pgsql: Fix the fallback memory barrier implementation to be reentrant.
pgsql: Fix the fallback memory barrier implementation to be reentrant.
От:
Andres Freund <andres@anarazel.de>
Дата:
Fix the fallback memory barrier implementation to be reentrant. This was essentially "broken" since 0c8eda62; but until more recently (14e8803f) barriers usage in signal handlers was infrequent. The failure to be reentrant was noticed because the test_shm_mq, which uses memory barriers at a high frequency, occasionally got stuck on some solaris buildfarm animals. Turns out, those machines use sun studio 12.1, which doesn't yet have efficient memory barrier support. A machine with a newer sun studio did not fail. Forcing the barrier fallback to be used on x86 allows to reproduce the problem. The new fallback is to use kill(PostmasterPid, 0) based on the theory that that'll always imply a barrier due to checking the liveliness of PostmasterPid on systems old enough to need fallback support. It's hard to come up with a good and performant fallback. I'm not backpatching this for now - the problem isn't active in the back branches, and we haven't backpatched barrier changes for now. Additionally master looks entirely different than the back branches due to the new atomics abstraction. It seems better to let this rest in master, where the non-reentrancy actively causes a problem, and then consider backpatching. Found-By: Robert Haas Discussion: 55626265.3060800@dunslane.net Branch ------ master Details ------- http://git.postgresql.org/pg/commitdiff/1b468a131bd260c9041484f78b8580c7f232d580 Modified Files -------------- src/backend/port/atomics.c | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-)
Re: pgsql: Fix the fallback memory barrier implementation to be reentrant.
От:
Tom Lane <tgl@sss.pgh.pa.us>
Дата:
Andres Freund writes: > Fix the fallback memory barrier implementation to be reentrant. Seems this has not done the trick: anole just crashed with "stuck spinlock" again. regards, tom lane
Re: pgsql: Fix the fallback memory barrier implementation to be reentrant.
От:
Andres Freund <andres@anarazel.de>
Дата:
On 2015-06-28 18:42:55 -0400, Tom Lane wrote: > Andres Freund writes: > > Fix the fallback memory barrier implementation to be reentrant. > > Seems this has not done the trick: anole just crashed with "stuck > spinlock" again. Hopefully it fixed protosciurus and castoroides though, that had different symptoms. Looking into anole specifically.