When the server is shutting down a flag _stopping is set and listeners
are aborted using abort_accept(), which causes accept() calls to return
failed futures. However, accept handler just checks that the flag
_stopping is set and returns which causes a failed future to be
destroyed and a warning is printed.
Signed-off-by: Paweł Dziepak <pdziepak@scylladb.com>
The underlying data source for cache should not be the same memtable
which is later used to update the cache from. This fixes the following
assertion failure:
row_cache_test_g: utils/logalloc.hh:289: decltype(auto) logalloc::allocating_section::operator()(logalloc::region&, Func&&) [with Func = memtable::make_reader(schema_ptr, const partition_range&)::<lambda()>]: Assertion `r.reclaiming_enabled()' failed.
The problem is that when memtable is merged into cache their regions
are also merged, so locking cache's region locks the memtable region
as well.
Currently sourcing for the second time causes an exception from
pretty printer registration:
Traceback (most recent call last):
File "./scylla-gdb.py", line 41, in <module>
gdb.printing.register_pretty_printer(gdb.current_objfile(), build_pretty_printer())
File "/usr/share/gdb/python/gdb/printing.py", line 152, in register_pretty_printer
printer.name)
RuntimeError: pretty-printer already registered: scylla
Fixes the case where background activity needed to complete CL=ONE writes
is queued up in the storage proxy, and the client adds new work faster
than it can be cleared.
The last two loops were incorrectly inside the first one. That's a
bug because a new sstable may be emplaced more than once in the
sstable list, which can cause several problems. mark_for_deletion
may also be called more than once for compacted sstables, however,
it is idempotent.
Found this issue while auditing the code.
Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
"* seastar 294ea30...b44d729 (5):
> Merge "Properly distribute IO queues" from Glauber
> reactor: allow more poll time in virtualized environments
> reactor: fix idle-poll limit
> reactor: use a vector of unique_ptr for the IO queues
> io queues: make the queues really part of the reactor"
With consistency level less then ALL mutation processing can move to
background (meaning client was answered, but there is still work to
do on behalf of the request). If background request rate completion
is lower than incoming request rate background request will accumulate
and eventually will exhaust all memory resources. This patch's aim is
to prevent this situation by monitoring how much memory all current
background request take and when some threshold is passed stop moving
request to background (by not replying to a client until either memory
consumptions moves below the threshold or request is fully completed).
There are two main point where each background mutation consumes memory:
holding frozen mutation until operation is complete in order to hint it
if it does not) and on rpc queue to each replica where it sits until it's
sent out on the wire. The patch accounts for both of those separately
and limits the former to be 10% of total memory and the later to be 6M.
Why 6M? The best answer I can give is why not :) But on a more serious
note the number should be small enough so that all the data can be
sent out in a reasonable amount of time and one shard is not capable to
achieve even close to a full bandwidth, so empirical evidence shows 6M
to be a good number.
I am sure it's a compiler issue but I am not ready to give up and
upgrade just yet:
sstables/compaction.cc:307:55: error: converting to ‘std::unordered_map<int, long int>’ from initializer list would use explicit constructor ‘std::unordered_map<_Key, _Tp, _Hash, _Pred, _Alloc>::unordered_map(std::unordered_map<_Key, _Tp, _Hash, _Pred, _Alloc>::size_type, const hasher&, const key_equal&, const allocator_type&) [with _Key = int; _Tp = long int; _Hash = std::hash<int>; _Pred = std::equal_to<int>; _Alloc = std::allocator<std::pair<const int, long int> >; std::unordered_map<_Key, _Tp, _Hash, _Pred, _Alloc>::size_type = long unsigned int; std::unordered_map<_Key, _Tp, _Hash, _Pred, _Alloc>::hasher = std::hash<int>; std::unordered_map<_Key, _Tp, _Hash, _Pred, _Alloc>::key_equal = std::equal_to<int>; std::unordered_map<_Key, _Tp, _Hash, _Pred, _Alloc>::allocator_type = std::allocator<std::pair<const int, long int> >]’
stats->start_size, stats->end_size, {});
Test was failing because _qp (distributed<cql3::query_processor>) was stopped
before _db (distributed<database>).
Compaction manager is member of database, and when database is stopped,
compaction manager is also stopped. After a2fb0ec9a, compaction updates the
system table compaction history, and that requires a working query context.
We cannot simply move _qp->stop() to after _db->stop() because the former
relies on migration_manager and storage_proxy. So the most obvious fix is to
clean the global variable that stores query context after _qp was stopped.
Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
The previous patch added message_service read()/write() support for all
types which know how to serialize themselves through our "old" serialization
API (serialize()/deserialize()/serialized_size()).
So we no longer need the almost 200 lines of repetitive code in
messaging_service.{cc,hh} which defined these read/write templates
separately for a dozen different types using their *serialize() methods.
We also no longer need the helper functions read_gms()/write_gms(), which
are basically the same code as that in the template functions added in the
previous patch.
Compilation is not significantly slowed down by this patch, because it
merely replaces a dozen templates by one template that covers them all -
it does not add new template complexity, and these templates are anyway
instantiated only in messaging_service.cc (other code only calls specific
functions defined in messaging_service.cc, and does not use these templates).
Signed-off-by: Nadav Har'El <nyh@scylladb.com>
Currently, messaging_service only supports sending types for which a read/
write function has been explicitly implemented in messageing_service.hh/cc.
Some types already have serialization/deserialization methods inside them,
and those could have been used for the serialization without having to write
new functions for each of these types. Many of these types were already
supported explicitly in messaging_service.{cc,hh}, but some were forgot -
for example, dht::token.
So this patch adds a default implemention of messaging_service write()/read()
which will work for any type which has these serialization methods.
Signed-off-by: Nadav Har'El <nyh@scylladb.com>
* seastar 5b9e3da...294ea30 (9):
> Merge "IO queues" from Glauber
> reactor: increment check_direct_io_support to also deal with files
> Merge "SSL/TLS initial certificate validation" from Calle
> tutorial.md: remove inaccurate statements about x86
> build: verify that the installed compiler is up to date
> build: complain if fossil version of gnutls is installed
> build: fix debian naming of gnutls-devel package
> build: add configure-time check for gnutls-devel
> tutorial.md: introduction to asynchrnous programming
send_to_live_endpoints() is never waited upon, it does its job in the
background. This patch formalize that by changing return value to void
and also refactoring code so that frozen_mutation shared pointer is not
held more that it should: currently it is held until send_mutation()
completes, but since send_mutation() does not use frozen_mutation
asynchronously this is not necessary.
Replace db_clock::now_in_usec() and db_clock::now() * 1000 accesses
where the intent is to create a new auto-generate cell timestamp with
a call to new_timestamp(). Now the knowledge of how to create timestamps
is in a single place.
"get_compactions returns progress information for each compaction
running in the system. It can be accessed using swagger UI.
'nodetool compactionstats' is not working yet because of some
pending work in the nodetool side."
Apparently, link hook copy constructor is a no-op and move contructor
doesn't exist so the code is correct, but that explicit move makes code
needlessly confusing.
Signed-off-by: Paweł Dziepak <pdziepak@scylladb.com>
