Re: dump/restore - individual file
On Sun, 21 Aug 2011 18:22:15 -0500 Stefan Johnson tigerphoenixdra...@gmail.com wrote: # restore -xf root.dump './etc/pf.conf' restore: ./etc: File exists You have not read any tapes yet. Unless you know which volume your file(s) are on you should start with the last volume and work towards the first. Specify next volume #: And here I'm failing, why volume? Thank you for tips. jirib I believe restore with -x flag always asks for which volume, even if it is just a dump to a file. Just tell it to use volume 1 (type 1 then hit enter.) Also, I notice in your dump example, you dumped the raw device. You can just tell it to use / instead, and it will dump just fine as well. Hi, it would be nice if `restore' would know if it is restoring from a file or from a tape. Even `-s 1' doesn't supress prompting for volume number. This is from AIX man page: -s SeekBackup Specifies the backup to seek and restore on a multiple-backup tape archive. The -s flag is only applicable when the archive is written to a tape device. To use the -s flag properly, a no-rewind-on-close and no-retension-on-open tape device, such as /dev/rmt0.1 or /dev/rmt0.5, must be specified. If the -s flag is specified with a rewind tape device, the restore command displays an error message and exits with a nonzero return code. If a no-rewind tape device is used and the -s flag is not specified, a default value of -s 1 is used. The value of the SeekBackup parameter must be in the range of 1 to 100 inclusive. It is necessary to use a no-rewind-on-close, no-retension-on-open tape device because of the behavior of the -s flag. The value specified with -s is relative to the position of the tapes read/write head and not to an archives position on the tape. For example, to restore the first, second, and fourth backups from a multiple-backup tape archive, the respective values for the -s flag would be -s 1, -s 1, and -s 2. I cannot do C so I cannot send a diff :( jirib
Re: Expected throughput in an OpenBSD virtual server
Le Tue, 23 Aug 2011 19:21:32 +0200, Per-Olov SjC6holm p...@incedo.org a C)crit : Hello, Here we reach 400 MBits/s with a CPU rate ~70% but we run OpenBSD 4.9. How fast is your CPU ? cpu0: Intel(R) Xeon(R) CPU E5520 @ 2.27GHz, 2261.30 MHz It's a Dell R610 with 4Go RAM.
xpdf slow
Hello there, May someone help me with the following. My xpdf is very slow on pdf files from www.archive.org. pdf is attached. xpdfrc # #- display fonts # These map the Base-14 fonts to the Type 1 fonts that ship with # ghostscript. You'll almost certainly want to use something like # this, but you'll need to adjust this to point to wherever # ghostscript is installed on your system. (But if the fonts are # installed in a standard location, xpdf will find them # automatically.) displayFontT1 /usr/X11R6/lib/X11/fonts/misc/ displayFontT1 /usr/X11R6/lib/X11/fonts/75dpi/:unscaled displayFontT1 /usr/X11R6/lib/X11/fonts/100dpi/:unscaled displayFontT1 Times-Roman /usr/local/share/ghostscript/fonts/n021003l.pfb displayFontT1 Times-Italic /usr/local/share/ghostscript/fonts/n021023l.pfb displayFontT1 Times-Bold /usr/local/share/ghostscript/fonts/n021004l.pfb displayFontT1 Times-BoldItalic /usr/local/share/ghostscript/fonts/n021024l.pfb displayFontT1 Helvetica /usr/local/share/ghostscript/fonts/n019003l.pfb displayFontT1 Helvetica-Oblique /usr/local/share/ghostscript/fonts/n019023l.pfb displayFontT1 Helvetica /usr/local/share/ghostscript/fonts/n019003l.pfb displayFontT1 Helvetica-Oblique /usr/local/share/ghostscript/fonts/n019023l.pfb displayFontT1 Helvetica-Bold /usr/local/share/ghostscript/fonts/n019004l.pfb displayFontT1 Helvetica-BoldOblique /usr/local/share/ghostscript/fonts/n019024l.pfb displayFontT1 Courier /usr/local/share/ghostscript/fonts/n022003l.pfb displayFontT1 Courier-Oblique /usr/local/share/ghostscript/fonts/n022023l.pfb displayFontT1 Courier-Bold /usr/local/share/ghostscript/fonts/n022004l.pfb displayFontT1 Courier-BoldOblique /usr/local/share/ghostscript/fonts/n022024l.pfb displayFontT1 Symbol /usr/local/share/ghostscript/fonts/s05l.pfb displayFontT1 ZapfDingbats /usr/local/share/ghostscript/fonts/d05l.pfb displayFontT1 /usr/X11R6/lib/X11/fonts/Type1/ # If you need to display PDF files that refer to non-embedded fonts, # you should add one or more fontDir options to point to the # directories containing the font files. Xpdf will only look at .pfa, # .pfb, and .ttf files in those directories (other files will simply # be ignored). #fontDir/usr/local/fonts/bakoma [demime 1.01d removed an attachment of type application/pdf which had a name of appliedgeophysic00rast.pdf]
Re: CDDL vs GPL and maybe some implications for BSD?
On 8/23/2011 11:17 PM, Theo de Raadt wrote: Who are these ZFS and dtrace people? Are they HFT programmers? I really don't know. Do they help the project? I can assure you that they do not. Perhaps they want to use dtrace to find out where their ZFS data went...
Re: xpdf slow
On Wed, Aug 24, 2011 at 7:09 AM, igor denisov saufe...@gmail.com wrote: Hello there, May someone help me with the following. My xpdf is very slow on pdf files from www.archive.org. pdf is attached. xpdfrc # #- display fonts # These map the Base-14 fonts to the Type 1 fonts that ship with # ghostscript. B You'll almost certainly want to use something like # this, but you'll need to adjust this to point to wherever # ghostscript is installed on your system. B (But if the fonts are # installed in a standard location, xpdf will find them # automatically.) displayFontT1 B B B B B B B B B B B B B /usr/X11R6/lib/X11/fonts/misc/ displayFontT1 B B B B B B B B B B B B B /usr/X11R6/lib/X11/fonts/75dpi/:unscaled displayFontT1 /usr/X11R6/lib/X11/fonts/100dpi/:unscaled displayFontT1 Times-Roman /usr/local/share/ghostscript/fonts/n021003l.pfb displayFontT1 Times-Italic /usr/local/share/ghostscript/fonts/n021023l.pfb displayFontT1 Times-Bold /usr/local/share/ghostscript/fonts/n021004l.pfb displayFontT1 Times-BoldItalic /usr/local/share/ghostscript/fonts/n021024l.pfb displayFontT1 Helvetica /usr/local/share/ghostscript/fonts/n019003l.pfb displayFontT1 Helvetica-Oblique /usr/local/share/ghostscript/fonts/n019023l.pfb displayFontT1 Helvetica /usr/local/share/ghostscript/fonts/n019003l.pfb displayFontT1 Helvetica-Oblique /usr/local/share/ghostscript/fonts/n019023l.pfb displayFontT1 Helvetica-Bold /usr/local/share/ghostscript/fonts/n019004l.pfb displayFontT1 Helvetica-BoldOblique /usr/local/share/ghostscript/fonts/n019024l.pfb displayFontT1 Courier /usr/local/share/ghostscript/fonts/n022003l.pfb displayFontT1 Courier-Oblique /usr/local/share/ghostscript/fonts/n022023l.pfb displayFontT1 Courier-Bold /usr/local/share/ghostscript/fonts/n022004l.pfb displayFontT1 Courier-BoldOblique /usr/local/share/ghostscript/fonts/n022024l.pfb displayFontT1 Symbol /usr/local/share/ghostscript/fonts/s05l.pfb displayFontT1 ZapfDingbats /usr/local/share/ghostscript/fonts/d05l.pfb displayFontT1 B B B B B B B B B B B B B /usr/X11R6/lib/X11/fonts/Type1/ # If you need to display PDF files that refer to non-embedded fonts, # you should add one or more fontDir options to point to the # directories containing the font files. B Xpdf will only look at .pfa, # .pfb, and .ttf files in those directories (other files will simply # be ignored). #fontDir B B B B B B B B /usr/local/fonts/bakoma [demime 1.01d removed an attachment of type application/pdf which had a name of appliedgeophysic00rast.pdf] xpdf is always slow :P unrelated: have you tried zathura?, it's in ports, it seems a whole lot faster to me...
Re: CDDL vs GPL and maybe some implications for BSD?
On Wed, Aug 24, 2011 at 3:03 PM, Steve Shockley steve.shock...@shockley.net wrote: On 8/23/2011 11:17 PM, Theo de Raadt wrote: Who are these ZFS and dtrace people? Are they HFT programmers? B I really don't know. B Do they help the project? B I can assure you that they do not. Perhaps they want to use dtrace to find out where their ZFS data went... Heh. Nice one :-) Anyway maybe I used really bad wording. With ZFS and Dtrace I meant only that that there were couple of threads in misc@ when people asked for support of it and because of that new approach of Joyent to GPL/CDDL it seems possible in theory (not that we want it or need it). Regarding filesystems I like Hammer FS more ;-) . My post was meant completely licenses related. Because I just don't think that it's possible to mix CDDL with GPL in that way or even BSD with CDDL (thx to some patent related parts of that license. There's couple of projects which started from OpenSolaris code, but all of them are under CDDL which was created by Sun and Oracle get all of it. Maybe if some of those projects will be enough popular (more then Oracle stuff) then Oracle will step in with suits. At least CDDL sounds like good weapon for that for me.
Re: xpdf slow
xpdf is always slow :P unrelated: have you tried zathura?, it's in ports, it seems a whole lot faster to me... or mupdf, my current favorite.
Re: xpdf slow
On Wed, Aug 24, 2011 at 08:09:00AM -0400, igor denisov wrote: Hello there, May someone help me with the following. My xpdf is very slow on pdf files from www.archive.org. That is to be expected. Get the djvu files instead. There is no way to /decently/ use big image pdf files like those, even with acrobat reader and on the latest hardware.
Re: Expected throughput in an OpenBSD virtual server
On 24 aug 2011, at 12:01, Patrick Lamaiziere wrote: Le Tue, 23 Aug 2011 19:21:32 +0200, Per-Olov SjC6holm p...@incedo.org a C)crit : Hello, Here we reach 400 MBits/s with a CPU rate ~70% but we run OpenBSD 4.9. How fast is your CPU ? cpu0: Intel(R) Xeon(R) CPU E5520 @ 2.27GHz, 2261.30 MHz It's a Dell R610 with 4Go RAM. Maybe that is normal then (if we have similar quality on NICs, tuning and RAM) that I reach 400Mbit at 100% with one dedicated Xeon 5504 2GHz core. (I have two Intel(R) Xeon(R) CPU E5504 @ 2.00GHz stepping 05) You run on a physical server, right? As I run on a virtual server with near similar performance and a slower CPU it seems I have very good performance. It's hard for me to try faster CPUs just for fun as they are VERY expensive with faster ones... /Per-Olov
src build failure in -current (23.08)
Hello all, I wanted to update my -current, running in VirtualBox, and after a while it stopped with === usr.bin/write install -c -S -s -o root -g tty -m 2555 write /usr/bin/write install -c -o root -g bin -m 444 /usr/src/usr.bin/write/write.1 /usr/share/man/man1/write.1 === usr.bin/x99token install -c -S -s -o root -g bin -m 555 x99token /usr/bin/x99token install -c -o root -g bin -m 444 /usr/src/usr.bin/x99token/x99token.1 /usr/share/man/man1/x99token.1 === usr.bin/xargs install -c -S -s -o root -g bin -m 555 xargs /usr/bin/xargs install -c -o root -g bin -m 444 /usr/src/usr.bin/xargs/xargs.1 /usr/share/man/man1/xargs.1 === usr.bin/xinstall install -c -s -o root -g bin -m 555 xinstall /usr/bin/install install -c -o root -g bin -m 444 /usr/src/usr.bin/xinstall/install.1 /usr/share/man/man1/install.1 install: Permission denied *** Error code 1 Stop in /usr/src/usr.bin/xinstall: Exit status 1 (/usr/share/man/man1/install.1, line 53 of /usr/share/mk/bsd.man.mk) *** Error code 2 Stop in /usr/src/usr.bin: Exit status 2 (realinstall, line 48 of /usr/share/mk/bsd.subdir.mk) *** Error code 2 Stop in /usr/src: Exit status 2 (realinstall, line 48 of /usr/share/mk/bsd.subdir.mk) *** Error code 2 Stop in /usr/src: Exit status 2 (build, line 79 of Makefile) The steps I did were exacly as instructed in the FAQ, as for permissions, I'm building as root, so I don't know what the issue may be. OpenBSD 5.0-current (GENERIC.MP) #3: Tue Aug 23 22:31:35 EEST 2011 r...@openbsdv.my.domain:/usr/src/sys/arch/amd64/compile/GENERIC.MP real mem = 334430208 (318MB) avail mem = 311603200 (297MB) mainbus0 at root bios0 at mainbus0: SMBIOS rev. 2.5 @ 0xe1000 (5 entries) bios0: vendor innotek GmbH version VirtualBox date 12/01/2006 bios0: innotek GmbH VirtualBox acpi0 at bios0: rev 2 acpi0: sleep states S0 S5 acpi0: tables DSDT FACP APIC SSDT acpi0: wakeup devices acpitimer0 at acpi0: 3579545 Hz, 32 bits acpimadt0 at acpi0 addr 0xfee0: PC-AT compat cpu0 at mainbus0: apid 0 (boot processor) cpu0: AMD Athlon(tm) 64 X2 Dual Core Processor 5600+, 1005.54 MHz cpu0: FPU,VME,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,MTRR,PGE,MCA,CMOV,PAT,PSE36,CFLUSH,MMX,FXSR,SSE,SSE2,HTT,SSE3,NXE,FFXSR,LONG,3DNOW2,3DNOW cpu0: 64KB 64b/line 2-way I-cache, 64KB 64b/line 2-way D-cache, 512KB 64b/line 16-way L2 cache cpu0: ITLB 32 4KB entries fully associative, 8 4MB entries fully associative cpu0: DTLB 32 4KB entries fully associative, 8 4MB entries fully associative cpu0: apic clock running at 1000MHz cpu1 at mainbus0: apid 1 (application processor) cpu1: AMD Athlon(tm) 64 X2 Dual Core Processor 5600+, 1005.45 MHz cpu1: FPU,VME,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,MTRR,PGE,MCA,CMOV,PAT,PSE36,CFLUSH,MMX,FXSR,SSE,SSE2,HTT,SSE3,NXE,FFXSR,LONG,3DNOW2,3DNOW cpu1: 64KB 64b/line 2-way I-cache, 64KB 64b/line 2-way D-cache, 512KB 64b/line 16-way L2 cache cpu1: ITLB 32 4KB entries fully associative, 8 4MB entries fully associative cpu1: DTLB 32 4KB entries fully associative, 8 4MB entries fully associative ioapic0 at mainbus0: apid 2 pa 0xfec0, version 11, 24 pins ioapic0: misconfigured as apic 0, remapped to apid 2 acpiprt0 at acpi0: bus 0 (PCI0) acpicpu0 at acpi0 acpicpu1 at acpi0 acpibat0 at acpi0: BAT0 not present acpiac0 at acpi0: AC unit online pci0 at mainbus0 bus 0 pchb0 at pci0 dev 0 function 0 Intel 82441FX rev 0x02 pcib0 at pci0 dev 1 function 0 Intel 82371SB ISA rev 0x00 pciide0 at pci0 dev 1 function 1 Intel 82371AB IDE rev 0x01: DMA, channel 0 configured to compatibility, channel 1 configured to compatibility wd0 at pciide0 channel 0 drive 0: VBOX HARDDISK wd0: 128-sector PIO, LBA, 13312MB, 27262976 sectors wd0(pciide0:0:0): using PIO mode 4, Ultra-DMA mode 2 atapiscsi0 at pciide0 channel 1 drive 0 scsibus0 at atapiscsi0: 2 targets cd0 at scsibus0 targ 0 lun 0: VBOX, CD-ROM, 1.0 ATAPI 5/cdrom removable cd0(pciide0:1:0): using PIO mode 4, Ultra-DMA mode 2 vga1 at pci0 dev 2 function 0 InnoTek VirtualBox Graphics Adapter rev 0x00 wsdisplay0 at vga1 mux 1: console (80x25, vt100 emulation) wsdisplay0: screen 1-5 added (80x25, vt100 emulation) em0 at pci0 dev 3 function 0 Intel PRO/1000MT (82540EM) rev 0x02: apic 2 int 19, address 08:00:27:af:14:89 InnoTek VirtualBox Guest Service rev 0x00 at pci0 dev 4 function 0 not configured auich0 at pci0 dev 5 function 0 Intel 82801AA AC97 rev 0x01: apic 2 int 21, ICH AC97 cpu1: FPU,VME,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,MTRR,PGE,MCA,CMOV,PAT,PSE36,CFLUSH,MMX,FXSR,SSE,SSE2,HTT,SSE3,NXE,FFXSR,LONG,3DNOW2,3DNOW cpu1: 64KB 64b/line 2-way I-cache, 64KB 64b/line 2-way D-cache, 512KB 64b/line 16-way L2 cache cpu1: ITLB 32 4KB entries fully associative, 8 4MB entries fully associative cpu1: DTLB 32 4KB entries fully associative, 8 4MB entries fully associative ioapic0 at mainbus0: apid 2 pa 0xfec0, version 11, 24 pins ioapic0: misconfigured as apic 0, remapped to apid 2 acpiprt0 at acpi0: bus 0 (PCI0) acpicpu0 at acpi0 acpicpu1 at acpi0 acpibat0 at acpi0: BAT0 not present acpiac0
Re: Expected throughput in an OpenBSD virtual server
On 23 aug 2011, at 19:30, Tomas Bodzar wrote: On Tue, Aug 23, 2011 at 7:21 PM, Per-Olov Sjvholm p...@incedo.org wrote: On 23 aug 2011, at 10:54, Patrick Lamaiziere wrote: Le Mon, 22 Aug 2011 22:49:47 +0200, Per-Olov SjC6holm p...@incedo.org a C)crit : Hello, Have not tried current, but will try current as soon as I can. Also... I will try to do some laborations with CPU speed of the core the OpenBSD virtual machine has. This to see how the interrupts and throughput is related to the CPU speed of the allocated core. It would be nice to know if current is better with Intel em(4) cards. because of this commit : http://freshbsd.org/2011/04/13/00/19/01 Here we reach 400 MBits/s with a CPU rate ~70% but we run OpenBSD 4.9. Regards. How fast is your CPU ? Yes I can see the 1.254 commit with this came in after the 4.9 release that I use. I can try to see if I can measure any performance gain with this update. I will try this from aug 17... http://ftp.sunet.se/pub/os/OpenBSD/snapshots/i386/install50.iso Can't see that mirror here http://www.openbsd.org/ftp.html , it's better to use something more official I4ll get back [ YES !! More fun tests :D ] Regards Per-Olov Have tried it now... I tried the 5.0 snapshot from aug 17 with the improved em driver. Also tested with more allocated cores and the SMP kernel. Result on 5.0 snapshot with improved em driver: - SMP worse. Really sucks! _Dramatically_ reduced throughput. - One processor core (as most of my tests have used) An improvement, but very little. Maybe 10% better /Per-Olov
Re: Expected throughput in an OpenBSD virtual server
On Wed, Aug 24, 2011 at 7:00 PM, Per-Olov SjC6holm p...@incedo.org wrote: On 23 aug 2011, at 19:30, Tomas Bodzar wrote: On Tue, Aug 23, 2011 at 7:21 PM, Per-Olov Sjvholm p...@incedo.org wrote: On 23 aug 2011, at 10:54, Patrick Lamaiziere wrote: Le Mon, 22 Aug 2011 22:49:47 +0200, Per-Olov SjC6holm p...@incedo.org a C)crit : Hello, Have not tried current, but will try current as soon as I can. Also... I will try to do some laborations with CPU speed of the core the OpenBSD virtual machine has. This to see how the interrupts and throughput is related to the CPU speed of the allocated core. It would be nice to know if current is better with Intel em(4) cards. because of this commit : http://freshbsd.org/2011/04/13/00/19/01 Here we reach 400 MBits/s with a CPU rate ~70% but we run OpenBSD 4.9. Regards. How fast is your CPU ? Yes I can see the 1.254 commit with this came in after the 4.9 release that I use. I can try to see if I can measure any performance gain with this update. I will try this from aug 17... http://ftp.sunet.se/pub/os/OpenBSD/snapshots/i386/install50.iso Can't see that mirror here http://www.openbsd.org/ftp.html , it's better to use something more official I4ll get back [ YES !! More fun tests :D ] Regards Per-Olov Have tried it now... I tried the 5.0 snapshot from aug 17 with the improved em driver. Also tested with more allocated cores and the SMP kernel. Result on 5.0 snapshot with improved em driver: - SMP worse. Really sucks! _Dramatically_ reduced throughput. Will be fine to see systat ; systat mbufs ; netstat -m ; vmstat -i and compare them with previous version. Including dmesg (if something changed in dmesg) - One processor core (as most of my tests have used) An improvement, but very little. Maybe 10% better As stated in some of links and posts sent to you - SMP doesn't offer better throughput/sped automatically. You need to test on i386 non-SMP/SMP and amd64 non-SMP/SMP to see what's best. /Per-Olov
check status of mpbios
Hi Is there a way to check status if the mpbios is enabled or disabled ? I Checked man config, tried find and list in UKC This is seen in a dmesg, but doesn't say if it's enabled or not... --snip-- root@xanadu:~#dmesg |grep -i mpbios mpbios0 at bios0: Intel MP Specification 1.4 mpbios0: bus 0 is type PCI mpbios0: bus 1 is type ISA root@xanadu:~# --snip-- Can mpbios on or off affect network performance as mpbios play with interrupts. Or is it only related to the assignment? If so... If the system works without it (i.e mpbios disabled) are there any drawbacks to have it disabled if the system works ok with AND without it? /Per-Olov
Re: check status of mpbios
Use config: [nembus]$ config -e -f /bsd OpenBSD 4.9 (GENERIC) #671: Wed Mar 2 07:09:00 MST 2011 dera...@i386.openbsd.org:/usr/src/sys/arch/i386/compile/GENERIC Enter 'help' for information ukc find mpbios 352 mpbios0 at bios0 disable flags 0x0 ukc Cheers, Lars Hansson
Re: check status of mpbios
If you're running under KVM then ACPI shutdown will not work unless you disable mpbios. I always disable it with KVM since I don't allocate more than one CPU to a VM anyway. I haven't noticed any performance problems or other issues with it disabled. Cheers, Lars Hansson
Re: check status of mpbios
On Wed, Aug 24, 2011 at 12:30 PM, Per-Olov Sjvholm p...@incedo.org wrote: Hi Is there a way to check status if the mpbios is enabled or disabled ? I Checked man config, tried find and list in UKC Booting a qemu instance with it enabled and again with it disabled shows the following: Enabled: mpbios0 at bios0: Intel MP Specification 1.4 mpbios0: bus 0 is type ISA Disabled: mpbios at bios0 function 0x0 not configured It looks like if you disable it, dmesg will indicate such. Can mpbios on or off affect network performance as mpbios play with interrupts. Or is it only related to the assignment? If so... If the system works without it (i.e mpbios disabled) are there any drawbacks to have it disabled if the system works ok with AND without it? I'm not sure why you would want to disable it. I disable mine because I'm running it in qemu and the virtual machine apparently has a flaky mpbios. The virtual network cards it presents never receive the DHCP response from the virtual DHCP server with it turned on, and I get watchdog time out errors. Disabling it makes those go away. But again, that's on a virtual machine and not a production environment. Maybe someone else can speak to the wisdom of enabling/disabling it for your scenario. Stefan Johnson
Re: Expected throughput in an OpenBSD virtual server
If you want a comparison, I have run a small OpenBSD router under KVM and it easily sustained 80Mbps. It was connected to a FastEthernet switch so it couldnt actually go much higher. This was using the emulated e1000 KVM device and OpenBSD 4.9 release with mpbios iic disabled (disabling iic removes some annoying boot messages). The KVM server was a modest 3Ghz Core2 Duo with 4Gb RAM and a lot of other VM's running. Cheers, Lars
Re: Expected throughput in an OpenBSD virtual server
On 8/24/2011 11:31 AM, Lars Hansson wrote: If you want a comparison, I have run a small OpenBSD router under KVM and it easily sustained 80Mbps. It was connected to a FastEthernet switch so it couldnt actually go much higher. This was using the emulated e1000 KVM device and OpenBSD 4.9 release with mpbios iic disabled (disabling iic removes some annoying boot messages). The KVM server was a modest 3Ghz Core2 Duo with 4Gb RAM and a lot of other VM's running. Cheers, Lars You might see a bit more performance by load-balancing across two or more VMs. Where I work, we have a couple virtual routers / firewalls (these systems are internal-only so security on these machines isn't critical) I found that having 2 VMs load balanced in CARP gave more performance than doubling the resources on a single system. No tweaking was done on the systems which makes them much easier to maintain. Plus we can spin up more to add additional throughput without any downtime Recently we have added a few more firewalls to load balance with, each using the same configuration and adding performance to the cluster. We are seeing diminishing returns on each firewall we add (Overhead due to pfsync, CARP, etc) The VM host runs VMware ESXi on 16 GB RAM and 2 8-core Opterons (6128HE, 2 Ghz) and has two 10-Gb network cards (inside and outside) and 2x 1 Gb cards (Management and inter-host network). The VMs are configured with a single processor core and 256 Mb RAM and 3 Virtual Gb network cards (Inside, outside and pf-sync)
Re: Expected throughput in an OpenBSD virtual server
On 24 aug 2011, at 19:13, Tomas Bodzar wrote: On Wed, Aug 24, 2011 at 7:00 PM, Per-Olov Sjvholm p...@incedo.org wrote: On 23 aug 2011, at 19:30, Tomas Bodzar wrote: On Tue, Aug 23, 2011 at 7:21 PM, Per-Olov Sjvholm p...@incedo.org wrote: On 23 aug 2011, at 10:54, Patrick Lamaiziere wrote: Le Mon, 22 Aug 2011 22:49:47 +0200, Per-Olov SjC6holm p...@incedo.org a C)crit : Hello, Have not tried current, but will try current as soon as I can. Also... I will try to do some laborations with CPU speed of the core the OpenBSD virtual machine has. This to see how the interrupts and throughput is related to the CPU speed of the allocated core. It would be nice to know if current is better with Intel em(4) cards. because of this commit : http://freshbsd.org/2011/04/13/00/19/01 Here we reach 400 MBits/s with a CPU rate ~70% but we run OpenBSD 4.9. Regards. How fast is your CPU ? Yes I can see the 1.254 commit with this came in after the 4.9 release that I use. I can try to see if I can measure any performance gain with this update. I will try this from aug 17... http://ftp.sunet.se/pub/os/OpenBSD/snapshots/i386/install50.iso Can't see that mirror here http://www.openbsd.org/ftp.html , it's better to use something more official I4ll get back [ YES !! More fun tests :D ] Regards Per-Olov Have tried it now... I tried the 5.0 snapshot from aug 17 with the improved em driver. Also tested with more allocated cores and the SMP kernel. Result on 5.0 snapshot with improved em driver: - SMP worse. Really sucks! _Dramatically_ reduced throughput. Will be fine to see systat ; systat mbufs ; netstat -m ; vmstat -i and compare them with previous version. Including dmesg (if something changed in dmesg) - One processor core (as most of my tests have used) An improvement, but very little. Maybe 10% better As stated in some of links and posts sent to you - SMP doesn't offer better throughput/sped automatically. You need to test on i386 non-SMP/SMP and amd64 non-SMP/SMP to see what's best. /Per-Olov YES, YES and YES again !!! I have done a huge mistake during my tests. To much kernel copying... The result was that the kernel with disabled mpbios was /bsd.old. Very embarrassing. I have now a throughput of no less than 560Mbit / s. And that is through the VIRTUAL firewall with more than 50% IDLE CPU. Y e e e e e e s s ! How is really possible. But it is... ### Summary: ### - KVM virtualized STOCK OpenBSD 4.9 + Stable updates + sysctl.conf tuning + disabled mpbios. running uniprocesor kernel - 324 rows PF ruleset - 2 Intel PRO/1000 MT (82574L) desktop NICs used through PCI passthrough from the KVM virtualization host - OpenBSD have got 512MB RAM, One CPU core from host (Xeon 5504 2.0Ghz) Test: An SCP with the crypto overhead (default crypto) you get from A 64 bit SuseLinux through the firewall to my Macbook pro (quadcore i7 2.2GHz 8GM RAM, OCZ-Vertex 3 SSD disk). Several tests with DVD ISO files between 3-6 GB i size. 540Mbit was the _lowest_ average speed in the test and 560 Mbit / s was the highest # I am really satisfied with this. I was going to test FreeBSD beta 9 with its PF 4.5 just for fun. But I will skip that when the results ended up this good. OpenBSD really indeed perform V E R Y well in this area. Per-Olov
Inscripciones Congreso Nacional Internet Marketing
186135 [IMAGE] WSI, Pms de Mixico Adsmedia presentan Capacitacisn Efectiva de Mixico presenta: Congreso Nacional Internet Marketing Evolution Presentando las tematicas y tendencias mas innovadoras que le permitan desarrollar una estrategia de MKT Digital apropiada a su necesidad. Presentacisn Exclusiva: 30 de Septiembre Ciudad de Mixico Traemos los mejores eventos para usted, conozca los beneficios de capacitarse con los mejores! Empresa Registrada ante la STPS Reg. COLG640205CP30005 Smguenos en Twitter@pmscapacitacion o bien en Facebook PMS de Mixico !Solicite Mayores Informes! Por favor responda este e-mail con los datos siguientes. Empresa: Nombre: Telifono: Email: Nzmero de Interesados: En breve recibira la informacisn completa de este inigualable evento. Comunmquese a los telifonos y con gusto uno de nuestros ejecutivos le atendera. Telifonos: (0133) 8851-2365, (0133) 8851-2741, (0133) 1568-4647. Copyright (C) 2011, PMS Capacitacisn Efectiva de Mixico S.C. Derechos Reservados. PMS de Mixico, El logo de PMS de Mixico son marcas registradas. ADVERTENCIA PMS de Mixico no cuenta con alianzas estratigicas de ningzn tipo dentro de la Republica Mexicana. NO SE DEJE ENGAQAR - DIGA NO A LA PIRATERIA. Todos los logotipos, marcas comerciales e imagenes son propiedad de sus respectivas corporaciones y se utilizan con fines informativos solamente. Este Mensaje ha sido enviado a misc@openbsd.org como usuario de Pms de Mixico o bien un usuario le refiris para recibir este boletmn. Como usuario de Pms de Mixico, en este acto autoriza de manera expresa que Pms de Mixico le puede contactar vma correo electrsnico u otros medios. Si usted ha recibido este mensaje por error, haga caso omiso de el y reporte su cuenta respondiendo este correo con el subject BAJAMKT Unsubscribe to this mailing list, reply a blank message with the subject UNSUBSCRIBE BAJAMKT Tenga en cuenta que la gestisn de nuestras bases de datos es de suma importancia y no es intencisn de la empresa la inconformidad del receptor. [demime 1.01d removed an attachment of type image/jpeg which had a name of evolution2.jpg]
Re: Expected throughput in an OpenBSD virtual server
On Wed, Aug 24, 2011 at 07:00:09PM +0200, Per-Olov SjC6holm wrote: - SMP worse. Really sucks! _Dramatically_ reduced throughput. This is probably a result of you testing a virtualised guest rather than real hardware. - One processor core (as most of my tests have used) An improvement, but very little. Maybe 10% better 10% is fantastic. What were you expecting? 10x improvement from a network driver change? All the easy optimizations have already been done.
Why am I not surprised?
I recently saw the Full Disclosure mailing list discussion of the Apache DoS vuln. (http://seclists.org/fulldisclosure/2011/Aug/175) So I did pkg_add p5-Parallel-ForkManager on a 4.9 release i386, and ran the perl script from killapache_pl.bin (on the FD mail list). It had absolutely no visible effect on our Apache 1.3 running on a 5.0 snapshot (Generic #16) It didn't run out of memory, the server didn't crash and the CPU load seen by systat was minimal (1%). As the title says Why am I not surprised? Thanks devs for fixing bugs before they have sec numbers, you've done it again! R/ *** NOTE *** Please DO NOT CC me. I am subscribed to the list. Mail to the sender address that does not originate at the list server is tarpitted. The reply-to: address is provided for those who feel compelled to reply off list. Thankyou. Rod/ --- This life is not the real thing. It is not even in Beta. If it was, then OpenBSD would already have a man page for it.