Bingo! Test Page for the Centmin Mod Nginx HTTP Server It be the cloudflare fork =X
Ah i am wonder whether it's older cpus support for pclmul which Cloudflare zlib uses/looks for ? Cloudflare zlib says pclmul is supported in both your working and non-working nginx logs But GCC 7.2.1 native support/enabled flags only show -mpclmul enabled support for your working server and not not the non-working E5620. So maybe need further checks to cpus to determine if Cloudflare zlib is enabled by default for Nginx
strange though just checked one of my older openvz vps servers running Intel Xeon L5640 Westmere-EP and Cloudflare zlib fork and runs fine with access to Nginx but also on older OpenVZ host node kernel Code (Text): 2.6.32-042stab127.2 Code (Text): processor : 3 vendor_id : GenuineIntel cpu family : 6 model : 44 model name : Intel(R) Xeon(R) CPU L5640 @ 2.27GHz stepping : 2 microcode : 26 cpu MHz : 2260.970 cache size : 12288 KB physical id : 0 siblings : 12 core id : 1 cpu cores : 6 apicid : 2 initial apicid : 2 fpu : yes fpu_exception : yes cpuid level : 11 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm pcid dca sse4_1 sse4_2 popcnt aes lahf_lm ida arat dtherm tpr_shadow vnmi flexpriority ept vpid bogomips : 4521.83 clflush size : 64 cache_alignment : 64 address sizes : 40 bits physical, 48 bits virtual power management: and running fine with Interesting GCC 7.2.1 does report cpu native -mpclmul enabled on mine unlike on your E5620 Code (Text): -mpclmul [enabled] Code (Text): /opt/rh/devtoolset-7/root/usr/bin/gcc /opt/rh/devtoolset-7/root/usr/bin/g++ -m64 [enabled] -m80387 [enabled] -m96bit-long-double [enabled] -maes [enabled] -malign-stringops [enabled] -march= westmere -mcx16 [enabled] -mfancy-math-387 [enabled] -mfentry [enabled] -mfp-ret-in-387 [enabled] -mfxsr [enabled] -mglibc [enabled] -mhard-float [enabled] -mieee-fp [enabled] -mlong-double-80 [enabled] -mmmx [enabled] -mpclmul [enabled] -mpopcnt [enabled] -mpush-args [enabled] -mred-zone [enabled] -msahf [enabled] -msse [enabled] -msse2 [enabled] -msse3 [enabled] -msse4 [enabled] -msse4.1 [enabled] -msse4.2 [enabled] -mssse3 [enabled] -mstackrealign [enabled] -mtls-direct-seg-refs [enabled] -mtune-ctrl= -mtune= westmere
@R0rke @jcat just updated Centmin Mod 123.09beta01 with additional checks for pclmul cpu instruction support to double check that GCC native flags also support pclmul Beta Branch - additional nginx & php-fpm Cloudflare zlib library prechecks So update your 123.09beta01 code on local server. For 123.09beta01 and higher that means running SSH command = cmupdate and then re-enter /usr/local/src/centminmod and re-run centmin.sh menu. Then try recompiling nginx via centmin.sh menu option 4. It should now detect that GCC native option is missing pclmul support on your specific cpu models and auto fallback to standard zlib library instead of cloudflare zlib performance library.
Ok awesome, Ill do a test install now and let you know Did you still need any additional info from me? Code: # cat /proc/cpuinfo processor : 0 vendor_id : GenuineIntel cpu family : 6 model : 44 model name : Intel(R) Xeon(R) CPU E5620 @ 2.40GHz stepping : 2 microcode : 16 cpu MHz : 2399.831 cache size : 12288 KB physical id : 0 siblings : 8 core id : 0 cpu cores : 4 apicid : 0 initial apicid : 0 fpu : yes fpu_exception : yes cpuid level : 11 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm pcid dca sse4_1 sse4_2 popcnt lahf_lm ida arat epb dtherm pti retpoline tpr_shadow vnmi flexpriority ept vpid bogomips : 4799.66 clflush size : 64 cache_alignment : 64 address sizes : 40 bits physical, 48 bits virtual power management: processor : 1 vendor_id : GenuineIntel cpu family : 6 model : 44 model name : Intel(R) Xeon(R) CPU E5620 @ 2.40GHz stepping : 2 microcode : 16 cpu MHz : 2399.831 cache size : 12288 KB physical id : 0 siblings : 8 core id : 1 cpu cores : 4 apicid : 2 initial apicid : 2 fpu : yes fpu_exception : yes cpuid level : 11 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm pcid dca sse4_1 sse4_2 popcnt lahf_lm ida arat epb dtherm pti retpoline tpr_shadow vnmi flexpriority ept vpid bogomips : 4799.66 clflush size : 64 cache_alignment : 64 address sizes : 40 bits physical, 48 bits virtual power management: processor : 2 vendor_id : GenuineIntel cpu family : 6 model : 44 model name : Intel(R) Xeon(R) CPU E5620 @ 2.40GHz stepping : 2 microcode : 16 cpu MHz : 2399.831 cache size : 12288 KB physical id : 0 siblings : 8 core id : 9 cpu cores : 4 apicid : 18 initial apicid : 18 fpu : yes fpu_exception : yes cpuid level : 11 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm pcid dca sse4_1 sse4_2 popcnt lahf_lm ida arat epb dtherm pti retpoline tpr_shadow vnmi flexpriority ept vpid bogomips : 4799.66 clflush size : 64 cache_alignment : 64 address sizes : 40 bits physical, 48 bits virtual power management: processor : 3 vendor_id : GenuineIntel cpu family : 6 model : 44 model name : Intel(R) Xeon(R) CPU E5620 @ 2.40GHz stepping : 2 microcode : 16 cpu MHz : 2399.831 cache size : 12288 KB physical id : 0 siblings : 8 core id : 10 cpu cores : 4 apicid : 20 initial apicid : 20 fpu : yes fpu_exception : yes cpuid level : 11 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm pcid dca sse4_1 sse4_2 popcnt lahf_lm ida arat epb dtherm pti retpoline tpr_shadow vnmi flexpriority ept vpid bogomips : 4799.66 clflush size : 64 cache_alignment : 64 address sizes : 40 bits physical, 48 bits virtual power management: processor : 4 vendor_id : GenuineIntel cpu family : 6 model : 44 model name : Intel(R) Xeon(R) CPU E5620 @ 2.40GHz stepping : 2 microcode : 16 cpu MHz : 2399.831 cache size : 12288 KB physical id : 1 siblings : 8 core id : 0 cpu cores : 4 apicid : 32 initial apicid : 32 fpu : yes fpu_exception : yes cpuid level : 11 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm pcid dca sse4_1 sse4_2 popcnt lahf_lm ida arat epb dtherm pti retpoline tpr_shadow vnmi flexpriority ept vpid bogomips : 4799.88 clflush size : 64 cache_alignment : 64 address sizes : 40 bits physical, 48 bits virtual power management: processor : 5 vendor_id : GenuineIntel cpu family : 6 model : 44 model name : Intel(R) Xeon(R) CPU E5620 @ 2.40GHz stepping : 2 microcode : 16 cpu MHz : 2399.831 cache size : 12288 KB physical id : 1 siblings : 8 core id : 1 cpu cores : 4 apicid : 34 initial apicid : 34 fpu : yes fpu_exception : yes cpuid level : 11 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm pcid dca sse4_1 sse4_2 popcnt lahf_lm ida arat epb dtherm pti retpoline tpr_shadow vnmi flexpriority ept vpid bogomips : 4799.88 clflush size : 64 cache_alignment : 64 address sizes : 40 bits physical, 48 bits virtual power management:
Cheers the /proc/cpuinfo cpu flags output is enough to confirm my suspicion that your E5620 cpu is missing pclmulqdq instruction flag so pclmul support was missing which is required by Cloudflare zlib performance forked library. Strangely, Cloudflare zlib compile reports pclmul is supported in your E5620 logs which is actually true Westmere-EP cpus such as E56xx series and L56xx series do have pclmul support. Checking Cloudflare zlib's pclmul detection routine Code (Text): grep -C8 -rn 'pclmul' /svr-setup/zlib-cloudflare-1.3.0/configure 766- # Check for PCLMUL support 767-cat > $test.c << EOF 768-#include <immintrin.h> 769-void foo(void) { 770- _mm_clmulepi64_si128(_mm_set1_epi16(1), _mm_set1_epi16(2), 0); 771-} 772-EOF 773- 774: if try $CC -c -mpclmul $CFLAGS $test.c ; then 775: CFLAGS="-DHAS_PCLMUL -mpclmul $CFLAGS" 776: SFLAGS="-DHAS_PCLMUL -mpclmul $SFLAGS" 777- echo "Checking for PCLMUL support ... Yes" | tee -a configure.log 778- else 779- echo "Checking for PCLMUL support ... No" | tee -a configure.log 780- fi 781- 782-elif [ x$TGT_ARCH = "xaarch64" -a $(uname -m) = "aarch64" ] ; then 783- 784- # Check for NEON and CRC support But looks like OpenVZ didn't pass that onto guest OS so is missing and thus GCC march=native compiled nginx server was also missing the -mpclmul enabled flag. Not familar with OpenVZ host node setups, but if you can configure a pclmul supported cpu to pass the supported flag to OpenVZ guest OSes, you would fix the underlying issue and be able to use Cloudflare zlib performance library then. Looks like you may have disabled AES-NI support and thus pclmul within your server bios settings ? i.e. VMware Knowledge Base Side by side compare of your E5620 OpenVZ and one of my L5640 OpenVZ VPS which is running Nginx 1.13.12 fine with Cloudflare zlib performance library built Nginx web server. E5620 (left) vs L5640 (right) - notice line at bottom shows pclmulqdq instruction missing from cpu flags line for E5620
looks like you have AES-NI disabled in bios so pclmulqdq instruction was disabled too. So enable AES-NI in bios E5620 (top) vs L5640 (bottom)
You smart SOB, that's what it was I honestly have no idea why we would of ever disabled it, never any reason to venture there in BIOS, the server was deployed in 2013 so who the hell knows =X Thanks as always!
Yeah with AES-NI disabled cryptographic performance would been alot less too ! Guess we all learnt something from this !
he got speed of light , Knowledge of God , Technical as f... . do u believe in legends ? he is the real super man . lol @eva2000. as you said the problem is from Network adaptor . they told me they will fix it but i decide to money back . for now im running centminmod on my other servers cool . thanks for help the problem fixed , it was from Public and Private stuff you told me before