Envie correos para publicitar - Mas ventas, mas clientes
?Queres que tu negocio lo conozcan MILLARES en instantes? Recibm en tu domicilio, la mayor base de datos de emails jamas compilada!!! Bases de emails de Argentina (3.975.023 emails) : * bases de emails bulk (sslo direcciones de emails), actualizada, con 2.585.334 correos electrsnicos + base adicional de 85.511 emails de Argentina * bases de emails por portales, con 404.853 emails * base ABC1 de emails con datos (nombre, empresa, cargo, etc) , con 43.722 emails * bases de emails de dominios propios empresarios (100.000 emails) * bases de emails de pymes argentinas (374.103 emails) * 226.309 emails de empresas con datos (nombre, empresa, cargo, etc) * 3.000 emails de exportadores e importadores con datos completos (nombre, empresa, cargo, etc) * 30.000 emails de gerentes de empresas con datos (nombre, empresa, cargo, etc) * 12.000 emails de industriales con datos (nombre, empresa, cargo, etc) * base de emails de mujeres de toda la Argentina (45.209 emails) * bases de emails del sector agropecuario (6.613 emails) * 57.817 emails por profesiones : escribanos (150 emails), sicslogos (1.707 emails), abogados (1.808 emails), ingenieros (1.811 emails), midicos y terapeutas (5.121 emails), docentes (2.232 emails), periodismo y medios (2.741 emails), contadores pzblicos (27.487 emails), cientmficos (3.904 emails), midicos (433 emails), gerentes de sistemas (4.554 emails), dentistas (518 emails), arquitectos (5.299 emails) * 299 emails de hoteles y restaurantes * 230 emails de cibercafes * 23 emails de empresas de servicio tecnico Bases de Espaqa y Latinoamirica (5.457.400 emails) : * bases de Bolivia (4.900 emails en total) * bases de Brasil (2.680.000 emails en total) : base bulk (2.200.000), empresas de Brasil (450.000), rubros comerciales (29.164) * bases de pamses de Centro Amirica (41.000 emails en total) * bases de Chile (170.000 emails en total) : base bulk (152.000), rubros comerciales (17.974) * bases de Colombia (410.000 emails en total) : base bulk (260.000), rubros comerciales (150.000) * bases de Ecuador (8.500 emails en total) * bases de Espaqa (516.000 emails en total) : base bulk (400.000 emails), por regiones (65.000), por rubros comerciales (51.000) * bases de Mexico (933.000 emails en total) : base bulk (700.000), por estados (115.000), universitarios (65.000), empresas (53.000) * bases de Paraguay (8.100 emails en total) * bases de Peru (352.900 emails en total) : base bulk (280.000), empresas (10.000), profesionales (62.900) * bases de Uruguay (256.000 emails en total) : base bulk (254.000), por rubros comerciales (2.153) * bases de Venezuela (77.000 emails en total) : base bulk (67.000), por rubros comerciales (9.560) PEDILA YA! ENVIA UN EMAIL A basedatosema...@gmail.com PARA PEDIR INFORMACISN DE LA FORMA DE PAGO Y ENVMO ACLARACiSN: Los que forman esta base han dado su consentimiento para ello. SU email NO FORMA PARTE DE ESTA BASE, solo de las nuestras privadas. Si desea ser eliminado de ellas envme REMOVER a esa direccisn. Gracias
Kernel page fault trap, code=0, uvm_fault, what to do next
Hello
Few days ago my friend ask me to update his firewall (he is running OBSD
4.1).
I prepared new box and installed OpenBSD 4.6 (i386.mp).
I did have prepared pf.conf also so it work without problems and at night
i just swithed cables and it did work. But in the morning when i wake up
there was problem:
uvm_fault(0xd0891180, 0x4000, 0, 3) -e
kernel: page fault trap, code=0
Stopped at pf_state_key_detach+0x40: movl %eax0,4(%ecx)
ddb{0}
The problem is i cannot make trace in ddb because computer freeze then
and it do not
respond on anything. After reset i cannot also find any core dump.
I happend in 3 days now, one after another. So i always swith back to
old box.
It is always same situation, at morning more people use internet, so the
transfer
go up for interfaces and then it happen. The last time when i checked it was
7335 Kbps in and 12775Kbps out on em1
12825 Kbps in and 7263 Kbps out on em2
em0 transfer was null because i use it only to connect it directly to
other computers.
I laso got some messages on ifstat screen like this:
istat: warning: rollover for interface % reinitialising
Here are some additional informations that may help:
The kernel was generic (stable). I had to change one line in altq_hfsc.h
from #define HFSC_MAX_CLASSES64
to #define HFSC_MAX_CLASSES4096
dmesg:
OpenBSD 4.6 (NICRAM.MP) #0: Wed Feb 10 12:10:36 CET 2010
r...@router.marponet.pl:/usr/src/sys/arch/i386/compile/NICRAM.MP
cpu0: Intel(R) Core(TM)2 Duo CPU E6850 @ 3.00GHz (GenuineIntel
686-class) 2.99 GHz
cpu0:
FPU,V86,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,MTRR,PGE,MCA,CMOV,PAT,PSE36,CFLUSH,DS,ACPI,MMX,FXSR,SSE,SSE2,SS,HTT,TM,SBF,SSE3,DS-CPL,VMX,SMX,EST,TM2,CX16,xTPR
real mem = 2097115136 (1999MB)
avail mem = 2018914304 (1925MB)
mainbus0 at root
bios0 at mainbus0: AT/286+ BIOS, date 07/16/09, SMBIOS rev. 2.4 @
0xe23e0 (35 entries)
bios0: vendor Intel Corp. version JOQ3510J.86A.1109.2009.0716.0319
date 07/16/2009
bios0: Intel Corporation DQ35JO
acpi0 at bios0: rev 0
acpi0: tables DSDT FACP APIC WDDT MCFG ASF! DMAR ASPT WDTT SSDT SSDT
SSDT SSDT SSDT SSDT SSDT TCPA
acpi0: wakeup devices SLPB(S4) P32_(S4) UAR1(S4) ILAN(S4) PEGP(S4)
PEX0(S4) PEX1(S4) PEX2(S4) PEX3(S4) PEX4(S4) PEX5(S4) UHC1(S3) UHC2(S3)
UHC3(S3) UHC4(S3) EHCI(S3) EHC2(S3) UH42(S3) UHC5(S3) UHC6(S3) AZAL(S3)
acpitimer0 at acpi0: 3579545 Hz, 24 bits
acpimadt0 at acpi0 addr 0xfee0: PC-AT compat
cpu0 at mainbus0: apid 0 (boot processor)
cpu0: apic clock running at 332MHz
cpu1 at mainbus0: apid 1 (application processor)
cpu1: Intel(R) Core(TM)2 Duo CPU E6850 @ 3.00GHz (GenuineIntel
686-class) 2.99 GHz
cpu1:
FPU,V86,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,MTRR,PGE,MCA,CMOV,PAT,PSE36,CFLUSH,DS,ACPI,MMX,FXSR,SSE,SSE2,SS,HTT,TM,SBF,SSE3,DS-CPL,VMX,SMX,EST,TM2,CX16,xTPR
ioapic0 at mainbus0: apid 2 pa 0xfec0, version 20, 24 pins
ioapic0: misconfigured as apic 0, remapped to apid 2
acpiprt0 at acpi0: bus 0 (PCI0)
acpiprt1 at acpi0: bus 6 (P32_)
acpiprt2 at acpi0: bus 1 (PEX0)
acpiprt3 at acpi0: bus 2 (PEX1)
acpiprt4 at acpi0: bus 3 (PEX2)
acpiprt5 at acpi0: bus 4 (PEX3)
acpiprt6 at acpi0: bus 5 (PEX4)
acpiprt7 at acpi0: bus -1 (PEX5)
acpicpu0 at acpi0: C1, PSS
acpicpu1 at acpi0: C1, PSS
acpibtn0 at acpi0: SLPB
bios0: ROM list: 0xc/0xb400! 0xcb800/0x2200!
cpu0: Enhanced SpeedStep 2990 MHz: speeds: 2997, 2664, 2331, 1998 MHz
pci0 at mainbus0 bus 0: configuration mode 1 (bios)
pchb0 at pci0 dev 0 function 0 Intel 82Q35 Host rev 0x02
vga1 at pci0 dev 2 function 0 Intel 82Q35 Video rev 0x02
wsdisplay0 at vga1 mux 1: console (80x25, vt100 emulation)
wsdisplay0: screen 1-5 added (80x25, vt100 emulation)
intagp0 at vga1
agp0 at intagp0: aperture at 0x8000, size 0x800
inteldrm0 at vga1: apic 2 int 16 (irq 11)
drm0 at inteldrm0
Intel 82Q35 Video rev 0x02 at pci0 dev 2 function 1 not configured
Intel 82Q35 HECI rev 0x02 at pci0 dev 3 function 0 not configured
em0 at pci0 dev 25 function 0 Intel ICH9 IGP AMT rev 0x02: apic 2 int
20 (irq 9), address 00:1c:c0:06:8f:d1
uhci0 at pci0 dev 26 function 0 Intel 82801I USB rev 0x02: apic 2 int
18 (irq 10)
uhci1 at pci0 dev 26 function 1 Intel 82801I USB rev 0x02: apic 2 int
21 (irq 11)
uhci2 at pci0 dev 26 function 2 Intel 82801I USB rev 0x02: apic 2 int
17 (irq 9)
ehci0 at pci0 dev 26 function 7 Intel 82801I USB rev 0x02: apic 2 int
17 (irq 9)
usb0 at ehci0: USB revision 2.0
uhub0 at usb0 Intel EHCI root hub rev 2.00/1.00 addr 1
ppb0 at pci0 dev 28 function 0 Intel 82801I PCIE rev 0x02: apic 2 int
17 (irq 255)
pci1 at ppb0 bus 1
em1 at pci1 dev 0 function 0 Intel PRO/1000 PT (82572EI) rev 0x06:
apic 2 int 16 (irq 11), address 00:1b:21:04:ec:92
ppb1 at pci0 dev 28 function 1 Intel 82801I PCIE rev 0x02: apic 2 int
20 (irq 255)
pci2 at ppb1 bus 2
em2 at pci2 dev 0 function 0 Intel PRO/1000 PT (82572EI) rev 0x06:
apic 2 int 17 (irq 9), address 00:1b:21:04:bb:1f
ppb2 at pci0 dev 28 function 2 Intel 82801I PCIE rev 0x02: apic 2 int
18 (irq 255)
pci3 at ppb2 bus 3
pciide0 at pci3
Re: OpenBGP filter question
On 2010-02-11, Ivo Chutkin open...@bgone.net wrote:
match to $my_upstream_1 source-as {some_as} set prepend-self 4
I would like to prepend my as to make as path longer for some_as
trough my_upstream_1 and make it to prefer path trough my_upstream_2.
It does not produce error with bgpd-n but there is no effect as well.
Are you certain it has no effect (and how?) - you can't rely on
AS path prepending to change how traffic flows, if someone gives you
a higher localpref they'll use that path irrespective of the path length.
Hi Stuart,
I am certain as I don't see my prepend on some_as looking glass.
The actual filter looks like this without the comment:
match to $spnet_bg #(AS8717) sourse_as 9070 set prepend-seff 4
and this is what I see on 9070 looking glass:
This filter affects prefixes you send to the peer, and only those
with source_as 9070. Unless you are providing transit for 9070
you won't be sending anything to 34224 that matches this (and if
you are, it wouldn't be a useful thing to do, as 9070 won't
accept routes with their own AS in the path).
If I understand correctly, you'd like 9070 to see a longer path
to you via 34224, but not affect things for other AS that see you
via 34224.
I think there are just two ways you can do this via prepending
1. ask 34224 to prepend their announcements to 9070.
Some providers let you set communities on your prefixes to
do this, see e.g. whois -r as3356|more +/ties.acc
but many do not.
2. ask 9070 to prepend the paths they receive from 34224.
Re: routing and pf at 10Gbps
* Alexander Shikoff minot...@crete.org.ua [2010-02-12 08:06]: Every OS can have it's vulnerabilities. OpenBSD is very secure, but I'm sure it cannot route (even without pf) 10Gbit/s traffic. you have no idea, obviously. interesting how much fuzz my graphics card bullshit caused. it was onbiously not to be taken seriously, of course the graphics adapter is irrelevant (i'm sure you could construct a case where a stupid one actually hurts, but please). -- Henning Brauer, h...@bsws.de, henn...@openbsd.org BS Web Services, http://bsws.de Full-Service ISP - Secure Hosting, Mail and DNS Services Dedicated Servers, Rootservers, Application Hosting
Re: Is OpenBSD + PF accredited or certified in any way ?
* Keith ke...@scott-land.net [2010-02-02 00:16]: I've used OpenBSD PF for a number of years without issue and am now in the position that I want to create a dmz between the Internet and my organisations WAN. Our security people are asking if the firewall that we use is accreditated by ITSEC and I am pretty sure it isn't but it turns out that our security people will be happy is the firewall is accredited for use by another government ! i herewith certify openbsd + pf for use by government clowns -- Henning Brauer, h...@bsws.de, henn...@openbsd.org BS Web Services, http://bsws.de Full-Service ISP - Secure Hosting, Mail and DNS Services Dedicated Servers, Rootservers, Application Hosting
iSCSI NAS/SAN for claudio@
hello, i would encourage people to consider sending donations in for this, i think it would be an extremely good investment. claudio already has a good start on an implementation of an iscsi initiator, but he's at the point where he needs real gear to work and test against. given the gear i fully expect him to be able to make progress pretty quickly, which in turn means the rest of us can then use it. aside from the usefulness of it, i would love to see some iscsi code done the OpenBSD Way(tm) out in the wild too. cheers, dlg Begin forwarded message: From: Claudio Jeker clau...@cvs.openbsd.org Date: 11 February 2010 7:38:40 PM AEST To: source-chan...@cvs.openbsd.org Subject: CVS: cvs.openbsd.org: www CVSROOT: /cvs Module name: www Changes by: clau...@cvs.openbsd.org 2010/02/11 02:38:39 Modified files: . : want.html Log message: I'm looking for a rack-mountable iSCSI capable NAS/SAN for iSCSI initiator developement.
Re: OpenBGP filter question
Am 11.02.2010 11:31, schrieb Ivo Chutkin:
The actual filter looks like this without the comment:
match to $spnet_bg #(AS8717) sourse_as 9070 set prepend-seff 4
These are typos, right?
match to neighborip source-as as to prepend set { prepend-self 3 }
works in our setup
Latest snapshot doesn't work in Qemu under Fedora 12
Hi,
funny problems with :
$ qemu --version
QEMU PC emulator version 0.11.0 (qemu-kvm-0.11.0), Copyright (c)
2003-2008 Fabrice Bellard
on :
$ uname -a
Linux 2.6.31.12-174.2.3.fc12.i686 #1 SMP Mon Jan 18 20:22:46 UTC 2010
i686 i686 i386 GNU/Linux
I can't use network in OpenBSD with any driver which is provided. All
show just 'watchdog timeout -- resetting'. I tried re, em and fpx
drivers. With fxp there was even core dump and Qemu crashed. Looks
like problem is with their management of memory which they improved
for KVM :
# dmesg | grep -i not
Qumranet Virtio Memory rev 0x00 at pci0 dev 4 function 0 not configured
Command for Qemu which end with core dump was 'qemu -m 64 -boot c -usb
-hda ./obsd.img -net nic,model=i82551 -net user '
For those who are interested here is output from Automatic Bug Reporting Tool :
[New Thread 5580]
warning: .dynamic section for /usr/lib/libX11.so.6 is not at the
expected address
warning: difference appears to be caused by prelink, adjusting expectations
Core was generated by `qemu -m 64 -boot c -usb -hda ./obsd.img -net
nic,model=i82551 -net user'.
Program terminated with signal 6, Aborted.
#0 0x002bf416 in __kernel_vsyscall ()
Thread 2 (Thread 5580):
#0 0x002bf416 in __kernel_vsyscall ()
No symbol table info available.
#1 0x0099af72 in pthread_cond_timedwait@@GLIBC_2.3.2 ()
at ../nptl/sysdeps/unix/sysv/linux/i386/i486/pthread_cond_timedwait.S:179
No locals.
#2 0x080b8f96 in cond_timedwait (unused=value optimized out)
at posix-aio-compat.c:68
ret = value optimized out
#3 aio_thread (unused=value optimized out) at posix-aio-compat.c:301
aiocb = value optimized out
ret = value optimized out
tv = {tv_sec = 1265976505, tv_usec = 396331}
ts = {tv_sec = 1265976515, tv_nsec = 0}
pid = value optimized out
set = {__val = {2147483647, 4294967294,
4294967295 repeats 30 times}}
#4 0x00996ab5 in start_thread (arg=value optimized out)
at pthread_create.c:297
__res = value optimized out
__ignore1 = 128
__ignore2 = 2545
now = value optimized out
unwind_buf = {cancel_jmp_buf = {{jmp_buf = {10125300, 0, 4001536,
-1318489032, -777369161, 832168660}, mask_was_saved = 0}},
priv = {pad = {0x0, 0x0, 0x0, 0x0}, data = {prev = 0x0,
cleanup = 0x0, canceltype = 0}}}
not_first_call = value optimized out
pagesize_m1 = value optimized out
freesize = value optimized out
#5 0x008eddce in clone () at ../sysdeps/unix/sysv/linux/i386/clone.S:130
No locals.
Thread 1 (Thread 5578):
#0 0x002bf416 in __kernel_vsyscall ()
No symbol table info available.
#1 0x0083da91 in raise (sig=6) at ../nptl/sysdeps/unix/sysv/linux/raise.c:64
resultvar = value optimized out
resultvar = value optimized out
pid = 9977844
selftid = 5578
#2 0x0083f35a in abort () at abort.c:92
save_stage = 2
act = {__sigaction_handler = {sa_handler = 0x985380 main_arena,
sa_sigaction = 0x985380 main_arena}, sa_mask = {__val = {
9977844, 168, 1, 3216681904, 3216681692, 0, 304, 163, 9982848,
9977844, 163, 162, 3216681864, 562, 169560536, 163,
3216681904, 169622560, 0, 4222451712, 169560536, 169560637,
169560536, 169560536, 169560698, 169560836, 169560536,
169560836, 0, 0, 0, 0}}, sa_flags = 0, sa_restorer = 0xb}
sigs = {__val = {32, 0 repeats 31 times}}
#3 0x00836be8 in __assert_fail (assertion=value optimized out,
file=value optimized out, line=value optimized out,
function=value optimized out) at assert.c:81
buf = 0xa1b49d8 qemu:
/builddir/build/BUILD/qemu-kvm-0.11.0/hw/eepro100.c:1176:
eepro100_read2: Assertion `!\feature is missing in this emulation: \
\unknown word read\' failed.\n
#4 0x080695a9 in eepro100_read2 (s=value optimized out,
addr=value optimized out)
at /usr/src/debug/qemu-kvm-0.11.0/hw/eepro100.c:1176
val = 0
__PRETTY_FUNCTION__ = eepro100_read2
#5 0x08069605 in ioport_read2 (opaque=value optimized out,
addr=value optimized out)
at /usr/src/debug/qemu-kvm-0.11.0/hw/eepro100.c:1310
s = value optimized out
#6 0x080627ea in ioport_read (index=value optimized out,
address=value optimized out)
at /usr/src/debug/qemu-kvm-0.11.0/ioport.c:67
default_func = {0x8062850 default_ioport_readb,
0x8062870 default_ioport_readw, 0x80628f0 default_ioport_readl}
func = value optimized out
#7 0x08062a24 in cpu_inw (env=value optimized out,
addr=value optimized out) at /usr/src/debug/qemu-kvm-0.11.0/ioport.c:240
val = value optimized out
#8 0x08188004 in helper_inw (port=value optimized out)
at /usr/src/debug/qemu-kvm-0.11.0/target-i386/op_helper.c:576
No locals.
#9 0x010f11d2 in ?? ()
No symbol table info available.
#10 0xc042 in ?? ()
No symbol table info available.
#11 0xd027d000 in ?? ()
No
Προσφορά γνωριμίας με έκπτωση 10 ευρώ
travelplanet24.com - Newsletter If you are unable to see the message below, click here [2] [3] N N5N=N?N4N?ON5N/N1 NN5ON?ON?ON9N:N, N5N9ON9ON.ON9N1 NOON?N:N/N=N7ON1 NN:ON?ON;N?O N:N, N5N9ON9ON.ON9N1 N1OO 16b, N1OO 39b,b,-- N1OO 17b, N1OO 15b, 6b, 29b,b,-- 7b, 5b, [4] [5] [6] [7] * N N9 ON9NN-O N9OOO N?ON= N3N9N1 OON3N:N5N:ON9NN-N=N?OO OON?N?ON9ONN?O O N:N1N9 ON5ON9N?ON9ONN-N=N? N1ON9N8NO N8N-ON5O N= N:N1N9 N4O NN1ON/O N= N ON?OO ON9N:O O N:O N4N9N:O O ON?O N:N?OON?N=N9N?O ON1O: E303383561450 travelplanet24.com [1] N. N#ON3N3ON?O 241 NN;N9N:N1ON=N1OON?O 2, 17122 N N-N1 N#NO ON=N7 , NN8N.N=N1 N$N7N;: +30 (210) 72-99-660 NN1N: +30 (210) 72-99-664 N$N7N;. N:ON1ON.ON5O N=: 801 11 454545 Email: serv...@travelplanet24.com To be removed from this newsletter, click here - unsubsrcibe [8] [1] http://newsletter.travelplanet24.com/go/9RO0AB6-1UODJT5-1UOD4C1-XH3CD9.html [2] http://newsletter.travelplanet24.com/go/9RO0AB6-1UODJT5-1UMABXI-F4MP5F.html [3] http://newsletter.travelplanet24.com/go/9RO0AB6-1UODJT5-1UOD4BY-K05ORB.html [4] http://newsletter.travelplanet24.com/go/9RO0AB6-1UODJT5-1UOD4C3-XWA16DH.html [5] http://newsletter.travelplanet24.com/go/9RO0AB6-1UODJT5-1UOD4BZ-19TMWWK.html [6] http://newsletter.travelplanet24.com/go/9RO0AB6-1UODJT5-1UOD4C0-C6Y9CU.html [7] http://newsletter.travelplanet24.com/go/9RO0AB6-1UODJT5-1UOD4C2-KQNHEW.html [8] http://newsletter.travelplanet24.com/go/9RO0AB6-1UODJT5-1UJ5DOF-HOUHQ3-U.html
Pour votre information
NewsLetter
Re: routing and pf at 10Gbps
On Thu, 11 Feb 2010, Claudio Jeker wrote: Henning, I told you, we should not talk about unfinsihed projects. We planned to announce this in exactly 7 weeks. Anyway, to late, the cat is out of the bag. So Henning and Oga are working at offloading pf into the graphic card cores by using the DRI interface. The shader will evaluate the ruleset and packets in parallel and use the graphic memory for the state table. Additionally if the speed of one card is not enough you can use SLI or crossfire to use multiple cards in parallel. -- :wq Claudio okay, now you have piqued my interest I will sit back and wait for mor info thanks diana
Re: routing and pf at 10Gbps
On Thu, 11 Feb 2010, Claudio Jeker wrote: Henning, I told you, we should not talk about unfinsihed projects. We planned to announce this in exactly 7 weeks. Anyway, to late, the cat is out of the bag. So Henning and Oga are working at offloading pf into the graphic card cores by using the DRI interface. The shader will evaluate the ruleset and packets in parallel and use the graphic memory for the state table. Additionally if the speed of one card is not enough you can use SLI or crossfire to use multiple cards in parallel. -- :wq Claudio Damn Claudio, I thought y'all were going to announce support for the Hammer filesystem in 7 weeks. It would really help in saving captured packets to files. thanks diana
Re: routing and pf at 10Gbps
On Fri, Feb 12, 2010 at 2:52 PM, Diana Eichert deich...@wrench.com wrote: On Thu, 11 Feb 2010, Claudio Jeker wrote: Henning, I told you, we should not talk about unfinsihed projects. We planned to announce this in exactly 7 weeks. Anyway, to late, the cat is out of the bag. So Henning and Oga are working at offloading pf into the graphic card cores by using the DRI interface. The shader will evaluate the ruleset and packets in parallel and use the graphic memory for the state table. Additionally if the speed of one card is not enough you can use SLI or crossfire to use multiple cards in parallel. -- :wq Claudio okay, now you have piqued my interest I will sit back and wait for mor info I, too, hope to get news of this shortly after March is over. thanks diana
Re: routing and pf at 10Gbps
On Fri, 12 Feb 2010 14:59 +0100, Bret Lambert bret.lamb...@gmail.com wrote: On Fri, Feb 12, 2010 at 2:52 PM, Diana Eichert deich...@wrench.com wrote: On Thu, 11 Feb 2010, Claudio Jeker wrote: Henning, I told you, we should not talk about unfinsihed projects. We planned to announce this in exactly 7 weeks. Anyway, to late, the cat is out of the bag. So Henning and Oga are working at offloading pf into the graphic card cores by using the DRI interface. The shader will evaluate the ruleset and packets in parallel and use the graphic memory for the state table. Additionally if the speed of one card is not enough you can use SLI or crossfire to use multiple cards in parallel. -- :wq Claudio okay, now you have piqued my interest I will sit back and wait for mor info I, too, hope to get news of this shortly after March is over. The rumor is that they are using CUDA on Nvidia graphics cards with advanced object oriented C++ and it is so fast that several developers are considering switching from C to C++ even for the kernel, after migrating to ZFS and replacing Perl in base with Java. Good times for OpenBSD indeed. Glad to see they are finally making some much needed improvements. OK... enough Friday humor. thanks diana
Un año gratuito.Master Internacional.8235 pesos
SI NO VE LA INFORMACISN, HAGA CLICK AQUM [IMAGE] [IMAGE] [IMAGE] [IMAGE] [IMAGE] [IMAGE] Cursos que ofrecemos: MASTER EN EMPLEO Y DESARROLLO LOCAL MASTER EN DINAMIZACISN COMUNITARIA EN EL MUNDO RURAL MASTER EN COOPERACISN INTERNACIONAL MASTER EN INTERVENCISN SOCIAL MASTER EN ANIMACISN SOCIOCULTURAL Y COMUNITARIA MASTER EN GESTISN Y DESARROLLO DE SERVICIOS Y EMPRESAS DE AYUDA A DOMICILIO MASTER EN MEDIACISN SOCIAL E INTERCULTURAL MASTER EN PATRIMONIO CULTURAL MASTER EN SISTEMAS DE FORMACISN PRESENCIAL, A DISTANCIA Y E-LEARNING [IMAGE] [IMAGE] [IMAGE] Conforme a la Ley de servicios de la sociedad de la informacisn y de comercio electrsnico, y a la vigente Ley organica 15 13/12/1999 de proteccisn de datos espaqola, le informamos que su direccisn de correo esta incluida en nuestra base de datos, con la finalidad de enviarle informacisn de su interis. Si no desea seguir recibiendo ningzn correo futuro por nuestra parte o quiere modificar sus datos, por favor, responda directamente este mail con su peticisn. En caso de que no tengamos respuesta en este envmo, consideramos su autorizacisn para posteriores envmos. SI DESEA DARSE DE BAJA, HAGA CLICK AQUM [IMAGE]
Re: routing and pf at 10Gbps
On Fri, 12 Feb 2010, Brad Tilley wrote: The rumor is that they are using CUDA on Nvidia graphics cards with advanced object oriented C++ and it is so fast that several developers are considering switching from C to C++ even for the kernel, after migrating to ZFS and replacing Perl in base with Java. Good times for OpenBSD indeed. Glad to see they are finally making some much needed improvements. If I understand some recent developer conversations only a small, wait a very small number of developers are elite enough to code using C++. What I found more interesting was the inclusion of a forth interpreter in mg. OK... enough Friday humor. what Friday humor? diana
¿Problemas de memoria?
Haga clic sobre la imagen para visitar nuestro web site. A g r a d e c e r e m o s s u d i f u s i o n ! [demime 1.01d removed an attachment of type image/jpeg which had a name of ciencorto.jpg]
network performance problems
Hi, I'm not satisfied with the network performance on my OpenBSD firewall/router. CPU is Intel(R) Core(TM)2 Duo CPU E6550 @ 2.33GHz / with 4G ram OpenBSD server 4.6 GENERIC.MP#89 i386 This pc/router/firewall is directly connected to a Gigabit HP 2810-48G switch. Server: Ext interface: Realtek 8169SC (re0 - IP 192.168.1.2/30 Int interface: Marvell Yukon 88E8056 (msk0 - vlan61 - IP 10.100.61.2/30) The internal interface is a VLAN trunk (802.1Q) interface. I have a client on VLAN 61 with IP 10.100.61.1/30 connected to the same switch. I run iperf tests with iperf -s on server / iperc -c server on client. Changing window sizes didn't help. I get 300 Mbps on the internal Interface and 350 Mbps on the external interface. Packet fowarding from an ftp server outside - to the client inside is around 350-400Mbps wget -O /dev/null I've tried changing net.inet.tcp.recvspace and net.inet.tcp.sendspace and the throughput settled in the values above with any value above 32768. Now if I reboot the obsd machine in linux (same machine/same network configuration) I get 885 Mbps on the internal interface and 660 Mbps on the external interface) Packet fowarding from an ftp server outside - to the client is around 600Mbps So apparently on the same machine I get double performance while running linux. I've also tried changing net.inet.ip.ifq.maxlen, net.inet.tcp.rfc1323, net.bpf.bufsize, net.bpf.maxbufsize, kern.maxclusters without any significant change in performance. The machine itself downloads with max 350-400Mbps. Linux did at 600-800Mbps (wget -O /dev/null). pf is disabled and if enabled (+client nat) there is no significant loss from there. Any ideas on how I could improve the performance? Any sysctl parameter I'm missing? Maybe it could be a driver problem (both of them?). Something wrong in the setup? best regards, Giannis
Re: Latest snapshot doesn't work in Qemu under Fedora 12
Uhm, looks seriously off-topic on any mailinglist that ends in @openbsd.org. I hope you reported this to Fedora. On Fri, Feb 12, 2010 at 01:25:11PM +0100, Tomas Bodzar wrote: [ backtrace of crash in hand-rolled Drepper assembly ]
Iznenadite nekog koga volite
Top Shop Tragate za poklonom koji De pokazati svu Vašu ljubav? Iznenadite nekog koga volite! U mesecu ljubavi, Top Shop ima pravo rešenje za Vas: Najpopularniji proizvodi uz najniEe cene! ; Popusti i do 25%! ; Super ponuda traje samo do 28. februara, zato poEurite! ; PronaDite super poklon - pokaEite koliko Vam znaD i! Darujte ljubav, izmamite osmeh... Ponuda za zaljubljene Pogledajte sve iz ove ponude; Dan zaljubljenih Air Sofa Bed - višenamenski leEaj na naduvavanje Air Sofa Bed 6.741 RSD PoruD ite Ab Rocket - fitnes sprava za trbušnjake Ab Rocket 6.741 RSD PoruD ite Celluless - vakuumski anticelulit masaEer Celluless 2.990 RSD PoruD ite Velform Enchance Bra - prsluk za podizanje grudi n Velgorm Enchance Bra 3.141 RSD n PoruD ite n Micro Force - izuzetno mali i moDan beEiD ni brijaD n Micro Force 2.691 RSD n PoruD ite n Massage Cushion - jastuk za masaEu n Massage Cushion 2.691 RSD n PoruD ite n Ovu elektronsku poštu primate, ukoliko ste svojevoljno ostavili svoju e-mail adresu na nekom od sajtova Top Shop-a, uD estvovali u našoj poklon igri ili nagradnom kvizu ili se prijavili za e-D asopis Top Shop-a ili nekog od nasih brendova. Ponude date u ovom e-mailu vaEe iskljuD ivo za porudEbine upuDene putem Interneta ili broja telefona 021 489 26 60. Ponude vaEe do 10. 02. 2010. ili do isteka zaliha. Isporuku vršimo samo u Srbiji. Ukoliko ne Eelite više da primate naše elektronske poruke, za odjavljivanje sa naše e-mailing liste, , kliknite ovde. U obrazac na internet stranici upišite svoju taD nu e-mail adresu i odjavu potvrdite. Studio Moderna d.o.o., Bulevar vojvode Stepe 30, 21000 Novi Sad, Tel: 021 489 26 60, Fax: 021 489 29 08, E-mail: i...@news.e-topshop.tv [IMAGE]If you would no longer like to receive our emails please unsubscribe by clicking here.
Re: Latest snapshot doesn't work in Qemu under Fedora 12
On Fri, Feb 12, 2010 at 9:24 PM, Tobias Ulmer tobi...@tmux.org wrote: Uhm, looks seriously off-topic on any mailinglist that ends in @openbsd.org. I hope you reported this to Fedora. On Fri, Feb 12, 2010 at 01:25:11PM +0100, Tomas Bodzar wrote: [ backtrace of crash in hand-rolled Drepper assembly ] Actually less to do with Fedora and more a query for the QEMU project and you're processor manufacturer I think. Seems to be an issue within KVM and and how its trying to use hardware to emulate a machine. A while back I ran OpenBSD without any issues under QEMU and VirtualBox on various recent Linux distros. Only thing is I had countless issues on Intel CPUs and none at all on the AMD CPUs,... seems the Intel virtualization enhancements are a bit behind. -- Opportunity is most often missed by people because it is dressed in overalls and looks like work. Thomas Alva Edison Inventor of 1093 patents, including: The light bulb, phonogram and motion pictures.
Re: routing and pf at 10Gbps
On Thu, Feb 11, 2010 at 08:46:22PM +0100, Henning Brauer wrote: * Diana Eichert deich...@wrench.com [2010-02-11 17:02]: yes, people run firewalls on 10G circuits I am not aware of anyone filtering at 10G who is using off the shelf hardware, with open source O/S. I know of some. I don't remember specifics, dunno wether anybody does linerate and with what kind of packet characteristics. I'm interested in this discussion in a low-key sense; I don't need 10Gbps firewalling, but would like to move beyond 1Gbps. 2Gbps would do nicely for a start. My current firewall hardware, which is a carp failover pair of now-oldish Dell 1750s with Intel 1000/pro MT nics, is probably close to the limit of what it can do, at around 600-700Mbps (the switch from openbsd 4.4 to 4.6 did make a night and day difference for them - the recent network stack tuning has been amazing). I wonder if it's a viable option simply to run an active-active carp/pf pair, since the pfsync changes in 4.6? In principle it should even be possible to add nodes to the pfsync cluster to scale bandwidth beyond 2Gbps. For my specific situation, where the high-bandwidth transfers tend to be applications like gridftp, involving many different hosts, it seems like this could work well. Obviously no single stream could exceed the bandwidth of one node, but besides that, are there any big shortfalls to this approach? Graham --
Re: routing and pf at 10Gbps
I know there was some facetious comments regarding use of video cards but there are commercially avaiable cards that allow you to roll your own. http://www.tilera.com/ , specifically one's based on the TILEPro64 . Though cost wise they are a bit higher end than commodity hardware. diana
Re: routing and pf at 10Gbps
2010/2/12 Diana Eichert deich...@wrench.com: I know there was some facetious comments regarding use of video cards but there are commercially avaiable cards that allow you to roll your own. http://www.tilera.com/ , specifically one's based on the TILEPro64 . Though cost wise they are a bit higher end than commodity hardware. Nice. Although it probably doesn't run OpenBSD. :-) This might well do: http://www.lannerinc.com/Network_Application_Platforms/x86_Network_Appliance/ 2U_Network_Appliances/FW-8910 Best Martin
Re: routing and pf at 10Gbps
On Fri, Feb 12, 2010 at 09:13:38AM -0500, Brad Tilley wrote: The rumor is that they are using CUDA on Nvidia graphics cards with advanced object oriented C++ and it is so fast that several developers are considering switching from C to C++ even for the kernel, after migrating to ZFS and replacing Perl in base with Java. Good times for OpenBSD indeed. Glad to see they are finally making some much needed improvements. Nope, entire kernel in elisp... (Unix device drivers written in C++ has already been done) -- Chris Dukes
Re: Latest snapshot doesn't work in Qemu under Fedora 12
Problem was of course reported immediately to Fedora. I know that it's not very useful for @openbsd, but a lot of us use it on real machines and under virtualization for testing/playing/whatelse. And Qemu was best VM platform for all BSDs for a longer time. So just OT info to pay attention. On Fri, Feb 12, 2010 at 9:29 PM, Ross Cameron abal...@gmail.com wrote: On Fri, Feb 12, 2010 at 9:24 PM, Tobias Ulmer tobi...@tmux.org wrote: Uhm, looks seriously off-topic on any mailinglist that ends in @openbsd.org. I hope you reported this to Fedora. On Fri, Feb 12, 2010 at 01:25:11PM +0100, Tomas Bodzar wrote: [ backtrace of crash in hand-rolled Drepper assembly ] Actually less to do with Fedora and more a query for the QEMU project and you're processor manufacturer I think. Seems to be an issue within KVM and and how its trying to use hardware to emulate a machine. B B A while back I ran OpenBSD without any issues under QEMU and VirtualBox on various recent Linux distros. Only thing is I had countless issues on Intel CPUs and none at all on the AMD CPUs,... seems the Intel virtualization enhancements are a bit behind. -- Opportunity is most often missed by people because it is dressed in overalls and looks like work. B B Thomas Alva Edison B B Inventor of 1093 patents, including: B B B B The light bulb, phonogram and motion pictures.
