| Commit message (Collapse) | Author | Age | Files | Lines |
|---|
| | |
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The Erlang runtime gives many of its threads descriptive names. When
those threads are part of a logical group, a unique ID is added to the
name for disambiguation. After construction, many thread names in
Erlang have a string length greater than 16 characters. To fit within
operating system limits, Erlang then truncates them from right to
left. To minimize confusion after truncation, the unique ID is always
placed at the left of a thread name so its information is not likely
to be lost.
The convention used by Erlang presents challenges to the use of thread
names as keys when reporting on thread activity at the operating
system level. The more common convention, used by other runtimes, is
to have the description followed by a unique ID. When followed,
sorting threads by name places like workers next to each other and the
unique ID can be dropped to create a grouping key. Placing the unique
ID first, as Erlang does, means that a different strategy needs to be
used for sorting the threads of an Erlang process. Furthermore, the
truncation necessitates a complicated strategy for analyzing the
description to identify a possible common substring to be used as a
grouping key.
This change switches the Erlang runtime to use the more common
convention in order to make reporting on the thread usage in an Erlang
process easier for tooling. To do so, it shortens the content of the
initial printf(3) format strings to ensure their output is always 16
or fewer characters so the name is never truncated. It also moves the
unique ID in the format string to the right of the description, so the
names of worker threads appear next to each other after sorting
alphabetically from left to right.
To prevent the accidental creation of long thread names in the future,
the silent truncation has been eliminated from the lowest-layer of
thread functionality. It now returns an EINVAL when given a long name
which will be caught when the runtime is started. This would break
the NIF and driver libraries so the silent truncation has moved up to
a higher layer in order to preserve compatibility. New unit tests have
been added to test setting and getting thread names.
|
| | |
|
| |\
| |
| |
| |
| | |
* maint:
Update copyright year
|
| | | |
|
| | | |
|
| |\ \
| |/
| |
| |
| | |
* maint:
Limit timeout value in calls to select()
|
| | |\
| | |
| | |
| | |
| | | |
* rickard/select-timeout-fix/GH-5339/OTP-17735:
Limit timeout value in calls to select()
|
| | | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | | |
We previously did not limit the timeout value when calling select()
which could cause select() to fail when passed a huge timeout value
causing a runtime system crash.
We currently only use select() on Darwin which accepts a timeout value
of up to 100 million seconds. However, according to posix, select()
implementations are only required to provide 31 days as max timeout
value. We therefore limit the timeout value to 31 days.
|
| |/ /
| |
| |
| | |
Replace obsolete macros and fix warnings
|
| |\ \
| | |
| | |
| | |
| | | |
* rickard/tse/OTP-16766/ERL-1304:
Fix multiple usage of same thread specific event at the same time
|
| | | | |
|
| | | | |
|
| | |/
|/|
| |
| |
| |
| | |
This uses a non-pthread API. Also double hard-coded assumptions;
on vanilla 16-char pthread systems, the set thread name function
will truncate for us.
|
| | | |
|
| |/
|
|
|
|
|
|
|
|
| |
Ask compiler to generate unique label name. Using named label has implications
on optimizer, that may lead to the compilation errors as the following:
pthread/ethread.c: Assembler messages:
pthread/ethread.c:213: Error: symbol `no_cpuid' is already defined
pthread/ethread.c:213: Error: symbol `no_cpuid' is already defined
pthread/ethread.c:213: Error: symbol `no_cpuid' is already defined
|
| | |
|
| | |
|
| |
|
|
|
|
|
| |
Improve accuracy of timeouts using a premature timeout then
return to sleep with a shorter timeout just before requested
timeout. This approach is only used on certain platforms where
we know it improves the accuracy of the timeouts, e.g. MacOS X.
|
| |\
| |
| |
| |
| | |
* henrik/update-copyrightyear:
update copyright-year
|
| | | |
|
| |/ |
|
| |
|
|
|
|
|
|
|
|
|
|
| |
Lots of pthread platforms unnecessarily falled back on the pipe/select
solution. This since we tried to use the same monotonic clock source
for pthread_cond_timedwait() as used by OS monotonic time. This has
been fixed on most platforms by using another clock source.
Darwin can however not use pthread_cond_timedwait() with monotonic
clock source and has to use the pipe/select solution. On darwin we
now use select with _DARWIN_UNLIMITED_SELECT in order to be able to
handle a large amount of file descriptors.
|
| | |
|
| |\
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
* rickard/time_api/OTP-11997: (22 commits)
Update primary bootstrap
inets: Suppress deprecated warning on erlang:now/0
inets: Cleanup of multiple copies of functions Add inets_lib with common functions used by multiple modules
inets: Update comments
Suppress deprecated warning on erlang:now/0
Use new time API and be back-compatible in inets Remove unused functions and removed redundant test
asn1 test SUITE: Eliminate use of now/0
Disable deprecated warning on erlang:now/0 in diameter_lib
Use new time API and be back-compatible in ssh
Replace all calls to now/0 in CT with new time API functions
test_server: Replace usage of erlang:now() with usage of new API
Replace usage of erlang:now() with usage of new API
Replace usage of erlang:now() with usage of new API
Replace usage of erlang:now() with usage of new API
Replace usage of erlang:now() with usage of new API
otp_SUITE: Warn for calls to erlang:now/0
Replace usage of erlang:now() with usage of new API
Multiple timer wheels
Erlang based BIF timer implementation for scalability
Implement ethread events with timeout
...
Conflicts:
bootstrap/bin/start.boot
bootstrap/bin/start_clean.boot
bootstrap/lib/compiler/ebin/beam_asm.beam
bootstrap/lib/compiler/ebin/compile.beam
bootstrap/lib/kernel/ebin/auth.beam
bootstrap/lib/kernel/ebin/dist_util.beam
bootstrap/lib/kernel/ebin/global.beam
bootstrap/lib/kernel/ebin/hipe_unified_loader.beam
bootstrap/lib/kernel/ebin/inet_db.beam
bootstrap/lib/kernel/ebin/inet_dns.beam
bootstrap/lib/kernel/ebin/inet_res.beam
bootstrap/lib/kernel/ebin/os.beam
bootstrap/lib/kernel/ebin/pg2.beam
bootstrap/lib/stdlib/ebin/dets.beam
bootstrap/lib/stdlib/ebin/dets_utils.beam
bootstrap/lib/stdlib/ebin/erl_tar.beam
bootstrap/lib/stdlib/ebin/escript.beam
bootstrap/lib/stdlib/ebin/file_sorter.beam
bootstrap/lib/stdlib/ebin/otp_internal.beam
bootstrap/lib/stdlib/ebin/qlc.beam
bootstrap/lib/stdlib/ebin/random.beam
bootstrap/lib/stdlib/ebin/supervisor.beam
bootstrap/lib/stdlib/ebin/timer.beam
erts/aclocal.m4
erts/emulator/beam/bif.c
erts/emulator/beam/erl_bif_info.c
erts/emulator/beam/erl_db_hash.c
erts/emulator/beam/erl_init.c
erts/emulator/beam/erl_process.h
erts/emulator/beam/erl_thr_progress.c
erts/emulator/beam/utils.c
erts/emulator/sys/unix/sys.c
erts/preloaded/ebin/erlang.beam
erts/preloaded/ebin/erts_internal.beam
erts/preloaded/ebin/init.beam
erts/preloaded/src/erts_internal.erl
lib/common_test/test/ct_hooks_SUITE_data/cth/tests/empty_cth.erl
lib/diameter/src/base/diameter_lib.erl
lib/kernel/src/os.erl
lib/ssh/test/ssh_basic_SUITE.erl
system/doc/efficiency_guide/advanced.xml
|
| | | |
|
| | |
| |
| |
| |
| |
| |
| | |
These functions allow any thread to suspend any other thread
immediately and then resume all threads. This is useful when
doing a crash dump in order to get a more accurate picture
of what state the system is in.
|
| |/ |
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Enable a cross compile Erlang/OTP platform to Android or Raspberry PI
using Android NDK. Port emulator and core application to support target
HW platform. Exclude any add-on services required for OTP platform deployment
into target hardware due to device fragmentation and jail-break requirements.
* fix erts/emulator/beam/sys.h
Disable redefinition of __noreturn macro
* port erts/emulator/sys/unix/erl_child_setup.c
Use techniques proposed by https://code.google.com/p/erlang4android to
access system properties
* fix erts/emulator/sys/unix/erl_unix_sys_ddll.c
The static linking of emulator cannot find dlerror(), dlopen() symbols
* port erts/emulator/sys/unix/sys.c
make path to shell configurable at build time
* port erts/etc/common/Makefile.in
disable librt for *-linux-androideabi
* port erts/lib_src/pthread/ethread.c
Use techniques proposed by https://code.google.com/p/erlang4android to
disable emulator crash if kernel threads are on. Replace unreliable
pthread_sigmask() by sigprocmask()
* port lib/erl_interface/src/connect/ei_connect.c
Disable call to undefined gethostid()
* port lib/erl_interface/src/connect/ei_resolve.c
Use gethostbyname_r() on Android platform
|
| |
|
|
|
| |
This simplified debugging on OSE and also limits the number of ppdata
keys that are created when beam is restarted.
|
| |
|
|
|
|
|
| |
A feature test for the lwsync instruction performed on PowerPC
hardware at runtime system startup got into an eternal loop if
the instruction was not supported. This bug was introduced in
erts-5.9/OTP-R15B.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The ethread atomics API now also provide double word size atomics.
Double word size atomics are implemented using native atomic
instructions on x86 (when the cmpxchg8b instruction is available)
and on x86_64 (when the cmpxchg16b instruction is available). On
other hardware where 32-bit atomics or word size atomics are
available, an optimized fallback is used; otherwise, a spinlock,
or a mutex based fallback is used.
The ethread library now performs runtime tests for presence of
hardware features, such as for example SSE2 instructions, instead
of requiring this to be determined at compile time.
There are now functions implementing each atomic operation with the
following implied memory barrier semantics: none, read, write,
acquire, release, and full. Some of the operation-barrier
combinations aren't especially useful. But instead of filtering
useful ones out, and potentially miss a useful one, we implement
them all.
A much smaller set of functionality for native atomics are required
to be implemented than before. More or less only cmpxchg and a
membar macro are required to be implemented for each atomic size.
Other functions will automatically be constructed from these. It is,
of course, often wise to implement more that this if possible from a
performance perspective.
|
| | |
|
| | |
|
| | |
|
| |
|
|
|
|
| |
The atomic memory operations interface used the 'long' type and assumed that
it was of the same size as 'void *'. This is true on most platforms, however,
not on Windows 64.
|
|
|
Large parts of the ethread library have been rewritten. The
ethread library is an Erlang runtime system internal, portable
thread library used by the runtime system itself.
Most notable improvement is a reader optimized rwlock
implementation which dramatically improve the performance of
read-lock/read-unlock operations on multi processor systems by
avoiding ping-ponging of the rwlock cache lines. The reader
optimized rwlock implementation is used by miscellaneous
rwlocks in the runtime system that are known to be read-locked
frequently, and can be enabled on ETS tables by passing the
`{read_concurrency, true}' option upon table creation. See the
documentation of `ets:new/2' for more information.
The ethread library can now also use the libatomic_ops library
for atomic memory accesses. This makes it possible for the
Erlang runtime system to utilize optimized atomic operations
on more platforms than before. Use the
`--with-libatomic_ops=PATH' configure command line argument
when specifying where the libatomic_ops installation is
located. The libatomic_ops library can be downloaded from:
http://www.hpl.hp.com/research/linux/atomic_ops/
The changed API of the ethread library has also caused
modifications in the Erlang runtime system. Preparations for
the to come "delayed deallocation" feature has also been done
since it depends on the ethread library.
Note: When building for x86, the ethread library will now use
instructions that first appeared on the pentium 4 processor. If
you want the runtime system to be compatible with older
processors (back to 486) you need to pass the
`--enable-ethread-pre-pentium4-compatibility' configure command
line argument when configuring the system.
|
