The only problem is that i have to use modopen etc to be able to access
apic_cpus[].
This makes me to wonder if Solaris can be enhanced to let one kernel module to
easily access the object in another kernel module like the way Linux does.
--
This message posted from opensolaris.org
_
Eric, Thanks for the informtion.
>From the opensolaris source code, it seems like to get the target_apic_id from
>cpuid is to use apic_cpu[cpuid].
> apic_cpus/J
apic_cpus:
apic_cpus: ff04e68775c0
> ff04e68775c0::print -axt apic_cpus_info_t
{
ff04e68775c0 uint32_t aci_local_
Qiang Liu wrote:
Gurus,
Not sure if this sit is the right place to post my question. Anyway my goal is to get better performance for my IO board.
On x64 platform (AMD x4600 for example) with snv_109 installed, the apic_id is written by Solaris to MSIX table on my HBA card, I wonder if there is
Gurus,
Not sure if this sit is the right place to post my question. Anyway my goal is
to get better performance for my IO board.
On x64 platform (AMD x4600 for example) with snv_109 installed, the apic_id is
written by Solaris to MSIX table on my HBA card, I wonder if there is any way
to asso
Frank,
I looked at what my lex compiler is producing, and the parser_lex.c
file is about 4000 lines. Note that I am NOT using Sun Studio 12. If I
am interpreting the error message you are seeing correctly, it looks
like your parser_lex.c file is ending after only 212 lines, hence the
unexpe
Hello,
i removed the trailings from the mentioned lines
but this doesn't help.
Same error message than before
Frank
--
This message posted from opensolaris.org
___
perf-discuss mailing list
perf-discuss@opensolaris.org
Joachim Worringen wrote:
I succeeded to compile & run filebench on our Linux box (CentOS4) as
follows:
Actually, it was CentOS *5*.
--
Joachim Worringen, Software Architect, Dolphin Interconnect Solutions
phone ++49/(0)228/324 08 17 - http://www.dolphinics.com
_
I agree with Jim, we need some numbers to help. I would recommend also
looking not just at 'iostat' but also 'fsstat' to get a better idea of
what the IO load is like on an op basis.
Some questions and suggestions come to mind:
1) Have you disabled atime on the dataset(s)? (zfs set atime=off po
