[#87773] timer thread [was Re: [ruby-alerts:7905] failure alert on trunk-asserts@silicon-docker (NG (r63844))] — Eric Wong <normalperson@...>
> test_all <main>: warning: pthread_create failed for timer: Resource temporarily unavailable, scheduling broken
3 messages
2018/07/04
[#87836] [Ruby trunk Bug#14898] test/lib/test/unit/parallel.rb: TestSocket#test_timestamp stuck sometimes — ko1@...
Issue #14898 has been reported by ko1 (Koichi Sasada).
5 messages
2018/07/06
[#87838] Re: [Ruby trunk Bug#14898] test/lib/test/unit/parallel.rb: TestSocket#test_timestamp stuck sometimes
— Eric Wong <normalperson@...>
2018/07/06
[email protected] wrote:
[#87842] Re: [Ruby trunk Bug#14898] test/lib/test/unit/parallel.rb: TestSocket#test_timestamp stuck sometimes
— Koichi Sasada <ko1@...>
2018/07/07
On 2018/07/06 18:47, Eric Wong wrote:
[#87847] undefined symbol: mjit_init_p — Leam Hall <leamhall@...>
I pulled Ruby trunk on 3 Jul and am now getting errors similar to the
10 messages
2018/07/07
[#87849] Re: undefined symbol: mjit_init_p
— Takashi Kokubun <takashikkbn@...>
2018/07/07
QXMgSSB0b2xkIHlvdSwgYG1ha2UgaW5zdGFsbGAgaXMgbmVlZGVkIHRvIG1ha2UgUnVieSB3b3Jr
[#87852] Re: undefined symbol: mjit_init_p
— Benoit Daloze <eregontp@...>
2018/07/07
T25lIG1vcmUgcmVhc29uIGZvciBodHRwczovL2J1Z3MucnVieS1sYW5nLm9yZy9pc3N1ZXMvMTM2
[#87986] [Ruby trunk Feature#14915] Deprecate String#crypt, move implementation to string/crypt — mame@...
Issue #14915 has been updated by mame (Yusuke Endoh).
5 messages
2018/07/18
[#87987] Re: [Ruby trunk Feature#14915] Deprecate String#crypt, move implementation to string/crypt
— Eric Wong <normalperson@...>
2018/07/18
[email protected] wrote:
[#88000] Re: [Ruby trunk Feature#14915] Deprecate String#crypt, move implementation to string/crypt
— "Urabe, Shyouhei" <shyouhei@...>
2018/07/19
normalperson (Eric Wong) wrote:
[#88088] [Ruby trunk Misc#14937] [PATCH] thread_pthread: lazy-spawn timer-thread only on contention — normalperson@...
Issue #14937 has been reported by normalperson (Eric Wong).
9 messages
2018/07/24
[#88104] [Ruby trunk Bug#14898] test/lib/test/unit/parallel.rb: TestSocket#test_timestamp stuck sometimes — ko1@...
Issue #14898 has been updated by ko1 (Koichi Sasada).
3 messages
2018/07/25
[#88173] [Ruby trunk Bug#14950] r64109 thread.c: move ppoll wrapper before thread_pthread.c - Windows compile failure - thread.c — Greg.mpls@...
Issue #14950 has been reported by MSP-Greg (Greg L).
3 messages
2018/07/29
[#88189] [Ruby trunk Bug#14950] r64109 thread.c: move ppoll wrapper before thread_pthread.c - Windows compile failure - thread.c — nobu@...
Issue #14950 has been updated by nobu (Nobuyoshi Nakada).
3 messages
2018/07/30
[#88199] [Ruby trunk Misc#14937] [PATCH] thread_pthread: lazy-spawn timer-thread only on contention — takashikkbn@...
Issue #14937 has been updated by k0kubun (Takashi Kokubun).
7 messages
2018/07/30
[#88213] Re: [Ruby trunk Misc#14937] [PATCH] thread_pthread: lazy-spawn timer-thread only on contention
— Eric Wong <normalperson@...>
2018/07/30
[email protected] wrote:
[#88219] Re: [Ruby trunk Misc#14937] [PATCH] thread_pthread: lazy-spawn timer-thread only on contention
— Eric Wong <normalperson@...>
2018/07/30
> yet, sky3 had a failure at
[#88306] Re: [Ruby trunk Misc#14937] [PATCH] thread_pthread: lazy-spawn timer-thread only on contention
— Eric Wong <normalperson@...>
2018/08/06
> http://ci.rvm.jp/results/trunk@P895/1173951
[#88308] Re: [Ruby trunk Misc#14937] [PATCH] thread_pthread: lazy-spawn timer-thread only on contention
— Eric Wong <normalperson@...>
2018/08/06
> > http://ci.rvm.jp/results/trunk@P895/1173951
[ruby-core:88192] Re: [Ruby trunk Feature#14718] Use jemalloc by default?
From:
Eric Wong <normalperson@...>
Date:
2018-07-30 10:16:22 UTC
List:
ruby-core #88192
[email protected] wrote: > https://sourceware.org/bugzilla/show_bug.cgi?id=14581 > The Ruby allocator calls posix_memalign (16384, 16344), and > unfortunately, such allocations, when freed, can not always be > reused for subsequent allocations because the glibc allocator > will not search for existing unused aligned allocations of a > given size. Thanks for bringing this to our attention. I wonder how beneficial it is for Ruby to free the memalign-ed sections used for object slots. Each of those allocations is "only" 400 or so objects and apps churn through that quickly, so. Testing the following patch with "MALLOC_ARENA_MAX=1 MALLOC_ARENA_TEST=1 make gcbench-rdoc" seems show a small improvement in VmHWM across repeated runs, but the results aren't stable... https://80x24.org/spew/[email protected]/raw The other problems are we hit malloc a lot and we use native threads (despite the GVL) in unnecessary ways; and having a process-wide GC means the associated free() for an allocation can happen from a thread the allocation didn't come from. Having multiple malloc arenas to avoid contention isn't very useful with the GVL, either. Anyways I'm working on several topics to reduce unnecessary uses of native threads; and ko1 is introducing transient heap to deal with short-lived allocations. So I'm hoping these ideas pan out and we can put less stress the on malloc implementation. Unsubscribe: <mailto:[email protected]?subject=unsubscribe> <http://lists.ruby-lang.org/cgi-bin/mailman/options/ruby-core>
