted&) { });
}
db::consistency_level password_authenticator::consistency_for_user(std::string_view role_name) {
db::consistency_level password_authenticator::consistency_for_user(stdx::string_view role_name) {
if (role_name == DEFAULT_USER_NAME) {
return db::consistency_level::QUORUM;
}
@@ -213,10 +284,10 @@ authentication_option_set password_authenticator::alterable_options() const {
future<authenticated_user> password_authenticator::authenticate(
const credentials_map& credentials) const {
if (!credentials.count(USERNAME_KEY)) {
throw exceptions::authentication_exception(format("Required key '{}' is missing", USERNAME_KEY));
throw exceptions::authentication_exception(sprint("Required key '%s' is missing", USERNAME_KEY));
}
if (!credentials.count(PASSWORD_KEY)) {
throw exceptions::authentication_exception(format("Required key '{}' is missing", PASSWORD_KEY));
throw exceptions::authentication_exception(sprint("Required key '%s' is missing", PASSWORD_KEY));
}
auto& username = credentials.at(USERNAME_KEY);
@@ -228,7 +299,8 @@ future<authenticated_user> password_authenticator::authenticate(
// Rely on query processing caching statements instead, and lets assume
// that a map lookup string->statement is not gonna kill us much.
return futurize_apply([this, username, password] {
static const sstring query = format("SELECT {} FROM {} WHERE {} = ?",
static const sstring query = sprint(
"SELECT %s FROM %s WHERE %s = ?",
SALTED_HASH,
meta::roles_table::qualified_name(),
meta::roles_table::role_col_name);
@@ -236,17 +308,12 @@ future<authenticated_user> password_authenticator::authenticate(
return _qp.process(
query,
consistency_for_user(username),
internal_distributed_timeout_config(),
{username},
true);
}).then_wrapped([=](future<::shared_ptr<cql3::untyped_result_set>> f) {
try {
auto res = f.get0();
auto salted_hash = std::optional<sstring>();
if (!res->empty()) {
salted_hash = res->one().get_opt<sstring>(SALTED_HASH);
}
if (!salted_hash || !passwords::check(password, *salted_hash)) {
if (res->empty() || !checkpw(password, res->one().get_as<sstring>(SALTED_HASH))) {
throw exceptions::authentication_exception("Username and/or password are incorrect");
}
return make_ready_future<authenticated_user>(username);
@@ -254,15 +321,13 @@ future<authenticated_user> password_authenticator::authenticate(
std::throw_with_nested(exceptions::authentication_exception("Could not verify password"));
} catch (exceptions::request_execution_exception& e) {
std::throw_with_nested(exceptions::authentication_exception(e.what()));
} catch (exceptions::authentication_exception& e) {
std::throw_with_nested(e);
} catch (...) {
std::throw_with_nested(exceptions::authentication_exception("authentication failed"));
}
});
}
future<> password_authenticator::create(std::string_view role_name, const authentication_options& options) const {
future<> password_authenticator::create(stdx::string_view role_name, const authentication_options& options) const {
if (!options.password) {
return make_ready_future<>();
}
@@ -270,16 +335,16 @@ future<> password_authenticator::create(std::string_view role_name, const authen
return _qp.process(
update_row_query,
consistency_for_user(role_name),
internal_distributed_timeout_config(),
{passwords::hash(*options.password, rng_for_salt), sstring(role_name)}).discard_result();
{hashpw(*options.password), sstring(role_name)}).discard_result();
}
future<> password_authenticator::alter(std::string_view role_name, const authentication_options& options) const {
future<> password_authenticator::alter(stdx::string_view role_name, const authentication_options& options) const {
if (!options.password) {
return make_ready_future<>();
}
static const sstring query = format("UPDATE {} SET {} = ? WHERE {} = ?",
static const sstring query = sprint(
"UPDATE %s SET %s = ? WHERE %s = ?",
meta::roles_table::qualified_name(),
SALTED_HASH,
meta::roles_table::role_col_name);
@@ -287,23 +352,20 @@ future<> password_authenticator::alter(std::string_view role_name, const authent
return _qp.process(
query,
consistency_for_user(role_name),
internal_distributed_timeout_config(),
{passwords::hash(*options.password, rng_for_salt), sstring(role_name)}).discard_result();
{hashpw(*options.password), sstring(role_name)}).discard_result();
}
future<> password_authenticator::drop(std::string_view name) const {
static const sstring query = format("DELETE {} FROM {} WHERE {} = ?",
future<> password_authenticator::drop(stdx::string_view name) const {
static const sstring query = sprint(
"DELETE %s FROM %s WHERE %s = ?",
SALTED_HASH,
meta::roles_table::qualified_name(),
meta::roles_table::role_col_name);
return _qp.process(
query, consistency_for_user(name),
internal_distributed_timeout_config(),
{sstring(name)}).discard_result();
return _qp.process(query, consistency_for_user(name), {sstring(name)}).discard_result();
}
future<custom_options> password_authenticator::query_custom_options(std::string_view role_name) const {
future<custom_options> password_authenticator::query_custom_options(stdx::string_view role_name) const {
return make_ready_future<custom_options>();
}
@@ -312,13 +374,75 @@ const resource_set& password_authenticator::protected_resources() const {
return resources;
}
::shared_ptr<sasl_challenge> password_authenticator::new_sasl_challenge() const {
return ::make_shared<plain_sasl_challenge>([this](std::string_view username, std::string_view password) {
credentials_map credentials{};
credentials[USERNAME_KEY] = sstring(username);
credentials[PASSWORD_KEY] = sstring(password);
return this->authenticate(credentials);
});
::shared_ptr<authenticator::sasl_challenge> password_authenticator::new_sasl_challenge() const {
class plain_text_password_challenge : public sasl_challenge {
const password_authenticator& _self;
public:
plain_text_password_challenge(const password_authenticator& self) : _self(self) {
}
/**
* SASL PLAIN mechanism specifies that credentials are encoded in a
* sequence of UTF-8 bytes, delimited by 0 (US-ASCII NUL).
* The form is : {code}authzId<NUL>authnId<NUL>password<NUL>{code}
* authzId is optional, and in fact we don't care about it here as we'll
* set the authzId to match the authnId (that is, there is no concept of
* a user being authorized to act on behalf of another).
*
* @param bytes encoded credentials string sent by the client
* @return map containing the username/password pairs in the form an IAuthenticator
* would expect
* @throws javax.security.sasl.SaslException
*/
bytes evaluate_response(bytes_view client_response) override {
plogger.debug("Decoding credentials from client token");
sstring username, password;
auto b = client_response.crbegin();
auto e = client_response.crend();
auto i = b;
while (i != e) {
if (*i == 0) {
sstring tmp(i.base(), b.base());
if (password.empty()) {
password = std::move(tmp);
} else if (username.empty()) {
username = std::move(tmp);
}
b = ++i;
continue;
}
++i;
}
if (username.empty()) {
throw exceptions::authentication_exception("Authentication ID must not be null");
}
if (password.empty()) {
throw exceptions::authentication_exception("Password must not be null");
}
_credentials[USERNAME_KEY] = std::move(username);
_credentials[PASSWORD_KEY] = std::move(password);
_complete = true;
return {};
}
bool is_complete() const override {
return _complete;
}
future<authenticated_user> get_authenticated_user() const override {
return _self.authenticate(_credentials);
}
private:
credentials_map _credentials;
bool _complete = false;
};
return ::make_shared<plain_text_password_challenge>(*this);
}
}

View File

@@ -61,7 +61,7 @@ class password_authenticator : public authenticator {
seastar::abort_source _as;
public:
static db::consistency_level consistency_for_user(std::string_view role_name);
static db::consistency_level consistency_for_user(stdx::string_view role_name);
password_authenticator(cql3::query_processor&, ::service::migration_manager&);
@@ -81,13 +81,13 @@ public:
virtual future<authenticated_user> authenticate(const credentials_map& credentials) const override;
virtual future<> create(std::string_view role_name, const authentication_options& options) const override;
virtual future<> create(stdx::string_view role_name, const authentication_options& options) const override;
virtual future<> alter(std::string_view role_name, const authentication_options& options) const override;
virtual future<> alter(stdx::string_view role_name, const authentication_options& options) const override;
virtual future<> drop(std::string_view role_name) const override;
virtual future<> drop(stdx::string_view role_name) const override;
virtual future<custom_options> query_custom_options(std::string_view role_name) const override;
virtual future<custom_options> query_custom_options(stdx::string_view role_name) const override;
virtual const resource_set& protected_resources() const override;

View File

@@ -1,84 +0,0 @@
/*
* Copyright (C) 2018 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "auth/passwords.hh"
#include <cerrno>
#include <optional>
extern "C" {
#include <crypt.h>
#include <unistd.h>
}
namespace auth::passwords {
static thread_local crypt_data tlcrypt = { 0, };
namespace detail {
scheme identify_best_supported_scheme() {
const auto all_schemes = { scheme::bcrypt_y, scheme::bcrypt_a, scheme::sha_512, scheme::sha_256, scheme::md5 };
// "Random", for testing schemes.
const sstring random_part_of_salt = "aaaabbbbccccdddd";
for (scheme c : all_schemes) {
const sstring salt = sstring(prefix_for_scheme(c)) + random_part_of_salt;
const char* e = crypt_r("fisk", salt.c_str(), &tlcrypt);
if (e && (e[0] != '*')) {
return c;
}
}
throw no_supported_schemes();
}
sstring hash_with_salt(const sstring& pass, const sstring& salt) {
auto res = crypt_r(pass.c_str(), salt.c_str(), &tlcrypt);
if (!res || (res[0] == '*')) {
throw std::system_error(errno, std::system_category());
}
return res;
}
const char* prefix_for_scheme(scheme c) noexcept {
switch (c) {
case scheme::bcrypt_y: return "$2y$";
case scheme::bcrypt_a: return "$2a$";
case scheme::sha_512: return "$6$";
case scheme::sha_256: return "$5$";
case scheme::md5: return "$1$";
default: return nullptr;
}
}
} // namespace detail
no_supported_schemes::no_supported_schemes()
: std::runtime_error("No allowed hashing schemes are supported on this system") {
}
bool check(const sstring& pass, const sstring& salted_hash) {
return detail::hash_with_salt(pass, salted_hash) == salted_hash;
}
} // namespace auth::paswords

View File

@@ -1,125 +0,0 @@
/*
* Copyright (C) 2018 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include <random>
#include <stdexcept>
#include <seastar/core/sstring.hh>
#include "seastarx.hh"
namespace auth::passwords {
class no_supported_schemes : public std::runtime_error {
public:
no_supported_schemes();
};
///
/// Apache Cassandra uses a library to provide the bcrypt scheme. Many Linux implementations do not support bcrypt, so
/// we support alternatives. The cost is loss of direct compatibility with Apache Cassandra system tables.
///
enum class scheme {
bcrypt_y,
bcrypt_a,
sha_512,
sha_256,
md5
};
namespace detail {
template <typename RandomNumberEngine>
sstring generate_random_salt_bytes(RandomNumberEngine& g) {
static const sstring valid_bytes = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789./";
static constexpr std::size_t num_bytes = 16;
std::uniform_int_distribution<std::size_t> dist(0, valid_bytes.size() - 1);
sstring result(num_bytes, 0);
for (char& c : result) {
c = valid_bytes[dist(g)];
}
return result;
}
///
/// Test each allowed hashing scheme and report the best supported one on the current system.
///
/// \throws \ref no_supported_schemes when none of the known schemes is supported.
///
scheme identify_best_supported_scheme();
const char* prefix_for_scheme(scheme) noexcept;
///
/// Generate a implementation-specific salt string for hashing passwords.
///
/// The `RandomNumberEngine` is used to generate the string, which is an implementation-specific length.
///
/// \throws \ref no_supported_schemes when no known hashing schemes are supported on the system.
///
template <typename RandomNumberEngine>
sstring generate_salt(RandomNumberEngine& g) {
static const scheme scheme = identify_best_supported_scheme();
static const sstring prefix = sstring(prefix_for_scheme(scheme));
return prefix + generate_random_salt_bytes(g);
}
///
/// Hash a password combined with an implementation-specific salt string.
///
/// \throws \ref std::system_error when an unexpected implementation-specific error occurs.
///
sstring hash_with_salt(const sstring& pass, const sstring& salt);
} // namespace detail
///
/// Run a one-way hashing function on cleartext to produce encrypted text.
///
/// Prior to applying the hashing function, random salt is amended to the cleartext. The random salt bytes are generated
/// according to the random number engine `g`.
///
/// The result is the encrypted cyphertext, and also the salt used but in a implementation-specific format.
///
/// \throws \ref std::system_error when the implementation-specific implementation fails to hash the cleartext.
///
template <typename RandomNumberEngine>
sstring hash(const sstring& pass, RandomNumberEngine& g) {
return detail::hash_with_salt(pass, detail::generate_salt(g));
}
///
/// Check that cleartext matches previously hashed cleartext with salt.
///
/// \ref salted_hash is the result of invoking \ref hash, which is the implementation-specific combination of the hashed
/// password and the salt that was generated for it.
///
/// \returns `true` if the cleartext matches the salted hash.
///
/// \throws \ref std::system_error when an unexpected implementation-specific error occurs.
///
bool check(const sstring& pass, const sstring& salted_hash);
} // namespace auth::passwords

View File

@@ -24,9 +24,19 @@
#include "auth/authorizer.hh"
#include "auth/common.hh"
#include "auth/service.hh"
#include "db/config.hh"
namespace auth {
permissions_cache_config permissions_cache_config::from_db_config(const db::config& dc) {
permissions_cache_config c;
c.max_entries = dc.permissions_cache_max_entries();
c.validity_period = std::chrono::milliseconds(dc.permissions_validity_in_ms());
c.update_period = std::chrono::milliseconds(dc.permissions_update_interval_in_ms());
return c;
}
permissions_cache::permissions_cache(const permissions_cache_config& c, service& ser, logging::logger& log)
: _cache(c.max_entries, c.validity_period, c.update_period, log, [&ser, &log](const key_type& k) {
log.debug("Refreshing permissions for {}", k.first);

View File

@@ -22,7 +22,7 @@
#pragma once
#include <chrono>
#include <string_view>
#include <experimental/string_view>
#include <functional>
#include <iostream>
#include <optional>
@@ -37,6 +37,7 @@
#include "auth/resource.hh"
#include "auth/role_or_anonymous.hh"
#include "log.hh"
#include "stdx.hh"
#include "utils/hash.hh"
#include "utils/loading_cache.hh"
@@ -58,6 +59,8 @@ namespace auth {
class service;
struct permissions_cache_config final {
static permissions_cache_config from_db_config(const db::config&);
std::size_t max_entries;
std::chrono::milliseconds validity_period;
std::chrono::milliseconds update_period;

View File

@@ -61,7 +61,7 @@ std::ostream& operator<<(std::ostream& os, resource_kind kind) {
return os;
}
static const std::unordered_map<resource_kind, std::string_view> roots{
static const std::unordered_map<resource_kind, stdx::string_view> roots{
{resource_kind::data, "data"},
{resource_kind::role, "roles"}};
@@ -101,25 +101,24 @@ static permission_set applicable_permissions(const role_resource_view& rv) {
permission::DESCRIBE>();
}
resource::resource(resource_kind kind) : _kind(kind) {
_parts.emplace_back(roots.at(kind));
resource::resource(resource_kind kind) : _kind(kind), _parts{sstring(roots.at(kind))} {
}
resource::resource(resource_kind kind, utils::small_vector<sstring, 3> parts) : resource(kind) {
resource::resource(resource_kind kind, std::vector<sstring> parts) : resource(kind) {
_parts.reserve(parts.size() + 1);
_parts.insert(_parts.end(), std::make_move_iterator(parts.begin()), std::make_move_iterator(parts.end()));
}
resource::resource(data_resource_t, std::string_view keyspace) : resource(resource_kind::data) {
_parts.emplace_back(keyspace);
resource::resource(data_resource_t, stdx::string_view keyspace)
: resource(resource_kind::data, std::vector<sstring>{sstring(keyspace)}) {
}
resource::resource(data_resource_t, std::string_view keyspace, std::string_view table) : resource(resource_kind::data) {
_parts.emplace_back(keyspace);
_parts.emplace_back(table);
resource::resource(data_resource_t, stdx::string_view keyspace, stdx::string_view table)
: resource(resource_kind::data, std::vector<sstring>{sstring(keyspace), sstring(table)}) {
}
resource::resource(role_resource_t, std::string_view role) : resource(resource_kind::role) {
_parts.emplace_back(role);
resource::resource(role_resource_t, stdx::string_view role)
: resource(resource_kind::role, std::vector<sstring>{sstring(role)}) {
}
sstring resource::name() const {
@@ -174,7 +173,7 @@ data_resource_view::data_resource_view(const resource& r) : _resource(r) {
}
}
std::optional<std::string_view> data_resource_view::keyspace() const {
std::optional<stdx::string_view> data_resource_view::keyspace() const {
if (_resource._parts.size() == 1) {
return {};
}
@@ -182,7 +181,7 @@ std::optional<std::string_view> data_resource_view::keyspace() const {
return _resource._parts[1];
}
std::optional<std::string_view> data_resource_view::table() const {
std::optional<stdx::string_view> data_resource_view::table() const {
if (_resource._parts.size() <= 2) {
return {};
}
@@ -211,7 +210,7 @@ role_resource_view::role_resource_view(const resource& r) : _resource(r) {
}
}
std::optional<std::string_view> role_resource_view::role() const {
std::optional<stdx::string_view> role_resource_view::role() const {
if (_resource._parts.size() == 1) {
return {};
}
@@ -231,9 +230,9 @@ std::ostream& operator<<(std::ostream& os, const role_resource_view& v) {
return os;
}
resource parse_resource(std::string_view name) {
static const std::unordered_map<std::string_view, resource_kind> reverse_roots = [] {
std::unordered_map<std::string_view, resource_kind> result;
resource parse_resource(stdx::string_view name) {
static const std::unordered_map<stdx::string_view, resource_kind> reverse_roots = [] {
std::unordered_map<stdx::string_view, resource_kind> result;
for (const auto& pair : roots) {
result.emplace(pair.second, pair.first);
@@ -242,7 +241,7 @@ resource parse_resource(std::string_view name) {
return result;
}();
utils::small_vector<sstring, 3> parts;
std::vector<sstring> parts;
boost::split(parts, name, [](char ch) { return ch == '/'; });
if (parts.empty()) {

View File

@@ -41,7 +41,7 @@
#pragma once
#include <string_view>
#include <experimental/string_view>
#include <iostream>
#include <optional>
#include <stdexcept>
@@ -54,15 +54,15 @@
#include "auth/permission.hh"
#include "seastarx.hh"
#include "stdx.hh"
#include "utils/hash.hh"
#include "utils/small_vector.hh"
namespace auth {
class invalid_resource_name : public std::invalid_argument {
public:
explicit invalid_resource_name(std::string_view name)
: std::invalid_argument(format("The resource name '{}' is invalid.", name)) {
explicit invalid_resource_name(stdx::string_view name)
: std::invalid_argument(sprint("The resource name '%s' is invalid.", name)) {
}
};
@@ -98,16 +98,16 @@ struct role_resource_t final {};
class resource final {
resource_kind _kind;
utils::small_vector<sstring, 3> _parts;
std::vector<sstring> _parts;
public:
///
/// A root resource of a particular kind.
///
explicit resource(resource_kind);
resource(data_resource_t, std::string_view keyspace);
resource(data_resource_t, std::string_view keyspace, std::string_view table);
resource(role_resource_t, std::string_view role);
resource(data_resource_t, stdx::string_view keyspace);
resource(data_resource_t, stdx::string_view keyspace, stdx::string_view table);
resource(role_resource_t, stdx::string_view role);
resource_kind kind() const noexcept {
return _kind;
@@ -123,7 +123,7 @@ public:
permission_set applicable_permissions() const;
private:
resource(resource_kind, utils::small_vector<sstring, 3> parts);
resource(resource_kind, std::vector<sstring> parts);
friend class std::hash<resource>;
friend class data_resource_view;
@@ -131,7 +131,7 @@ private:
friend bool operator<(const resource&, const resource&);
friend bool operator==(const resource&, const resource&);
friend resource parse_resource(std::string_view);
friend resource parse_resource(stdx::string_view);
};
bool operator<(const resource&, const resource&);
@@ -150,7 +150,7 @@ class resource_kind_mismatch : public std::invalid_argument {
public:
explicit resource_kind_mismatch(resource_kind expected, resource_kind actual)
: std::invalid_argument(
format("This resource has kind '{}', but was expected to have kind '{}'.", actual, expected)) {
sprint("This resource has kind '%s', but was expected to have kind '%s'.", actual, expected)) {
}
};
@@ -166,9 +166,9 @@ public:
///
explicit data_resource_view(const resource& r);
std::optional<std::string_view> keyspace() const;
std::optional<stdx::string_view> keyspace() const;
std::optional<std::string_view> table() const;
std::optional<stdx::string_view> table() const;
};
std::ostream& operator<<(std::ostream&, const data_resource_view&);
@@ -187,7 +187,7 @@ public:
///
explicit role_resource_view(const resource&);
std::optional<std::string_view> role() const;
std::optional<stdx::string_view> role() const;
};
std::ostream& operator<<(std::ostream&, const role_resource_view&);
@@ -197,20 +197,20 @@ std::ostream& operator<<(std::ostream&, const role_resource_view&);
///
/// \throws \ref invalid_resource_name when the name is malformed.
///
resource parse_resource(std::string_view name);
resource parse_resource(stdx::string_view name);
const resource& root_data_resource();
inline resource make_data_resource(std::string_view keyspace) {
inline resource make_data_resource(stdx::string_view keyspace) {
return resource(data_resource_t{}, keyspace);
}
inline resource make_data_resource(std::string_view keyspace, std::string_view table) {
inline resource make_data_resource(stdx::string_view keyspace, stdx::string_view table) {
return resource(data_resource_t{}, keyspace, table);
}
const resource& root_role_resource();
inline resource make_role_resource(std::string_view role) {
inline resource make_role_resource(stdx::string_view role) {
return resource(role_resource_t{}, role);
}

View File

@@ -21,7 +21,7 @@
#pragma once
#include <string_view>
#include <experimental/string_view>
#include <memory>
#include <optional>
#include <stdexcept>
@@ -33,6 +33,7 @@
#include "auth/resource.hh"
#include "seastarx.hh"
#include "stdx.hh"
namespace auth {
@@ -59,31 +60,31 @@ public:
class role_already_exists : public roles_argument_exception {
public:
explicit role_already_exists(std::string_view role_name)
: roles_argument_exception(format("Role {} already exists.", role_name)) {
explicit role_already_exists(stdx::string_view role_name)
: roles_argument_exception(sprint("Role %s already exists.", role_name)) {
}
};
class nonexistant_role : public roles_argument_exception {
public:
explicit nonexistant_role(std::string_view role_name)
: roles_argument_exception(format("Role {} doesn't exist.", role_name)) {
explicit nonexistant_role(stdx::string_view role_name)
: roles_argument_exception(sprint("Role %s doesn't exist.", role_name)) {
}
};
class role_already_included : public roles_argument_exception {
public:
role_already_included(std::string_view grantee_name, std::string_view role_name)
role_already_included(stdx::string_view grantee_name, stdx::string_view role_name)
: roles_argument_exception(
format("{} already includes role {}.", grantee_name, role_name)) {
sprint("%s already includes role %s.", grantee_name, role_name)) {
}
};
class revoke_ungranted_role : public roles_argument_exception {
public:
revoke_ungranted_role(std::string_view revokee_name, std::string_view role_name)
revoke_ungranted_role(stdx::string_view revokee_name, stdx::string_view role_name)
: roles_argument_exception(
format("{} was not granted role {}, so it cannot be revoked.", revokee_name, role_name)) {
sprint("%s was not granted role %s, so it cannot be revoked.", revokee_name, role_name)) {
}
};
@@ -103,7 +104,7 @@ class role_manager {
public:
virtual ~role_manager() = default;
virtual std::string_view qualified_java_name() const noexcept = 0;
virtual stdx::string_view qualified_java_name() const noexcept = 0;
virtual const resource_set& protected_resources() const = 0;
@@ -114,17 +115,17 @@ public:
///
/// \returns an exceptional future with \ref role_already_exists for a role that has previously been created.
///
virtual future<> create(std::string_view role_name, const role_config&) const = 0;
virtual future<> create(stdx::string_view role_name, const role_config&) const = 0;
///
/// \returns an exceptional future with \ref nonexistant_role if the role does not exist.
///
virtual future<> drop(std::string_view role_name) const = 0;
virtual future<> drop(stdx::string_view role_name) const = 0;
///
/// \returns an exceptional future with \ref nonexistant_role if the role does not exist.
///
virtual future<> alter(std::string_view role_name, const role_config_update&) const = 0;
virtual future<> alter(stdx::string_view role_name, const role_config_update&) const = 0;
///
/// Grant `role_name` to `grantee_name`.
@@ -134,7 +135,7 @@ public:
/// \returns an exceptional future with \ref role_already_included if granting the role would be redundant, or
/// create a cycle.
///
virtual future<> grant(std::string_view grantee_name, std::string_view role_name) const = 0;
virtual future<> grant(stdx::string_view grantee_name, stdx::string_view role_name) const = 0;
///
/// Revoke `role_name` from `revokee_name`.
@@ -143,26 +144,26 @@ public:
///
/// \returns an exceptional future with \ref revoke_ungranted_role if the role was not granted.
///
virtual future<> revoke(std::string_view revokee_name, std::string_view role_name) const = 0;
virtual future<> revoke(stdx::string_view revokee_name, stdx::string_view role_name) const = 0;
///
/// \returns an exceptional future with \ref nonexistant_role if the role does not exist.
///
virtual future<role_set> query_granted(std::string_view grantee, recursive_role_query) const = 0;
virtual future<role_set> query_granted(stdx::string_view grantee, recursive_role_query) const = 0;
virtual future<role_set> query_all() const = 0;
virtual future<bool> exists(std::string_view role_name) const = 0;
virtual future<bool> exists(stdx::string_view role_name) const = 0;
///
/// \returns an exceptional future with \ref nonexistant_role if the role does not exist.
///
virtual future<bool> is_superuser(std::string_view role_name) const = 0;
virtual future<bool> is_superuser(stdx::string_view role_name) const = 0;
///
/// \returns an exceptional future with \ref nonexistant_role if the role does not exist.
///
virtual future<bool> can_login(std::string_view role_name) const = 0;
virtual future<bool> can_login(stdx::string_view role_name) const = 0;
};
}

View File

@@ -21,7 +21,7 @@
#pragma once
#include <string_view>
#include <experimental/string_view>
#include <functional>
#include <iosfwd>
#include <optional>
@@ -29,6 +29,7 @@
#include <seastar/core/sstring.hh>
#include "seastarx.hh"
#include "stdx.hh"
namespace auth {
@@ -37,7 +38,7 @@ public:
std::optional<sstring> name{};
role_or_anonymous() = default;
role_or_anonymous(std::string_view name) : name(name) {
role_or_anonymous(stdx::string_view name) : name(name) {
}
};

View File

@@ -36,7 +36,7 @@ namespace meta {
namespace roles_table {
std::string_view creation_query() {
stdx::string_view creation_query() {
static const sstring instance = sprint(
"CREATE TABLE %s ("
" %s text PRIMARY KEY,"
@@ -51,7 +51,7 @@ std::string_view creation_query() {
return instance;
}
std::string_view qualified_name() noexcept {
stdx::string_view qualified_name() noexcept {
static const sstring instance = AUTH_KS + "." + sstring(name);
return instance;
}
@@ -63,7 +63,8 @@ std::string_view qualified_name() noexcept {
future<bool> default_role_row_satisfies(
cql3::query_processor& qp,
std::function<bool(const cql3::untyped_result_set_row&)> p) {
static const sstring query = format("SELECT * FROM {} WHERE {} = ?",
static const sstring query = sprint(
"SELECT * FROM %s WHERE %s = ?",
meta::roles_table::qualified_name(),
meta::roles_table::role_col_name);
@@ -71,14 +72,12 @@ future<bool> default_role_row_satisfies(
return qp.process(
query,
db::consistency_level::ONE,
infinite_timeout_config,
{meta::DEFAULT_SUPERUSER_NAME},
true).then([&qp, &p](::shared_ptr<cql3::untyped_result_set> results) {
if (results->empty()) {
return qp.process(
query,
db::consistency_level::QUORUM,
internal_distributed_timeout_config(),
{meta::DEFAULT_SUPERUSER_NAME},
true).then([&p](::shared_ptr<cql3::untyped_result_set> results) {
if (results->empty()) {
@@ -97,13 +96,12 @@ future<bool> default_role_row_satisfies(
future<bool> any_nondefault_role_row_satisfies(
cql3::query_processor& qp,
std::function<bool(const cql3::untyped_result_set_row&)> p) {
static const sstring query = format("SELECT * FROM {}", meta::roles_table::qualified_name());
static const sstring query = sprint("SELECT * FROM %s", meta::roles_table::qualified_name());
return do_with(std::move(p), [&qp](const auto& p) {
return qp.process(
query,
db::consistency_level::QUORUM,
internal_distributed_timeout_config()).then([&p](::shared_ptr<cql3::untyped_result_set> results) {
db::consistency_level::QUORUM).then([&p](::shared_ptr<cql3::untyped_result_set> results) {
if (results->empty()) {
return false;
}

View File

@@ -21,12 +21,13 @@
#pragma once
#include <string_view>
#include <experimental/string_view>
#include <functional>
#include <seastar/core/future.hh>
#include "seastarx.hh"
#include "stdx.hh"
namespace cql3 {
class query_processor;
@@ -39,13 +40,13 @@ namespace meta {
namespace roles_table {
std::string_view creation_query();
stdx::string_view creation_query();
constexpr std::string_view name{"roles", 5};
constexpr stdx::string_view name{"roles", 5};
std::string_view qualified_name() noexcept;
stdx::string_view qualified_name() noexcept;
constexpr std::string_view role_col_name{"role", 4};
constexpr stdx::string_view role_col_name{"role", 4};
}

View File

@@ -1,102 +0,0 @@
/*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
/*
* Copyright (C) 2019 ScyllaDB
*
* Modified by ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#include "auth/sasl_challenge.hh"
#include "exceptions/exceptions.hh"
namespace auth {
/**
* SASL PLAIN mechanism specifies that credentials are encoded in a
* sequence of UTF-8 bytes, delimited by 0 (US-ASCII NUL).
* The form is : {code}authzId<NUL>authnId<NUL>password<NUL>{code}
* authzId is optional, and in fact we don't care about it here as we'll
* set the authzId to match the authnId (that is, there is no concept of
* a user being authorized to act on behalf of another).
*
* @param bytes encoded credentials string sent by the client
* @return map containing the username/password pairs in the form an IAuthenticator
* would expect
* @throws javax.security.sasl.SaslException
*/
bytes plain_sasl_challenge::evaluate_response(bytes_view client_response) {
sstring username, password;
auto b = client_response.crbegin();
auto e = client_response.crend();
auto i = b;
while (i != e) {
if (*i == 0) {
sstring tmp(i.base(), b.base());
if (password.empty()) {
password = std::move(tmp);
} else if (username.empty()) {
username = std::move(tmp);
}
b = ++i;
continue;
}
++i;
}
if (username.empty()) {
throw exceptions::authentication_exception("Authentication ID must not be null");
}
if (password.empty()) {
throw exceptions::authentication_exception("Password must not be null");
}
_username = std::move(username);
_password = std::move(password);
return {};
}
bool plain_sasl_challenge::is_complete() const {
return _username && _password;
}
future<authenticated_user> plain_sasl_challenge::get_authenticated_user() const {
return _when_complete(*_username, *_password);
}
}

View File

@@ -1,89 +0,0 @@
/*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
/*
* Copyright (C) 2019 ScyllaDB
*
* Modified by ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include <functional>
#include <optional>
#include <string_view>
#include <seastar/core/future.hh>
#include <seastar/core/sstring.hh>
#include "auth/authenticated_user.hh"
#include "bytes.hh"
#include "seastarx.hh"
namespace auth {
///
/// A stateful SASL challenge which supports many authentication schemes (depending on the implementation).
///
class sasl_challenge {
public:
virtual ~sasl_challenge() = default;
virtual bytes evaluate_response(bytes_view client_response) = 0;
virtual bool is_complete() const = 0;
virtual future<authenticated_user> get_authenticated_user() const = 0;
};
class plain_sasl_challenge : public sasl_challenge {
public:
using completion_callback = std::function<future<authenticated_user>(std::string_view, std::string_view)>;
explicit plain_sasl_challenge(completion_callback f) : _when_complete(std::move(f)) {
}
virtual bytes evaluate_response(bytes_view) override;
virtual bool is_complete() const override;
virtual future<authenticated_user> get_authenticated_user() const override;
private:
std::optional<sstring> _username, _password;
completion_callback _when_complete;
};
}

View File

@@ -36,12 +36,12 @@
#include "auth/standard_role_manager.hh"
#include "cql3/query_processor.hh"
#include "cql3/untyped_result_set.hh"
#include "db/consistency_level_type.hh"
#include "db/config.hh"
#include "db/consistency_level.hh"
#include "exceptions/exceptions.hh"
#include "log.hh"
#include "service/migration_listener.hh"
#include "utils/class_registrator.hh"
#include "database.hh"
namespace auth {
@@ -97,7 +97,7 @@ private:
void on_drop_view(const sstring& ks_name, const sstring& view_name) override {}
};
static future<> validate_role_exists(const service& ser, std::string_view role_name) {
static future<> validate_role_exists(const service& ser, stdx::string_view role_name) {
return ser.underlying_role_manager().exists(role_name).then([role_name](bool exists) {
if (!exists) {
throw nonexistant_role(role_name);
@@ -105,6 +105,19 @@ static future<> validate_role_exists(const service& ser, std::string_view role_n
});
}
service_config service_config::from_db_config(const db::config& dc) {
const qualified_name qualified_authorizer_name(meta::AUTH_PACKAGE_NAME, dc.authorizer());
const qualified_name qualified_authenticator_name(meta::AUTH_PACKAGE_NAME, dc.authenticator());
const qualified_name qualified_role_manager_name(meta::AUTH_PACKAGE_NAME, dc.role_manager());
service_config c;
c.authorizer_java_name = qualified_authorizer_name;
c.authenticator_java_name = qualified_authenticator_name;
c.role_manager_java_name = qualified_role_manager_name;
return c;
}
service::service(
permissions_cache_config c,
cql3::query_processor& qp,
@@ -126,7 +139,8 @@ service::service(
if ((_authenticator->qualified_java_name() == password_authenticator_name())
&& (_role_manager->qualified_java_name() != standard_role_manager_name())) {
throw incompatible_module_combination(
format("The {} authenticator must be loaded alongside the {} role-manager.",
sprint(
"The %s authenticator must be loaded alongside the %s role-manager.",
password_authenticator_name(),
standard_role_manager_name()));
}
@@ -147,7 +161,7 @@ service::service(
}
future<> service::create_keyspace_if_missing() const {
auto& db = _qp.db();
auto& db = _qp.db().local();
if (!db.has_keyspace(meta::AUTH_KS)) {
std::map<sstring, sstring> opts{{"replication_factor", "1"}};
@@ -170,9 +184,7 @@ future<> service::start() {
return once_among_shards([this] {
return create_keyspace_if_missing();
}).then([this] {
return _role_manager->start().then([this] {
return when_all_succeed(_authorizer->start(), _authenticator->start());
});
return when_all_succeed(_role_manager->start(), _authorizer->start(), _authenticator->start());
}).then([this] {
_permissions_cache = std::make_unique<permissions_cache>(_permissions_cache_config, *this, log);
}).then([this] {
@@ -184,26 +196,24 @@ future<> service::start() {
}
future<> service::stop() {
// Only one of the shards has the listener registered, but let's try to
// unregister on each one just to make sure.
_migration_manager.unregister_listener(_migration_listener.get());
return _permissions_cache->stop().then([this] {
return when_all_succeed(_role_manager->stop(), _authorizer->stop(), _authenticator->stop());
});
}
future<bool> service::has_existing_legacy_users() const {
if (!_qp.db().has_schema(meta::AUTH_KS, meta::USERS_CF)) {
if (!_qp.db().local().has_schema(meta::AUTH_KS, meta::USERS_CF)) {
return make_ready_future<bool>(false);
}
static const sstring default_user_query = format("SELECT * FROM {}.{} WHERE {} = ?",
static const sstring default_user_query = sprint(
"SELECT * FROM %s.%s WHERE %s = ?",
meta::AUTH_KS,
meta::USERS_CF,
meta::user_name_col_name);
static const sstring all_users_query = format("SELECT * FROM {}.{} LIMIT 1",
static const sstring all_users_query = sprint(
"SELECT * FROM %s.%s LIMIT 1",
meta::AUTH_KS,
meta::USERS_CF);
@@ -213,7 +223,6 @@ future<bool> service::has_existing_legacy_users() const {
return _qp.process(
default_user_query,
db::consistency_level::ONE,
infinite_timeout_config,
{meta::DEFAULT_SUPERUSER_NAME},
true).then([this](auto results) {
if (!results->empty()) {
@@ -223,7 +232,6 @@ future<bool> service::has_existing_legacy_users() const {
return _qp.process(
default_user_query,
db::consistency_level::QUORUM,
infinite_timeout_config,
{meta::DEFAULT_SUPERUSER_NAME},
true).then([this](auto results) {
if (!results->empty()) {
@@ -232,8 +240,7 @@ future<bool> service::has_existing_legacy_users() const {
return _qp.process(
all_users_query,
db::consistency_level::QUORUM,
infinite_timeout_config).then([](auto results) {
db::consistency_level::QUORUM).then([](auto results) {
return make_ready_future<bool>(!results->empty());
});
});
@@ -246,7 +253,7 @@ service::get_uncached_permissions(const role_or_anonymous& maybe_role, const res
return _authorizer->authorize(maybe_role, r);
}
const std::string_view role_name = *maybe_role.name;
const stdx::string_view role_name = *maybe_role.name;
return has_superuser(role_name).then([this, role_name, &r](bool superuser) {
if (superuser) {
@@ -260,7 +267,7 @@ service::get_uncached_permissions(const role_or_anonymous& maybe_role, const res
return do_with(permission_set(), [this, role_name, &r](auto& all_perms) {
return get_roles(role_name).then([this, &r, &all_perms](role_set all_roles) {
return do_with(std::move(all_roles), [this, &r, &all_perms](const auto& all_roles) {
return parallel_for_each(all_roles, [this, &r, &all_perms](std::string_view role_name) {
return parallel_for_each(all_roles, [this, &r, &all_perms](stdx::string_view role_name) {
return _authorizer->authorize(role_name, r).then([&all_perms](permission_set perms) {
all_perms = permission_set::from_mask(all_perms.mask() | perms.mask());
});
@@ -277,7 +284,7 @@ future<permission_set> service::get_permissions(const role_or_anonymous& maybe_r
return _permissions_cache->get(maybe_role, r);
}
future<bool> service::has_superuser(std::string_view role_name) const {
future<bool> service::has_superuser(stdx::string_view role_name) const {
return this->get_roles(std::move(role_name)).then([this](role_set roles) {
return do_with(std::move(roles), [this](const role_set& roles) {
return do_with(false, roles.begin(), [this, &roles](bool& any_super, auto& iter) {
@@ -295,7 +302,7 @@ future<bool> service::has_superuser(std::string_view role_name) const {
});
}
future<role_set> service::get_roles(std::string_view role_name) const {
future<role_set> service::get_roles(stdx::string_view role_name) const {
//
// We may wish to cache this information in the future (as Apache Cassandra does).
//
@@ -306,7 +313,7 @@ future<role_set> service::get_roles(std::string_view role_name) const {
future<bool> service::exists(const resource& r) const {
switch (r.kind()) {
case resource_kind::data: {
const auto& db = _qp.db();
const auto& db = _qp.db().local();
data_resource_view v(r);
const auto keyspace = v.keyspace();
@@ -401,7 +408,7 @@ static void validate_authentication_options_are_supported(
future<> create_role(
const service& ser,
std::string_view name,
stdx::string_view name,
const role_config& config,
const authentication_options& options) {
return ser.underlying_role_manager().create(name, config).then([&ser, name, &options] {
@@ -425,7 +432,7 @@ future<> create_role(
future<> alter_role(
const service& ser,
std::string_view name,
stdx::string_view name,
const role_config_update& config_update,
const authentication_options& options) {
return ser.underlying_role_manager().alter(name, config_update).then([&ser, name, &options] {
@@ -442,7 +449,7 @@ future<> alter_role(
});
}
future<> drop_role(const service& ser, std::string_view name) {
future<> drop_role(const service& ser, stdx::string_view name) {
return do_with(make_role_resource(name), [&ser, name](const resource& r) {
auto& a = ser.underlying_authorizer();
@@ -458,14 +465,14 @@ future<> drop_role(const service& ser, std::string_view name) {
});
}
future<bool> has_role(const service& ser, std::string_view grantee, std::string_view name) {
future<bool> has_role(const service& ser, stdx::string_view grantee, stdx::string_view name) {
return when_all_succeed(
validate_role_exists(ser, name),
ser.get_roles(grantee)).then([name](role_set all_roles) {
return make_ready_future<bool>(all_roles.count(sstring(name)) != 0);
});
}
future<bool> has_role(const service& ser, const authenticated_user& u, std::string_view name) {
future<bool> has_role(const service& ser, const authenticated_user& u, stdx::string_view name) {
if (is_anonymous(u)) {
return make_ready_future<bool>(false);
}
@@ -475,7 +482,7 @@ future<bool> has_role(const service& ser, const authenticated_user& u, std::stri
future<> grant_permissions(
const service& ser,
std::string_view role_name,
stdx::string_view role_name,
permission_set perms,
const resource& r) {
return validate_role_exists(ser, role_name).then([&ser, role_name, perms, &r] {
@@ -483,7 +490,7 @@ future<> grant_permissions(
});
}
future<> grant_applicable_permissions(const service& ser, std::string_view role_name, const resource& r) {
future<> grant_applicable_permissions(const service& ser, stdx::string_view role_name, const resource& r) {
return grant_permissions(ser, role_name, r.applicable_permissions(), r);
}
future<> grant_applicable_permissions(const service& ser, const authenticated_user& u, const resource& r) {
@@ -496,7 +503,7 @@ future<> grant_applicable_permissions(const service& ser, const authenticated_us
future<> revoke_permissions(
const service& ser,
std::string_view role_name,
stdx::string_view role_name,
permission_set perms,
const resource& r) {
return validate_role_exists(ser, role_name).then([&ser, role_name, perms, &r] {
@@ -507,7 +514,7 @@ future<> revoke_permissions(
future<std::vector<permission_details>> list_filtered_permissions(
const service& ser,
permission_set perms,
std::optional<std::string_view> role_name,
std::optional<stdx::string_view> role_name,
const std::optional<std::pair<resource, recursive_permissions>>& resource_filter) {
return ser.underlying_authorizer().list_all().then([&ser, perms, role_name, &resource_filter](
std::vector<permission_details> all_details) {

View File

@@ -21,7 +21,7 @@
#pragma once
#include <string_view>
#include <experimental/string_view>
#include <memory>
#include <optional>
@@ -35,11 +35,16 @@
#include "auth/permissions_cache.hh"
#include "auth/role_manager.hh"
#include "seastarx.hh"
#include "stdx.hh"
namespace cql3 {
class query_processor;
}
namespace db {
class config;
}
namespace service {
class migration_manager;
class migration_listener;
@@ -50,6 +55,8 @@ namespace auth {
class role_or_anonymous;
struct service_config final {
static service_config from_db_config(const db::config&);
sstring authorizer_java_name;
sstring authenticator_java_name;
sstring role_manager_java_name;
@@ -134,13 +141,13 @@ public:
///
/// \returns an exceptional future with \ref nonexistant_role if the role does not exist.
///
future<bool> has_superuser(std::string_view role_name) const;
future<bool> has_superuser(stdx::string_view role_name) const;
///
/// Return the set of all roles granted to the given role, including itself and roles granted through other roles.
///
/// \returns an exceptional future with \ref nonexistent_role if the role does not exist.
future<role_set> get_roles(std::string_view role_name) const;
future<role_set> get_roles(stdx::string_view role_name) const;
future<bool> exists(const resource&) const;
@@ -190,7 +197,7 @@ bool is_protected(const service&, const resource&) noexcept;
///
future<> create_role(
const service&,
std::string_view name,
stdx::string_view name,
const role_config&,
const authentication_options&);
@@ -203,7 +210,7 @@ future<> create_role(
///
future<> alter_role(
const service&,
std::string_view name,
stdx::string_view name,
const role_config_update&,
const authentication_options&);
@@ -212,20 +219,20 @@ future<> alter_role(
///
/// \returns an exceptional future with \ref nonexistant_role if the named role does not exist.
///
future<> drop_role(const service&, std::string_view name);
future<> drop_role(const service&, stdx::string_view name);
///
/// Check if `grantee` has been granted the named role.
///
/// \returns an exceptional future with \ref nonexistent_role if `grantee` or `name` do not exist.
///
future<bool> has_role(const service&, std::string_view grantee, std::string_view name);
future<bool> has_role(const service&, stdx::string_view grantee, stdx::string_view name);
///
/// Check if the authenticated user has been granted the named role.
///
/// \returns an exceptional future with \ref nonexistent_role if the user or `name` do not exist.
///
future<bool> has_role(const service&, const authenticated_user&, std::string_view name);
future<bool> has_role(const service&, const authenticated_user&, stdx::string_view name);
///
/// \returns an exceptional future with \ref nonexistent_role if the named role does not exist.
@@ -235,7 +242,7 @@ future<bool> has_role(const service&, const authenticated_user&, std::string_vie
///
future<> grant_permissions(
const service&,
std::string_view role_name,
stdx::string_view role_name,
permission_set,
const resource&);
@@ -247,7 +254,7 @@ future<> grant_permissions(
/// \returns an exceptional future with \ref unsupported_authorization_operation if granting permissions is not
/// supported.
///
future<> grant_applicable_permissions(const service&, std::string_view role_name, const resource&);
future<> grant_applicable_permissions(const service&, stdx::string_view role_name, const resource&);
future<> grant_applicable_permissions(const service&, const authenticated_user&, const resource&);
///
@@ -258,7 +265,7 @@ future<> grant_applicable_permissions(const service&, const authenticated_user&,
///
future<> revoke_permissions(
const service&,
std::string_view role_name,
stdx::string_view role_name,
permission_set,
const resource&);
@@ -283,7 +290,7 @@ using recursive_permissions = bool_class<struct recursive_permissions_tag>;
future<std::vector<permission_details>> list_filtered_permissions(
const service&,
permission_set,
std::optional<std::string_view> role_name,
std::optional<stdx::string_view> role_name,
const std::optional<std::pair<resource, recursive_permissions>>& resource_filter);
}

View File

@@ -21,7 +21,7 @@
#include "auth/standard_role_manager.hh"
#include <optional>
#include <experimental/optional>
#include <unordered_set>
#include <vector>
@@ -39,7 +39,6 @@
#include "exceptions/exceptions.hh"
#include "log.hh"
#include "utils/class_registrator.hh"
#include "database.hh"
namespace auth {
@@ -47,9 +46,9 @@ namespace meta {
namespace role_members_table {
constexpr std::string_view name{"role_members" , 12};
constexpr stdx::string_view name{"role_members" , 12};
static std::string_view qualified_name() noexcept {
static stdx::string_view qualified_name() noexcept {
static const sstring instance = AUTH_KS + "." + sstring(name);
return instance;
}
@@ -73,7 +72,7 @@ struct record final {
role_set member_of;
};
static db::consistency_level consistency_for_role(std::string_view role_name) noexcept {
static db::consistency_level consistency_for_role(stdx::string_view role_name) noexcept {
if (role_name == meta::DEFAULT_SUPERUSER_NAME) {
return db::consistency_level::QUORUM;
}
@@ -81,24 +80,24 @@ static db::consistency_level consistency_for_role(std::string_view role_name) no
return db::consistency_level::LOCAL_ONE;
}
static future<std::optional<record>> find_record(cql3::query_processor& qp, std::string_view role_name) {
static const sstring query = format("SELECT * FROM {} WHERE {} = ?",
static future<stdx::optional<record>> find_record(cql3::query_processor& qp, stdx::string_view role_name) {
static const sstring query = sprint(
"SELECT * FROM %s WHERE %s = ?",
meta::roles_table::qualified_name(),
meta::roles_table::role_col_name);
return qp.process(
query,
consistency_for_role(role_name),
internal_distributed_timeout_config(),
{sstring(role_name)},
true).then([](::shared_ptr<cql3::untyped_result_set> results) {
if (results->empty()) {
return std::optional<record>();
return stdx::optional<record>();
}
const cql3::untyped_result_set_row& row = results->one();
return std::make_optional(
return stdx::make_optional(
record{
row.get_as<sstring>(sstring(meta::roles_table::role_col_name)),
row.get_as<bool>("is_superuser"),
@@ -109,8 +108,8 @@ static future<std::optional<record>> find_record(cql3::query_processor& qp, std:
});
}
static future<record> require_record(cql3::query_processor& qp, std::string_view role_name) {
return find_record(qp, role_name).then([role_name](std::optional<record> mr) {
static future<record> require_record(cql3::query_processor& qp, stdx::string_view role_name) {
return find_record(qp, role_name).then([role_name](stdx::optional<record> mr) {
if (!mr) {
throw nonexistant_role(role_name);
}
@@ -123,12 +122,12 @@ static bool has_can_login(const cql3::untyped_result_set_row& row) {
return row.has("can_login") && !(boolean_type->deserialize(row.get_blob("can_login")).is_null());
}
std::string_view standard_role_manager_name() noexcept {
stdx::string_view standard_role_manager_name() noexcept {
static const sstring instance = meta::AUTH_PACKAGE_NAME + "CassandraRoleManager";
return instance;
}
std::string_view standard_role_manager::qualified_java_name() const noexcept {
stdx::string_view standard_role_manager::qualified_java_name() const noexcept {
return standard_role_manager_name();
}
@@ -166,14 +165,14 @@ future<> standard_role_manager::create_metadata_tables_if_missing() const {
future<> standard_role_manager::create_default_role_if_missing() const {
return default_role_row_satisfies(_qp, &has_can_login).then([this](bool exists) {
if (!exists) {
static const sstring query = format("INSERT INTO {} ({}, is_superuser, can_login) VALUES (?, true, true)",
static const sstring query = sprint(
"INSERT INTO %s (%s, is_superuser, can_login) VALUES (?, true, true)",
meta::roles_table::qualified_name(),
meta::roles_table::role_col_name);
return _qp.process(
query,
db::consistency_level::QUORUM,
internal_distributed_timeout_config(),
{meta::DEFAULT_SUPERUSER_NAME}).then([](auto&&) {
log.info("Created default superuser role '{}'.", meta::DEFAULT_SUPERUSER_NAME);
return make_ready_future<>();
@@ -190,17 +189,16 @@ future<> standard_role_manager::create_default_role_if_missing() const {
static const sstring legacy_table_name{"users"};
bool standard_role_manager::legacy_metadata_exists() const {
return _qp.db().has_schema(meta::AUTH_KS, legacy_table_name);
return _qp.db().local().has_schema(meta::AUTH_KS, legacy_table_name);
}
future<> standard_role_manager::migrate_legacy_metadata() const {
log.info("Starting migration of legacy user metadata.");
static const sstring query = format("SELECT * FROM {}.{}", meta::AUTH_KS, legacy_table_name);
static const sstring query = sprint("SELECT * FROM %s.%s", meta::AUTH_KS, legacy_table_name);
return _qp.process(
query,
db::consistency_level::QUORUM,
internal_distributed_timeout_config()).then([this](::shared_ptr<cql3::untyped_result_set> results) {
db::consistency_level::QUORUM).then([this](::shared_ptr<cql3::untyped_result_set> results) {
return do_for_each(*results, [this](const cql3::untyped_result_set_row& row) {
role_config config;
config.is_superuser = row.get_as<bool>("super");
@@ -226,7 +224,7 @@ future<> standard_role_manager::start() {
return this->create_metadata_tables_if_missing().then([this] {
_stopped = auth::do_after_system_ready(_as, [this] {
return seastar::async([this] {
wait_for_schema_agreement(_migration_manager, _qp.db(), _as).get0();
wait_for_schema_agreement(_migration_manager, _qp.db().local()).get0();
if (any_nondefault_role_row_satisfies(_qp, &has_can_login).get0()) {
if (this->legacy_metadata_exists()) {
@@ -250,24 +248,24 @@ future<> standard_role_manager::start() {
future<> standard_role_manager::stop() {
_as.request_abort();
return _stopped.handle_exception_type([] (const sleep_aborted&) { }).handle_exception_type([](const abort_requested_exception&) {});;
return _stopped.handle_exception_type([] (const sleep_aborted&) { });
}
future<> standard_role_manager::create_or_replace(std::string_view role_name, const role_config& c) const {
static const sstring query = format("INSERT INTO {} ({}, is_superuser, can_login) VALUES (?, ?, ?)",
future<> standard_role_manager::create_or_replace(stdx::string_view role_name, const role_config& c) const {
static const sstring query = sprint(
"INSERT INTO %s (%s, is_superuser, can_login) VALUES (?, ?, ?)",
meta::roles_table::qualified_name(),
meta::roles_table::role_col_name);
return _qp.process(
query,
consistency_for_role(role_name),
internal_distributed_timeout_config(),
{sstring(role_name), c.is_superuser, c.can_login},
true).discard_result();
}
future<>
standard_role_manager::create(std::string_view role_name, const role_config& c) const {
standard_role_manager::create(stdx::string_view role_name, const role_config& c) const {
return this->exists(role_name).then([this, role_name, &c](bool role_exists) {
if (role_exists) {
throw role_already_exists(role_name);
@@ -278,7 +276,7 @@ standard_role_manager::create(std::string_view role_name, const role_config& c)
}
future<>
standard_role_manager::alter(std::string_view role_name, const role_config_update& u) const {
standard_role_manager::alter(stdx::string_view role_name, const role_config_update& u) const {
static const auto build_column_assignments = [](const role_config_update& u) -> sstring {
std::vector<sstring> assignments;
@@ -299,17 +297,17 @@ standard_role_manager::alter(std::string_view role_name, const role_config_updat
}
return _qp.process(
format("UPDATE {} SET {} WHERE {} = ?",
sprint(
"UPDATE %s SET %s WHERE %s = ?",
meta::roles_table::qualified_name(),
build_column_assignments(u),
meta::roles_table::role_col_name),
consistency_for_role(role_name),
internal_distributed_timeout_config(),
{sstring(role_name)}).discard_result();
});
}
future<> standard_role_manager::drop(std::string_view role_name) const {
future<> standard_role_manager::drop(stdx::string_view role_name) const {
return this->exists(role_name).then([this, role_name](bool role_exists) {
if (!role_exists) {
throw nonexistant_role(role_name);
@@ -317,13 +315,13 @@ future<> standard_role_manager::drop(std::string_view role_name) const {
// First, revoke this role from all roles that are members of it.
const auto revoke_from_members = [this, role_name] {
static const sstring query = format("SELECT member FROM {} WHERE role = ?",
static const sstring query = sprint(
"SELECT member FROM %s WHERE role = ?",
meta::role_members_table::qualified_name());
return _qp.process(
query,
consistency_for_role(role_name),
internal_distributed_timeout_config(),
{sstring(role_name)}).then([this, role_name](::shared_ptr<cql3::untyped_result_set> members) {
return parallel_for_each(
members->begin(),
@@ -355,14 +353,14 @@ future<> standard_role_manager::drop(std::string_view role_name) const {
// Finally, delete the role itself.
auto delete_role = [this, role_name] {
static const sstring query = format("DELETE FROM {} WHERE {} = ?",
static const sstring query = sprint(
"DELETE FROM %s WHERE %s = ?",
meta::roles_table::qualified_name(),
meta::roles_table::role_col_name);
return _qp.process(
query,
consistency_for_role(role_name),
internal_distributed_timeout_config(),
{sstring(role_name)}).discard_result();
};
@@ -374,14 +372,14 @@ future<> standard_role_manager::drop(std::string_view role_name) const {
future<>
standard_role_manager::modify_membership(
std::string_view grantee_name,
std::string_view role_name,
stdx::string_view grantee_name,
stdx::string_view role_name,
membership_change ch) const {
const auto modify_roles = [this, role_name, grantee_name, ch] {
const auto query = format(
"UPDATE {} SET member_of = member_of {} ? WHERE {} = ?",
const auto query = sprint(
"UPDATE %s SET member_of = member_of %s ? WHERE %s = ?",
meta::roles_table::qualified_name(),
(ch == membership_change::add ? '+' : '-'),
meta::roles_table::role_col_name);
@@ -389,7 +387,6 @@ standard_role_manager::modify_membership(
return _qp.process(
query,
consistency_for_role(grantee_name),
internal_distributed_timeout_config(),
{role_set{sstring(role_name)}, sstring(grantee_name)}).discard_result();
};
@@ -397,18 +394,18 @@ standard_role_manager::modify_membership(
switch (ch) {
case membership_change::add:
return _qp.process(
format("INSERT INTO {} (role, member) VALUES (?, ?)",
sprint(
"INSERT INTO %s (role, member) VALUES (?, ?)",
meta::role_members_table::qualified_name()),
consistency_for_role(role_name),
internal_distributed_timeout_config(),
{sstring(role_name), sstring(grantee_name)}).discard_result();
case membership_change::remove:
return _qp.process(
format("DELETE FROM {} WHERE role = ? AND member = ?",
sprint(
"DELETE FROM %s WHERE role = ? AND member = ?",
meta::role_members_table::qualified_name()),
consistency_for_role(role_name),
internal_distributed_timeout_config(),
{sstring(role_name), sstring(grantee_name)}).discard_result();
}
@@ -419,7 +416,7 @@ standard_role_manager::modify_membership(
}
future<>
standard_role_manager::grant(std::string_view grantee_name, std::string_view role_name) const {
standard_role_manager::grant(stdx::string_view grantee_name, stdx::string_view role_name) const {
const auto check_redundant = [this, role_name, grantee_name] {
return this->query_granted(
grantee_name,
@@ -450,7 +447,7 @@ standard_role_manager::grant(std::string_view grantee_name, std::string_view rol
}
future<>
standard_role_manager::revoke(std::string_view revokee_name, std::string_view role_name) const {
standard_role_manager::revoke(stdx::string_view revokee_name, stdx::string_view role_name) const {
return this->exists(role_name).then([this, revokee_name, role_name](bool role_exists) {
if (!role_exists) {
throw nonexistant_role(sstring(role_name));
@@ -472,7 +469,7 @@ standard_role_manager::revoke(std::string_view revokee_name, std::string_view ro
static future<> collect_roles(
cql3::query_processor& qp,
std::string_view grantee_name,
stdx::string_view grantee_name,
bool recurse,
role_set& roles) {
return require_record(qp, grantee_name).then([&qp, &roles, recurse](record r) {
@@ -490,7 +487,7 @@ static future<> collect_roles(
});
}
future<role_set> standard_role_manager::query_granted(std::string_view grantee_name, recursive_role_query m) const {
future<role_set> standard_role_manager::query_granted(stdx::string_view grantee_name, recursive_role_query m) const {
const bool recurse = (m == recursive_role_query::yes);
return do_with(
@@ -501,17 +498,15 @@ future<role_set> standard_role_manager::query_granted(std::string_view grantee_n
}
future<role_set> standard_role_manager::query_all() const {
static const sstring query = format("SELECT {} FROM {}",
static const sstring query = sprint(
"SELECT %s FROM %s",
meta::roles_table::role_col_name,
meta::roles_table::qualified_name());
// To avoid many copies of a view.
static const auto role_col_name_string = sstring(meta::roles_table::role_col_name);
return _qp.process(
query,
db::consistency_level::QUORUM,
internal_distributed_timeout_config()).then([](::shared_ptr<cql3::untyped_result_set> results) {
return _qp.process(query, db::consistency_level::QUORUM).then([](::shared_ptr<cql3::untyped_result_set> results) {
role_set roles;
std::transform(
@@ -526,19 +521,19 @@ future<role_set> standard_role_manager::query_all() const {
});
}
future<bool> standard_role_manager::exists(std::string_view role_name) const {
return find_record(_qp, role_name).then([](std::optional<record> mr) {
future<bool> standard_role_manager::exists(stdx::string_view role_name) const {
return find_record(_qp, role_name).then([](stdx::optional<record> mr) {
return static_cast<bool>(mr);
});
}
future<bool> standard_role_manager::is_superuser(std::string_view role_name) const {
future<bool> standard_role_manager::is_superuser(stdx::string_view role_name) const {
return require_record(_qp, role_name).then([](record r) {
return r.is_superuser;
});
}
future<bool> standard_role_manager::can_login(std::string_view role_name) const {
future<bool> standard_role_manager::can_login(stdx::string_view role_name) const {
return require_record(_qp, role_name).then([](record r) {
return r.can_login;
});

View File

@@ -23,13 +23,14 @@
#include "auth/role_manager.hh"
#include <string_view>
#include <experimental/string_view>
#include <unordered_set>
#include <seastar/core/abort_source.hh>
#include <seastar/core/future.hh>
#include <seastar/core/sstring.hh>
#include "stdx.hh"
#include "seastarx.hh"
namespace cql3 {
@@ -42,7 +43,7 @@ class migration_manager;
namespace auth {
std::string_view standard_role_manager_name() noexcept;
stdx::string_view standard_role_manager_name() noexcept;
class standard_role_manager final : public role_manager {
cql3::query_processor& _qp;
@@ -57,7 +58,7 @@ public:
, _stopped(make_ready_future<>()) {
}
virtual std::string_view qualified_java_name() const noexcept override;
virtual stdx::string_view qualified_java_name() const noexcept override;
virtual const resource_set& protected_resources() const override;
@@ -65,25 +66,25 @@ public:
virtual future<> stop() override;
virtual future<> create(std::string_view role_name, const role_config&) const override;
virtual future<> create(stdx::string_view role_name, const role_config&) const override;
virtual future<> drop(std::string_view role_name) const override;
virtual future<> drop(stdx::string_view role_name) const override;
virtual future<> alter(std::string_view role_name, const role_config_update&) const override;
virtual future<> alter(stdx::string_view role_name, const role_config_update&) const override;
virtual future<> grant(std::string_view grantee_name, std::string_view role_name) const override;
virtual future<> grant(stdx::string_view grantee_name, stdx::string_view role_name) const override;
virtual future<> revoke(std::string_view revokee_name, std::string_view role_name) const override;
virtual future<> revoke(stdx::string_view revokee_name, stdx::string_view role_name) const override;
virtual future<role_set> query_granted(std::string_view grantee_name, recursive_role_query) const override;
virtual future<role_set> query_granted(stdx::string_view grantee_name, recursive_role_query) const override;
virtual future<role_set> query_all() const override;
virtual future<bool> exists(std::string_view role_name) const override;
virtual future<bool> exists(stdx::string_view role_name) const override;
virtual future<bool> is_superuser(std::string_view role_name) const override;
virtual future<bool> is_superuser(stdx::string_view role_name) const override;
virtual future<bool> can_login(std::string_view role_name) const override;
virtual future<bool> can_login(stdx::string_view role_name) const override;
private:
enum class membership_change { add, remove };
@@ -96,9 +97,9 @@ private:
future<> create_default_role_if_missing() const;
future<> create_or_replace(std::string_view role_name, const role_config&) const;
future<> create_or_replace(stdx::string_view role_name, const role_config&) const;
future<> modify_membership(std::string_view role_name, std::string_view grantee_name, membership_change) const;
future<> modify_membership(stdx::string_view role_name, stdx::string_view grantee_name, membership_change) const;
};
}

View File

@@ -45,6 +45,7 @@
#include "auth/default_authorizer.hh"
#include "auth/password_authenticator.hh"
#include "auth/permission.hh"
#include "db/config.hh"
#include "utils/class_registrator.hh"
namespace auth {
@@ -117,19 +118,19 @@ public:
});
}
virtual future<> create(std::string_view role_name, const authentication_options& options) const override {
virtual future<> create(stdx::string_view role_name, const authentication_options& options) const override {
return _authenticator->create(role_name, options);
}
virtual future<> alter(std::string_view role_name, const authentication_options& options) const override {
virtual future<> alter(stdx::string_view role_name, const authentication_options& options) const override {
return _authenticator->alter(role_name, options);
}
virtual future<> drop(std::string_view role_name) const override {
virtual future<> drop(stdx::string_view role_name) const override {
return _authenticator->drop(role_name);
}
virtual future<custom_options> query_custom_options(std::string_view role_name) const override {
virtual future<custom_options> query_custom_options(stdx::string_view role_name) const override {
return _authenticator->query_custom_options(role_name);
}
@@ -217,11 +218,11 @@ public:
return make_ready_future<permission_set>(transitional_permissions);
}
virtual future<> grant(std::string_view s, permission_set ps, const resource& r) const override {
virtual future<> grant(stdx::string_view s, permission_set ps, const resource& r) const override {
return _authorizer->grant(s, std::move(ps), r);
}
virtual future<> revoke(std::string_view s, permission_set ps, const resource& r) const override {
virtual future<> revoke(stdx::string_view s, permission_set ps, const resource& r) const override {
return _authorizer->revoke(s, std::move(ps), r);
}
@@ -229,7 +230,7 @@ public:
return _authorizer->list_all();
}
virtual future<> revoke_all(std::string_view s) const override {
virtual future<> revoke_all(stdx::string_view s) const override {
return _authorizer->revoke_all(s);
}

View File

@@ -77,7 +77,7 @@ protected:
, _io_priority(iop)
, _interval(interval)
, _update_timer([this] { adjust(); })
, _control_points()
, _control_points({{0,0}})
, _current_backlog(std::move(backlog))
, _inflight_update(make_ready_future<>())
{
@@ -96,12 +96,6 @@ protected:
}
virtual ~backlog_controller() {}
public:
backlog_controller(backlog_controller&&) = default;
float backlog_of_shares(float shares) const;
seastar::scheduling_group sg() {
return _scheduling_group;
}
};
// memtable flush CPU controller.
@@ -125,7 +119,7 @@ public:
flush_controller(seastar::scheduling_group sg, const ::io_priority_class& iop, float static_shares) : backlog_controller(sg, iop, static_shares) {}
flush_controller(seastar::scheduling_group sg, const ::io_priority_class& iop, std::chrono::milliseconds interval, float soft_limit, std::function<float()> current_dirty)
: backlog_controller(sg, iop, std::move(interval),
std::vector<backlog_controller::control_point>({{0.0, 0.0}, {soft_limit, 10}, {soft_limit + (hard_dirty_limit - soft_limit) / 2, 200} , {hard_dirty_limit, 1000}}),
std::vector<backlog_controller::control_point>({{soft_limit, 100}, {soft_limit + (hard_dirty_limit - soft_limit) / 2, 200} , {hard_dirty_limit, 1000}}),
std::move(current_dirty)
)
{}
@@ -134,12 +128,10 @@ public:
class compaction_controller : public backlog_controller {
public:
static constexpr unsigned normalization_factor = 30;
static constexpr float disable_backlog = std::numeric_limits<double>::infinity();
static constexpr float backlog_disabled(float backlog) { return std::isinf(backlog); }
compaction_controller(seastar::scheduling_group sg, const ::io_priority_class& iop, float static_shares) : backlog_controller(sg, iop, static_shares) {}
compaction_controller(seastar::scheduling_group sg, const ::io_priority_class& iop, std::chrono::milliseconds interval, std::function<float()> current_backlog)
: backlog_controller(sg, iop, std::move(interval),
std::vector<backlog_controller::control_point>({{0.0, 50}, {1.5, 100} , {normalization_factor, 1000}}),
std::vector<backlog_controller::control_point>({{0.5, 10}, {1.5, 100} , {normalization_factor, 1000}}),
std::move(current_backlog)
)
{}

View File

@@ -20,7 +20,7 @@
*/
#include "bytes.hh"
#include <seastar/core/print.hh>
#include "core/print.hh"
static inline int8_t hex_to_int(unsigned char c) {
switch (c) {
@@ -55,7 +55,7 @@ bytes from_hex(sstring_view s) {
auto half_byte1 = hex_to_int(s[i * 2]);
auto half_byte2 = hex_to_int(s[i * 2 + 1]);
if (half_byte1 == -1 || half_byte2 == -1) {
throw std::invalid_argument(format("Non-hex characters in {}", s));
throw std::invalid_argument(sprint("Non-hex characters in %s", s));
}
out[i] = (half_byte1 << 4) | half_byte2;
}

View File

@@ -22,22 +22,18 @@
#pragma once
#include "seastarx.hh"
#include <seastar/core/sstring.hh>
#include "core/sstring.hh"
#include "hashing.hh"
#include <optional>
#include <experimental/optional>
#include <iosfwd>
#include <functional>
#include "utils/mutable_view.hh"
using bytes = basic_sstring<int8_t, uint32_t, 31, false>;
using bytes_view = std::basic_string_view<int8_t>;
using bytes = basic_sstring<int8_t, uint32_t, 31>;
using bytes_view = std::experimental::basic_string_view<int8_t>;
using bytes_mutable_view = basic_mutable_view<bytes_view::value_type>;
using bytes_opt = std::optional<bytes>;
using sstring_view = std::string_view;
inline sstring_view to_sstring_view(bytes_view view) {
return {reinterpret_cast<const char*>(view.data()), view.size()};
}
using bytes_opt = std::experimental::optional<bytes>;
using sstring_view = std::experimental::string_view;
namespace std {
@@ -82,11 +78,3 @@ struct appending_hash<bytes_view> {
h.update(reinterpret_cast<const char*>(v.begin()), v.size() * sizeof(bytes_view::value_type));
}
};
inline int32_t compare_unsigned(bytes_view v1, bytes_view v2) {
auto n = memcmp(v1.begin(), v2.begin(), std::min(v1.size(), v2.size()));
if (n) {
return n;
}
return (int32_t) (v1.size() - v2.size());
}

View File

@@ -24,9 +24,9 @@
#include <boost/range/iterator_range.hpp>
#include "bytes.hh"
#include <seastar/core/unaligned.hh>
#include "core/unaligned.hh"
#include "hashing.hh"
#include <seastar/core/simple-stream.hh>
#include "seastar/core/simple-stream.hh"
/**
* Utility for writing data into a buffer when its final size is not known up front.
*
@@ -38,7 +38,7 @@ class bytes_ostream {
public:
using size_type = bytes::size_type;
using value_type = bytes::value_type;
static constexpr size_type max_chunk_size() { return 128 * 1024; }
static constexpr size_type max_chunk_size() { return 16 * 1024; }
private:
static_assert(sizeof(value_type) == 1, "value_type is assumed to be one byte long");
struct chunk {
@@ -57,17 +57,16 @@ private:
value_type data[0];
void operator delete(void* ptr) { free(ptr); }
};
static constexpr size_type default_chunk_size{512};
// FIXME: consider increasing chunk size as the buffer grows
static constexpr size_type chunk_size{512};
private:
std::unique_ptr<chunk> _begin;
chunk* _current;
size_type _size;
size_type _initial_chunk_size = default_chunk_size;
public:
class fragment_iterator : public std::iterator<std::input_iterator_tag, bytes_view> {
chunk* _current = nullptr;
chunk* _current;
public:
fragment_iterator() = default;
fragment_iterator(chunk* current) : _current(current) {}
fragment_iterator(const fragment_iterator&) = default;
fragment_iterator& operator=(const fragment_iterator&) = default;
@@ -102,13 +101,13 @@ private:
}
// Figure out next chunk size.
// - must be enough for data_size
// - must be at least _initial_chunk_size
// - must be at least chunk_size
// - try to double each time to prevent too many allocations
// - do not exceed max_chunk_size
size_type next_alloc_size(size_t data_size) const {
auto next_size = _current
? _current->size * 2
: _initial_chunk_size;
: chunk_size;
next_size = std::min(next_size, max_chunk_size());
// FIXME: check for overflow?
return std::max<size_type>(next_size, data_size + sizeof(chunk));
@@ -116,19 +115,13 @@ private:
// Makes room for a contiguous region of given size.
// The region is accounted for as already written.
// size must not be zero.
[[gnu::always_inline]]
value_type* alloc(size_type size) {
if (__builtin_expect(size <= current_space_left(), true)) {
if (size <= current_space_left()) {
auto ret = _current->data + _current->offset;
_current->offset += size;
_size += size;
return ret;
} else {
return alloc_new(size);
}
}
[[gnu::noinline]]
value_type* alloc_new(size_type size) {
auto alloc_size = next_alloc_size(size);
auto space = malloc(alloc_size);
if (!space) {
@@ -146,22 +139,19 @@ private:
}
_size += size;
return _current->data;
};
}
public:
explicit bytes_ostream(size_t initial_chunk_size) noexcept
bytes_ostream() noexcept
: _begin()
, _current(nullptr)
, _size(0)
, _initial_chunk_size(initial_chunk_size)
{ }
bytes_ostream() noexcept : bytes_ostream(default_chunk_size) {}
bytes_ostream(bytes_ostream&& o) noexcept
: _begin(std::move(o._begin))
, _current(o._current)
, _size(o._size)
, _initial_chunk_size(o._initial_chunk_size)
{
o._current = nullptr;
o._size = 0;
@@ -171,7 +161,6 @@ public:
: _begin()
, _current(nullptr)
, _size(0)
, _initial_chunk_size(o._initial_chunk_size)
{
append(o);
}
@@ -209,20 +198,18 @@ public:
return place_holder<T>{alloc(sizeof(T))};
}
[[gnu::always_inline]]
value_type* write_place_holder(size_type size) {
return alloc(size);
}
// Writes given sequence of bytes
[[gnu::always_inline]]
inline void write(bytes_view v) {
if (v.empty()) {
return;
}
auto this_size = std::min(v.size(), size_t(current_space_left()));
if (__builtin_expect(this_size, true)) {
if (this_size) {
memcpy(_current->data + _current->offset, v.begin(), this_size);
_current->offset += this_size;
_size += this_size;
@@ -231,12 +218,11 @@ public:
while (!v.empty()) {
auto this_size = std::min(v.size(), size_t(max_chunk_size()));
std::copy_n(v.begin(), this_size, alloc_new(this_size));
std::copy_n(v.begin(), this_size, alloc(this_size));
v.remove_prefix(this_size);
}
}
[[gnu::always_inline]]
void write(const char* ptr, size_t size) {
write(bytes_view(reinterpret_cast<const signed char*>(ptr), size));
}
@@ -303,24 +289,6 @@ public:
}
}
// Removes n bytes from the end of the bytes_ostream.
// Beware of O(n) algorithm.
void remove_suffix(size_t n) {
_size -= n;
auto left = _size;
auto current = _begin.get();
while (current) {
if (current->offset >= left) {
current->offset = left;
_current = current;
current->next.reset();
return;
}
left -= current->offset;
current = current->next.get();
}
}
// begin() and end() form an input range to bytes_view representing fragments.
// Any modification of this instance invalidates iterators.
fragment_iterator begin() const { return { _begin.get() }; }
@@ -406,19 +374,14 @@ public:
bool operator!=(const bytes_ostream& other) const {
return !(*this == other);
}
};
// Makes this instance empty.
//
// The first buffer is not deallocated, so callers may rely on the
// fact that if they write less than the initial chunk size between
// the clear() calls then writes will not involve any memory allocations,
// except for the first write made on this instance.
void clear() {
if (_begin) {
_begin->offset = 0;
_size = 0;
_current = _begin.get();
_begin->next.reset();
template<>
struct appending_hash<bytes_ostream> {
template<typename Hasher>
void operator()(Hasher& h, const bytes_ostream& b) const {
for (auto&& frag : b.fragments()) {
feed_hash(h, frag);
}
}
};

View File

@@ -61,12 +61,11 @@ class cache_flat_mutation_reader final : public flat_mutation_reader::impl {
// - _last_row points at a direct predecessor of the next row which is going to be read.
// Used for populating continuity.
// - _population_range_starts_before_all_rows is set accordingly
// - _underlying is engaged and fast-forwarded
reading_from_underlying,
end_of_stream
};
partition_snapshot_ptr _snp;
lw_shared_ptr<partition_snapshot> _snp;
position_in_partition::tri_compare _position_cmp;
query::clustering_key_filter_ranges _ck_ranges;
@@ -95,18 +94,7 @@ class cache_flat_mutation_reader final : public flat_mutation_reader::impl {
// Valid when _state == reading_from_underlying.
bool _population_range_starts_before_all_rows;
// Whether _lower_bound was changed within current fill_buffer().
// If it did not then we cannot break out of it (e.g. on preemption) because
// forward progress is not guaranteed in case iterators are getting constantly invalidated.
bool _lower_bound_changed = false;
// Points to the underlying reader conforming to _schema,
// either to *_underlying_holder or _read_context->underlying().underlying().
flat_mutation_reader* _underlying = nullptr;
std::optional<flat_mutation_reader> _underlying_holder;
future<> do_fill_buffer(db::timeout_clock::time_point);
future<> ensure_underlying(db::timeout_clock::time_point);
void copy_from_cache_to_buffer();
future<> process_static_row(db::timeout_clock::time_point);
void move_to_end();
@@ -144,7 +132,7 @@ public:
dht::decorated_key dk,
query::clustering_key_filter_ranges&& crr,
lw_shared_ptr<read_context> ctx,
partition_snapshot_ptr snp,
lw_shared_ptr<partition_snapshot> snp,
row_cache& cache)
: flat_mutation_reader::impl(std::move(s))
, _snp(std::move(snp))
@@ -164,6 +152,9 @@ public:
cache_flat_mutation_reader(const cache_flat_mutation_reader&) = delete;
cache_flat_mutation_reader(cache_flat_mutation_reader&&) = delete;
virtual future<> fill_buffer(db::timeout_clock::time_point timeout) override;
virtual ~cache_flat_mutation_reader() {
maybe_merge_versions(_snp, _lsa_manager.region(), _lsa_manager.read_section());
}
virtual void next_partition() override {
clear_buffer_to_next_partition();
if (is_buffer_empty()) {
@@ -193,22 +184,23 @@ future<> cache_flat_mutation_reader::process_static_row(db::timeout_clock::time_
return make_ready_future<>();
} else {
_read_context->cache().on_row_miss();
return ensure_underlying(timeout).then([this, timeout] {
return (*_underlying)(timeout).then([this] (mutation_fragment_opt&& sr) {
if (sr) {
assert(sr->is_static_row());
maybe_add_to_cache(sr->as_static_row());
push_mutation_fragment(std::move(*sr));
}
maybe_set_static_row_continuous();
});
return _read_context->get_next_fragment(timeout).then([this] (mutation_fragment_opt&& sr) {
if (sr) {
assert(sr->is_static_row());
maybe_add_to_cache(sr->as_static_row());
push_mutation_fragment(std::move(*sr));
}
maybe_set_static_row_continuous();
});
}
}
inline
void cache_flat_mutation_reader::touch_partition() {
_snp->touch();
if (_snp->at_latest_version()) {
rows_entry& last_dummy = *_snp->version()->partition().clustered_rows().rbegin();
_snp->tracker()->touch(last_dummy);
}
}
inline
@@ -238,36 +230,14 @@ future<> cache_flat_mutation_reader::fill_buffer(db::timeout_clock::time_point t
});
}
inline
future<> cache_flat_mutation_reader::ensure_underlying(db::timeout_clock::time_point timeout) {
if (_underlying) {
return make_ready_future<>();
}
return _read_context->ensure_underlying(timeout).then([this, timeout] {
flat_mutation_reader& ctx_underlying = _read_context->underlying().underlying();
if (ctx_underlying.schema() != _schema) {
_underlying_holder = make_delegating_reader(ctx_underlying);
_underlying_holder->upgrade_schema(_schema);
_underlying = &*_underlying_holder;
} else {
_underlying = &ctx_underlying;
}
});
}
inline
future<> cache_flat_mutation_reader::do_fill_buffer(db::timeout_clock::time_point timeout) {
if (_state == state::move_to_underlying) {
if (!_underlying) {
return ensure_underlying(timeout).then([this, timeout] {
return do_fill_buffer(timeout);
});
}
_state = state::reading_from_underlying;
_population_range_starts_before_all_rows = _lower_bound.is_before_all_clustered_rows(*_schema);
auto end = _next_row_in_range ? position_in_partition(_next_row.position())
: position_in_partition(_upper_bound);
return _underlying->fast_forward_to(position_range{_lower_bound, std::move(end)}, timeout).then([this, timeout] {
return _read_context->fast_forward_to(position_range{_lower_bound, std::move(end)}, timeout).then([this, timeout] {
return read_from_underlying(timeout);
});
}
@@ -292,13 +262,9 @@ future<> cache_flat_mutation_reader::do_fill_buffer(db::timeout_clock::time_poin
}
_next_row.maybe_refresh();
clogger.trace("csm {}: next={}, cont={}", this, _next_row.position(), _next_row.continuous());
_lower_bound_changed = false;
while (_state == state::reading_from_cache) {
while (!is_buffer_full() && _state == state::reading_from_cache) {
copy_from_cache_to_buffer();
// We need to check _lower_bound_changed even if is_buffer_full() because
// we may have emitted only a range tombstone which overlapped with _lower_bound
// and thus didn't cause _lower_bound to change.
if ((need_preempt() || is_buffer_full()) && _lower_bound_changed) {
if (need_preempt()) {
break;
}
}
@@ -308,7 +274,7 @@ future<> cache_flat_mutation_reader::do_fill_buffer(db::timeout_clock::time_poin
inline
future<> cache_flat_mutation_reader::read_from_underlying(db::timeout_clock::time_point timeout) {
return consume_mutation_fragments_until(*_underlying,
return consume_mutation_fragments_until(_read_context->underlying().underlying(),
[this] { return _state != state::reading_from_underlying || is_buffer_full(); },
[this] (mutation_fragment mf) {
_read_context->cache().on_row_miss();
@@ -389,7 +355,7 @@ future<> cache_flat_mutation_reader::read_from_underlying(db::timeout_clock::tim
}
});
return make_ready_future<>();
}, timeout);
});
}
inline
@@ -408,7 +374,7 @@ bool cache_flat_mutation_reader::ensure_population_lower_bound() {
rows_entry::compare less(*_schema);
// FIXME: Avoid the copy by inserting an incomplete clustering row
auto e = alloc_strategy_unique_ptr<rows_entry>(
current_allocator().construct<rows_entry>(*_schema, *_last_row));
current_allocator().construct<rows_entry>(*_last_row));
e->set_continuous(false);
auto insert_result = rows.insert_check(rows.end(), *e, less);
auto inserted = insert_result.second;
@@ -453,7 +419,7 @@ void cache_flat_mutation_reader::maybe_add_to_cache(const clustering_row& cr) {
_read_context->cache().on_mispopulate();
return;
}
clogger.trace("csm {}: populate({})", this, clustering_row::printer(*_schema, cr));
clogger.trace("csm {}: populate({})", this, cr);
_lsa_manager.run_in_update_section_with_allocator([this, &cr] {
mutation_partition& mp = _snp->version()->partition();
rows_entry::compare less(*_schema);
@@ -462,7 +428,7 @@ void cache_flat_mutation_reader::maybe_add_to_cache(const clustering_row& cr) {
cr.cells().prepare_hash(*_schema, column_kind::regular_column);
}
auto new_entry = alloc_strategy_unique_ptr<rows_entry>(
current_allocator().construct<rows_entry>(*_schema, cr.key(), cr.tomb(), cr.marker(), cr.cells()));
current_allocator().construct<rows_entry>(cr.key(), cr.tomb(), cr.marker(), cr.cells()));
new_entry->set_continuous(false);
auto it = _next_row.iterators_valid() ? _next_row.get_iterator_in_latest_version()
: mp.clustered_rows().lower_bound(cr.key(), less);
@@ -505,19 +471,15 @@ void cache_flat_mutation_reader::copy_from_cache_to_buffer() {
_next_row.touch();
position_in_partition_view next_lower_bound = _next_row.dummy() ? _next_row.position() : position_in_partition_view::after_key(_next_row.key());
for (auto &&rts : _snp->range_tombstones(_lower_bound, _next_row_in_range ? next_lower_bound : _upper_bound)) {
position_in_partition::less_compare less(*_schema);
// This guarantees that rts starts after any emitted clustering_row
// and not before any emitted range tombstone.
if (!less(_lower_bound, rts.position())) {
rts.set_start(*_schema, _lower_bound);
} else {
if (rts.trim_front(*_schema, _lower_bound)) {
_lower_bound = position_in_partition(rts.position());
_lower_bound_changed = true;
if (is_buffer_full()) {
return;
}
push_mutation_fragment(std::move(rts));
}
push_mutation_fragment(std::move(rts));
}
// We add the row to the buffer even when it's full.
// This simplifies the code. For more info see #3139.
@@ -554,7 +516,6 @@ void cache_flat_mutation_reader::move_to_range(query::clustering_row_ranges::con
_last_row = nullptr;
_lower_bound = std::move(lb);
_upper_bound = std::move(ub);
_lower_bound_changed = true;
_ck_ranges_curr = next_it;
auto adjacent = _next_row.advance_to(_lower_bound);
_next_row_in_range = !after_current_range(_next_row.position());
@@ -605,7 +566,7 @@ void cache_flat_mutation_reader::move_to_next_entry() {
inline
void cache_flat_mutation_reader::add_to_buffer(mutation_fragment&& mf) {
clogger.trace("csm {}: add_to_buffer({})", this, mutation_fragment::printer(*_schema, mf));
clogger.trace("csm {}: add_to_buffer({})", this, mf);
if (mf.is_clustering_row()) {
add_clustering_row_to_buffer(std::move(mf));
} else {
@@ -627,12 +588,11 @@ void cache_flat_mutation_reader::add_to_buffer(const partition_snapshot_row_curs
// (2) If _lower_bound > mf.position(), mf was emitted
inline
void cache_flat_mutation_reader::add_clustering_row_to_buffer(mutation_fragment&& mf) {
clogger.trace("csm {}: add_clustering_row_to_buffer({})", this, mutation_fragment::printer(*_schema, mf));
clogger.trace("csm {}: add_clustering_row_to_buffer({})", this, mf);
auto& row = mf.as_clustering_row();
auto new_lower_bound = position_in_partition::after_key(row.key());
push_mutation_fragment(std::move(mf));
_lower_bound = std::move(new_lower_bound);
_lower_bound_changed = true;
}
inline
@@ -640,16 +600,10 @@ void cache_flat_mutation_reader::add_to_buffer(range_tombstone&& rt) {
clogger.trace("csm {}: add_to_buffer({})", this, rt);
// This guarantees that rt starts after any emitted clustering_row
// and not before any emitted range tombstone.
position_in_partition::less_compare less(*_schema);
if (!less(_lower_bound, rt.end_position())) {
if (!rt.trim_front(*_schema, _lower_bound)) {
return;
}
if (!less(_lower_bound, rt.position())) {
rt.set_start(*_schema, _lower_bound);
} else {
_lower_bound = position_in_partition(rt.position());
_lower_bound_changed = true;
}
_lower_bound = position_in_partition(rt.position());
push_mutation_fragment(std::move(rt));
}
@@ -668,7 +622,7 @@ void cache_flat_mutation_reader::maybe_add_to_cache(const range_tombstone& rt) {
inline
void cache_flat_mutation_reader::maybe_add_to_cache(const static_row& sr) {
if (can_populate()) {
clogger.trace("csm {}: populate({})", this, static_row::printer(*_schema, sr));
clogger.trace("csm {}: populate({})", this, sr);
_read_context->cache().on_static_row_insert();
_lsa_manager.run_in_update_section_with_allocator([&] {
if (_read_context->digest_requested()) {
@@ -703,7 +657,7 @@ inline flat_mutation_reader make_cache_flat_mutation_reader(schema_ptr s,
query::clustering_key_filter_ranges crr,
row_cache& cache,
lw_shared_ptr<cache::read_context> ctx,
partition_snapshot_ptr snp)
lw_shared_ptr<partition_snapshot> snp)
{
return make_flat_mutation_reader<cache::cache_flat_mutation_reader>(
std::move(s), std::move(dk), std::move(crr), std::move(ctx), std::move(snp), cache);

View File

@@ -1,45 +0,0 @@
/*
* Copyright 2018 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include <stdint.h>
namespace ser {
template <typename T>
class serializer;
};
class cache_temperature {
float hit_rate;
explicit cache_temperature(uint8_t hr) : hit_rate(hr/255.0f) {}
public:
uint8_t get_serialized_temperature() const {
return hit_rate * 255;
}
cache_temperature() : hit_rate(0) {}
explicit cache_temperature(float hr) : hit_rate(hr) {}
explicit operator float() const { return hit_rate; }
static cache_temperature invalid() { return cache_temperature(-1.0f); }
friend struct ser::serializer<cache_temperature>;
};

View File

@@ -20,7 +20,7 @@
*/
#pragma once
#include <seastar/core/sstring.hh>
#include <core/sstring.hh>
#include <boost/lexical_cast.hpp>
#include "exceptions/exceptions.hh"
#include "json.hh"

View File

@@ -68,7 +68,7 @@ mutation canonical_mutation::to_mutation(schema_ptr s) const {
auto cf_id = mv.table_id();
if (s->id() != cf_id) {
throw std::runtime_error(format("Attempted to deserialize canonical_mutation of table {} with schema of table {} ({}.{})",
throw std::runtime_error(sprint("Attempted to deserialize canonical_mutation of table %s with schema of table %s (%s.%s)",
cf_id, s->id(), s->ks_name(), s->cf_name()));
}

View File

@@ -23,15 +23,29 @@
#include <boost/intrusive/unordered_set.hpp>
#include "utils/small_vector.hh"
#if __has_include(<boost/container/small_vector.hpp>)
#include <boost/container/small_vector.hpp>
template <typename T, size_t N>
using small_vector = boost::container::small_vector<T, N>;
#else
#include <vector>
template <typename T, size_t N>
using small_vector = std::vector<T>;
#endif
#include "fnv1a_hasher.hh"
#include "mutation_fragment.hh"
#include "mutation_partition.hh"
#include "xx_hasher.hh"
#include "db/timeout_clock.hh"
class cells_range {
using ids_vector_type = utils::small_vector<column_id, 5>;
using ids_vector_type = small_vector<column_id, 5>;
position_in_partition_view _position;
ids_vector_type _ids;
@@ -63,7 +77,7 @@ class partition_cells_range {
public:
class iterator {
const mutation_partition& _mp;
std::optional<mutation_partition::rows_type::const_iterator> _position;
stdx::optional<mutation_partition::rows_type::const_iterator> _position;
cells_range _current;
public:
explicit iterator(const mutation_partition& mp)
@@ -194,10 +208,10 @@ private:
explicit hasher(const schema& s) : _schema(&s) { }
size_t operator()(const cell_address& ca) const {
xx_hasher hasher;
fnv1a_hasher hasher;
ca.position.feed_hash(hasher, *_schema);
::feed_hash(hasher, ca.id);
return static_cast<size_t>(hasher.finalize_uint64());
return hasher.finalize();
}
size_t operator()(const cell_entry& ce) const {
return operator()(ce._address);

View File

@@ -22,7 +22,6 @@
#pragma once
#include <functional>
#include "keys.hh"
#include "schema.hh"
#include "range.hh"
@@ -44,20 +43,22 @@ bound_kind invert_kind(bound_kind k);
int32_t weight(bound_kind k);
class bound_view {
const static thread_local clustering_key _empty_prefix;
std::reference_wrapper<const clustering_key_prefix> _prefix;
bound_kind _kind;
public:
const static thread_local clustering_key empty_prefix;
const clustering_key_prefix& prefix;
bound_kind kind;
bound_view(const clustering_key_prefix& prefix, bound_kind kind)
: _prefix(prefix)
, _kind(kind)
: prefix(prefix)
, kind(kind)
{ }
bound_view(const bound_view& other) noexcept = default;
bound_view& operator=(const bound_view& other) noexcept = default;
bound_kind kind() const { return _kind; }
const clustering_key_prefix& prefix() const { return _prefix; }
bound_view& operator=(const bound_view& other) noexcept {
if (this != &other) {
this->~bound_view();
new (this) bound_view(other);
}
return *this;
}
struct tri_compare {
// To make it assignable and to avoid taking a schema_ptr, we
// wrap the schema reference.
@@ -81,13 +82,13 @@ public:
return d1 < d2 ? w1 - (w1 <= 0) : -(w2 - (w2 <= 0));
}
int operator()(const bound_view b, const clustering_key_prefix& p) const {
return operator()(b._prefix, weight(b._kind), p, 0);
return operator()(b.prefix, weight(b.kind), p, 0);
}
int operator()(const clustering_key_prefix& p, const bound_view b) const {
return operator()(p, 0, b._prefix, weight(b._kind));
return operator()(p, 0, b.prefix, weight(b.kind));
}
int operator()(const bound_view b1, const bound_view b2) const {
return operator()(b1._prefix, weight(b1._kind), b2._prefix, weight(b2._kind));
return operator()(b1.prefix, weight(b1.kind), b2.prefix, weight(b2.kind));
}
};
struct compare {
@@ -100,26 +101,26 @@ public:
return _cmp(p1, w1, p2, w2) < 0;
}
bool operator()(const bound_view b, const clustering_key_prefix& p) const {
return operator()(b._prefix, weight(b._kind), p, 0);
return operator()(b.prefix, weight(b.kind), p, 0);
}
bool operator()(const clustering_key_prefix& p, const bound_view b) const {
return operator()(p, 0, b._prefix, weight(b._kind));
return operator()(p, 0, b.prefix, weight(b.kind));
}
bool operator()(const bound_view b1, const bound_view b2) const {
return operator()(b1._prefix, weight(b1._kind), b2._prefix, weight(b2._kind));
return operator()(b1.prefix, weight(b1.kind), b2.prefix, weight(b2.kind));
}
};
bool equal(const schema& s, const bound_view other) const {
return _kind == other._kind && _prefix.get().equal(s, other._prefix.get());
return kind == other.kind && prefix.equal(s, other.prefix);
}
bool adjacent(const schema& s, const bound_view other) const {
return invert_kind(other._kind) == _kind && _prefix.get().equal(s, other._prefix.get());
return invert_kind(other.kind) == kind && prefix.equal(s, other.prefix);
}
static bound_view bottom() {
return {_empty_prefix, bound_kind::incl_start};
return {empty_prefix, bound_kind::incl_start};
}
static bound_view top() {
return {_empty_prefix, bound_kind::incl_end};
return {empty_prefix, bound_kind::incl_end};
}
template<template<typename> typename R>
GCC6_CONCEPT( requires Range<R, clustering_key_prefix_view> )
@@ -142,14 +143,14 @@ public:
}
template<template<typename> typename R>
GCC6_CONCEPT( requires Range<R, clustering_key_prefix_view> )
static std::optional<typename R<clustering_key_prefix_view>::bound> to_range_bound(const bound_view& bv) {
if (&bv._prefix.get() == &_empty_prefix) {
static stdx::optional<typename R<clustering_key_prefix_view>::bound> to_range_bound(const bound_view& bv) {
if (&bv.prefix == &empty_prefix) {
return {};
}
bool inclusive = bv._kind != bound_kind::excl_end && bv._kind != bound_kind::excl_start;
return {typename R<clustering_key_prefix_view>::bound(bv._prefix.get().view(), inclusive)};
bool inclusive = bv.kind != bound_kind::excl_end && bv.kind != bound_kind::excl_start;
return {typename R<clustering_key_prefix_view>::bound(bv.prefix.view(), inclusive)};
}
friend std::ostream& operator<<(std::ostream& out, const bound_view& b) {
return out << "{bound: prefix=" << b._prefix.get() << ", kind=" << b._kind << "}";
return out << "{bound: prefix=" << b.prefix << ", kind=" << b.kind << "}";
}
};

View File

@@ -30,7 +30,7 @@ namespace query {
class clustering_key_filter_ranges {
clustering_row_ranges _storage;
std::reference_wrapper<const clustering_row_ranges> _ref;
const clustering_row_ranges& _ref;
public:
clustering_key_filter_ranges(const clustering_row_ranges& ranges) : _ref(ranges) { }
struct reversed { };
@@ -39,21 +39,21 @@ public:
clustering_key_filter_ranges(clustering_key_filter_ranges&& other) noexcept
: _storage(std::move(other._storage))
, _ref(&other._ref.get() == &other._storage ? _storage : other._ref.get())
, _ref(&other._ref == &other._storage ? _storage : other._ref)
{ }
clustering_key_filter_ranges& operator=(clustering_key_filter_ranges&& other) noexcept {
if (this != &other) {
_storage = std::move(other._storage);
_ref = (&other._ref.get() == &other._storage) ? _storage : other._ref.get();
this->~clustering_key_filter_ranges();
new (this) clustering_key_filter_ranges(std::move(other));
}
return *this;
}
auto begin() const { return _ref.get().begin(); }
auto end() const { return _ref.get().end(); }
bool empty() const { return _ref.get().empty(); }
size_t size() const { return _ref.get().size(); }
auto begin() const { return _ref.begin(); }
auto end() const { return _ref.end(); }
bool empty() const { return _ref.empty(); }
size_t size() const { return _ref.size(); }
const clustering_row_ranges& ranges() const { return _ref; }
static clustering_key_filter_ranges get_ranges(const schema& schema, const query::partition_slice& slice, const partition_key& key) {

View File

@@ -31,61 +31,72 @@
class clustering_ranges_walker {
const schema& _schema;
const query::clustering_row_ranges& _ranges;
boost::iterator_range<query::clustering_row_ranges::const_iterator> _current_range;
query::clustering_row_ranges::const_iterator _current;
query::clustering_row_ranges::const_iterator _end;
bool _in_current; // next position is known to be >= _current_start
bool _with_static_row;
position_in_partition_view _current_start;
position_in_partition_view _current_end;
std::optional<position_in_partition> _trim;
stdx::optional<position_in_partition> _trim;
size_t _change_counter = 1;
private:
bool advance_to_next_range() {
_in_current = false;
if (!_current_start.is_static_row()) {
if (!_current_range) {
if (_current == _end) {
return false;
}
_current_range.advance_begin(1);
++_current;
}
++_change_counter;
if (!_current_range) {
if (_current == _end) {
_current_end = _current_start = position_in_partition_view::after_all_clustered_rows();
return false;
}
_current_start = position_in_partition_view::for_range_start(_current_range.front());
_current_end = position_in_partition_view::for_range_end(_current_range.front());
_current_start = position_in_partition_view::for_range_start(*_current);
_current_end = position_in_partition_view::for_range_end(*_current);
return true;
}
void set_current_positions() {
if (!_with_static_row) {
if (!_current_range) {
public:
clustering_ranges_walker(const schema& s, const query::clustering_row_ranges& ranges, bool with_static_row = true)
: _schema(s)
, _ranges(ranges)
, _current(ranges.begin())
, _end(ranges.end())
, _in_current(with_static_row)
, _with_static_row(with_static_row)
, _current_start(position_in_partition_view::for_static_row())
, _current_end(position_in_partition_view::before_all_clustered_rows())
{
if (!with_static_row) {
if (_current == _end) {
_current_start = position_in_partition_view::before_all_clustered_rows();
} else {
_current_start = position_in_partition_view::for_range_start(_current_range.front());
_current_end = position_in_partition_view::for_range_end(_current_range.front());
_current_start = position_in_partition_view::for_range_start(*_current);
_current_end = position_in_partition_view::for_range_end(*_current);
}
}
}
public:
clustering_ranges_walker(const schema& s, const query::clustering_row_ranges& ranges, bool with_static_row = true)
: _schema(s)
, _ranges(ranges)
, _current_range(ranges)
, _in_current(with_static_row)
, _with_static_row(with_static_row)
, _current_start(position_in_partition_view::for_static_row())
, _current_end(position_in_partition_view::before_all_clustered_rows()) {
set_current_positions();
clustering_ranges_walker(clustering_ranges_walker&& o) noexcept
: _schema(o._schema)
, _ranges(o._ranges)
, _current(o._current)
, _end(o._end)
, _in_current(o._in_current)
, _with_static_row(o._with_static_row)
, _current_start(o._current_start)
, _current_end(o._current_end)
, _trim(std::move(o._trim))
, _change_counter(o._change_counter)
{ }
clustering_ranges_walker& operator=(clustering_ranges_walker&& o) {
if (this != &o) {
this->~clustering_ranges_walker();
new (this) clustering_ranges_walker(std::move(o));
}
return *this;
}
clustering_ranges_walker(const clustering_ranges_walker&) = delete;
clustering_ranges_walker(clustering_ranges_walker&&) = delete;
clustering_ranges_walker& operator=(const clustering_ranges_walker&) = delete;
clustering_ranges_walker& operator=(clustering_ranges_walker&&) = delete;
// Excludes positions smaller than pos from the ranges.
// pos should be monotonic.
// No constraints between pos and positions passed to advance_to().
@@ -162,15 +173,17 @@ public:
return false;
}
for (const auto& rng : _current_range) {
auto range_start = position_in_partition_view::for_range_start(rng);
auto i = _current;
while (i != _end) {
auto range_start = position_in_partition_view::for_range_start(*i);
if (!less(range_start, end)) {
return false;
}
auto range_end = position_in_partition_view::for_range_end(rng);
auto range_end = position_in_partition_view::for_range_end(*i);
if (less(start, range_end)) {
return true;
}
++i;
}
return false;
@@ -178,20 +191,18 @@ public:
// Returns true if advanced past all contained positions. Any later advance_to() until reset() will return false.
bool out_of_range() const {
return !_in_current && !_current_range;
return !_in_current && _current == _end;
}
// Resets the state of the walker so that advance_to() can be now called for new sequence of positions.
// Any range trimmings still hold after this.
void reset() {
_current_range = _ranges;
_in_current = _with_static_row;
_current_start = position_in_partition_view::for_static_row();
_current_end = position_in_partition_view::before_all_clustered_rows();
set_current_positions();
++_change_counter;
if (_trim) {
trim_front(*std::exchange(_trim, {}));
auto trim = std::move(_trim);
auto ctr = _change_counter;
*this = clustering_ranges_walker(_schema, _ranges, _with_static_row);
_change_counter = ctr + 1;
if (trim) {
trim_front(std::move(*trim));
}
}
@@ -200,11 +211,6 @@ public:
return _current_start;
}
// Returns the upper bound of the last range in provided ranges set
position_in_partition_view uppermost_bound() const {
return position_in_partition_view::for_range_end(_ranges.back());
}
// When lower_bound() changes, this also does
// Always > 0.
size_t lower_bound_change_counter() const {

View File

@@ -25,8 +25,7 @@
#include "exceptions/exceptions.hh"
#include "sstables/compaction_backlog_manager.hh"
class table;
using column_family = table;
class column_family;
class schema;
using schema_ptr = lw_shared_ptr<const schema>;
@@ -61,8 +60,6 @@ public:
// Return a list of sstables to be compacted after applying the strategy.
compaction_descriptor get_sstables_for_compaction(column_family& cfs, std::vector<shared_sstable> candidates);
compaction_descriptor get_major_compaction_job(column_family& cf, std::vector<shared_sstable> candidates);
std::vector<resharding_descriptor> get_resharding_jobs(column_family& cf, std::vector<shared_sstable> candidates);
// Some strategies may look at the compacted and resulting sstables to
@@ -75,9 +72,6 @@ public:
// Return if optimization to rule out sstables based on clustering key filter should be applied.
bool use_clustering_key_filter() const;
// Return true if compaction strategy ignores sstables coming from partial runs.
bool ignore_partial_runs() const;
// An estimation of number of compaction for strategy to be satisfied.
int64_t estimated_pending_compactions(column_family& cf) const;
@@ -116,7 +110,7 @@ public:
} else if (short_name == "TimeWindowCompactionStrategy") {
return compaction_strategy_type::time_window;
} else {
throw exceptions::configuration_exception(format("Unable to find compaction strategy class '{}'", name));
throw exceptions::configuration_exception(sprint("Unable to find compaction strategy class '%s'", name));
}
}

View File

@@ -0,0 +1,67 @@
/*
* Copyright (C) 2016 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include "query-request.hh"
#include <experimental/optional>
// Wraps ring_position so it is compatible with old-style C++: default constructor,
// stateless comparators, yada yada
class compatible_ring_position {
const schema* _schema = nullptr;
// optional to supply a default constructor, no more
std::experimental::optional<dht::ring_position> _rp;
public:
compatible_ring_position() noexcept = default;
compatible_ring_position(const schema& s, const dht::ring_position& rp)
: _schema(&s), _rp(rp) {
}
compatible_ring_position(const schema& s, dht::ring_position&& rp)
: _schema(&s), _rp(std::move(rp)) {
}
const dht::token& token() const {
return _rp->token();
}
friend int tri_compare(const compatible_ring_position& x, const compatible_ring_position& y) {
return x._rp->tri_compare(*x._schema, *y._rp);
}
friend bool operator<(const compatible_ring_position& x, const compatible_ring_position& y) {
return tri_compare(x, y) < 0;
}
friend bool operator<=(const compatible_ring_position& x, const compatible_ring_position& y) {
return tri_compare(x, y) <= 0;
}
friend bool operator>(const compatible_ring_position& x, const compatible_ring_position& y) {
return tri_compare(x, y) > 0;
}
friend bool operator>=(const compatible_ring_position& x, const compatible_ring_position& y) {
return tri_compare(x, y) >= 0;
}
friend bool operator==(const compatible_ring_position& x, const compatible_ring_position& y) {
return tri_compare(x, y) == 0;
}
friend bool operator!=(const compatible_ring_position& x, const compatible_ring_position& y) {
return tri_compare(x, y) != 0;
}
};

View File

@@ -1,64 +0,0 @@
/*
* Copyright (C) 2016 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include "query-request.hh"
#include <optional>
// Wraps ring_position_view so it is compatible with old-style C++: default
// constructor, stateless comparators, yada yada.
class compatible_ring_position_view {
const schema* _schema = nullptr;
// Optional to supply a default constructor, no more.
std::optional<dht::ring_position_view> _rpv;
public:
constexpr compatible_ring_position_view() = default;
compatible_ring_position_view(const schema& s, dht::ring_position_view rpv)
: _schema(&s), _rpv(rpv) {
}
const dht::ring_position_view& position() const {
return *_rpv;
}
friend int tri_compare(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
return dht::ring_position_tri_compare(*x._schema, *x._rpv, *y._rpv);
}
friend bool operator<(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
return tri_compare(x, y) < 0;
}
friend bool operator<=(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
return tri_compare(x, y) <= 0;
}
friend bool operator>(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
return tri_compare(x, y) > 0;
}
friend bool operator>=(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
return tri_compare(x, y) >= 0;
}
friend bool operator==(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
return tri_compare(x, y) == 0;
}
friend bool operator!=(const compatible_ring_position_view& x, const compatible_ring_position_view& y) {
return tri_compare(x, y) != 0;
}
};

View File

@@ -28,7 +28,7 @@
#include <boost/range/iterator_range.hpp>
#include <boost/range/adaptor/transformed.hpp>
#include "utils/serialization.hh"
#include <seastar/util/backtrace.hh>
#include "util/backtrace.hh"
#include "unimplemented.hh"
enum class allow_prefixes { no, yes };
@@ -98,7 +98,7 @@ public:
static bytes serialize_value(RangeOfSerializedComponents&& values) {
auto size = serialized_size(values);
if (size > std::numeric_limits<size_type>::max()) {
throw std::runtime_error(format("Key size too large: {:d} > {:d}", size, std::numeric_limits<size_type>::max()));
throw std::runtime_error(sprint("Key size too large: %d > %d", size, std::numeric_limits<size_type>::max()));
}
bytes b(bytes::initialized_later(), size);
auto i = b.begin();
@@ -145,7 +145,7 @@ public:
}
len = read_simple<size_type>(_v);
if (_v.size() < len) {
throw_with_backtrace<marshal_exception>(format("compound_type iterator - not enough bytes, expected {:d}, got {:d}", len, _v.size()));
throw_with_backtrace<marshal_exception>(sprint("compound_type iterator - not enough bytes, expected %d, got %d", len, _v.size()));
}
}
_current = bytes_view(_v.begin(), len);

View File

@@ -25,7 +25,6 @@
#include <boost/range/adaptor/transformed.hpp>
#include "compound.hh"
#include "schema.hh"
#include "sstables/version.hh"
//
// This header provides adaptors between the representation used by our compound_type<>
@@ -284,7 +283,7 @@ private:
// bytes is the static prefix or not).
auto value_size = size(*it);
if (value_size > static_cast<size_type>(std::numeric_limits<size_type>::max() - uint8_t(is_compound))) {
throw std::runtime_error(format("First component size too large: {:d} > {:d}", value_size, std::numeric_limits<size_type>::max() - is_compound));
throw std::runtime_error(sprint("First component size too large: %d > %d", value_size, std::numeric_limits<size_type>::max() - is_compound));
}
if (!is_compound) {
return value_size;
@@ -295,7 +294,7 @@ private:
for ( ; it != values.end(); ++it) {
auto value_size = size(*it);
if (value_size > std::numeric_limits<size_type>::max()) {
throw std::runtime_error(format("Component size too large: {:d} > {:d}", value_size, std::numeric_limits<size_type>::max()));
throw std::runtime_error(sprint("Component size too large: %d > %d", value_size, std::numeric_limits<size_type>::max()));
}
len += sizeof(size_type) + value_size + sizeof(eoc_type);
}
@@ -303,7 +302,7 @@ private:
}
public:
template <typename Describer>
auto describe_type(sstables::sstable_version_types v, Describer f) const {
auto describe_type(Describer f) const {
return f(const_cast<bytes&>(_bytes));
}
@@ -346,7 +345,7 @@ public:
}
len = read_simple<size_type>(_v);
if (_v.size() < len) {
throw_with_backtrace<marshal_exception>(format("composite iterator - not enough bytes, expected {:d}, got {:d}", len, _v.size()));
throw_with_backtrace<marshal_exception>(sprint("composite iterator - not enough bytes, expected %d, got %d", len, _v.size()));
}
}
auto value = bytes_view(_v.begin(), len);
@@ -468,7 +467,7 @@ public:
template <typename Component>
friend inline std::ostream& operator<<(std::ostream& os, const std::pair<Component, eoc>& c) {
return os << "{value=" << c.first << "; eoc=" << format("0x{:02x}", eoc_type(c.second) & 0xff) << "}";
return os << "{value=" << c.first << "; eoc=" << sprint("0x%02x", eoc_type(c.second) & 0xff) << "}";
}
friend std::ostream& operator<<(std::ostream& os, const composite& v);
@@ -511,7 +510,7 @@ public:
auto marker = it->second;
++it;
if (it != e && marker != composite::eoc::none) {
throw runtime_exception(format("non-zero component divider found ({:d}) mid", format("0x{:02x}", composite::eoc_type(marker) & 0xff)));
throw runtime_exception(sprint("non-zero component divider found (%d) mid", sprint("0x%02x", composite::eoc_type(marker) & 0xff)));
}
}
return ret;

View File

@@ -95,7 +95,7 @@ shared_ptr<compressor> compressor::create(const std::map<sstring, sstring>& opti
return create(i->second, [&options](const sstring& key) -> opt_string {
auto i = options.find(key);
if (i == options.end()) {
return std::nullopt;
return std::experimental::nullopt;
}
return { i->second };
});
@@ -108,12 +108,11 @@ thread_local const shared_ptr<compressor> compressor::snappy = make_shared<snapp
thread_local const shared_ptr<compressor> compressor::deflate = make_shared<deflate_processor>(namespace_prefix + "DeflateCompressor");
const sstring compression_parameters::SSTABLE_COMPRESSION = "sstable_compression";
const sstring compression_parameters::CHUNK_LENGTH_KB = "chunk_length_in_kb";
const sstring compression_parameters::CHUNK_LENGTH_KB_ERR = "chunk_length_kb";
const sstring compression_parameters::CHUNK_LENGTH_KB = "chunk_length_kb";
const sstring compression_parameters::CRC_CHECK_CHANCE = "crc_check_chance";
compression_parameters::compression_parameters()
: compression_parameters(compressor::lz4)
: compression_parameters(nullptr)
{}
compression_parameters::~compression_parameters()
@@ -128,14 +127,12 @@ compression_parameters::compression_parameters(const std::map<sstring, sstring>&
validate_options(options);
auto chunk_length = options.find(CHUNK_LENGTH_KB) != options.end() ?
options.find(CHUNK_LENGTH_KB) : options.find(CHUNK_LENGTH_KB_ERR);
auto chunk_length = options.find(CHUNK_LENGTH_KB);
if (chunk_length != options.end()) {
try {
_chunk_length = std::stoi(chunk_length->second) * 1024;
} catch (const std::exception& e) {
throw exceptions::syntax_exception(sstring("Invalid integer value ") + chunk_length->second + " for " + chunk_length->first);
throw exceptions::syntax_exception(sstring("Invalid integer value ") + chunk_length->second + " for " + CHUNK_LENGTH_KB);
}
}
auto crc_chance = options.find(CRC_CHECK_CHANCE);
@@ -152,13 +149,11 @@ void compression_parameters::validate() {
if (_chunk_length) {
auto chunk_length = _chunk_length.value();
if (chunk_length <= 0) {
throw exceptions::configuration_exception(
fmt::sprintf("Invalid negative or null for %s/%s", CHUNK_LENGTH_KB, CHUNK_LENGTH_KB_ERR));
throw exceptions::configuration_exception(sstring("Invalid negative or null ") + CHUNK_LENGTH_KB);
}
// _chunk_length must be a power of two
if (chunk_length & (chunk_length - 1)) {
throw exceptions::configuration_exception(
fmt::sprintf("%s/%s must be a power of 2.", CHUNK_LENGTH_KB, CHUNK_LENGTH_KB_ERR));
throw exceptions::configuration_exception(sstring(CHUNK_LENGTH_KB) + " must be a power of 2.");
}
}
if (_crc_check_chance && (_crc_check_chance.value() < 0.0 || _crc_check_chance.value() > 1.0)) {
@@ -197,7 +192,6 @@ void compression_parameters::validate_options(const std::map<sstring, sstring>&
static std::set<sstring> keywords({
sstring(SSTABLE_COMPRESSION),
sstring(CHUNK_LENGTH_KB),
sstring(CHUNK_LENGTH_KB_ERR),
sstring(CRC_CHECK_CHANCE),
});
std::set<sstring> ckw;
@@ -206,7 +200,7 @@ void compression_parameters::validate_options(const std::map<sstring, sstring>&
}
for (auto&& opt : options) {
if (!keywords.count(opt.first) && !ckw.count(opt.first)) {
throw exceptions::configuration_exception(format("Unknown compression option '{}'.", opt.first));
throw exceptions::configuration_exception(sprint("Unknown compression option '%s'.", opt.first));
}
}
}

View File

@@ -29,6 +29,7 @@
#include <seastar/core/sstring.hh>
#include "exceptions/exceptions.hh"
#include "stdx.hh"
class compressor {
@@ -72,7 +73,7 @@ public:
}
// to cheaply bridge sstable compression options / maps
using opt_string = std::optional<sstring>;
using opt_string = stdx::optional<sstring>;
using opt_getter = std::function<opt_string(const sstring&)>;
static shared_ptr<compressor> create(const sstring& name, const opt_getter&);
@@ -98,12 +99,11 @@ public:
static const sstring SSTABLE_COMPRESSION;
static const sstring CHUNK_LENGTH_KB;
static const sstring CHUNK_LENGTH_KB_ERR;
static const sstring CRC_CHECK_CHANCE;
private:
compressor_ptr _compressor;
std::optional<int> _chunk_length;
std::optional<double> _crc_check_chance;
std::experimental::optional<int> _chunk_length;
std::experimental::optional<double> _crc_check_chance;
public:
compression_parameters();
compression_parameters(compressor_ptr);
@@ -118,10 +118,6 @@ public:
std::map<sstring, sstring> get_options() const;
bool operator==(const compression_parameters& other) const;
bool operator!=(const compression_parameters& other) const;
static compression_parameters no_compression() {
return compression_parameters(nullptr);
}
private:
void validate_options(const std::map<sstring, sstring>&);
};

View File

@@ -22,17 +22,17 @@
# of tokens assuming they have equal hardware capability.
#
# If you already have a cluster with 1 token per node, and wish to migrate to
# multiple tokens per node, see http://cassandra.apache.org/doc/latest/operating
# multiple tokens per node, see http://wiki.apache.org/cassandra/Operations
num_tokens: 256
# Directory where Scylla should store data on disk.
# If not set, the default directory is /var/lib/scylla/data.
# If not set, the default directory is $CASSANDRA_HOME/data/data.
data_file_directories:
- /var/lib/scylla/data
# commit log. when running on magnetic HDD, this should be a
# separate spindle than the data directories.
# If not set, the default directory is /var/lib/scylla/commitlog.
# If not set, the default directory is $CASSANDRA_HOME/data/commitlog.
commitlog_directory: /var/lib/scylla/commitlog
# commitlog_sync may be either "periodic" or "batch."
@@ -65,7 +65,7 @@ commitlog_sync_period_in_ms: 10000
commitlog_segment_size_in_mb: 32
# seed_provider class_name is saved for future use.
# seeds address(es) are mandatory!
# seeds address are mandatory!
seed_provider:
# Addresses of hosts that are deemed contact points.
# Scylla nodes use this list of hosts to find each other and learn
@@ -242,11 +242,8 @@ batch_size_fail_threshold_in_kb: 50
# The directory where hints files are stored if hinted handoff is enabled.
# hints_directory: /var/lib/scylla/hints
# The directory where hints files are stored for materialized-view updates
# view_hints_directory: /var/lib/scylla/view_hints
# See https://docs.scylladb.com/architecture/anti-entropy/hinted-handoff
# See http://wiki.apache.org/cassandra/HintedHandoff
# May either be "true" or "false" to enable globally, or contain a list
# of data centers to enable per-datacenter.
# hinted_handoff_enabled: DC1,DC2
@@ -392,7 +389,7 @@ partitioner: org.apache.cassandra.dht.Murmur3Partitioner
# memory_allocator: NativeAllocator
# saved caches
# If not set, the default directory is /var/lib/scylla/saved_caches.
# If not set, the default directory is $CASSANDRA_HOME/data/saved_caches.
# saved_caches_directory: /var/lib/scylla/saved_caches
@@ -538,7 +535,7 @@ commitlog_total_space_in_mb: -1
# /proc/sys/net/core/wmem_max
# /proc/sys/net/core/rmem_max
# /proc/sys/net/ipv4/tcp_wmem
# /proc/sys/net/ipv4/tcp_rmem
# /proc/sys/net/ipv4/tcp_wmem
# and: man tcp
# internode_send_buff_size_in_bytes:
# internode_recv_buff_size_in_bytes:
@@ -612,12 +609,9 @@ commitlog_total_space_in_mb: -1
# of compaction, including validation compaction.
# compaction_throughput_mb_per_sec: 16
# Log a warning when writing partitions larger than this value
# Log a warning when compacting partitions larger than this value
# compaction_large_partition_warning_threshold_mb: 100
# Log a warning when writing rows larger than this value
# compaction_large_row_warning_threshold_mb: 50
# When compacting, the replacement sstable(s) can be opened before they
# are completely written, and used in place of the prior sstables for
# any range that has been written. This helps to smoothly transfer reads

File diff suppressed because it is too large Load Diff

View File

@@ -38,45 +38,28 @@ private:
static bool is_compatible(const column_definition& new_def, const data_type& old_type, column_kind kind) {
return ::is_compatible(new_def.kind, kind) && new_def.type->is_value_compatible_with(*old_type);
}
static atomic_cell upgrade_cell(const abstract_type& new_type, const abstract_type& old_type, atomic_cell_view cell,
atomic_cell::collection_member cm = atomic_cell::collection_member::no) {
if (cell.is_live() && !old_type.is_counter()) {
if (cell.is_live_and_has_ttl()) {
return atomic_cell::make_live(new_type, cell.timestamp(), cell.value().linearize(), cell.expiry(), cell.ttl(), cm);
}
return atomic_cell::make_live(new_type, cell.timestamp(), cell.value().linearize(), cm);
} else {
return atomic_cell(new_type, cell);
}
}
static void accept_cell(row& dst, column_kind kind, const column_definition& new_def, const data_type& old_type, atomic_cell_view cell) {
if (!is_compatible(new_def, old_type, kind) || cell.timestamp() <= new_def.dropped_at()) {
return;
if (is_compatible(new_def, old_type, kind) && cell.timestamp() > new_def.dropped_at()) {
dst.apply(new_def, atomic_cell_or_collection(cell));
}
dst.apply(new_def, upgrade_cell(*new_def.type, *old_type, cell));
}
static void accept_cell(row& dst, column_kind kind, const column_definition& new_def, const data_type& old_type, collection_mutation_view cell) {
if (!is_compatible(new_def, old_type, kind)) {
return;
}
cell.data.with_linearized([&] (bytes_view cell_bv) {
auto new_ctype = static_pointer_cast<const collection_type_impl>(new_def.type);
auto old_ctype = static_pointer_cast<const collection_type_impl>(old_type);
auto old_view = old_ctype->deserialize_mutation_form(cell_bv);
auto&& ctype = static_pointer_cast<const collection_type_impl>(old_type);
auto old_view = ctype->deserialize_mutation_form(cell);
collection_type_impl::mutation new_view;
collection_type_impl::mutation_view new_view;
if (old_view.tomb.timestamp > new_def.dropped_at()) {
new_view.tomb = old_view.tomb;
}
for (auto& c : old_view.cells) {
if (c.second.timestamp() > new_def.dropped_at()) {
new_view.cells.emplace_back(c.first, upgrade_cell(*new_ctype->value_comparator(), *old_ctype->value_comparator(), c.second, atomic_cell::collection_member::yes));
new_view.cells.emplace_back(std::move(c));
}
}
if (new_view.tomb || !new_view.cells.empty()) {
dst.apply(new_def, new_ctype->serialize_mutation_form(std::move(new_view)));
}
});
dst.apply(new_def, ctype->serialize_mutation_form(std::move(new_view)));
}
public:
converting_mutation_partition_applier(
@@ -92,10 +75,6 @@ public:
_p.apply(t);
}
void accept_static_cell(column_id id, atomic_cell cell) {
return accept_static_cell(id, atomic_cell_view(cell));
}
virtual void accept_static_cell(column_id id, atomic_cell_view cell) override {
const column_mapping_entry& col = _visited_column_mapping.static_column_at(id);
const column_definition* def = _p_schema.get_column_definition(col.name());
@@ -123,10 +102,6 @@ public:
_current_row = &r;
}
void accept_row_cell(column_id id, atomic_cell cell) {
return accept_row_cell(id, atomic_cell_view(cell));
}
virtual void accept_row_cell(column_id id, atomic_cell_view cell) override {
const column_mapping_entry& col = _visited_column_mapping.regular_column_at(id);
const column_definition* def = _p_schema.get_column_definition(col.name());
@@ -145,11 +120,11 @@ public:
// Appends the cell to dst upgrading it to the new schema.
// Cells must have monotonic names.
static void append_cell(row& dst, column_kind kind, const column_definition& new_def, const column_definition& old_def, const atomic_cell_or_collection& cell) {
static void append_cell(row& dst, column_kind kind, const column_definition& new_def, const data_type& old_type, const atomic_cell_or_collection& cell) {
if (new_def.is_atomic()) {
accept_cell(dst, kind, new_def, old_def.type, cell.as_atomic_cell(old_def));
accept_cell(dst, kind, new_def, old_type, cell.as_atomic_cell());
} else {
accept_cell(dst, kind, new_def, old_def.type, cell.as_collection_mutation());
accept_cell(dst, kind, new_def, old_type, cell.as_collection_mutation());
}
}
};

View File

@@ -78,10 +78,10 @@ std::vector<counter_shard> counter_cell_view::shards_compatible_with_1_7_4() con
return sorted_shards;
}
static bool apply_in_place(const column_definition& cdef, atomic_cell_mutable_view dst, atomic_cell_mutable_view src)
static bool apply_in_place(atomic_cell_or_collection& dst, atomic_cell_or_collection& src)
{
auto dst_ccmv = counter_cell_mutable_view(dst);
auto src_ccmv = counter_cell_mutable_view(src);
auto dst_ccmv = counter_cell_mutable_view(dst.as_mutable_atomic_cell());
auto src_ccmv = counter_cell_mutable_view(src.as_mutable_atomic_cell());
auto dst_shards = dst_ccmv.shards();
auto src_shards = src_ccmv.shards();
@@ -118,19 +118,48 @@ static bool apply_in_place(const column_definition& cdef, atomic_cell_mutable_vi
auto src_ts = src_ccmv.timestamp();
dst_ccmv.set_timestamp(std::max(dst_ts, src_ts));
src_ccmv.set_timestamp(dst_ts);
src.as_mutable_atomic_cell().set_counter_in_place_revert(true);
return true;
}
void counter_cell_view::apply(const column_definition& cdef, atomic_cell_or_collection& dst, atomic_cell_or_collection& src)
static void revert_in_place_apply(atomic_cell_or_collection& dst, atomic_cell_or_collection& src)
{
auto dst_ac = dst.as_atomic_cell(cdef);
auto src_ac = src.as_atomic_cell(cdef);
assert(dst.can_use_mutable_view() && src.can_use_mutable_view());
auto dst_ccmv = counter_cell_mutable_view(dst.as_mutable_atomic_cell());
auto src_ccmv = counter_cell_mutable_view(src.as_mutable_atomic_cell());
auto dst_shards = dst_ccmv.shards();
auto src_shards = src_ccmv.shards();
auto dst_it = dst_shards.begin();
auto src_it = src_shards.begin();
while (src_it != src_shards.end()) {
while (dst_it != dst_shards.end() && dst_it->id() < src_it->id()) {
++dst_it;
}
assert(dst_it != dst_shards.end() && dst_it->id() == src_it->id());
dst_it->swap_value_and_clock(*src_it);
++src_it;
}
auto dst_ts = dst_ccmv.timestamp();
auto src_ts = src_ccmv.timestamp();
dst_ccmv.set_timestamp(src_ts);
src_ccmv.set_timestamp(dst_ts);
src.as_mutable_atomic_cell().set_counter_in_place_revert(false);
}
bool counter_cell_view::apply_reversibly(atomic_cell_or_collection& dst, atomic_cell_or_collection& src)
{
auto dst_ac = dst.as_atomic_cell();
auto src_ac = src.as_atomic_cell();
if (!dst_ac.is_live() || !src_ac.is_live()) {
if (dst_ac.is_live() || (!src_ac.is_live() && compare_atomic_cell_for_merge(dst_ac, src_ac) < 0)) {
std::swap(dst, src);
return true;
}
return;
return false;
}
if (dst_ac.is_counter_update() && src_ac.is_counter_update()) {
@@ -138,26 +167,22 @@ void counter_cell_view::apply(const column_definition& cdef, atomic_cell_or_coll
auto dst_v = dst_ac.counter_update_value();
dst = atomic_cell::make_live_counter_update(std::max(dst_ac.timestamp(), src_ac.timestamp()),
src_v + dst_v);
return;
return true;
}
assert(!dst_ac.is_counter_update());
assert(!src_ac.is_counter_update());
with_linearized(dst_ac, [&] (counter_cell_view dst_ccv) {
with_linearized(src_ac, [&] (counter_cell_view src_ccv) {
if (dst_ccv.shard_count() >= src_ccv.shard_count()) {
auto dst_amc = dst.as_mutable_atomic_cell(cdef);
auto src_amc = src.as_mutable_atomic_cell(cdef);
if (!dst_amc.is_value_fragmented() && !src_amc.is_value_fragmented()) {
if (apply_in_place(cdef, dst_amc, src_amc)) {
return;
}
if (counter_cell_view(dst_ac).shard_count() >= counter_cell_view(src_ac).shard_count()
&& dst.can_use_mutable_view() && src.can_use_mutable_view()) {
if (apply_in_place(dst, src)) {
return true;
}
}
auto dst_shards = dst_ccv.shards();
auto src_shards = src_ccv.shards();
src.as_mutable_atomic_cell().set_counter_in_place_revert(false);
auto dst_shards = counter_cell_view(dst_ac).shards();
auto src_shards = counter_cell_view(src_ac).shards();
counter_cell_builder result;
combine(dst_shards.begin(), dst_shards.end(), src_shards.begin(), src_shards.end(),
@@ -166,27 +191,38 @@ void counter_cell_view::apply(const column_definition& cdef, atomic_cell_or_coll
});
auto cell = result.build(std::max(dst_ac.timestamp(), src_ac.timestamp()));
src = std::exchange(dst, atomic_cell_or_collection(std::move(cell)));
});
});
src = std::exchange(dst, atomic_cell_or_collection(cell));
return true;
}
std::optional<atomic_cell> counter_cell_view::difference(atomic_cell_view a, atomic_cell_view b)
void counter_cell_view::revert_apply(atomic_cell_or_collection& dst, atomic_cell_or_collection& src)
{
if (dst.as_atomic_cell().is_counter_update()) {
auto src_v = src.as_atomic_cell().counter_update_value();
auto dst_v = dst.as_atomic_cell().counter_update_value();
dst = atomic_cell::make_live(dst.as_atomic_cell().timestamp(),
long_type->decompose(dst_v - src_v));
} else if (src.as_atomic_cell().is_counter_in_place_revert_set()) {
revert_in_place_apply(dst, src);
} else {
std::swap(dst, src);
}
}
stdx::optional<atomic_cell> counter_cell_view::difference(atomic_cell_view a, atomic_cell_view b)
{
assert(!a.is_counter_update());
assert(!b.is_counter_update());
if (!b.is_live() || !a.is_live()) {
if (b.is_live() || (!a.is_live() && compare_atomic_cell_for_merge(b, a) < 0)) {
return atomic_cell(*counter_type, a);
return atomic_cell(a);
}
return { };
}
return with_linearized(a, [&] (counter_cell_view a_ccv) {
return with_linearized(b, [&] (counter_cell_view b_ccv) {
auto a_shards = a_ccv.shards();
auto b_shards = b_ccv.shards();
auto a_shards = counter_cell_view(a).shards();
auto b_shards = counter_cell_view(b).shards();
auto a_it = a_shards.begin();
auto a_end = a_shards.end();
@@ -204,25 +240,22 @@ std::optional<atomic_cell> counter_cell_view::difference(atomic_cell_view a, ato
++a_it;
}
std::optional<atomic_cell> diff;
stdx::optional<atomic_cell> diff;
if (!result.empty()) {
diff = result.build(std::max(a.timestamp(), b.timestamp()));
} else if (a.timestamp() > b.timestamp()) {
diff = atomic_cell::make_live(*counter_type, a.timestamp(), bytes_view());
diff = atomic_cell::make_live(a.timestamp(), bytes_view());
}
return diff;
});
});
}
void transform_counter_updates_to_shards(mutation& m, const mutation* current_state, uint64_t clock_offset) {
// FIXME: allow current_state to be frozen_mutation
auto transform_new_row_to_shards = [&s = *m.schema(), clock_offset] (column_kind kind, auto& cells) {
cells.for_each_cell([&] (column_id id, atomic_cell_or_collection& ac_o_c) {
auto& cdef = s.column_at(kind, id);
auto acv = ac_o_c.as_atomic_cell(cdef);
auto transform_new_row_to_shards = [clock_offset] (auto& cells) {
cells.for_each_cell([clock_offset] (auto, atomic_cell_or_collection& ac_o_c) {
auto acv = ac_o_c.as_atomic_cell();
if (!acv.is_live()) {
return; // continue -- we are in lambda
}
@@ -233,35 +266,32 @@ void transform_counter_updates_to_shards(mutation& m, const mutation* current_st
};
if (!current_state) {
transform_new_row_to_shards(column_kind::static_column, m.partition().static_row());
transform_new_row_to_shards(m.partition().static_row());
for (auto& cr : m.partition().clustered_rows()) {
transform_new_row_to_shards(column_kind::regular_column, cr.row().cells());
transform_new_row_to_shards(cr.row().cells());
}
return;
}
clustering_key::less_compare cmp(*m.schema());
auto transform_row_to_shards = [&s = *m.schema(), clock_offset] (column_kind kind, auto& transformee, auto& state) {
auto transform_row_to_shards = [clock_offset] (auto& transformee, auto& state) {
std::deque<std::pair<column_id, counter_shard>> shards;
state.for_each_cell([&] (column_id id, const atomic_cell_or_collection& ac_o_c) {
auto& cdef = s.column_at(kind, id);
auto acv = ac_o_c.as_atomic_cell(cdef);
auto acv = ac_o_c.as_atomic_cell();
if (!acv.is_live()) {
return; // continue -- we are in lambda
}
counter_cell_view::with_linearized(acv, [&] (counter_cell_view ccv) {
counter_cell_view ccv(acv);
auto cs = ccv.local_shard();
if (!cs) {
return; // continue
}
shards.emplace_back(std::make_pair(id, counter_shard(*cs)));
});
});
transformee.for_each_cell([&] (column_id id, atomic_cell_or_collection& ac_o_c) {
auto& cdef = s.column_at(kind, id);
auto acv = ac_o_c.as_atomic_cell(cdef);
auto acv = ac_o_c.as_atomic_cell();
if (!acv.is_live()) {
return; // continue -- we are in lambda
}
@@ -283,7 +313,7 @@ void transform_counter_updates_to_shards(mutation& m, const mutation* current_st
});
};
transform_row_to_shards(column_kind::static_column, m.partition().static_row(), current_state->partition().static_row());
transform_row_to_shards(m.partition().static_row(), current_state->partition().static_row());
auto& cstate = current_state->partition();
auto it = cstate.clustered_rows().begin();
@@ -293,10 +323,10 @@ void transform_counter_updates_to_shards(mutation& m, const mutation* current_st
++it;
}
if (it == end || cmp(cr.key(), it->key())) {
transform_new_row_to_shards(column_kind::regular_column, cr.row().cells());
transform_new_row_to_shards(cr.row().cells());
continue;
}
transform_row_to_shards(column_kind::regular_column, cr.row().cells(), it->row().cells());
transform_row_to_shards(cr.row().cells(), it->row().cells());
}
}

View File

@@ -26,6 +26,8 @@
#include "atomic_cell_or_collection.hh"
#include "types.hh"
#include "stdx.hh"
class mutation;
class mutation;
@@ -77,7 +79,7 @@ static_assert(std::is_pod<counter_id>::value, "counter_id should be a POD type")
std::ostream& operator<<(std::ostream& os, const counter_id& id);
template<mutable_view is_mutable>
template<typename View>
class basic_counter_shard_view {
enum class offset : unsigned {
id = 0u,
@@ -86,8 +88,7 @@ class basic_counter_shard_view {
total_size = unsigned(logical_clock) + sizeof(int64_t),
};
private:
using pointer_type = std::conditional_t<is_mutable == mutable_view::no, const signed char*, signed char*>;
pointer_type _base;
typename View::pointer _base;
private:
template<typename T>
T read(offset off) const {
@@ -99,7 +100,7 @@ public:
static constexpr auto size = size_t(offset::total_size);
public:
basic_counter_shard_view() = default;
explicit basic_counter_shard_view(pointer_type ptr) noexcept
explicit basic_counter_shard_view(typename View::pointer ptr) noexcept
: _base(ptr) { }
counter_id id() const { return read<counter_id>(offset::id); }
@@ -110,7 +111,7 @@ public:
static constexpr size_t off = size_t(offset::value);
static constexpr size_t size = size_t(offset::total_size) - off;
signed char tmp[size];
typename View::value_type tmp[size];
std::copy_n(_base + off, size, tmp);
std::copy_n(other._base + off, size, _base + off);
std::copy_n(tmp, size, other._base + off);
@@ -137,7 +138,7 @@ public:
};
};
using counter_shard_view = basic_counter_shard_view<mutable_view::no>;
using counter_shard_view = basic_counter_shard_view<bytes_view>;
std::ostream& operator<<(std::ostream& os, counter_shard_view csv);
@@ -197,7 +198,7 @@ public:
return do_apply(other);
}
static constexpr size_t serialized_size() {
static size_t serialized_size() {
return counter_shard_view::size;
}
void serialize(bytes::iterator& out) const {
@@ -251,33 +252,15 @@ public:
}
atomic_cell build(api::timestamp_type timestamp) const {
// If we can assume that the counter shards never cross fragment boundaries
// the serialisation code gets much simpler.
static_assert(data::cell::maximum_external_chunk_length % counter_shard::serialized_size() == 0);
auto ac = atomic_cell::make_live_uninitialized(*counter_type, timestamp, serialized_size());
auto dst_it = ac.value().begin();
auto dst_current = *dst_it++;
for (auto&& cs : _shards) {
if (dst_current.empty()) {
dst_current = *dst_it++;
}
assert(!dst_current.empty());
auto value_dst = dst_current.data();
cs.serialize(value_dst);
dst_current.remove_prefix(counter_shard::serialized_size());
}
return ac;
return atomic_cell::make_live_from_serializer(timestamp, serialized_size(), [this] (bytes::iterator out) {
serialize(out);
});
}
static atomic_cell from_single_shard(api::timestamp_type timestamp, const counter_shard& cs) {
// We don't really need to bother with fragmentation here.
static_assert(data::cell::maximum_external_chunk_length >= counter_shard::serialized_size());
auto ac = atomic_cell::make_live_uninitialized(*counter_type, timestamp, counter_shard::serialized_size());
auto dst = ac.value().first_fragment().begin();
cs.serialize(dst);
return ac;
return atomic_cell::make_live_from_serializer(timestamp, counter_shard::serialized_size(), [&cs] (bytes::iterator out) {
cs.serialize(out);
});
}
class inserter_iterator : public std::iterator<std::output_iterator_tag, counter_shard> {
@@ -304,32 +287,28 @@ public:
// <counter_id> := <int64_t><int64_t>
// <shard> := <counter_id><int64_t:value><int64_t:logical_clock>
// <counter_cell> := <shard>*
template<mutable_view is_mutable>
template<typename View>
class basic_counter_cell_view {
protected:
using linearized_value_view = std::conditional_t<is_mutable == mutable_view::no,
bytes_view, bytes_mutable_view>;
using pointer_type = typename linearized_value_view::pointer;
basic_atomic_cell_view<is_mutable> _cell;
linearized_value_view _value;
atomic_cell_base<View> _cell;
private:
class shard_iterator : public std::iterator<std::input_iterator_tag, basic_counter_shard_view<is_mutable>> {
pointer_type _current;
basic_counter_shard_view<is_mutable> _current_view;
class shard_iterator : public std::iterator<std::input_iterator_tag, basic_counter_shard_view<View>> {
typename View::pointer _current;
basic_counter_shard_view<View> _current_view;
public:
shard_iterator() = default;
shard_iterator(pointer_type ptr) noexcept
shard_iterator(typename View::pointer ptr) noexcept
: _current(ptr), _current_view(ptr) { }
basic_counter_shard_view<is_mutable>& operator*() noexcept {
basic_counter_shard_view<View>& operator*() noexcept {
return _current_view;
}
basic_counter_shard_view<is_mutable>* operator->() noexcept {
basic_counter_shard_view<View>* operator->() noexcept {
return &_current_view;
}
shard_iterator& operator++() noexcept {
_current += counter_shard_view::size;
_current_view = basic_counter_shard_view<is_mutable>(_current);
_current_view = basic_counter_shard_view<View>(_current);
return *this;
}
shard_iterator operator++(int) noexcept {
@@ -339,7 +318,7 @@ private:
}
shard_iterator& operator--() noexcept {
_current -= counter_shard_view::size;
_current_view = basic_counter_shard_view<is_mutable>(_current);
_current_view = basic_counter_shard_view<View>(_current);
return *this;
}
shard_iterator operator--(int) noexcept {
@@ -356,23 +335,22 @@ private:
};
public:
boost::iterator_range<shard_iterator> shards() const {
auto begin = shard_iterator(_value.data());
auto end = shard_iterator(_value.data() + _value.size());
auto bv = _cell.value();
auto begin = shard_iterator(bv.data());
auto end = shard_iterator(bv.data() + bv.size());
return boost::make_iterator_range(begin, end);
}
size_t shard_count() const {
return _cell.value().size_bytes() / counter_shard_view::size;
return _cell.value().size() / counter_shard_view::size;
}
protected:
public:
// ac must be a live counter cell
explicit basic_counter_cell_view(basic_atomic_cell_view<is_mutable> ac, linearized_value_view vv) noexcept
: _cell(ac), _value(vv)
{
explicit basic_counter_cell_view(atomic_cell_base<View> ac) noexcept : _cell(ac) {
assert(_cell.is_live());
assert(!_cell.is_counter_update());
}
public:
api::timestamp_type timestamp() const { return _cell.timestamp(); }
static data_type total_value_type() { return long_type; }
@@ -383,7 +361,7 @@ public:
});
}
std::optional<counter_shard_view> get_shard(const counter_id& id) const {
stdx::optional<counter_shard_view> get_shard(const counter_id& id) const {
auto it = boost::range::find_if(shards(), [&id] (counter_shard_view csv) {
return csv.id() == id;
});
@@ -393,7 +371,7 @@ public:
return *it;
}
std::optional<counter_shard_view> local_shard() const {
stdx::optional<counter_shard_view> local_shard() const {
// TODO: consider caching local shard position
return get_shard(counter_id::local());
}
@@ -403,39 +381,29 @@ public:
}
};
struct counter_cell_view : basic_counter_cell_view<mutable_view::no> {
struct counter_cell_view : basic_counter_cell_view<bytes_view> {
using basic_counter_cell_view::basic_counter_cell_view;
template<typename Function>
static decltype(auto) with_linearized(basic_atomic_cell_view<mutable_view::no> ac, Function&& fn) {
return ac.value().with_linearized([&] (bytes_view value_view) {
counter_cell_view ccv(ac, value_view);
return fn(ccv);
});
}
// Returns counter shards in an order that is compatible with Scylla 1.7.4.
std::vector<counter_shard> shards_compatible_with_1_7_4() const;
// Reversibly applies two counter cells, at least one of them must be live.
static void apply(const column_definition& cdef, atomic_cell_or_collection& dst, atomic_cell_or_collection& src);
// Returns true iff dst was modified.
static bool apply_reversibly(atomic_cell_or_collection& dst, atomic_cell_or_collection& src);
// Reverts apply performed by apply_reversible().
static void revert_apply(atomic_cell_or_collection& dst, atomic_cell_or_collection& src);
// Computes a counter cell containing minimal amount of data which, when
// applied to 'b' returns the same cell as 'a' and 'b' applied together.
static std::optional<atomic_cell> difference(atomic_cell_view a, atomic_cell_view b);
static stdx::optional<atomic_cell> difference(atomic_cell_view a, atomic_cell_view b);
friend std::ostream& operator<<(std::ostream& os, counter_cell_view ccv);
};
struct counter_cell_mutable_view : basic_counter_cell_view<mutable_view::yes> {
struct counter_cell_mutable_view : basic_counter_cell_view<bytes_mutable_view> {
using basic_counter_cell_view::basic_counter_cell_view;
explicit counter_cell_mutable_view(atomic_cell_mutable_view ac) noexcept
: basic_counter_cell_view<mutable_view::yes>(ac, ac.value().first_fragment())
{
assert(!ac.value().is_fragmented());
}
void set_timestamp(api::timestamp_type ts) { _cell.set_timestamp(ts); }
};

View File

@@ -91,7 +91,7 @@ options {
#include "cql3/ut_name.hh"
#include "cql3/functions/function_name.hh"
#include "cql3/functions/function_call.hh"
#include <seastar/core/sstring.hh>
#include "core/sstring.hh"
#include "CqlLexer.hpp"
#include <algorithm>
@@ -115,7 +115,7 @@ using operations_type = std::vector<std::pair<::shared_ptr<cql3::column_identifi
// problem. It is up to the user to ensure it is actually assigned to.
template <typename T>
struct uninitialized {
std::optional<T> _val;
std::experimental::optional<T> _val;
uninitialized() = default;
uninitialized(const uninitialized&) = default;
uninitialized(uninitialized&&) = default;
@@ -242,7 +242,7 @@ struct uninitialized {
return res;
}
bool convert_boolean_literal(std::string_view s) {
bool convert_boolean_literal(stdx::string_view s) {
std::string lower_s(s.size(), '\0');
std::transform(s.cbegin(), s.cend(), lower_s.begin(), &::tolower);
return lower_s == "true";
@@ -253,7 +253,8 @@ struct uninitialized {
{
for (auto&& p : operations) {
if (*p.first == *key && !p.second->is_compatible_with(update)) {
add_recognition_error(format("Multiple incompatible setting of column {}", *key));
// \%s is escaped for antlr
add_recognition_error(sprint("Multiple incompatible setting of column \%s", *key));
}
}
operations.emplace_back(std::move(key), std::move(update));
@@ -372,7 +373,7 @@ useStatement returns [::shared_ptr<raw::use_statement> stmt]
;
/**
* SELECT [JSON] <expression>
* SELECT <expression>
* FROM <CF>
* WHERE KEY = "key1" AND COL > 1 AND COL < 100
* LIMIT <NUMBER>;
@@ -381,28 +382,21 @@ selectStatement returns [shared_ptr<raw::select_statement> expr]
@init {
bool is_distinct = false;
::shared_ptr<cql3::term::raw> limit;
::shared_ptr<cql3::term::raw> per_partition_limit;
raw::select_statement::parameters::orderings_type orderings;
bool allow_filtering = false;
bool is_json = false;
bool bypass_cache = false;
}
: K_SELECT (
( K_JSON { is_json = true; } )?
( K_DISTINCT { is_distinct = true; } )?
sclause=selectClause
: K_SELECT ( ( K_DISTINCT { is_distinct = true; } )?
sclause=selectClause
)
K_FROM cf=columnFamilyName
( K_WHERE wclause=whereClause )?
( K_ORDER K_BY orderByClause[orderings] ( ',' orderByClause[orderings] )* )?
( K_PER K_PARTITION K_LIMIT rows=intValue { per_partition_limit = rows; } )?
( K_LIMIT rows=intValue { limit = rows; } )?
( K_ALLOW K_FILTERING { allow_filtering = true; } )?
( K_BYPASS K_CACHE { bypass_cache = true; })?
{
auto params = ::make_shared<raw::select_statement::parameters>(std::move(orderings), is_distinct, allow_filtering, is_json, bypass_cache);
auto params = ::make_shared<raw::select_statement::parameters>(std::move(orderings), is_distinct, allow_filtering);
$expr = ::make_shared<raw::select_statement>(std::move(cf), std::move(params),
std::move(sclause), std::move(wclause), std::move(limit), std::move(per_partition_limit));
std::move(sclause), std::move(wclause), std::move(limit));
}
;
@@ -454,54 +448,33 @@ orderByClause[raw::select_statement::parameters::orderings_type& orderings]
: c=cident (K_ASC | K_DESC { reversed = true; })? { orderings.emplace_back(c, reversed); }
;
jsonValue returns [::shared_ptr<cql3::term::raw> value]
:
| s=STRING_LITERAL { $value = cql3::constants::literal::string(sstring{$s.text}); }
| ':' id=ident { $value = new_bind_variables(id); }
| QMARK { $value = new_bind_variables(shared_ptr<cql3::column_identifier>{}); }
;
/**
* INSERT INTO <CF> (<column>, <column>, <column>, ...)
* VALUES (<value>, <value>, <value>, ...)
* USING TIMESTAMP <long>;
*
*/
insertStatement returns [::shared_ptr<raw::modification_statement> expr]
insertStatement returns [::shared_ptr<raw::insert_statement> expr]
@init {
auto attrs = ::make_shared<cql3::attributes::raw>();
std::vector<::shared_ptr<cql3::column_identifier::raw>> column_names;
std::vector<::shared_ptr<cql3::term::raw>> values;
bool if_not_exists = false;
bool default_unset = false;
::shared_ptr<cql3::term::raw> json_value;
}
: K_INSERT K_INTO cf=columnFamilyName
('(' c1=cident { column_names.push_back(c1); } ( ',' cn=cident { column_names.push_back(cn); } )* ')'
K_VALUES
'(' v1=term { values.push_back(v1); } ( ',' vn=term { values.push_back(vn); } )* ')'
( K_IF K_NOT K_EXISTS { if_not_exists = true; } )?
( usingClause[attrs] )?
{
$expr = ::make_shared<raw::insert_statement>(std::move(cf),
std::move(attrs),
std::move(column_names),
std::move(values),
if_not_exists);
}
| K_JSON
json_token=jsonValue { json_value = $json_token.value; }
( K_DEFAULT K_UNSET { default_unset = true; } | K_DEFAULT K_NULL )?
( K_IF K_NOT K_EXISTS { if_not_exists = true; } )?
( usingClause[attrs] )?
{
$expr = ::make_shared<raw::insert_json_statement>(std::move(cf),
std::move(attrs),
std::move(json_value),
if_not_exists,
default_unset);
}
)
'(' c1=cident { column_names.push_back(c1); } ( ',' cn=cident { column_names.push_back(cn); } )* ')'
K_VALUES
'(' v1=term { values.push_back(v1); } ( ',' vn=term { values.push_back(vn); } )* ')'
( K_IF K_NOT K_EXISTS { if_not_exists = true; } )?
( usingClause[attrs] )?
{
$expr = ::make_shared<raw::insert_statement>(std::move(cf),
std::move(attrs),
std::move(column_names),
std::move(values),
if_not_exists);
}
;
usingClause[::shared_ptr<cql3::attributes::raw> attrs]
@@ -823,15 +796,10 @@ createIndexStatement returns [::shared_ptr<create_index_statement> expr]
;
indexIdent returns [::shared_ptr<index_target::raw> id]
@init {
std::vector<::shared_ptr<cql3::column_identifier::raw>> columns;
}
: c=cident { $id = index_target::raw::values_of(c); }
| K_KEYS '(' c=cident ')' { $id = index_target::raw::keys_of(c); }
| K_ENTRIES '(' c=cident ')' { $id = index_target::raw::keys_and_values_of(c); }
| K_FULL '(' c=cident ')' { $id = index_target::raw::full_collection(c); }
| '(' c1=cident { columns.push_back(c1); } ( ',' cn=cident { columns.push_back(cn); } )* ')' { $id = index_target::raw::columns(std::move(columns)); }
;
/**
@@ -905,8 +873,8 @@ alterKeyspaceStatement returns [shared_ptr<cql3::statements::alter_keyspace_stat
/**
* ALTER COLUMN FAMILY <CF> ALTER <column> TYPE <newtype>;
* ALTER COLUMN FAMILY <CF> ADD <column> <newtype>; | ALTER COLUMN FAMILY <CF> ADD (<column> <newtype>,<column1> <newtype1>..... <column n> <newtype n>)
* ALTER COLUMN FAMILY <CF> DROP <column>; | ALTER COLUMN FAMILY <CF> DROP ( <column>,<column1>.....<column n>)
* ALTER COLUMN FAMILY <CF> ADD <column> <newtype>;
* ALTER COLUMN FAMILY <CF> DROP <column>;
* ALTER COLUMN FAMILY <CF> WITH <property> = <value>;
* ALTER COLUMN FAMILY <CF> RENAME <column> TO <column>;
*/
@@ -914,38 +882,21 @@ alterTableStatement returns [shared_ptr<alter_table_statement> expr]
@init {
alter_table_statement::type type;
auto props = make_shared<cql3::statements::cf_prop_defs>();
std::vector<alter_table_statement::column_change> column_changes;
std::vector<std::pair<shared_ptr<cql3::column_identifier::raw>, shared_ptr<cql3::column_identifier::raw>>> renames;
bool is_static = false;
}
: K_ALTER K_COLUMNFAMILY cf=columnFamilyName
( K_ALTER id=cident K_TYPE v=comparatorType { type = alter_table_statement::type::alter; column_changes.emplace_back(alter_table_statement::column_change{id, v}); }
| K_ADD { type = alter_table_statement::type::add; }
( id=cident v=comparatorType s=cfisStatic { column_changes.emplace_back(alter_table_statement::column_change{id, v, s}); }
| '(' id1=cident v1=comparatorType s1=cfisStatic { column_changes.emplace_back(alter_table_statement::column_change{id1, v1, s1}); }
(',' idn=cident vn=comparatorType sn=cfisStatic { column_changes.emplace_back(alter_table_statement::column_change{idn, vn, sn}); } )* ')'
)
| K_DROP { type = alter_table_statement::type::drop; }
( id=cident { column_changes.emplace_back(alter_table_statement::column_change{id}); }
| '(' id1=cident { column_changes.emplace_back(alter_table_statement::column_change{id1}); }
(',' idn=cident { column_changes.emplace_back(alter_table_statement::column_change{idn}); } )* ')'
)
( K_ALTER id=cident K_TYPE v=comparatorType { type = alter_table_statement::type::alter; }
| K_ADD id=cident v=comparatorType ({ is_static=true; } K_STATIC)? { type = alter_table_statement::type::add; }
| K_DROP id=cident { type = alter_table_statement::type::drop; }
| K_WITH properties[props] { type = alter_table_statement::type::opts; }
| K_RENAME { type = alter_table_statement::type::rename; }
id1=cident K_TO toId1=cident { renames.emplace_back(id1, toId1); }
( K_AND idn=cident K_TO toIdn=cident { renames.emplace_back(idn, toIdn); } )*
)
{
$expr = ::make_shared<alter_table_statement>(std::move(cf), type, std::move(column_changes), std::move(props), std::move(renames));
}
;
cfisStatic returns [bool isStaticColumn]
@init{
bool isStatic = false;
}
: (K_STATIC { isStatic=true; })?
{
$isStaticColumn = isStatic;
$expr = ::make_shared<alter_table_statement>(std::move(cf), type, std::move(id),
std::move(v), std::move(props), std::move(renames), is_static);
}
;
@@ -1559,22 +1510,12 @@ inMarkerForTuple returns [shared_ptr<cql3::tuples::in_raw> marker]
| ':' name=ident { $marker = new_tuple_in_bind_variables(name); }
;
// The comparator_type rule is used for users' queries (internal=false)
// and for internal calls from db::cql_type_parser::parse() (internal=true).
// The latter is used for reading schemas stored in the system tables, and
// may support additional column types that cannot be created through CQL,
// but only internally through code. Today the only such type is "empty":
// Scylla code internally creates columns with type "empty" or collections
// "empty" to represent unselected columns in materialized views.
// If a user (internal=false) tries to use "empty" as a type, it is treated -
// as do all unknown types - as an attempt to use a user-defined type, and
// we report this name is reserved (as for _reserved_type_names()).
comparator_type [bool internal] returns [shared_ptr<cql3_type::raw> t]
: n=native_or_internal_type[internal] { $t = cql3_type::raw::from(n); }
| c=collection_type[internal] { $t = c; }
| tt=tuple_type[internal] { $t = tt; }
comparatorType returns [shared_ptr<cql3_type::raw> t]
: n=native_type { $t = cql3_type::raw::from(n); }
| c=collection_type { $t = c; }
| tt=tuple_type { $t = tt; }
| id=userTypeName { $t = cql3::cql3_type::raw::user_type(id); }
| K_FROZEN '<' f=comparator_type[internal] '>'
| K_FROZEN '<' f=comparatorType '>'
{
try {
$t = cql3::cql3_type::raw::frozen(f);
@@ -1596,64 +1537,48 @@ comparator_type [bool internal] returns [shared_ptr<cql3_type::raw> t]
#endif
;
native_or_internal_type [bool internal] returns [data_type t]
: n=native_type { $t = n; }
// The "internal" types, only supported when internal==true:
| K_EMPTY {
if (internal) {
$t = empty_type;
} else {
add_recognition_error("Invalid (reserved) user type name empty");
}
}
native_type returns [shared_ptr<cql3_type> t]
: K_ASCII { $t = cql3_type::ascii; }
| K_BIGINT { $t = cql3_type::bigint; }
| K_BLOB { $t = cql3_type::blob; }
| K_BOOLEAN { $t = cql3_type::boolean; }
| K_COUNTER { $t = cql3_type::counter; }
| K_DECIMAL { $t = cql3_type::decimal; }
| K_DOUBLE { $t = cql3_type::double_; }
| K_DURATION { $t = cql3_type::duration; }
| K_FLOAT { $t = cql3_type::float_; }
| K_INET { $t = cql3_type::inet; }
| K_INT { $t = cql3_type::int_; }
| K_SMALLINT { $t = cql3_type::smallint; }
| K_TEXT { $t = cql3_type::text; }
| K_TIMESTAMP { $t = cql3_type::timestamp; }
| K_TINYINT { $t = cql3_type::tinyint; }
| K_UUID { $t = cql3_type::uuid; }
| K_VARCHAR { $t = cql3_type::varchar; }
| K_VARINT { $t = cql3_type::varint; }
| K_TIMEUUID { $t = cql3_type::timeuuid; }
| K_DATE { $t = cql3_type::date; }
| K_TIME { $t = cql3_type::time; }
;
comparatorType returns [shared_ptr<cql3_type::raw> t]
: tt=comparator_type[false] { $t = tt; }
;
native_type returns [data_type t]
: K_ASCII { $t = ascii_type; }
| K_BIGINT { $t = long_type; }
| K_BLOB { $t = bytes_type; }
| K_BOOLEAN { $t = boolean_type; }
| K_COUNTER { $t = counter_type; }
| K_DECIMAL { $t = decimal_type; }
| K_DOUBLE { $t = double_type; }
| K_DURATION { $t = duration_type; }
| K_FLOAT { $t = float_type; }
| K_INET { $t = inet_addr_type; }
| K_INT { $t = int32_type; }
| K_SMALLINT { $t = short_type; }
| K_TEXT { $t = utf8_type; }
| K_TIMESTAMP { $t = timestamp_type; }
| K_TINYINT { $t = byte_type; }
| K_UUID { $t = uuid_type; }
| K_VARCHAR { $t = utf8_type; }
| K_VARINT { $t = varint_type; }
| K_TIMEUUID { $t = timeuuid_type; }
| K_DATE { $t = simple_date_type; }
| K_TIME { $t = time_type; }
;
collection_type [bool internal] returns [shared_ptr<cql3::cql3_type::raw> pt]
: K_MAP '<' t1=comparator_type[internal] ',' t2=comparator_type[internal] '>'
collection_type returns [shared_ptr<cql3::cql3_type::raw> pt]
: K_MAP '<' t1=comparatorType ',' t2=comparatorType '>'
{
// if we can't parse either t1 or t2, antlr will "recover" and we may have t1 or t2 null.
if (t1 && t2) {
$pt = cql3::cql3_type::raw::map(t1, t2);
}
}
| K_LIST '<' t=comparator_type[internal] '>'
| K_LIST '<' t=comparatorType '>'
{ if (t) { $pt = cql3::cql3_type::raw::list(t); } }
| K_SET '<' t=comparator_type[internal] '>'
| K_SET '<' t=comparatorType '>'
{ if (t) { $pt = cql3::cql3_type::raw::set(t); } }
;
tuple_type [bool internal] returns [shared_ptr<cql3::cql3_type::raw> t]
tuple_type returns [shared_ptr<cql3::cql3_type::raw> t]
@init{ std::vector<shared_ptr<cql3::cql3_type::raw>> types; }
: K_TUPLE '<'
t1=comparator_type[internal] { types.push_back(t1); } (',' tn=comparator_type[internal] { types.push_back(tn); })*
t1=comparatorType { types.push_back(t1); } (',' tn=comparatorType { types.push_back(tn); })*
'>' { $t = cql3::cql3_type::raw::tuple(std::move(types)); }
;
@@ -1679,7 +1604,7 @@ unreserved_keyword returns [sstring str]
unreserved_function_keyword returns [sstring str]
: u=basic_unreserved_keyword { $str = u; }
| t=native_or_internal_type[true] { $str = t->as_cql3_type().to_string(); }
| t=native_type { $str = t->to_string(); }
;
basic_unreserved_keyword returns [sstring str]
@@ -1725,11 +1650,6 @@ basic_unreserved_keyword returns [sstring str]
| K_LANGUAGE
| K_NON
| K_DETERMINISTIC
| K_JSON
| K_CACHE
| K_BYPASS
| K_PER
| K_PARTITION
) { $str = $k.text; }
;
@@ -1866,17 +1786,6 @@ K_NON: N O N;
K_OR: O R;
K_REPLACE: R E P L A C E;
K_DETERMINISTIC: D E T E R M I N I S T I C;
K_JSON: J S O N;
K_DEFAULT: D E F A U L T;
K_UNSET: U N S E T;
K_EMPTY: E M P T Y;
K_BYPASS: B Y P A S S;
K_CACHE: C A C H E;
K_PER: P E R;
K_PARTITION: P A R T I T I O N;
K_SCYLLA_TIMEUUID_LIST_INDEX: S C Y L L A '_' T I M E U U I D '_' L I S T '_' I N D E X;
K_SCYLLA_COUNTER_SHARD_LIST: S C Y L L A '_' C O U N T E R '_' S H A R D '_' L I S T;

View File

@@ -45,7 +45,6 @@
#include "cql3/lists.hh"
#include "cql3/maps.hh"
#include "cql3/sets.hh"
#include "types/list.hh"
namespace cql3 {

View File

@@ -77,14 +77,12 @@ int64_t attributes::get_timestamp(int64_t now, const query_options& options) {
if (tval.is_unset_value()) {
return now;
}
return with_linearized(*tval, [&] (bytes_view val) {
try {
data_type_for<int64_t>()->validate(val, options.get_cql_serialization_format());
data_type_for<int64_t>()->validate(*tval);
} catch (marshal_exception& e) {
throw exceptions::invalid_request_exception("Invalid timestamp value");
}
return value_cast<int64_t>(data_type_for<int64_t>()->deserialize(val));
});
return value_cast<int64_t>(data_type_for<int64_t>()->deserialize(*tval));
}
int32_t attributes::get_time_to_live(const query_options& options) {
@@ -98,16 +96,14 @@ int32_t attributes::get_time_to_live(const query_options& options) {
if (tval.is_unset_value()) {
return 0;
}
auto ttl = with_linearized(*tval, [&] (bytes_view val) {
try {
data_type_for<int32_t>()->validate(val, options.get_cql_serialization_format());
data_type_for<int32_t>()->validate(*tval);
}
catch (marshal_exception& e) {
throw exceptions::invalid_request_exception("Invalid TTL value");
}
return value_cast<int32_t>(data_type_for<int32_t>()->deserialize(val));
});
auto ttl = value_cast<int32_t>(data_type_for<int32_t>()->deserialize(*tval));
if (ttl < 0) {
throw exceptions::invalid_request_exception("A TTL must be greater or equal to 0");
}

View File

@@ -43,7 +43,7 @@
#include "exceptions/exceptions.hh"
#include "cql3/term.hh"
#include <optional>
#include <experimental/optional>
namespace cql3 {
/**

View File

@@ -1,187 +0,0 @@
/*
* Copyright (C) 2018 ScyllaDB
*/
/*
* This file is part of Scylla.
*
* Scylla is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* Scylla is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with Scylla. If not, see <http://www.gnu.org/licenses/>.
*/
#pragma once
#include "cql3/prepared_statements_cache.hh"
namespace cql3 {
struct authorized_prepared_statements_cache_size {
size_t operator()(const statements::prepared_statement::checked_weak_ptr& val) {
// TODO: improve the size approximation - most of the entry is occupied by the key here.
return 100;
}
};
class authorized_prepared_statements_cache_key {
public:
using cache_key_type = std::pair<auth::authenticated_user, typename cql3::prepared_cache_key_type::cache_key_type>;
private:
cache_key_type _key;
public:
authorized_prepared_statements_cache_key(auth::authenticated_user user, cql3::prepared_cache_key_type prepared_cache_key)
: _key(std::move(user), std::move(prepared_cache_key.key())) {}
cache_key_type& key() { return _key; }
const cache_key_type& key() const { return _key; }
bool operator==(const authorized_prepared_statements_cache_key& other) const {
return _key == other._key;
}
bool operator!=(const authorized_prepared_statements_cache_key& other) const {
return !(*this == other);
}
static size_t hash(const auth::authenticated_user& user, const cql3::prepared_cache_key_type::cache_key_type& prep_cache_key) {
return utils::hash_combine(std::hash<auth::authenticated_user>()(user), utils::tuple_hash()(prep_cache_key));
}
};
/// \class authorized_prepared_statements_cache
/// \brief A cache of previously authorized statements.
///
/// Entries are inserted every time a new statement is authorized.
/// Entries are evicted in any of the following cases:
/// - When the corresponding prepared statement is not valid anymore.
/// - Periodically, with the same period as the permission cache is refreshed.
/// - If the corresponding entry hasn't been used for \ref entry_expiry.
class authorized_prepared_statements_cache {
public:
struct stats {
uint64_t authorized_prepared_statements_cache_evictions = 0;
};
static stats& shard_stats() {
static thread_local stats _stats;
return _stats;
}
struct authorized_prepared_statements_cache_stats_updater {
static void inc_hits() noexcept {}
static void inc_misses() noexcept {}
static void inc_blocks() noexcept {}
static void inc_evictions() noexcept {
++shard_stats().authorized_prepared_statements_cache_evictions;
}
};
private:
using cache_key_type = authorized_prepared_statements_cache_key;
using checked_weak_ptr = typename statements::prepared_statement::checked_weak_ptr;
using cache_type = utils::loading_cache<cache_key_type,
checked_weak_ptr,
utils::loading_cache_reload_enabled::yes,
authorized_prepared_statements_cache_size,
std::hash<cache_key_type>,
std::equal_to<cache_key_type>,
authorized_prepared_statements_cache_stats_updater>;
public:
using key_type = cache_key_type;
using value_type = checked_weak_ptr;
using entry_is_too_big = typename cache_type::entry_is_too_big;
using iterator = typename cache_type::iterator;
private:
cache_type _cache;
logging::logger& _logger;
public:
// Choose the memory budget such that would allow us ~4K entries when a shard gets 1GB of RAM
authorized_prepared_statements_cache(std::chrono::milliseconds entry_expiration, std::chrono::milliseconds entry_refresh, size_t cache_size, logging::logger& logger)
: _cache(cache_size, entry_expiration, entry_refresh, logger, [this] (const key_type& k) {
_cache.remove(k);
return make_ready_future<value_type>();
})
, _logger(logger)
{}
future<> insert(auth::authenticated_user user, cql3::prepared_cache_key_type prep_cache_key, value_type v) noexcept {
return _cache.get_ptr(key_type(std::move(user), std::move(prep_cache_key)), [v = std::move(v)] (const cache_key_type&) mutable {
return make_ready_future<value_type>(std::move(v));
}).discard_result();
}
iterator find(const auth::authenticated_user& user, const cql3::prepared_cache_key_type& prep_cache_key) {
struct key_view {
const auth::authenticated_user& user_ref;
const cql3::prepared_cache_key_type& prep_cache_key_ref;
};
struct hasher {
size_t operator()(const key_view& kv) {
return cql3::authorized_prepared_statements_cache_key::hash(kv.user_ref, kv.prep_cache_key_ref.key());
}
};
struct equal {
bool operator()(const key_type& k1, const key_view& k2) {
return k1.key().first == k2.user_ref && k1.key().second == k2.prep_cache_key_ref.key();
}
bool operator()(const key_view& k2, const key_type& k1) {
return operator()(k1, k2);
}
};
return _cache.find(key_view{user, prep_cache_key}, hasher(), equal());
}
iterator end() {
return _cache.end();
}
void remove(const auth::authenticated_user& user, const cql3::prepared_cache_key_type& prep_cache_key) {
iterator it = find(user, prep_cache_key);
_cache.remove(it);
}
size_t size() const {
return _cache.size();
}
size_t memory_footprint() const {
return _cache.memory_footprint();
}
future<> stop() {
return _cache.stop();
}
};
}
namespace std {
template <>
struct hash<cql3::authorized_prepared_statements_cache_key> final {
size_t operator()(const cql3::authorized_prepared_statements_cache_key& k) const {
return cql3::authorized_prepared_statements_cache_key::hash(k.key().first, k.key().second);
}
};
inline std::ostream& operator<<(std::ostream& out, const cql3::authorized_prepared_statements_cache_key& k) {
return out << "{ " << k.key().first << ", " << k.key().second << " }";
}
}

View File

@@ -57,7 +57,7 @@ void validate_operation_on_durations(const abstract_type& type, const cql3::oper
check_false(type.is_user_type(), "Slice conditions are not supported on UDTs containing durations");
// We're a duration.
throw exceptions::invalid_request_exception(format("Slice conditions are not supported on durations"));
throw exceptions::invalid_request_exception(sprint("Slice conditions are not supported on durations"));
}
}
@@ -119,7 +119,7 @@ column_condition::raw::prepare(database& db, const sstring& keyspace, const colu
}
if (!receiver.type->is_collection()) {
throw exceptions::invalid_request_exception(format("Invalid element access syntax for non-collection column {}", receiver.name_as_text()));
throw exceptions::invalid_request_exception(sprint("Invalid element access syntax for non-collection column %s", receiver.name_as_text()));
}
shared_ptr<column_specification> element_spec, value_spec;
@@ -131,7 +131,7 @@ column_condition::raw::prepare(database& db, const sstring& keyspace, const colu
element_spec = maps::key_spec_of(*receiver.column_specification);
value_spec = maps::value_spec_of(*receiver.column_specification);
} else if (&ctype->_kind == &collection_type_impl::kind::set) {
throw exceptions::invalid_request_exception(format("Invalid element access syntax for set column {}", receiver.name()));
throw exceptions::invalid_request_exception(sprint("Invalid element access syntax for set column %s", receiver.name()));
} else {
abort();
}

View File

@@ -22,7 +22,6 @@
#include "cql3/column_identifier.hh"
#include "exceptions/exceptions.hh"
#include "cql3/selection/simple_selector.hh"
#include "cql3/util.hh"
#include <regex>
@@ -63,11 +62,14 @@ sstring column_identifier::to_string() const {
}
sstring column_identifier::to_cql_string() const {
return util::maybe_quote(_text);
}
sstring column_identifier::raw::to_cql_string() const {
return util::maybe_quote(_text);
static const std::regex unquoted_identifier_re("[a-z][a-z0-9_]*");
if (std::regex_match(_text.begin(), _text.end(), unquoted_identifier_re)) {
return _text;
}
static const std::regex double_quote_re("\"");
std::string result = _text;
std::regex_replace(result, double_quote_re, "\"\"");
return '"' + result + '"';
}
column_identifier::raw::raw(sstring raw_text, bool keep_case)
@@ -125,13 +127,9 @@ std::ostream& operator<<(std::ostream& out, const column_identifier::raw& id) {
column_identifier::new_selector_factory(database& db, schema_ptr schema, std::vector<const column_definition*>& defs) {
auto def = get_column_definition(schema, *this);
if (!def) {
throw exceptions::invalid_request_exception(format("Undefined name {} in selection clause", _text));
}
// Do not allow explicitly selecting hidden columns. We also skip them on
// "SELECT *" (see selection::wildcard()).
if (def->is_hidden_from_cql()) {
throw exceptions::invalid_request_exception(format("Undefined name {} in selection clause", _text));
throw exceptions::invalid_request_exception(sprint("Undefined name %s in selection clause", _text));
}
return selection::simple_selector::new_factory(def->name_as_text(), add_and_get_index(*def, defs), def->type);
}

View File

@@ -123,7 +123,6 @@ public:
bool operator!=(const raw& other) const;
virtual sstring to_string() const;
sstring to_cql_string() const;
friend std::hash<column_identifier::raw>;
friend std::ostream& operator<<(std::ostream& out, const column_identifier::raw& id);

View File

@@ -85,19 +85,20 @@ assignment_testable::test_result
constants::literal::test_assignment(database& db, const sstring& keyspace, ::shared_ptr<column_specification> receiver)
{
auto receiver_type = receiver->type->as_cql3_type();
if (receiver_type.is_collection()) {
if (receiver_type->is_collection()) {
return test_result::NOT_ASSIGNABLE;
}
if (!receiver_type.is_native()) {
if (!receiver_type->is_native()) {
return test_result::WEAKLY_ASSIGNABLE;
}
auto kind = receiver_type.get_kind();
auto kind = receiver_type.get()->get_kind();
switch (_type) {
case type::STRING:
if (cql3_type::kind_enum_set::frozen<
cql3_type::kind::ASCII,
cql3_type::kind::TEXT,
cql3_type::kind::INET,
cql3_type::kind::VARCHAR,
cql3_type::kind::TIMESTAMP,
cql3_type::kind::DATE,
cql3_type::kind::TIME>::contains(kind)) {
@@ -158,8 +159,8 @@ constants::literal::test_assignment(database& db, const sstring& keyspace, ::sha
constants::literal::prepare(database& db, const sstring& keyspace, ::shared_ptr<column_specification> receiver)
{
if (!is_assignable(test_assignment(db, keyspace, receiver))) {
throw exceptions::invalid_request_exception(format("Invalid {} constant ({}) for \"{}\" of type {}",
_type, _text, *receiver->name, receiver->type->as_cql3_type().to_string()));
throw exceptions::invalid_request_exception(sprint("Invalid %s constant (%s) for \"%s\" of type %s",
_type, _text, *receiver->name, receiver->type->as_cql3_type()->to_string()));
}
return ::make_shared<value>(cql3::raw_value::make_value(parsed_value(receiver->type)));
}

View File

@@ -46,7 +46,7 @@
#include "cql3/operation.hh"
#include "cql3/values.hh"
#include "cql3/term.hh"
#include <seastar/core/shared_ptr.hh>
#include "core/shared_ptr.hh"
namespace cql3 {
@@ -85,8 +85,8 @@ public:
virtual ::shared_ptr<terminal> bind(const query_options& options) override { return {}; }
virtual sstring to_string() const override { return "null"; }
};
public:
static thread_local const ::shared_ptr<terminal> NULL_VALUE;
public:
virtual ::shared_ptr<term> prepare(database& db, const sstring& keyspace, ::shared_ptr<column_specification> receiver) override {
if (!is_assignable(test_assignment(db, keyspace, receiver))) {
throw exceptions::invalid_request_exception("Invalid null value for counter increment/decrement");
@@ -164,7 +164,7 @@ public:
virtual assignment_testable::test_result test_assignment(database& db, const sstring& keyspace, ::shared_ptr<column_specification> receiver);
virtual sstring to_string() const override {
return _type == type::STRING ? sstring(format("'{}'", _text)) : _text;
return _type == type::STRING ? sstring(sprint("'%s'", _text)) : _text;
}
};
@@ -180,7 +180,7 @@ public:
try {
auto value = options.get_value_at(_bind_index);
if (value) {
_receiver->type->validate(*value, options.get_cql_serialization_format());
_receiver->type->validate(*value);
}
return value;
} catch (const marshal_exception& e) {
@@ -203,14 +203,10 @@ public:
virtual void execute(mutation& m, const clustering_key_prefix& prefix, const update_parameters& params) override {
auto value = _t->bind_and_get(params._options);
execute(m, prefix, params, column, std::move(value));
}
static void execute(mutation& m, const clustering_key_prefix& prefix, const update_parameters& params, const column_definition& column, cql3::raw_value_view value) {
if (value.is_null()) {
m.set_cell(prefix, column, std::move(make_dead_cell(params)));
} else if (value.is_value()) {
m.set_cell(prefix, column, std::move(make_cell(*column.type, *value, params)));
m.set_cell(prefix, column, std::move(make_cell(*value, params)));
}
}
};
@@ -225,9 +221,7 @@ public:
} else if (value.is_unset_value()) {
return;
}
auto increment = with_linearized(*value, [] (bytes_view value_view) {
return value_cast<int64_t>(long_type->deserialize_value(value_view));
});
auto increment = value_cast<int64_t>(long_type->deserialize_value(*value));
m.set_cell(prefix, column, make_counter_update_cell(increment, params));
}
};
@@ -242,11 +236,9 @@ public:
} else if (value.is_unset_value()) {
return;
}
auto increment = with_linearized(*value, [] (bytes_view value_view) {
return value_cast<int64_t>(long_type->deserialize_value(value_view));
});
auto increment = value_cast<int64_t>(long_type->deserialize_value(*value));
if (increment == std::numeric_limits<int64_t>::min()) {
throw exceptions::invalid_request_exception(format("The negation of {:d} overflows supported counter precision (signed 8 bytes integer)", increment));
throw exceptions::invalid_request_exception(sprint("The negation of %d overflows supported counter precision (signed 8 bytes integer)", increment));
}
m.set_cell(prefix, column, make_counter_update_cell(-increment, params));
}

View File

@@ -26,15 +26,20 @@
#include "cql3_type.hh"
#include "cql3/util.hh"
#include "ut_name.hh"
#include "database.hh"
#include "user_types_metadata.hh"
#include "types/map.hh"
#include "types/set.hh"
#include "types/list.hh"
namespace cql3 {
cql3_type cql3_type::raw::prepare(database& db, const sstring& keyspace) {
sstring cql3_type::to_string() const {
if (_type->is_user_type()) {
return "frozen<" + util::maybe_quote(_name) + ">";
}
if (_type->is_tuple()) {
return "frozen<" + _name + ">";
}
return _name;
}
shared_ptr<cql3_type> cql3_type::raw::prepare(database& db, const sstring& keyspace) {
try {
auto&& ks = db.find_keyspace(keyspace);
return prepare_internal(keyspace, ks.metadata()->user_types());
@@ -53,16 +58,16 @@ bool cql3_type::raw::references_user_type(const sstring& name) const {
class cql3_type::raw_type : public raw {
private:
cql3_type _type;
shared_ptr<cql3_type> _type;
public:
raw_type(cql3_type type)
raw_type(shared_ptr<cql3_type> type)
: _type{type}
{ }
public:
virtual cql3_type prepare(database& db, const sstring& keyspace) {
virtual shared_ptr<cql3_type> prepare(database& db, const sstring& keyspace) {
return _type;
}
cql3_type prepare_internal(const sstring&, lw_shared_ptr<user_types_metadata>) override {
shared_ptr<cql3_type> prepare_internal(const sstring&, lw_shared_ptr<user_types_metadata>) override {
return _type;
}
@@ -71,15 +76,15 @@ public:
}
virtual bool is_counter() const {
return _type.is_counter();
return _type->is_counter();
}
virtual sstring to_string() const {
return _type.to_string();
return _type->to_string();
}
virtual bool is_duration() const override {
return _type.get_type()->equals(duration_type);
return _type->get_type()->equals(duration_type);
}
};
@@ -110,35 +115,35 @@ public:
return true;
}
virtual cql3_type prepare_internal(const sstring& keyspace, lw_shared_ptr<user_types_metadata> user_types) override {
virtual shared_ptr<cql3_type> prepare_internal(const sstring& keyspace, lw_shared_ptr<user_types_metadata> user_types) override {
assert(_values); // "Got null values type for a collection";
if (!_frozen && _values->supports_freezing() && !_values->_frozen) {
throw exceptions::invalid_request_exception(format("Non-frozen collections are not allowed inside collections: {}", *this));
throw exceptions::invalid_request_exception(sprint("Non-frozen collections are not allowed inside collections: %s", *this));
}
if (_values->is_counter()) {
throw exceptions::invalid_request_exception(format("Counters are not allowed inside collections: {}", *this));
throw exceptions::invalid_request_exception(sprint("Counters are not allowed inside collections: %s", *this));
}
if (_keys) {
if (!_frozen && _keys->supports_freezing() && !_keys->_frozen) {
throw exceptions::invalid_request_exception(format("Non-frozen collections are not allowed inside collections: {}", *this));
throw exceptions::invalid_request_exception(sprint("Non-frozen collections are not allowed inside collections: %s", *this));
}
}
if (_kind == &collection_type_impl::kind::list) {
return cql3_type(list_type_impl::get_instance(_values->prepare_internal(keyspace, user_types).get_type(), !_frozen));
return make_shared(cql3_type(to_string(), list_type_impl::get_instance(_values->prepare_internal(keyspace, user_types)->get_type(), !_frozen), false));
} else if (_kind == &collection_type_impl::kind::set) {
if (_values->is_duration()) {
throw exceptions::invalid_request_exception(format("Durations are not allowed inside sets: {}", *this));
throw exceptions::invalid_request_exception(sprint("Durations are not allowed inside sets: %s", *this));
}
return cql3_type(set_type_impl::get_instance(_values->prepare_internal(keyspace, user_types).get_type(), !_frozen));
return make_shared(cql3_type(to_string(), set_type_impl::get_instance(_values->prepare_internal(keyspace, user_types)->get_type(), !_frozen), false));
} else if (_kind == &collection_type_impl::kind::map) {
assert(_keys); // "Got null keys type for a collection";
if (_keys->is_duration()) {
throw exceptions::invalid_request_exception(format("Durations are not allowed as map keys: {}", *this));
throw exceptions::invalid_request_exception(sprint("Durations are not allowed as map keys: %s", *this));
}
return cql3_type(map_type_impl::get_instance(_keys->prepare_internal(keyspace, user_types).get_type(), _values->prepare_internal(keyspace, user_types).get_type(), !_frozen));
return make_shared(cql3_type(to_string(), map_type_impl::get_instance(_keys->prepare_internal(keyspace, user_types)->get_type(), _values->prepare_internal(keyspace, user_types)->get_type(), !_frozen), false));
}
abort();
}
@@ -155,11 +160,11 @@ public:
sstring start = _frozen ? "frozen<" : "";
sstring end = _frozen ? ">" : "";
if (_kind == &collection_type_impl::kind::list) {
return format("{}list<{}>{}", start, _values, end);
return sprint("%slist<%s>%s", start, _values, end);
} else if (_kind == &collection_type_impl::kind::set) {
return format("{}set<{}>{}", start, _values, end);
return sprint("%sset<%s>%s", start, _values, end);
} else if (_kind == &collection_type_impl::kind::map) {
return format("{}map<{}, {}>{}", start, _keys, _values, end);
return sprint("%smap<%s, %s>%s", start, _keys, _values, end);
}
abort();
}
@@ -172,7 +177,7 @@ public:
: _name(std::move(name)) {
}
virtual std::optional<sstring> keyspace() const override {
virtual std::experimental::optional<sstring> keyspace() const override {
return _name.get_keyspace();
}
@@ -180,7 +185,7 @@ public:
_frozen = true;
}
virtual cql3_type prepare_internal(const sstring& keyspace, lw_shared_ptr<user_types_metadata> user_types) override {
virtual shared_ptr<cql3_type> prepare_internal(const sstring& keyspace, lw_shared_ptr<user_types_metadata> user_types) override {
if (_name.has_keyspace()) {
// The provided keyspace is the one of the current statement this is part of. If it's different from the keyspace of
// the UTName, we reject since we want to limit user types to their own keyspace (see #6643)
@@ -194,16 +199,16 @@ public:
}
if (!user_types) {
// bootstrap mode.
throw exceptions::invalid_request_exception(format("Unknown type {}", _name));
throw exceptions::invalid_request_exception(sprint("Unknown type %s", _name));
}
try {
auto&& type = user_types->get_type(_name.get_user_type_name());
if (!_frozen) {
throw exceptions::invalid_request_exception("Non-frozen User-Defined types are not supported, please use frozen<>");
}
return cql3_type(std::move(type));
return make_shared<cql3_type>(_name.to_string(), std::move(type));
} catch (std::out_of_range& e) {
throw exceptions::invalid_request_exception(format("Unknown type {}", _name));
throw exceptions::invalid_request_exception(sprint("Unknown type %s", _name));
}
}
bool references_user_type(const sstring& name) const override {
@@ -239,7 +244,7 @@ public:
}
_frozen = true;
}
virtual cql3_type prepare_internal(const sstring& keyspace, lw_shared_ptr<user_types_metadata> user_types) override {
virtual shared_ptr<cql3_type> prepare_internal(const sstring& keyspace, lw_shared_ptr<user_types_metadata> user_types) override {
if (!_frozen) {
freeze();
}
@@ -248,9 +253,9 @@ public:
if (t->is_counter()) {
throw exceptions::invalid_request_exception("Counters are not allowed inside tuples");
}
ts.push_back(t->prepare_internal(keyspace, user_types).get_type());
ts.push_back(t->prepare_internal(keyspace, user_types)->get_type());
}
return tuple_type_impl::get_instance(std::move(ts))->as_cql3_type();
return make_cql3_tuple_type(tuple_type_impl::get_instance(std::move(ts)));
}
bool references_user_type(const sstring& name) const override {
@@ -260,7 +265,7 @@ public:
}
virtual sstring to_string() const override {
return format("tuple<{}>", join(", ", _types));
return sprint("tuple<%s>", join(", ", _types));
}
};
@@ -274,19 +279,19 @@ cql3_type::raw::is_counter() const {
return false;
}
std::optional<sstring>
std::experimental::optional<sstring>
cql3_type::raw::keyspace() const {
return std::nullopt;
return std::experimental::nullopt;
}
void
cql3_type::raw::freeze() {
sstring message = format("frozen<> is only allowed on collections, tuples, and user-defined types (got {})", to_string());
sstring message = sprint("frozen<> is only allowed on collections, tuples, and user-defined types (got %s)", to_string());
throw exceptions::invalid_request_exception(message);
}
shared_ptr<cql3_type::raw>
cql3_type::raw::from(cql3_type type) {
cql3_type::raw::from(shared_ptr<cql3_type> type) {
return ::make_shared<raw_type>(type);
}
@@ -321,31 +326,32 @@ cql3_type::raw::frozen(shared_ptr<raw> t) {
return t;
}
thread_local cql3_type cql3_type::ascii{ascii_type};
thread_local cql3_type cql3_type::bigint{long_type};
thread_local cql3_type cql3_type::blob{bytes_type};
thread_local cql3_type cql3_type::boolean{boolean_type};
thread_local cql3_type cql3_type::double_{double_type};
thread_local cql3_type cql3_type::empty{empty_type};
thread_local cql3_type cql3_type::float_{float_type};
thread_local cql3_type cql3_type::int_{int32_type};
thread_local cql3_type cql3_type::smallint{short_type};
thread_local cql3_type cql3_type::text{utf8_type};
thread_local cql3_type cql3_type::timestamp{timestamp_type};
thread_local cql3_type cql3_type::tinyint{byte_type};
thread_local cql3_type cql3_type::uuid{uuid_type};
thread_local cql3_type cql3_type::timeuuid{timeuuid_type};
thread_local cql3_type cql3_type::date{simple_date_type};
thread_local cql3_type cql3_type::time{time_type};
thread_local cql3_type cql3_type::inet{inet_addr_type};
thread_local cql3_type cql3_type::varint{varint_type};
thread_local cql3_type cql3_type::decimal{decimal_type};
thread_local cql3_type cql3_type::counter{counter_type};
thread_local cql3_type cql3_type::duration{duration_type};
thread_local shared_ptr<cql3_type> cql3_type::ascii = make("ascii", ascii_type, cql3_type::kind::ASCII);
thread_local shared_ptr<cql3_type> cql3_type::bigint = make("bigint", long_type, cql3_type::kind::BIGINT);
thread_local shared_ptr<cql3_type> cql3_type::blob = make("blob", bytes_type, cql3_type::kind::BLOB);
thread_local shared_ptr<cql3_type> cql3_type::boolean = make("boolean", boolean_type, cql3_type::kind::BOOLEAN);
thread_local shared_ptr<cql3_type> cql3_type::double_ = make("double", double_type, cql3_type::kind::DOUBLE);
thread_local shared_ptr<cql3_type> cql3_type::empty = make("empty", empty_type, cql3_type::kind::EMPTY);
thread_local shared_ptr<cql3_type> cql3_type::float_ = make("float", float_type, cql3_type::kind::FLOAT);
thread_local shared_ptr<cql3_type> cql3_type::int_ = make("int", int32_type, cql3_type::kind::INT);
thread_local shared_ptr<cql3_type> cql3_type::smallint = make("smallint", short_type, cql3_type::kind::SMALLINT);
thread_local shared_ptr<cql3_type> cql3_type::text = make("text", utf8_type, cql3_type::kind::TEXT);
thread_local shared_ptr<cql3_type> cql3_type::timestamp = make("timestamp", timestamp_type, cql3_type::kind::TIMESTAMP);
thread_local shared_ptr<cql3_type> cql3_type::tinyint = make("tinyint", byte_type, cql3_type::kind::TINYINT);
thread_local shared_ptr<cql3_type> cql3_type::uuid = make("uuid", uuid_type, cql3_type::kind::UUID);
thread_local shared_ptr<cql3_type> cql3_type::varchar = make("varchar", utf8_type, cql3_type::kind::TEXT);
thread_local shared_ptr<cql3_type> cql3_type::timeuuid = make("timeuuid", timeuuid_type, cql3_type::kind::TIMEUUID);
thread_local shared_ptr<cql3_type> cql3_type::date = make("date", simple_date_type, cql3_type::kind::DATE);
thread_local shared_ptr<cql3_type> cql3_type::time = make("time", time_type, cql3_type::kind::TIME);
thread_local shared_ptr<cql3_type> cql3_type::inet = make("inet", inet_addr_type, cql3_type::kind::INET);
thread_local shared_ptr<cql3_type> cql3_type::varint = make("varint", varint_type, cql3_type::kind::VARINT);
thread_local shared_ptr<cql3_type> cql3_type::decimal = make("decimal", decimal_type, cql3_type::kind::DECIMAL);
thread_local shared_ptr<cql3_type> cql3_type::counter = make("counter", counter_type, cql3_type::kind::COUNTER);
thread_local shared_ptr<cql3_type> cql3_type::duration = make("duration", duration_type, cql3_type::kind::DURATION);
const std::vector<cql3_type>&
const std::vector<shared_ptr<cql3_type>>&
cql3_type::values() {
static thread_local std::vector<cql3_type> v = {
static thread_local std::vector<shared_ptr<cql3_type>> v = {
cql3_type::ascii,
cql3_type::bigint,
cql3_type::blob,
@@ -362,6 +368,7 @@ cql3_type::values() {
cql3_type::timestamp,
cql3_type::tinyint,
cql3_type::uuid,
cql3_type::varchar,
cql3_type::varint,
cql3_type::timeuuid,
cql3_type::date,
@@ -371,6 +378,16 @@ cql3_type::values() {
return v;
}
shared_ptr<cql3_type>
make_cql3_tuple_type(tuple_type t) {
auto name = sprint("tuple<%s>",
::join(", ",
t->all_types()
| boost::adaptors::transformed(std::mem_fn(&abstract_type::as_cql3_type))));
return ::make_shared<cql3_type>(std::move(name), std::move(t), false);
}
std::ostream&
operator<<(std::ostream& os, const cql3_type::raw& r) {
return os << r.to_string();
@@ -378,15 +395,18 @@ operator<<(std::ostream& os, const cql3_type::raw& r) {
namespace util {
sstring maybe_quote(const sstring& identifier) {
static const std::regex unquoted_identifier_re("[a-z][a-z0-9_]*");
if (std::regex_match(identifier.begin(), identifier.end(), unquoted_identifier_re)) {
return identifier;
sstring maybe_quote(const sstring& s) {
static const std::regex unquoted("\\w*");
static const std::regex double_quote("\"");
if (std::regex_match(s.begin(), s.end(), unquoted)) {
return s;
}
static const std::regex double_quote_re("\"");
std::string result = identifier;
std::regex_replace(result, double_quote_re, "\"\"");
return '"' + result + '"';
std::ostringstream ss;
ss << "\"";
std::regex_replace(std::ostreambuf_iterator<char>(ss), s.begin(), s.end(), double_quote, "\"\"");
ss << "\"";
return ss.str();
}
}

View File

@@ -54,14 +54,17 @@ namespace cql3 {
class ut_name;
class cql3_type final {
sstring _name;
data_type _type;
bool _native;
public:
cql3_type(data_type type) : _type(std::move(type)) {}
cql3_type(sstring name, data_type type, bool native = true)
: _name(std::move(name)), _type(std::move(type)), _native(native) {}
bool is_collection() const { return _type->is_collection(); }
bool is_counter() const { return _type->is_counter(); }
bool is_native() const { return _type->is_native(); }
bool is_native() const { return _native; }
data_type get_type() const { return _type; }
const sstring& to_string() const { return _type->cql3_type_name(); }
sstring to_string() const;
// For UserTypes, we need to know the current keyspace to resolve the
// actual type used, so Raw is a "not yet prepared" CQL3Type.
@@ -74,11 +77,11 @@ public:
virtual bool is_counter() const;
virtual bool is_duration() const;
virtual bool references_user_type(const sstring&) const;
virtual std::optional<sstring> keyspace() const;
virtual std::experimental::optional<sstring> keyspace() const;
virtual void freeze();
virtual cql3_type prepare_internal(const sstring& keyspace, lw_shared_ptr<user_types_metadata>) = 0;
virtual cql3_type prepare(database& db, const sstring& keyspace);
static shared_ptr<raw> from(cql3_type type);
virtual shared_ptr<cql3_type> prepare_internal(const sstring& keyspace, lw_shared_ptr<user_types_metadata>) = 0;
virtual shared_ptr<cql3_type> prepare(database& db, const sstring& keyspace);
static shared_ptr<raw> from(shared_ptr<cql3_type> type);
static shared_ptr<raw> user_type(ut_name name);
static shared_ptr<raw> map(shared_ptr<raw> t1, shared_ptr<raw> t2);
static shared_ptr<raw> list(shared_ptr<raw> t);
@@ -99,38 +102,74 @@ private:
}
public:
static thread_local cql3_type ascii;
static thread_local cql3_type bigint;
static thread_local cql3_type blob;
static thread_local cql3_type boolean;
static thread_local cql3_type double_;
static thread_local cql3_type empty;
static thread_local cql3_type float_;
static thread_local cql3_type int_;
static thread_local cql3_type smallint;
static thread_local cql3_type text;
static thread_local cql3_type timestamp;
static thread_local cql3_type tinyint;
static thread_local cql3_type uuid;
static thread_local cql3_type timeuuid;
static thread_local cql3_type date;
static thread_local cql3_type time;
static thread_local cql3_type inet;
static thread_local cql3_type varint;
static thread_local cql3_type decimal;
static thread_local cql3_type counter;
static thread_local cql3_type duration;
static const std::vector<cql3_type>& values();
enum class kind : int8_t {
ASCII, BIGINT, BLOB, BOOLEAN, COUNTER, DECIMAL, DOUBLE, EMPTY, FLOAT, INT, SMALLINT, TINYINT, INET, TEXT, TIMESTAMP, UUID, VARCHAR, VARINT, TIMEUUID, DATE, TIME, DURATION
};
using kind_enum = super_enum<kind,
kind::ASCII,
kind::BIGINT,
kind::BLOB,
kind::BOOLEAN,
kind::COUNTER,
kind::DECIMAL,
kind::DOUBLE,
kind::EMPTY,
kind::FLOAT,
kind::INET,
kind::INT,
kind::SMALLINT,
kind::TINYINT,
kind::TEXT,
kind::TIMESTAMP,
kind::UUID,
kind::VARCHAR,
kind::VARINT,
kind::TIMEUUID,
kind::DATE,
kind::TIME,
kind::DURATION>;
using kind_enum_set = enum_set<kind_enum>;
private:
std::experimental::optional<kind_enum_set::prepared> _kind;
static shared_ptr<cql3_type> make(sstring name, data_type type, kind kind_) {
return make_shared<cql3_type>(std::move(name), std::move(type), kind_);
}
public:
using kind = abstract_type::cql3_kind;
using kind_enum_set = abstract_type::cql3_kind_enum_set;
kind_enum_set::prepared get_kind() const { return _type->get_cql3_kind(); }
static thread_local shared_ptr<cql3_type> ascii;
static thread_local shared_ptr<cql3_type> bigint;
static thread_local shared_ptr<cql3_type> blob;
static thread_local shared_ptr<cql3_type> boolean;
static thread_local shared_ptr<cql3_type> double_;
static thread_local shared_ptr<cql3_type> empty;
static thread_local shared_ptr<cql3_type> float_;
static thread_local shared_ptr<cql3_type> int_;
static thread_local shared_ptr<cql3_type> smallint;
static thread_local shared_ptr<cql3_type> text;
static thread_local shared_ptr<cql3_type> timestamp;
static thread_local shared_ptr<cql3_type> tinyint;
static thread_local shared_ptr<cql3_type> uuid;
static thread_local shared_ptr<cql3_type> varchar;
static thread_local shared_ptr<cql3_type> timeuuid;
static thread_local shared_ptr<cql3_type> date;
static thread_local shared_ptr<cql3_type> time;
static thread_local shared_ptr<cql3_type> inet;
static thread_local shared_ptr<cql3_type> varint;
static thread_local shared_ptr<cql3_type> decimal;
static thread_local shared_ptr<cql3_type> counter;
static thread_local shared_ptr<cql3_type> duration;
static const std::vector<shared_ptr<cql3_type>>& values();
public:
cql3_type(sstring name, data_type type, kind kind_)
: _name(std::move(name)), _type(std::move(type)), _native(true), _kind(kind_enum_set::prepare(kind_)) {
}
kind_enum_set::prepared get_kind() const {
assert(_kind);
return *_kind;
}
};
inline bool operator==(const cql3_type& a, const cql3_type& b) {
return a.get_type() == b.get_type();
}
shared_ptr<cql3_type> make_cql3_tuple_type(tuple_type t);
#if 0
public static class Custom implements CQL3Type

View File

@@ -45,7 +45,6 @@
#include "service/query_state.hh"
#include "service/storage_proxy.hh"
#include "cql3/query_options.hh"
#include "timeout_config.hh"
namespace cql_transport {
@@ -63,15 +62,10 @@ class metadata;
shared_ptr<const metadata> make_empty_metadata();
class cql_statement {
timeout_config_selector _timeout_config_selector;
public:
explicit cql_statement(timeout_config_selector timeout_selector) : _timeout_config_selector(timeout_selector) {}
virtual ~cql_statement()
{ }
timeout_config_selector get_timeout_config_selector() const { return _timeout_config_selector; }
virtual uint32_t get_bound_terms() = 0;
/**
@@ -87,7 +81,7 @@ public:
*
* @param state the current client state
*/
virtual void validate(service::storage_proxy& proxy, const service::client_state& state) = 0;
virtual void validate(distributed<service::storage_proxy>& proxy, const service::client_state& state) = 0;
/**
* Execute the statement and return the resulting result or null if there is no result.
@@ -96,7 +90,15 @@ public:
* @param options options for this query (consistency, variables, pageSize, ...)
*/
virtual future<::shared_ptr<cql_transport::messages::result_message>>
execute(service::storage_proxy& proxy, service::query_state& state, const query_options& options) = 0;
execute(distributed<service::storage_proxy>& proxy, service::query_state& state, const query_options& options) = 0;
/**
* Variant of execute used for internal query against the system tables, and thus only query the local node = 0.
*
* @param state the current query state
*/
virtual future<::shared_ptr<cql_transport::messages::result_message>>
execute_internal(distributed<service::storage_proxy>& proxy, service::query_state& state, const query_options& options) = 0;
virtual bool uses_function(const sstring& ks_name, const sstring& function_name) const = 0;
@@ -109,7 +111,6 @@ public:
class cql_statement_no_metadata : public cql_statement {
public:
using cql_statement::cql_statement;
virtual shared_ptr<const metadata> get_result_metadata() const override {
return make_empty_metadata();
}

View File

@@ -41,9 +41,7 @@
#pragma once
#include "function.hh"
#include "types.hh"
#include "cql3/cql3_type.hh"
#include <vector>
#include <iosfwd>
#include <boost/functional/hash.hpp>
@@ -74,7 +72,7 @@ public:
return _arg_types;
}
virtual const data_type& return_type() const {
virtual data_type return_type() const {
return _return_type;
}
@@ -93,7 +91,7 @@ public:
}
virtual sstring column_name(const std::vector<sstring>& column_names) override {
return format("{}({})", _name, join(", ", column_names));
return sprint("%s(%s)", _name, join(", ", column_names));
}
virtual void print(std::ostream& os) const override;
@@ -107,9 +105,9 @@ abstract_function::print(std::ostream& os) const {
if (i > 0) {
os << ", ";
}
os << _arg_types[i]->as_cql3_type().to_string();
os << _arg_types[i]->name(); // FIXME: asCQL3Type()
}
os << ") -> " << _return_type->as_cql3_type().to_string();
os << ") -> " << _return_type->name(); // FIXME: asCQL3Type()
}
}

Some files were not shown because too many files have changed in this diff Show More