Age | Commit message (Collapse) | Author | |
---|---|---|---|
2012-12-14 | erts: Do not cache segments that are misaligned | Björn-Egil Dahlberg | |
* SBC may realloc carriers to misaligned addresses which is perfectly fine. However, those segments may not be cached because MBC allocations might find them and MBC's *needs* correct alignment. | |||
2012-12-14 | erts: Add mseg cache for large sbc segments | Björn-Egil Dahlberg | |
* Not a power of two (unpowered) segements | |||
2012-12-14 | erts: Reintroduce mseg options amcbf and rmcbf | Björn-Egil Dahlberg | |
Used with new sbc cache | |||
2012-12-14 | erts: Optimize erl_alloc_util.c by substitute MBC_BLK_SZ | Sverker Eriksson | |
with either MBC_ABLK_SZ or MBC_FBLK_SZ in all cases when we already know what kind of block it is. | |||
2012-12-14 | erts: Fix bug when allocating size near sbc_threshold | Sverker Eriksson | |
A block larger than sbc_threshold can be allocated in MBC if the subsequent "residue block" is smaller than min_block_size. Solved by lowering sbc_threshold to ("hard limit" - min_block_size). | |||
2012-12-14 | erts: Make gc sizes fit into MB Carrier blocks | Björn-Egil Dahlberg | |
* Account for block header size in gc-sizes * Also slow down growth to 20% instead of 25% when size threshold is reached | |||
2012-12-14 | erts: Force sbmbc to be disabled in a crude way | Sverker Eriksson | |
2012-12-14 | erts: Fix new header scheme for win64 | Sverker Eriksson | |
2012-12-14 | erts: Fix mseg cache. Malplaced NULL pointer | Björn-Egil Dahlberg | |
2012-12-14 | erts: Remove unused mseg options amcbf and rmcbf | Björn-Egil Dahlberg | |
2012-12-14 | erts: Use aligned bits as constant in mseg_alloc | Björn-Egil Dahlberg | |
HAVE_SUPER_ALIGNED_MB_CARRIERS is always true with mmap and thus aligned bits is a constant and so is "page" size for mmap. Conflicts: erts/emulator/sys/common/erl_mseg.h | |||
2012-11-21 | erts: Don't let zero be considered a power of two | Björn-Egil Dahlberg | |
2012-11-21 | erts: Use MSEG_ALIGN_BITS and MSEG_ALIGNED_SIZE | Björn-Egil Dahlberg | |
* Don't redfine ALIGN_BITS or ALIGNED_SIZE, the global defined MSEG_* constants are just as good. | |||
2012-11-21 | erts: Make carrier header sizes compile time constants | Sverker Eriksson | |
No allocator strategy is using customized carrier headers anyway. | |||
2012-11-19 | erts: Cleanup minor things in alloc_util | Sverker Eriksson | |
2012-11-16 | erts: Fix compile warnings in alloc_util | Sverker Eriksson | |
2012-11-15 | erts: Enable new header scheme without super alignment on 64-bit | Sverker Eriksson | |
2012-11-15 | erts: Fix alloc_SUITE:coalesce for new header scheme | Sverker Eriksson | |
2012-11-15 | erts: Ensure MBC limits due to super alignment | Sverker Eriksson | |
2012-11-15 | erts: Add carrier pointer to header of free block | Sverker Eriksson | |
2012-11-15 | erts: Refactor renaming a couple of macros in alloc_util | Sverker Eriksson | |
To get a consistent naming scheme where FBLK = Free block ABLK = Allocated block | |||
2012-11-15 | erts: Refactor removing dummy footer in carrier header | Sverker Eriksson | |
2012-11-15 | erts: Save one word per block for thread preferred allocators | Sverker Eriksson | |
by making use of the new block header scheme to find the carrier header and thereby the allocator. | |||
2012-11-15 | erts: Refactor erl_alloc_util.c | Sverker Eriksson | |
Make use of type FreeBlkFtr_t Rename GET_MB_CARRIER into BLK2MBC (like BLK2SBC) Remove some unused macros | |||
2012-11-15 | erts: Change single carrier block header flags | Sverker Eriksson | |
to allow realloc to determine block size (in MBC or SBC) without having to read the footer of the previous block that might be written to by concurrent thread. | |||
2012-11-15 | erts: Make alloc_SUITE:bucket_mask handle larger carriers | Sverker Eriksson | |
2012-11-15 | erts: Use new mseg flag argument for carrier sizing | Sverker Eriksson | |
2012-11-15 | erts: Move carrier alignment define to erl_msg.h | Sverker Eriksson | |
2012-11-15 | erts: Add carrier offset to internal allocation headers | Sverker Eriksson | |
2012-11-13 | erts: Fix compiler warnings for halfword vm | Sverker Eriksson | |
2012-11-13 | erts: New mseg allocator cache | Björn-Egil Dahlberg | |
* utilize the power of two | |||
2012-11-13 | erts: Teach mseg alloc the value of halfword beam | Björn-Egil Dahlberg | |
2012-11-13 | erts: Let mseg allocate larger alignments | Björn-Egil Dahlberg | |
2012-10-31 | erts: Remove faked MSEG_ALLOC | Björn-Egil Dahlberg | |
* Not used except in valgrind but there mseg is disabled completely via Meamin. | |||
2012-10-31 | Merge branch 'raimo/IPV6_V6ONLY/OTP-8928' | Raimo Niskanen | |
* raimo/IPV6_V6ONLY/OTP-8928: kernel: Document socket option ipv6_v6only kernel: Add test cases for socket option ipv6_v6only erts,kernel: Implement socket option ipv6_v6only in erlang code erts: Implement socket option IPV6_V6ONLY erts: Add configure test for IPV6_V6ONLY | |||
2012-10-31 | erts,kernel: Implement socket option ipv6_v6only in erlang code | Raimo Niskanen | |
2012-10-31 | erts: Implement socket option IPV6_V6ONLY | Raimo Niskanen | |
2012-10-26 | Merge branch 'bjorn/erts/beam_makeops' | Björn Gustavsson | |
* bjorn/erts/beam_makeops: beam_makeops: Turn on warnings and eliminate existing warnings beam_makeops: Eliminate a deprecation warning | |||
2012-10-24 | Merge branch 'maint' | Björn-Egil Dahlberg | |
Conflicts: erts/etc/common/heart.c | |||
2012-10-24 | Merge branch 'egil/ensure-erl_crash.dump/OTP-10422' into maint | Björn-Egil Dahlberg | |
* egil/ensure-erl_crash.dump/OTP-10422: test: Relax timeouts for heart_SUITE erts: Fix crash dump write to port hack erts: Fix lock check assertion doc: Document ERL_CRASH_DUMP_SECONDS behaviour test: Add test for heart restart on crash test: Add test for heart restart on crash erts: Change ERL_CRASH_DUMP_SECONDS behaviour test: Refactor away ?line macros in heart_SUITE erts: Search for heart in ports that are alive heart: Refactor heart debugging erts, heart: Ensure erl_crash.dump is written | |||
2012-10-23 | Merge branch 'sverk/valgrind-quoting' | Sverker Eriksson | |
* sverk/valgrind-quoting: Make cerl -valgrind work with quoted spaces in command line | |||
2012-10-23 | erts: Fix crash dump write to port hack | Björn-Egil Dahlberg | |
More future proof with R16 | |||
2012-10-23 | erts: Fix lock check assertion | Björn-Egil Dahlberg | |
2012-10-22 | beam_makeops: Turn on warnings and eliminate existing warnings | Björn Gustavsson | |
2012-10-18 | doc: Document ERL_CRASH_DUMP_SECONDS behaviour | Björn-Egil Dahlberg | |
* heart reboot behaviour * erl_crash.dump file write behaviour | |||
2012-10-18 | Merge branch 'jf/fix_sctp_peeloff_active_true' | Henrik Nord | |
* jf/fix_sctp_peeloff_active_true: Set new peeled off SCTP socket to nonblocking socket SCTP test case with socket active options once and true OTP-10491 | |||
2012-10-16 | erts: Change ERL_CRASH_DUMP_SECONDS behaviour | Björn-Egil Dahlberg | |
Not setting ERL_CRASH_DUMP_SECONDS will now terminate beam immediately on a crash without writing a crash dump file. Setting ERL_CRASH_DUMP_SECONDS to 0 will also terminate beam immediately on a crash without writing a crash dump file, i.e. same as not setting ERL_CRASH_DUMP_SECONDS environment variable. Setting ERL_CRASH_DUMP_SECONDS to a negative value will let the beam wait indefinitely on the crash dump file being written. Setting ERL_CRASH_DUMP_SECONDS to a positive value will let the beam wait that many seconds on the crash dump file being written. A positive value will set both an alarm in beam AND a heart timeout for restart if heart is running. This is due to the change of 'heart' behavior when 'heart' is listening for a crash. | |||
2012-10-15 | erts: Search for heart in ports that are alive | Björn-Egil Dahlberg | |
2012-10-15 | heart: Refactor heart debugging | Björn-Egil Dahlberg | |
2012-10-15 | erts, heart: Ensure erl_crash.dump is written | Björn-Egil Dahlberg | |
When a crash dump is about to be written and we have heartbeat enabled on a system. We need time to write it before heart explicitly kills the beam. |