| Age | Commit message (Collapse) | Author |
|---|
|
The single byte lookups always rely on `memchr` and
never really use the good and bad shifts arrays.
|
|
Optimize binary match from 10% up to 70x
|
|
* rickard/full-cache-nif-env/OTP-15223/ERL-695:
Fix caching of NIF environment when executing dirty
# Conflicts:
# erts/emulator/beam/erl_nif.c
|
|
* dotsimon/ref_ordering_bug/OTP-15225:
Fixed #Ref ordering bug
Test #Ref ordering in lists and ets
|
|
* maint:
Fix caching of NIF environment when executing dirty
|
|
* rickard/full-cache-nif-env/OTP-15223/ERL-695:
Fix caching of NIF environment when executing dirty
|
|
|
|
|
|
* maint:
Fixed #Ref ordering bug
Test #Ref ordering in lists and ets
|
|
|
|
The idea is to use memchr on the first lookup for
binary:match/2 and also after every match on binary:matches/2.
We only use memchr in case of matches because benchmarks
showed that using memchr even when we had false positives
could negatively affect performance.
This speeds up binary matching and binary splitting by 4x
in some cases and by 70x in other scenarios (when the last
character in the needle does not occur in the subject).
The reason to use memchr is that it is highly specialized
in most modern operating systems, often defaulting to
SIMD operations.
The implementation uses the reduction count to figure out
how many bytes should be read with memchr. We could increase
those numbers but they do not seem to make a large difference.
|
|
Do not allocate a new map when the value is the same
|
|
|
|
A lot of erts internal messages used behind APIs to create
non-blocking calls, e.g. port_command, would cause the seq_trace
token to be cleared from the caller when it should not.
This commit fixes that and adds asserts that makes sure
that all messages sent have to correct token set.
Fixes: ERL-602
|
|
|
|
RaimoNiskanen/raimo/can_not-should-mostly-be-cannot
OTP-14282
'can not' should mostly be 'cannot'
|
|
|
|
I did not find any legitimate use of "can not", however skipped
changing e.g RFCs archived in the source tree.
|
|
After this whitespace modification there should be no "can not"s
separated by a newline in the entire OTP repository, so to find
them all a simple git grep will do just fine.
|
|
|
|
|
|
This patch optimizes map operations to not allocate new maps
when the key is being replaced by the exact same value in memory.
Imagine this very common idiom:
Map#{key := compute_new_value(Value, Condition)}
where:
compute_new_x(X, true) -> X + 1;
compute_new_x(X, false) -> X;
In many cases, we are not changing the value in `Key`, however
the code prior to this patch would still allocate a new array
for the map values. This optimization changes this.
The cost of optimization is minimum, as in the worst case scenario
it only adds a pointer comparison and boolean check. The major benefit
is reducing the GC pressure by avoiding allocating data.
Next we list the operations we have changed alongside the benchmark
results. The benchmarks basically create a map and perform the same
operations, roughly 20000 times, once replacing the key with the same
value, and another with a different value.
* Map#{Key := Value}
For a map with 4 keys, replacing the fourth key 20000 times went from
718us to 539us.
For a map with 8 keys, replacing the fourth key 20000 times went from
976us to 555us.
* maps:update/3
For a map with 4 keys, replacing the fourth key 20000 times went from
673us to 575us.
For a map with 8 keys, replacing the fourth key 20000 times went from
827us to 585us.
* maps:put/3
For a map with 4 keys, replacing the fourth key 20000 times went from
763us to 553us.
For a map with 8 keys, replacing the fourth key 20000 times went from
788us to 561us.
Note that we have ported some optimizations found in maps:update/3
to maps:put/3 while creating this patch.
|
|
to deselect read and/or writes without stop callback.
|
|
maps:new/0 is no longer a BIF
|
|
|
|
* sverker/erl_interface/valgrind/OTP-15171:
erl_interface: Fix bug in ei_*receive_msg* functions
erl_interface: Seal test case memory leaks
erl_interface: Initialize erl_errno to zero
erts: Remove use of VALGRIND_PRINTF_XML
erl_interface: Add valgrind ability for test port programs
erts: Fix benign bug in cerl for valgrind
erts: Fix buggy calls to erts_sys_explicit_8bit_getenv
|
|
which only existed in a patched version of valgrind (by pan)
no longer used.
Instead we use standard VALGRIND_PRINTF which will end up like this
if valgrind log format is XML and valgrind version >= 3.9:
<clientmsg>
<tid>7</tid>
<threadname>3_scheduler</threadname>
<text>Test case #20 ei_encode_SUITE:test_ei_encode_long/1
</text>
</clientmsg>
Note the extra trailing whitespace that may occure before </text>.
|
|
* john/erts/fix-literal-map-elements/OTP-15184:
Fix a rare crash when matching on literal maps
|
|
Optimise creation of anonymous functions
|
|
Implementing it in Erlang allows taking advantage of the literal pool
optimisation, this means the function implemented in Erlang does no
allocations, while the BIF had to allocate new map each time it was
called. Benchmarks show the function is also slightly faster now.
|
|
This introduces a similar optimisation for normal funs
to what was introduced for external funs in #1725.
It is possible to allocate the fun as a literal, if it does not capture
the environment (i.e. it does not close over any variables).
Unfortunately it's not possible to do this in the compiler due to
problems with representation of such functions in the `.beam` files.
Fortunately, we can do this in the loader.
Simple evaluation shows that functions that don't capture the
enviornment consistute over 60% of all funs in the source code of
Erlang/OTP itself.
The only downside is that we lose a meningful value in the `pid` field
of the fun. The goal of this field, beyond debugging, was to be
able to identify the original node of a function. To be able to still do
this, the functions that are created in the loader are assigned the init
pid as the creator.
To solve issues with staryp, initially set the `erts_init_process_id`
to `ERTS_INVALID_PID` and skip the described optimisation if the value
is still uninitialised.
|
|
|
|
* sverker/crash-dump-crash-literals/OTP-15181:
erts: Fix bug in crash dump generation
|
|
* maint:
Updated OTP version
Update release notes
Update version numbers
Fix trace_info/2
Provide build support for standalone corba repo
Fix release notes for OTP-21.0.2
Move to a dirty scheduler even when we have pending system tasks
|
|
* maint-21:
Updated OTP version
Update release notes
Update version numbers
Fix trace_info/2
Provide build support for standalone corba repo
Fix release notes for OTP-21.0.2
Move to a dirty scheduler even when we have pending system tasks
|
|
When matching on a literal map, the map is placed into the general
scratch register first. This is fine in isolation, but when the
key to be matched was in a Y register it would also be placed in
the scratch register, overwriting the map and crashing the
emulator.
|
|
* john/erts/fix-dirty-reschedule-bug/OTP-15154:
Move to a dirty scheduler even when we have pending system tasks
|
|
|
|
* john/erts/adjust-fix-alloc-sizes:
Adjust fix_alloc sizes to guarantee they fit a dd block
|
|
Symptom: emulator core dumps during crash dump generation.
Problem:
erts_dump_lit_areas did not grow correctly
to always be equal or larger than number of loaded modules.
The comment about twice the size to include both curr and old
did not seem right. The beam_ranges structure contains *all* loaded
module instances until they are removed when purged.
|
|
* sverker/erts/cpool-simplify:
erts: Simplify calc of allctr->cpool.abandon_limit
erts: Simplify cpool_fetch
|
|
Two of them only affect valgrind builds
and the one for ERL_CRASH_DUMP_NICE seems benign.
Return value changed in c2d70945dce9cb09d5d7120d6e9ddf7faac8d230
old -> new
-1 -> 0 not found
0 -> 1 found ok
1 -> -1 found but too big
|
|
This failed on 32-bit builds, and wasn't noticed because 32-bit
debug builds didn't run during the test period.
|
|
* maint:
Call test_lib:recompile/1 from init_per_suite/1
beam_debug: Fix printing of floating point registers
|
|
|
|
Remove check_limit_count
and just recalculate when needed,
that is when carriers are added/removed.
|
|
and avoid faulty bumps of 'entrance_removed' stat.
|
|
jhogberg/john/erts/cross-type-carrier-migration/OTP-15063
Allow carrier migration between different allocator types
|
|
* john/erts/merge-OTP-15067:
Don't enqueue system tasks if target process is in fail_state
Fix erroneous schedule of freed/exiting processes
Fix deadlock in run queue evacuation
Fix memory leak of processes that died in the run queue
|
|
|
