Re: Inphi CS4223 for 4x 10GbE SFP+
Hi folks, below you can find the summary of "openssl speed" on the network appliance. Speed is not amazing, but AFAIU "openssl speed" is single-threaded. The CPU has 8 cores (no hyperthreading). Assuming IPsec encryption/decryption is running in kernel space, I wonder if the OpenBSD kernel can make use of the 8 cores for running several IPsec connections in parallel? Does it use AES? Regards Harri Intel(R) Atom(TM) CPU C3758 @ 2.20GHz, 2195.40 MHz, 06-5f-01 8 cores LibreSSL 3.2.2 built on: date not available options:bn(64,64) rc4(16x,int) des(idx,cisc,16,int) aes(partial) idea(int) blowfish(idx) compiler: information not available The 'numbers' are in 1000s of bytes per second processed. type 16 bytes 64 bytes256 bytes 1024 bytes 8192 bytes md2 0.00 0.00 0.00 0.00 0.00 md4 13724.16k45836.82k 115244.57k 185000.74k 224988.79k md5 12057.24k44613.25k 136613.93k 278648.09k 399437.57k hmac(md5)12879.60k47239.51k 141646.50k 283716.38k 400684.06k sha1 14261.27k48934.66k 126469.61k 210988.57k 261128.85k rmd1607478.71k19132.30k36135.97k46448.78k50673.37k rc4 221676.80k 361020.98k 420244.07k 435180.27k 439858.69k des cbc 24940.07k25926.00k26213.89k26296.73k26323.26k des ede3 9125.12k 9257.70k 9296.80k 9306.83k 9310.58k idea cbc 19172.98k19989.11k20185.22k20235.06k20251.39k seed cbc 0.00 0.00 0.00 0.00 0.00 rc2 cbc 6654.11k 6724.98k 6744.20k 6749.21k 6752.28k rc5-32/12 cbc0.00 0.00 0.00 0.00 0.00 blowfish cbc 28152.30k29404.87k29758.43k29873.58k29907.60k cast cbc 32971.96k34915.95k35399.95k35561.38k35606.62k aes-128 cbc 42748.35k47506.54k49266.14k 123527.74k 124700.75k aes-192 cbc 36277.25k39905.49k41139.80k 103818.63k 105167.86k aes-256 cbc 31742.60k34425.15k35314.65k90007.22k90667.21k camellia-128 cbc45902.96k76808.12k92168.33k97341.92k 98943.57k camellia-192 cbc40179.04k62497.28k72516.04k75711.36k 76659.16k camellia-256 cbc40040.61k62499.19k72515.95k75711.36k 76678.21k sha256 17433.04k41804.06k73496.15k90807.03k97541.95k sha512 14251.64k57007.97k93895.44k 133096.53k 152066.38k whirlpool13191.30k28503.96k47912.31k57710.39k61385.57k aes-128 ige 42754.84k44870.36k45810.90k45989.51k46038.50k aes-192 ige 36277.18k38005.20k38754.83k38883.08k38926.97k aes-256 ige 31741.82k33237.39k33254.74k33254.83k33255.17k ghash 325142.67k 836113.05k 1256164.95k 1443524.30k 1517196.50k aes-128 gcm 42352.61k 149903.52k 379077.66k 617644.48k 751160.13k aes-256 gcm 40132.77k 141596.79k 342723.27k 538803.63k 641956.15k chacha20 poly130512735.36k48161.34k91694.86k 119161.28k 130459.64k signverifysign/s verify/s rsa 512 bits 0.000215s 0.23s 4643.0 44006.6 rsa 1024 bits 0.000546s 0.53s 1830.9 18834.8 rsa 2048 bits 0.003018s 0.000164s331.4 6113.8 rsa 4096 bits 0.028494s 0.000586s 35.1 1705.6 signverifysign/s verify/s dsa 512 bits 0.000324s 0.000219s 3083.5 4561.2 dsa 1024 bits 0.000518s 0.000409s 1929.2 2447.1 dsa 2048 bits 0.001207s 0.001104s828.6905.7 signverifysign/s verify/s 160 bit ecdsa (secp160r1) 0.0015s 0.0011s671.4870.5 192 bit ecdsa (nistp192) 0.0018s 0.0014s562.5724.7 224 bit ecdsa (nistp224) 0.0023s 0.0018s433.5569.6 256 bit ecdsa (nistp256) 0.0026s 0.0020s379.7503.0 384 bit ecdsa (nistp384) 0.0051s 0.0035s196.5284.0 521 bit ecdsa (nistp521) 0.0102s 0.0066s 97.8151.6 163 bit ecdsa (nistk163) 0.0085s 0.0058s118.3171.9 233 bit ecdsa (nistk233) 0.0208s 0.0142s 48.0 70.4 283 bit ecdsa (nistk283) 0.0355s 0.0237s 28.1 42.2 409 bit ecdsa (nistk409) 0.0970s 0.0646s 10.3 15.5 571 bit ecdsa (nistk571) 0.2271s 0.1517s 4.4 6.6 163 bit ecdsa (nistb163) 0.0084s 0.0056s118.6177.1 233 bit ecdsa (nistb233) 0.0208s 0.0140s 48.2 71.3 283 bit ecdsa (nistb283) 0.0355s 0.0242s 28.1 41.3 409 bit ecdsa (nistb409) 0.0972s 0.0646s 10.3 15.5 571 bit ecdsa (nistb571) 0.2267s 0.1518s 4.4 6.6 op op/s 160 bit ecdh (secp160r1) 0.0013s774.4 192 bit ecdh (nistp192) 0.0015s648.7 224 bit ecdh (nistp224) 0.0020s492.4 256 bit ecdh (ni
Re: Inphi CS4223 for 4x 10GbE SFP+
Hello, re bypass mechanisms on on other platforms they can be just purely passive relays, that when power is attached to the system and the bios /EFI firmware confirms load (after the beep) an 8pole relay (that is normally closed electrically linking two RJ45 ports together, it can be useful in scenarios if you have only 1 interface from an uplink provider and only have routers with a single power supply each and you want to create a failsafe failover... I tend to use a scenario where the OS replicates the connectivity when the OS loads, i.e. place the 2 interfaces that are in the same bypass group into a bridge... one has to be careful not to create loops with that type of config... as far as im aware there is usually dip switches or jumper pins on the mainboard to facilitate it... sorry for going off on a tangent here.. but when I heard bypass I thought I would share some of my humble experience here... All the Best Tom On Tue, 20 Oct 2020 at 13:39, Stuart Henderson wrote: > On 2020-10-20, Harald Dunkel wrote: > > On 10/19/20 9:46 PM, Stuart Henderson wrote: > >> On 2020-10-19, Harald Dunkel wrote: > >>> > >>> What would these bypass problems look like? Hopefully the bypass > feature > >>> can be turned off/ignored. > >> > >> If there are problems then possibly 2 of the ports either won't work > >> or will be connected directly to 2 of the other ports until a magic > >> command is sent somehow (either gpio or via some memory mapped io > >> port I guess, I don't know the hardware). > >> > > > > You mean the bypass might be active, even though its not configured and > > power is on? That sounds like a fatal problem to me. Is this restricted > > to OpenBSD or are other operating systems affected as well? > > I don't know how it works on this hardware. The general idea of bypass > NICs is so that they connect ports straight-through if the OS is not > running correctly, so it depends how they detect whether the OS is running > as to whether that will work. > > One would hope that it can be disabled if necessary, but one would also > hope that BIOS/firmware vendors don't make silly mistakes and experience > has shown that this is not always the case ;) > > It will probably be OK. But with new hardware, who knows! > > -- Kindest regards, Tom Smyth.
Re: Inphi CS4223 for 4x 10GbE SFP+
On 2020-10-21, Harald Dunkel wrote: >> dmesg would be of interest :) > > See attachment. Product web site: > > https://www.ibase.com.tw/english/ProductDetail/NetworkAppliance/FWA8506 > > OpenBSD 6.8 booted from USB cdrom and installed fine. I didn't try > the USB installer image. > > The host was preconfigured with serial console enabled. 115200 8N1. > There was no VGA adapter included. There is no bezel for a VGA socket, > either. There is however a bezel for a PCI card included. > > Hope this helps Nice, thanks. That looks like it should make a pretty decent router/firewall.
Re: Inphi CS4223 for 4x 10GbE SFP+
> Hope this helps How much did you pay per unit, please?
Re: Inphi CS4223 for 4x 10GbE SFP+
On 10/19/20 4:40 PM, Stuart Henderson wrote: On 2020-10-19, Harald Dunkel wrote: Hi folks, I am about to order 2 network appliances, providing an "Inphi CS4223 for 4x 10GbE SFP+". dmesg would be of interest :) See attachment. Product web site: https://www.ibase.com.tw/english/ProductDetail/NetworkAppliance/FWA8506 OpenBSD 6.8 booted from USB cdrom and installed fine. I didn't try the USB installer image. The host was preconfigured with serial console enabled. 115200 8N1. There was no VGA adapter included. There is no bezel for a VGA socket, either. There is however a bezel for a PCI card included. Hope this helps Regards Harri OpenBSD 6.8 (GENERIC.MP) #98: Sun Oct 4 18:13:26 MDT 2020 dera...@amd64.openbsd.org:/usr/src/sys/arch/amd64/compile/GENERIC.MP real mem = 17132859392 (16339MB) avail mem = 16598568960 (15829MB) random: good seed from bootblocks mpath0 at root scsibus0 at mpath0: 256 targets mainbus0 at root bios0 at mainbus0: SMBIOS rev. 3.0 @ 0x7f2f4000 (52 entries) bios0: vendor American Megatrends Inc. version "5.13" date 03/06/2018 bios0: Default string Default string acpi0 at bios0: ACPI 6.1 acpi0: sleep states S0 S4 S5 acpi0: tables DSDT FACP FPDT FIDT MCFG WDAT ECDT APIC BDAT HPET UEFI SSDT DMAR SPCR HEST BERT ERST EINJ WSMT acpi0: wakeup devices PEX2(S4) XHC1(S4) LAN0(S4) LAN1(S4) LAN2(S4) LAN3(S4) acpitimer0 at acpi0: 3579545 Hz, 24 bits acpimcfg0 at acpi0 acpimcfg0: addr 0xe000, bus 0-255 acpiec0 at acpi0 acpimadt0 at acpi0 addr 0xfee0: PC-AT compat cpu0 at mainbus0: apid 0 (boot processor) cpu0: Intel(R) Atom(TM) CPU C3758 @ 2.20GHz, 2195.39 MHz, 06-5f-01 cpu0: FPU,VME,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,PBE,SSE3,PCLMUL,DTES64,MWAIT,DS-CPL,VMX,EST,TM2,SSSE3,SDBG,CX16,xTPR,PDCM,SSE4.1,SSE4.2,x2APIC,MOVBE,POPCNT,DEADLINE,AES,XSAVE,RDRAND,NXE,PAGE1GB,RDTSCP,LONG,LAHF,3DNOWP,PERF,ITSC,FSGSBASE,TSC_ADJUST,SMEP,ERMS,MPX,RDSEED,SMAP,CLFLUSHOPT,PT,SHA,IBRS,IBPB,STIBP,SENSOR,ARAT,XSAVEOPT,XSAVEC,XGETBV1,XSAVES cpu0: 2MB 64b/line 16-way L2 cache cpu0: cannot disable silicon debug cpu0: smt 0, core 0, package 0 mtrr: Pentium Pro MTRR support, 10 var ranges, 88 fixed ranges cpu0: apic clock running at 25MHz cpu0: mwait min=64, max=64, C-substates=0.2.0.2, IBE cpu1 at mainbus0: apid 4 (application processor) cpu1: Intel(R) Atom(TM) CPU C3758 @ 2.20GHz, 2195.00 MHz, 06-5f-01 cpu1: FPU,VME,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,PBE,SSE3,PCLMUL,DTES64,MWAIT,DS-CPL,VMX,EST,TM2,SSSE3,SDBG,CX16,xTPR,PDCM,SSE4.1,SSE4.2,x2APIC,MOVBE,POPCNT,DEADLINE,AES,XSAVE,RDRAND,NXE,PAGE1GB,RDTSCP,LONG,LAHF,3DNOWP,PERF,ITSC,FSGSBASE,TSC_ADJUST,SMEP,ERMS,MPX,RDSEED,SMAP,CLFLUSHOPT,PT,SHA,IBRS,IBPB,STIBP,SENSOR,ARAT,XSAVEOPT,XSAVEC,XGETBV1,XSAVES cpu1: 2MB 64b/line 16-way L2 cache cpu1: cannot disable silicon debug cpu1: smt 0, core 2, package 0 cpu2 at mainbus0: apid 8 (application processor) cpu2: Intel(R) Atom(TM) CPU C3758 @ 2.20GHz, 2195.00 MHz, 06-5f-01 cpu2: FPU,VME,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,PBE,SSE3,PCLMUL,DTES64,MWAIT,DS-CPL,VMX,EST,TM2,SSSE3,SDBG,CX16,xTPR,PDCM,SSE4.1,SSE4.2,x2APIC,MOVBE,POPCNT,DEADLINE,AES,XSAVE,RDRAND,NXE,PAGE1GB,RDTSCP,LONG,LAHF,3DNOWP,PERF,ITSC,FSGSBASE,TSC_ADJUST,SMEP,ERMS,MPX,RDSEED,SMAP,CLFLUSHOPT,PT,SHA,IBRS,IBPB,STIBP,SENSOR,ARAT,XSAVEOPT,XSAVEC,XGETBV1,XSAVES cpu2: 2MB 64b/line 16-way L2 cache cpu2: cannot disable silicon debug cpu2: smt 0, core 4, package 0 cpu3 at mainbus0: apid 12 (application processor) cpu3: Intel(R) Atom(TM) CPU C3758 @ 2.20GHz, 2195.00 MHz, 06-5f-01 cpu3: FPU,VME,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,PBE,SSE3,PCLMUL,DTES64,MWAIT,DS-CPL,VMX,EST,TM2,SSSE3,SDBG,CX16,xTPR,PDCM,SSE4.1,SSE4.2,x2APIC,MOVBE,POPCNT,DEADLINE,AES,XSAVE,RDRAND,NXE,PAGE1GB,RDTSCP,LONG,LAHF,3DNOWP,PERF,ITSC,FSGSBASE,TSC_ADJUST,SMEP,ERMS,MPX,RDSEED,SMAP,CLFLUSHOPT,PT,SHA,IBRS,IBPB,STIBP,SENSOR,ARAT,XSAVEOPT,XSAVEC,XGETBV1,XSAVES cpu3: 2MB 64b/line 16-way L2 cache cpu3: cannot disable silicon debug cpu3: smt 0, core 6, package 0 cpu4 at mainbus0: apid 16 (application processor) cpu4: Intel(R) Atom(TM) CPU C3758 @ 2.20GHz, 2195.00 MHz, 06-5f-01 cpu4: FPU,VME,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,PBE,SSE3,PCLMUL,DTES64,MWAIT,DS-CPL,VMX,EST,TM2,SSSE3,SDBG,CX16,xTPR,PDCM,SSE4.1,SSE4.2,x2APIC,MOVBE,POPCNT,DEADLINE,AES,XSAVE,RDRAND,NXE,PAGE1GB,RDTSCP,LONG,LAHF,3DNOWP,PERF,ITSC,FSGSBASE,TSC_ADJUST,SMEP,ERMS,MPX,RDSEED,SMAP,CLFLUSHOPT,PT,SHA,IBRS,IBPB,STIBP,SENSOR,ARAT,XSAVEOPT,XSAVEC,XGETBV1,XSAVES cpu4: 2MB 64b/line 16-way L2 cache cpu4: cannot disable silicon debug cpu4: smt 0, core 8, package 0 cpu5 at mainbus0: apid 20 (application processor) cpu5: Intel(R) Atom(TM) CPU C3758 @ 2.20GHz, 2
Re: Inphi CS4223 for 4x 10GbE SFP+
On 2020-10-20, Harald Dunkel wrote: > On 10/19/20 9:46 PM, Stuart Henderson wrote: >> On 2020-10-19, Harald Dunkel wrote: >>> >>> What would these bypass problems look like? Hopefully the bypass feature >>> can be turned off/ignored. >> >> If there are problems then possibly 2 of the ports either won't work >> or will be connected directly to 2 of the other ports until a magic >> command is sent somehow (either gpio or via some memory mapped io >> port I guess, I don't know the hardware). >> > > You mean the bypass might be active, even though its not configured and > power is on? That sounds like a fatal problem to me. Is this restricted > to OpenBSD or are other operating systems affected as well? I don't know how it works on this hardware. The general idea of bypass NICs is so that they connect ports straight-through if the OS is not running correctly, so it depends how they detect whether the OS is running as to whether that will work. One would hope that it can be disabled if necessary, but one would also hope that BIOS/firmware vendors don't make silly mistakes and experience has shown that this is not always the case ;) It will probably be OK. But with new hardware, who knows!
Re: Inphi CS4223 for 4x 10GbE SFP+
On 10/19/20 9:46 PM, Stuart Henderson wrote: On 2020-10-19, Harald Dunkel wrote: What would these bypass problems look like? Hopefully the bypass feature can be turned off/ignored. If there are problems then possibly 2 of the ports either won't work or will be connected directly to 2 of the other ports until a magic command is sent somehow (either gpio or via some memory mapped io port I guess, I don't know the hardware). You mean the bypass might be active, even though its not configured and power is on? That sounds like a fatal problem to me. Is this restricted to OpenBSD or are other operating systems affected as well? Regards Harri
Re: Inphi CS4223 for 4x 10GbE SFP+
On 2020-10-19, Harald Dunkel wrote: > On 10/19/20 4:36 PM, Stuart Henderson wrote: >> On 2020-10-19, Tom Smyth wrote: >>> Hi Harald, check the Atom processor and make sure that it is not one >>> of those ones that fail after a while (some electrical issue) ... >> >> It isn't. >> >> > Anyway, some more precise information about the affected models would be > highly appreciated. > > Regards > Harri > > Denverton Atoms (C2000). Usual fix for those seems to be to pull-up LPC_CLKOUT0 or LPC_CLKOUT1 with approx 100 ohms to +3.3v. See https://www.eevblog.com/forum/microcontrollers/intel-atom-c2000-failures/
Re: Inphi CS4223 for 4x 10GbE SFP+
On 2020-10-19, Harald Dunkel wrote: > On 10/19/20 4:40 PM, Stuart Henderson wrote: >> >> I can't say for sure but I think there's a high chance that the 10G >> will work, and at least some of the 1G will work, but you might run into >> problems with the 1G "bypass" ports. >> >> dmesg would be of interest :) >> >> > > Of course. The host are already on the way. I will post the dmesg output > asap. > > What would these bypass problems look like? Hopefully the bypass feature > can be turned off/ignored. If there are problems then possibly 2 of the ports either won't work or will be connected directly to 2 of the other ports until a magic command is sent somehow (either gpio or via some memory mapped io port I guess, I don't know the hardware). > Anything else I should look for? Nothing in particular that I can think of.
Re: Inphi CS4223 for 4x 10GbE SFP+
On 10/19/20 4:36 PM, Stuart Henderson wrote: On 2020-10-19, Tom Smyth wrote: Hi Harald, check the Atom processor and make sure that it is not one of those ones that fail after a while (some electrical issue) ... It isn't. Anyway, some more precise information about the affected models would be highly appreciated. Regards Harri
Re: Inphi CS4223 for 4x 10GbE SFP+
On 10/19/20 4:40 PM, Stuart Henderson wrote: I can't say for sure but I think there's a high chance that the 10G will work, and at least some of the 1G will work, but you might run into problems with the 1G "bypass" ports. dmesg would be of interest :) Of course. The host are already on the way. I will post the dmesg output asap. What would these bypass problems look like? Hopefully the bypass feature can be turned off/ignored. Anything else I should look for? Regards Harri
Re: Inphi CS4223 for 4x 10GbE SFP+
On Mon, Oct 19, 2020 at 10:55 AM Stuart Henderson wrote: > > On 2020-10-19, Harald Dunkel wrote: > > Hi folks, > > > > I am about to order 2 network appliances, providing an > > "Inphi CS4223 for 4x 10GbE SFP+". > > This is the PHY (physical interface layer) not the NIC type itself. > Since the gigabit are listed as i211 (which *is* a NIC type) it would > seem likely they are attached to the main chipset. > > I can't say for sure but I think there's a high chance that the 10G > will work, and at least some of the 1G will work, but you might run into > problems with the 1G "bypass" ports. > > dmesg would be of interest :) > > 1G works over the SFP , I don't remember having a bypass port on the SFPs when i tested the thing Very difficult to have more speed, apparently some kernel quirks are limiting that according to comment in the code i saw. I tested against a dlink ethernet to SFP , on loopback and with some deverton based hardware. -- -- - Knowing is not enough; we must apply. Willing is not enough; we must do
Re: Inphi CS4223 for 4x 10GbE SFP+
On 2020-10-19, Harald Dunkel wrote: > Hi folks, > > I am about to order 2 network appliances, providing an > "Inphi CS4223 for 4x 10GbE SFP+". This is the PHY (physical interface layer) not the NIC type itself. Since the gigabit are listed as i211 (which *is* a NIC type) it would seem likely they are attached to the main chipset. I can't say for sure but I think there's a high chance that the 10G will work, and at least some of the 1G will work, but you might run into problems with the 1G "bypass" ports. dmesg would be of interest :)
Re: Inphi CS4223 for 4x 10GbE SFP+
On 2020-10-19, Tom Smyth wrote: > Hi Harald, check the Atom processor and make sure that it is not one > of those ones that fail after a while (some electrical issue) ... It isn't.
Re: Inphi CS4223 for 4x 10GbE SFP+
On Mon, Oct 19, 2020 at 01:28:50PM +0200, Harald Dunkel wrote: > Hi folks, > > I am about to order 2 network appliances, providing an > "Inphi CS4223 for 4x 10GbE SFP+". > > Does this ring a bell? Is this already supported by 6.8? Other > technical specs can be found on > > https://www.ibase.com.tw/english/ProductDetail/NetworkAppliance/FWA8506 Atom C3000 10 GbE is known as X553. Support was added in revision 1.161 date: 2020/03/02 01:59:01; author: jmatthew; state: Exp; lines: +134 -83; commitid: xmdy2UWGGO2CwfiN; Update ix(4) from freebsd to add support for X553 controllers. Tested on 82599 (sfp+) and X540 (baseT) by me and Hrvoje Popovski, and on X553 by sthen@ and abieber@, and possibly more via snapshots ok sthen@ mikeb@ And is present in 6.7 and 6.8. > > BTW, congratulations to the new release > > > Regards > Harri > >
Re: Inphi CS4223 for 4x 10GbE SFP+
Hi Harald, check the Atom processor and make sure that it is not one of those ones that fail after a while (some electrical issue) ... On Mon, 19 Oct 2020 at 12:48, Harald Dunkel wrote: > > Hi folks, > > I am about to order 2 network appliances, providing an > "Inphi CS4223 for 4x 10GbE SFP+". > > Does this ring a bell? Is this already supported by 6.8? Other > technical specs can be found on > > https://www.ibase.com.tw/english/ProductDetail/NetworkAppliance/FWA8506 > > BTW, congratulations to the new release > > > Regards > Harri > -- Kindest regards, Tom Smyth.
Inphi CS4223 for 4x 10GbE SFP+
Hi folks, I am about to order 2 network appliances, providing an "Inphi CS4223 for 4x 10GbE SFP+". Does this ring a bell? Is this already supported by 6.8? Other technical specs can be found on https://www.ibase.com.tw/english/ProductDetail/NetworkAppliance/FWA8506 BTW, congratulations to the new release Regards Harri