search

xebd / accel-ppp

High performance PPTP/L2TP/PPPoE/IPoE server for Linux
GNU General Public License v2.0
296 stars 108 forks source link

PPPoE: miscellaneous improvements #140

Open laarmen opened 4 years ago

laarmen commented 4 years ago

In the course of some work on the PPPoE subsystem regarding the configuration reload, I made various modifications to the codebase that are only loosely related. This PR is the first of several for these changes.

These patches shouldn't change anything to the behavior of the program, and are only aimed at easing the development.

laarmen commented 3 years ago

Hi, thank you for testing this, I appreciate it very much.

Could you share a bit more details about the error case? Is it on any client, or only some of them ? Are you running on amd64 or 32-bit x86?

micron10 commented 3 years ago

Hi Test on Proxmox latest version

cpu is Ryzen 7 1800X

in virtual machine is:

lscpu Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian Address sizes: 40 bits physical, 48 bits virtual CPU(s): 8 On-line CPU(s) list: 0-7 Thread(s) per core: 1 Core(s) per socket: 8 Socket(s): 1 NUMA node(s): 1 Vendor ID: AuthenticAMD CPU family: 23 Model: 1 Model name: AMD EPYC Processor Stepping: 2 CPU MHz: 3842.459 BogoMIPS: 7684.91 Hypervisor vendor: KVM Virtualization type: full L1d cache: 256 KiB L1i cache: 512 KiB L2 cache: 4 MiB L3 cache: 8 MiB NUMA node0 CPU(s): 0-7 Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Spec store bypass: Vulnerable Vulnerability Spectre v1: Vulnerable: __user pointer sanitization and usercopy barriers only; n o swapgs barriers Vulnerability Spectre v2: Vulnerable, STIBP: disabled Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse 36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rd tscp lm rep_good nopl cpuid extd_apicid pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hyperviso r lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch o svw topoext vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clfl ushopt sha_ni xsaveopt xsavec xgetbv1 arat

i have online one customer in this test server.

On Sun, Dec 20, 2020, 17:33 Simon Chopin notifications@github.com wrote:

Hi, thank you for testing this, I appreciate it very much.

Could you share a bit more details about the error case? Is it on any client, or only some of them ? Are you running on amd64 or 32-bit x86?

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/xebd/accel-ppp/pull/140#issuecomment-748622861, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADCWD5EYBI76OEIUIWNHB3TSVYKNJANCNFSM4OFPZQ4A .

micron10 commented 3 years ago

i try to change qemu cpu to intel SandyBridge and get same error

after remove patch all work fine

On Sun, Dec 20, 2020, 17:39 Martin Zaharinov micron10@gmail.com wrote:

Hi Test on Proxmox latest version

cpu is Ryzen 7 1800X

in virtual machine is:

lscpu Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian Address sizes: 40 bits physical, 48 bits virtual CPU(s): 8 On-line CPU(s) list: 0-7 Thread(s) per core: 1 Core(s) per socket: 8 Socket(s): 1 NUMA node(s): 1 Vendor ID: AuthenticAMD CPU family: 23 Model: 1 Model name: AMD EPYC Processor Stepping: 2 CPU MHz: 3842.459 BogoMIPS: 7684.91 Hypervisor vendor: KVM Virtualization type: full L1d cache: 256 KiB L1i cache: 512 KiB L2 cache: 4 MiB L3 cache: 8 MiB NUMA node0 CPU(s): 0-7 Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Spec store bypass: Vulnerable Vulnerability Spectre v1: Vulnerable: __user pointer sanitization and usercopy barriers only; n o swapgs barriers Vulnerability Spectre v2: Vulnerable, STIBP: disabled Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse 36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rd tscp lm rep_good nopl cpuid extd_apicid pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hyperviso r lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch o svw topoext vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clfl ushopt sha_ni xsaveopt xsavec xgetbv1 arat

i have online one customer in this test server.

On Sun, Dec 20, 2020, 17:33 Simon Chopin notifications@github.com wrote:

Hi, thank you for testing this, I appreciate it very much.

Could you share a bit more details about the error case? Is it on any client, or only some of them ? Are you running on amd64 or 32-bit x86?

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/xebd/accel-ppp/pull/140#issuecomment-748622861, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADCWD5EYBI76OEIUIWNHB3TSVYKNJANCNFSM4OFPZQ4A .

micron10 commented 3 years ago

Do you have idea from where is come this bug ? and do you have fix for them ?

На нд, 20.12.2020 г. в 18:54 ч. Martin Zaharinov micron10@gmail.com написа:

i try to change qemu cpu to intel SandyBridge and get same error

after remove patch all work fine

On Sun, Dec 20, 2020, 17:39 Martin Zaharinov micron10@gmail.com wrote:

Hi Test on Proxmox latest version

cpu is Ryzen 7 1800X

in virtual machine is:

lscpu Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian Address sizes: 40 bits physical, 48 bits virtual CPU(s): 8 On-line CPU(s) list: 0-7 Thread(s) per core: 1 Core(s) per socket: 8 Socket(s): 1 NUMA node(s): 1 Vendor ID: AuthenticAMD CPU family: 23 Model: 1 Model name: AMD EPYC Processor Stepping: 2 CPU MHz: 3842.459 BogoMIPS: 7684.91 Hypervisor vendor: KVM Virtualization type: full L1d cache: 256 KiB L1i cache: 512 KiB L2 cache: 4 MiB L3 cache: 8 MiB NUMA node0 CPU(s): 0-7 Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Spec store bypass: Vulnerable Vulnerability Spectre v1: Vulnerable: __user pointer sanitization and usercopy barriers only; n o swapgs barriers Vulnerability Spectre v2: Vulnerable, STIBP: disabled Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse 36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rd tscp lm rep_good nopl cpuid extd_apicid pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hyperviso r lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch o svw topoext vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clfl ushopt sha_ni xsaveopt xsavec xgetbv1 arat

i have online one customer in this test server.

On Sun, Dec 20, 2020, 17:33 Simon Chopin notifications@github.com wrote:

Hi, thank you for testing this, I appreciate it very much.

Could you share a bit more details about the error case? Is it on any client, or only some of them ? Are you running on amd64 or 32-bit x86?

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/xebd/accel-ppp/pull/140#issuecomment-748622861, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADCWD5EYBI76OEIUIWNHB3TSVYKNJANCNFSM4OFPZQ4A .

micron10 commented 3 years ago

Simon if you havw fix for this i will test

On Mon, Dec 21, 2020, 21:20 Martin Zaharinov micron10@gmail.com wrote:

Do you have idea from where is come this bug ? and do you have fix for them ?

На нд, 20.12.2020 г. в 18:54 ч. Martin Zaharinov micron10@gmail.com написа:

i try to change qemu cpu to intel SandyBridge and get same error

after remove patch all work fine

On Sun, Dec 20, 2020, 17:39 Martin Zaharinov micron10@gmail.com wrote:

Hi Test on Proxmox latest version

cpu is Ryzen 7 1800X

in virtual machine is:

lscpu Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian Address sizes: 40 bits physical, 48 bits virtual CPU(s): 8 On-line CPU(s) list: 0-7 Thread(s) per core: 1 Core(s) per socket: 8 Socket(s): 1 NUMA node(s): 1 Vendor ID: AuthenticAMD CPU family: 23 Model: 1 Model name: AMD EPYC Processor Stepping: 2 CPU MHz: 3842.459 BogoMIPS: 7684.91 Hypervisor vendor: KVM Virtualization type: full L1d cache: 256 KiB L1i cache: 512 KiB L2 cache: 4 MiB L3 cache: 8 MiB NUMA node0 CPU(s): 0-7 Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Spec store bypass: Vulnerable Vulnerability Spectre v1: Vulnerable: __user pointer sanitization and usercopy barriers only; n o swapgs barriers Vulnerability Spectre v2: Vulnerable, STIBP: disabled Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse 36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rd tscp lm rep_good nopl cpuid extd_apicid pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hyperviso r lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch o svw topoext vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clfl ushopt sha_ni xsaveopt xsavec xgetbv1 arat

i have online one customer in this test server.

On Sun, Dec 20, 2020, 17:33 Simon Chopin notifications@github.com wrote:

Hi, thank you for testing this, I appreciate it very much.

Could you share a bit more details about the error case? Is it on any client, or only some of them ? Are you running on amd64 or 32-bit x86?

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/xebd/accel-ppp/pull/140#issuecomment-748622861, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADCWD5EYBI76OEIUIWNHB3TSVYKNJANCNFSM4OFPZQ4A .

laarmen commented 3 years ago

I'll see what I can do after the holidays.

Le jeu. 24 déc. 2020 à 18:43, micron10 notifications@github.com a écrit :

Simon if you havw fix for this i will test

On Mon, Dec 21, 2020, 21:20 Martin Zaharinov micron10@gmail.com wrote:

Do you have idea from where is come this bug ? and do you have fix for them ?

На нд, 20.12.2020 г. в 18:54 ч. Martin Zaharinov micron10@gmail.com написа:

i try to change qemu cpu to intel SandyBridge and get same error

after remove patch all work fine

On Sun, Dec 20, 2020, 17:39 Martin Zaharinov micron10@gmail.com wrote:

Hi Test on Proxmox latest version

cpu is Ryzen 7 1800X

in virtual machine is:

lscpu Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian Address sizes: 40 bits physical, 48 bits virtual CPU(s): 8 On-line CPU(s) list: 0-7 Thread(s) per core: 1 Core(s) per socket: 8 Socket(s): 1 NUMA node(s): 1 Vendor ID: AuthenticAMD CPU family: 23 Model: 1 Model name: AMD EPYC Processor Stepping: 2 CPU MHz: 3842.459 BogoMIPS: 7684.91 Hypervisor vendor: KVM Virtualization type: full L1d cache: 256 KiB L1i cache: 512 KiB L2 cache: 4 MiB L3 cache: 8 MiB NUMA node0 CPU(s): 0-7 Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Spec store bypass: Vulnerable Vulnerability Spectre v1: Vulnerable: __user pointer sanitization and usercopy barriers only; n o swapgs barriers Vulnerability Spectre v2: Vulnerable, STIBP: disabled Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse 36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rd tscp lm rep_good nopl cpuid extd_apicid pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hyperviso r lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch o svw topoext vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clfl ushopt sha_ni xsaveopt xsavec xgetbv1 arat

i have online one customer in this test server.

On Sun, Dec 20, 2020, 17:33 Simon Chopin notifications@github.com wrote:

Hi, thank you for testing this, I appreciate it very much.

Could you share a bit more details about the error case? Is it on any client, or only some of them ? Are you running on amd64 or 32-bit x86?

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/xebd/accel-ppp/pull/140#issuecomment-748622861, or unsubscribe < https://github.com/notifications/unsubscribe-auth/ADCWD5EYBI76OEIUIWNHB3TSVYKNJANCNFSM4OFPZQ4A

.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/xebd/accel-ppp/pull/140#issuecomment-750934049, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAEQ4NOXTIZJJ5MUQ4LURPTSWN4SLANCNFSM4OFPZQ4A .

laarmen commented 3 years ago

Allright, this was a very silly mistake, and the reason I didn't catch it is that my test script failed silently even before getting to mounting a PPP.

That's what I get for trying to upstream my changes in small batches as early as possible: each PR isn't as heavily tested as it should :-/

On Thu, Dec 24, 2020 at 6:51 PM Simon Chopin chopin.simon@gmail.com wrote:

I'll see what I can do after the holidays.

Le jeu. 24 déc. 2020 à 18:43, micron10 notifications@github.com a écrit :

Simon if you havw fix for this i will test

On Mon, Dec 21, 2020, 21:20 Martin Zaharinov micron10@gmail.com wrote:

Do you have idea from where is come this bug ? and do you have fix for them ?

На нд, 20.12.2020 г. в 18:54 ч. Martin Zaharinov micron10@gmail.com написа:

i try to change qemu cpu to intel SandyBridge and get same error

after remove patch all work fine

On Sun, Dec 20, 2020, 17:39 Martin Zaharinov micron10@gmail.com wrote:

Hi Test on Proxmox latest version

cpu is Ryzen 7 1800X

in virtual machine is:

lscpu Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian Address sizes: 40 bits physical, 48 bits virtual CPU(s): 8 On-line CPU(s) list: 0-7 Thread(s) per core: 1 Core(s) per socket: 8 Socket(s): 1 NUMA node(s): 1 Vendor ID: AuthenticAMD CPU family: 23 Model: 1 Model name: AMD EPYC Processor Stepping: 2 CPU MHz: 3842.459 BogoMIPS: 7684.91 Hypervisor vendor: KVM Virtualization type: full L1d cache: 256 KiB L1i cache: 512 KiB L2 cache: 4 MiB L3 cache: 8 MiB NUMA node0 CPU(s): 0-7 Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Spec store bypass: Vulnerable Vulnerability Spectre v1: Vulnerable: __user pointer sanitization and usercopy barriers only; n o swapgs barriers Vulnerability Spectre v2: Vulnerable, STIBP: disabled Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse 36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rd tscp lm rep_good nopl cpuid extd_apicid pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hyperviso r lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch o svw topoext vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clfl ushopt sha_ni xsaveopt xsavec xgetbv1 arat

i have online one customer in this test server.

On Sun, Dec 20, 2020, 17:33 Simon Chopin notifications@github.com wrote:

Hi, thank you for testing this, I appreciate it very much.

Could you share a bit more details about the error case? Is it on any client, or only some of them ? Are you running on amd64 or 32-bit x86?

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/xebd/accel-ppp/pull/140#issuecomment-748622861, or unsubscribe < https://github.com/notifications/unsubscribe-auth/ADCWD5EYBI76OEIUIWNHB3TSVYKNJANCNFSM4OFPZQ4A

.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/xebd/accel-ppp/pull/140#issuecomment-750934049, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAEQ4NOXTIZJJ5MUQ4LURPTSWN4SLANCNFSM4OFPZQ4A .

micron10 commented 3 years ago

what do these updates change in operation? and whether these changes are already working?

On Mon, Jan 11, 2021, 20:53 Simon Chopin notifications@github.com wrote:

Allright, this was a very silly mistake, and the reason I didn't catch it is that my test script failed silently even before getting to mounting a PPP.

That's what I get for trying to upstream my changes in small batches as early as possible: each PR isn't as heavily tested as it should :-/

On Thu, Dec 24, 2020 at 6:51 PM Simon Chopin chopin.simon@gmail.com wrote:

I'll see what I can do after the holidays.

Le jeu. 24 déc. 2020 à 18:43, micron10 notifications@github.com a écrit :

Simon if you havw fix for this i will test

On Mon, Dec 21, 2020, 21:20 Martin Zaharinov micron10@gmail.com wrote:

Do you have idea from where is come this bug ? and do you have fix for them ?

На нд, 20.12.2020 г. в 18:54 ч. Martin Zaharinov micron10@gmail.com написа:

i try to change qemu cpu to intel SandyBridge and get same error

after remove patch all work fine

On Sun, Dec 20, 2020, 17:39 Martin Zaharinov micron10@gmail.com wrote:

Hi Test on Proxmox latest version

cpu is Ryzen 7 1800X

in virtual machine is:

lscpu Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian Address sizes: 40 bits physical, 48 bits virtual CPU(s): 8 On-line CPU(s) list: 0-7 Thread(s) per core: 1 Core(s) per socket: 8 Socket(s): 1 NUMA node(s): 1 Vendor ID: AuthenticAMD CPU family: 23 Model: 1 Model name: AMD EPYC Processor Stepping: 2 CPU MHz: 3842.459 BogoMIPS: 7684.91 Hypervisor vendor: KVM Virtualization type: full L1d cache: 256 KiB L1i cache: 512 KiB L2 cache: 4 MiB L3 cache: 8 MiB NUMA node0 CPU(s): 0-7 Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Spec store bypass: Vulnerable Vulnerability Spectre v1: Vulnerable: __user pointer sanitization and usercopy barriers only; n o swapgs barriers Vulnerability Spectre v2: Vulnerable, STIBP: disabled Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse 36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rd tscp lm rep_good nopl cpuid extd_apicid pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hyperviso r lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch o svw topoext vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clfl ushopt sha_ni xsaveopt xsavec xgetbv1 arat

i have online one customer in this test server.

On Sun, Dec 20, 2020, 17:33 Simon Chopin notifications@github.com wrote:

Hi, thank you for testing this, I appreciate it very much.

Could you share a bit more details about the error case? Is it on any client, or only some of them ? Are you running on amd64 or 32-bit x86?

— You are receiving this because you commented. Reply to this email directly, view it on GitHub <https://github.com/xebd/accel-ppp/pull/140#issuecomment-748622861 , or unsubscribe <

https://github.com/notifications/unsubscribe-auth/ADCWD5EYBI76OEIUIWNHB3TSVYKNJANCNFSM4OFPZQ4A

.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/xebd/accel-ppp/pull/140#issuecomment-750934049, or unsubscribe < https://github.com/notifications/unsubscribe-auth/AAEQ4NOXTIZJJ5MUQ4LURPTSWN4SLANCNFSM4OFPZQ4A

.

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/xebd/accel-ppp/pull/140#issuecomment-758151804, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADCWD5FAS25TITVN5G4B5B3SZNCJZANCNFSM4OFPZQ4A .

laarmen commented 3 years ago

These aren't supposed to have an effect in operations, it's simply patches to (in my view) improve the code readability and make further work easier. The initial PR description stated as much :-)

On Mon, Jan 11, 2021 at 9:32 PM micron10 notifications@github.com wrote:

what do these updates change in operation? and whether these changes are already working?

On Mon, Jan 11, 2021, 20:53 Simon Chopin notifications@github.com wrote:

Allright, this was a very silly mistake, and the reason I didn't catch it is that my test script failed silently even before getting to mounting a PPP.

That's what I get for trying to upstream my changes in small batches as early as possible: each PR isn't as heavily tested as it should :-/

On Thu, Dec 24, 2020 at 6:51 PM Simon Chopin chopin.simon@gmail.com wrote:

I'll see what I can do after the holidays.

Le jeu. 24 déc. 2020 à 18:43, micron10 notifications@github.com a écrit :

Simon if you havw fix for this i will test

On Mon, Dec 21, 2020, 21:20 Martin Zaharinov micron10@gmail.com wrote:

Do you have idea from where is come this bug ? and do you have fix for them ?

На нд, 20.12.2020 г. в 18:54 ч. Martin Zaharinov < micron10@gmail.com> написа:

i try to change qemu cpu to intel SandyBridge and get same error

after remove patch all work fine

On Sun, Dec 20, 2020, 17:39 Martin Zaharinov micron10@gmail.com wrote:

Hi Test on Proxmox latest version

cpu is Ryzen 7 1800X

in virtual machine is:

lscpu Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian Address sizes: 40 bits physical, 48 bits virtual CPU(s): 8 On-line CPU(s) list: 0-7 Thread(s) per core: 1 Core(s) per socket: 8 Socket(s): 1 NUMA node(s): 1 Vendor ID: AuthenticAMD CPU family: 23 Model: 1 Model name: AMD EPYC Processor Stepping: 2 CPU MHz: 3842.459 BogoMIPS: 7684.91 Hypervisor vendor: KVM Virtualization type: full L1d cache: 256 KiB L1i cache: 512 KiB L2 cache: 4 MiB L3 cache: 8 MiB NUMA node0 CPU(s): 0-7 Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Spec store bypass: Vulnerable Vulnerability Spectre v1: Vulnerable: __user pointer sanitization and usercopy barriers only; n o swapgs barriers Vulnerability Spectre v2: Vulnerable, STIBP: disabled Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse 36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rd tscp lm rep_good nopl cpuid extd_apicid pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hyperviso r lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch o svw topoext vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clfl ushopt sha_ni xsaveopt xsavec xgetbv1 arat

i have online one customer in this test server.

On Sun, Dec 20, 2020, 17:33 Simon Chopin < notifications@github.com> wrote:

Hi, thank you for testing this, I appreciate it very much.

Could you share a bit more details about the error case? Is it on any client, or only some of them ? Are you running on amd64 or 32-bit x86?

— You are receiving this because you commented. Reply to this email directly, view it on GitHub < https://github.com/xebd/accel-ppp/pull/140#issuecomment-748622861 , or unsubscribe <

https://github.com/notifications/unsubscribe-auth/ADCWD5EYBI76OEIUIWNHB3TSVYKNJANCNFSM4OFPZQ4A

.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/xebd/accel-ppp/pull/140#issuecomment-750934049, or unsubscribe <

https://github.com/notifications/unsubscribe-auth/AAEQ4NOXTIZJJ5MUQ4LURPTSWN4SLANCNFSM4OFPZQ4A

.

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/xebd/accel-ppp/pull/140#issuecomment-758151804, or unsubscribe < https://github.com/notifications/unsubscribe-auth/ADCWD5FAS25TITVN5G4B5B3SZNCJZANCNFSM4OFPZQ4A

.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/xebd/accel-ppp/pull/140#issuecomment-758205678, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAEQ4NITPZDBIZA5P5YOYDTSZNN63ANCNFSM4OFPZQ4A .