Alfred Perlstein <[EMAIL PROTECTED]> writes:
>> Just by making a thread call libc changes personality to use thread
>> safe routines (I.E. add mutex locking). Use one thread feature, get
>> the whole set...which may not be that bad.
> Actually it can be pretty bad. Locked bus cycles needed for mutex
> operations are very, very expensive, not something you want to do
> unless you really really need to do it.
It'd be interesting to try to get some numbers about the actual cost
of using a thread-aware libc, on platforms where there's a difference.
Shouldn't be that hard to build a postgres executable with the proper
library and run some benchmarks ... anyone care to try?
regards, tom lane
---------------------------(end of broadcast)---------------------------
TIP 1: subscribe and unsubscribe commands go to [EMAIL PROTECTED]
- Re: Re[4]: [HACKERS] Allowing... Tom Lane
- Re: Re[4]: [HACKERS] Allowing... Alfred Perlstein
- Re: Re[4]: [HACKERS] Allowing... Tom Lane
- Re: Re[4]: [HACKERS] Allowing... The Hermit Hacker
- Re: Re[4]: [HACKERS] Allowing... Larry Rosenman
- Re: Re[4]: [HACKERS] Allowing... Tom Lane
- Re: Re[4]: [HACKERS] Allowing... Bruce Momjian
- Re: Re[4]: [HACKERS] Allowing... Alfred Perlstein
- Re: [HACKERS] Allowing WAL fs... William K. Volkman
- Re: [HACKERS] Allowing WAL fs... Alfred Perlstein
- Re: [HACKERS] Allowing WAL fs... Tom Lane
- Re: [HACKERS] Allowing WAL fs... Larry Rosenman
- Re: [HACKERS] Allowing WAL fs... Alfred Perlstein
- Re: [HACKERS] Allowing WAL fs... Tom Lane
- Re: [HACKERS] Allowing WAL fs... Bruce Momjian
- Re: Re[4]: [HACKERS] Allowing... Doug McNaught
- Re: Re[2]: [HACKERS] Allowing WAL... Bruce Momjian
- Re: Re[2]: [HACKERS] Allowing... Alfred Perlstein
- Re: [HACKERS] Allowing WAL fs... Ken Hirsch
- RE: [HACKERS] Allowing WAL fsync to be done via O_SYNC Mikheev, Vadim
