This should significantly reduce the MemoryTracking drift, test shows
that there is 0 drift after query storm (100 queries, via http/tcp/tcp
in one session).
TL;DR;
To track memory, clickhouse creates memory tracker object for each
thread **explicitly**, but until it is not created the memory
allocations are not under account.
There should not be lot of allocations w/o memory tracker, since most of
the time it is created early enough, but even this maybe enough to
trigger some problems.
Plus sometimes it is not possible to create it, for example some 3d
party library does not allow to do this explicitly:
- for example before #15740 allocations from librdkafka threads,
- or even worse, poco threads, they don't have any routines to do this.
This won't be a problem for `MemoryTracking` metric if the deallocation
will be done from the same thread w/o memory tracker (or vise versa),
but this is not always true.
NOTE, that this will slow down per-thread allocations w/o memory
tracker, since before this patch there were no memory tracking for them
while now they will be accounted in total_memory_tracker, and for
total_memory_tracker max_untracked_memory is always reached.
But this should not be significant.
* master: (279 commits)
Convert to python3 (#15007)
update en and ru docs: add 128/256 types (#15515)
Drop unused code for numeric_limits<int128> in MergeTreeDataSelectExecutor (#15519)
Fix comment
More defaults on defaults
Recursive defaults
Fix bash
Update ActionsVisitor.cpp
Don't add memcpy for sanitizers builds
Fix gRPC build scripts.
Neutrialize thinlto's memcpy libcall gen.
Revert "Add fno-builtin-memcpy"
Throw an error when a single parameter is passed to ReplicatedMergeTree instead of ignoring it
Update SECURITY.md
Update tsan_suppressions.txt
Update ActionsVisitor.cpp
remove unrelated changes
Update SECURITY.md
fixes
Update ActionsVisitor.cpp
...
* master: (224 commits)
Update in.md
Add a test for embedded configs
Allow to run without /proc/self/maps
Update adopters.md
More convenient
Enable embedded configs for AArch64
More results
More handy
More handy
Added a comment
Adjustments
Adjustments
Adjustments
Added new results
Step 1: make adding hardware benchmark results more convenient
Revert "Avoid deadlocks in Log/TinyLog"
Fix MSan report in QueryLog
add some disabled tests from arcadia to skip_list.json
Update skip_list.json
Bump CI. [2]
...
# Conflicts:
# docker/test/testflows/runner/Dockerfile
* master: (375 commits)
Update type-conversion-functions.md
Update maxmap.md
Update maxmap.md
Update maxmap.md
Update single_fixed_string_groupby.xml
Alter remove column properties and TTLs (#14742)
better fixed string group by support
Fix incorrect key condition of fixed strings.
constant output order
more tests for #14646
Maybe fix MSan report in base64
Proper exception message for wrong number of arguments of CAST
Added a test
Fix buffer overflow in "bar" function
Update convertMySQLDataType.cpp
Fix clang-tidy
Remove obsolete code from performance test
Slightly better code
Even more
Even more
...
# Conflicts:
# src/Interpreters/Context.cpp
Add inter-server cluster secret, it is used for Distributed queries
inside cluster, you can configure in the configuration file:
<remote_servers>
<logs>
<shard>
<secret>foobar</secret> <!-- empty -- works as before -->
...
</shard>
</logs>
</remote_servers>
And this will allow clickhouse to make sure that the query was not
faked, and was issued from the node that knows the secret. And since
trust appeared it can use initial_user for query execution, this will
apply correct *_for_user (since with inter-server secret enabled, the
query will be executed from the same user on the shards as on initator,
unlike "default" user w/o it).
v2: Change user to the initial_user for Distributed queries if secret match
v3: Add Protocol::Cluster package
v4: Drop Protocol::Cluster and use plain Protocol::Hello + user marker
v5: Do not use user from Hello for cluster-secure (superfluous)
