[缺陷描述]： anolis8 5.10 x86 debug内核，dccp01和dccp01_ipv6用例fail，dccp01 2 TFAIL: performance result is -260% < threshold -100%；这2条用例只在debug内核fail，release内核是pass的 测试日志： <<<test_start>>> tag=dccp01 stime=1686883889 cmdline="dccp01.sh" contacts="" analysis=exit <<<test_output>>> dccp01 1 TINFO: initialize 'lhost' 'ltp_ns_veth2' interface dccp01 1 TINFO: add local addr 10.0.0.2/24 dccp01 1 TINFO: add local addr fd00:1:1:1::2/64 dccp01 1 TINFO: initialize 'rhost' 'ltp_ns_veth1' interface dccp01 1 TINFO: add remote addr 10.0.0.1/24 dccp01 1 TINFO: add remote addr fd00:1:1:1::1/64 dccp01 1 TINFO: Network config (local -- remote): dccp01 1 TINFO: ltp_ns_veth2 -- ltp_ns_veth1 dccp01 1 TINFO: 10.0.0.2/24 -- 10.0.0.1/24 dccp01 1 TINFO: fd00:1:1:1::2/64 -- fd00:1:1:1::1/64 dccp01 1 TINFO: timeout per run is 0h 5m 0s dccp01 1 TINFO: run UDP dccp01 1 TINFO: run server 'netstress -T udp -D ltp_ns_veth1 -R 500000 -B /tmp/ltp-hO6iZ9evnC/LTP_dccp01.kqNfARgkVn' dccp01 1 TINFO: run client 'netstress -l -T udp -H 10.0.0.1 -D ltp_ns_veth2 -a 2 -r 2000 -d tst_netload.res' 5 times dccp01 1 TPASS: netstress passed, mean time '139' ms dccp01 2 TINFO: compare UDP/DCCP performance dccp01 2 TINFO: run server 'netstress -T dccp -D ltp_ns_veth1 -R 500000 -B /tmp/ltp-hO6iZ9evnC/LTP_dccp01.kqNfARgkVn' dccp01 2 TINFO: run client 'netstress -l -T dccp -H 10.0.0.1 -D ltp_ns_veth2 -a 2 -r 2000 -d tst_netload.res' 5 times dccp01 2 TPASS: netstress passed, mean time '501' ms dccp01 2 TFAIL: performance result is -260% < threshold -100% dccp01 3 TINFO: compare UDP/UDP-Lite performance dccp01 3 TINFO: run server 'netstress -T udp_lite -D ltp_ns_veth1 -R 500000 -B /tmp/ltp-hO6iZ9evnC/LTP_dccp01.kqNfARgkVn' dccp01 3 TINFO: run client 'netstress -l -T udp_lite -H 10.0.0.1 -D ltp_ns_veth2 -a 2 -r 2000 -d tst_netload.res' 5 times dccp01 3 TPASS: netstress passed, mean time '143' ms dccp01 3 TPASS: performance result is -2%, in range [-100:100]% Summary: passed 4 failed 1 skipped 0 warnings 0 <<<execution_status>>> initiation_status="ok" duration=10 termination_type=exited termination_id=1 corefile=no cutime=64 cstime=741 <<<test_end>>> <<<test_start>>> tag=dccp01_ipv6 stime=1686883899 cmdline="dccp01.sh -6" contacts="" analysis=exit <<<test_output>>> incrementing stop dccp01 1 TINFO: initialize 'lhost' 'ltp_ns_veth2' interface dccp01 1 TINFO: add local addr 10.0.0.2/24 dccp01 1 TINFO: add local addr fd00:1:1:1::2/64 dccp01 1 TINFO: initialize 'rhost' 'ltp_ns_veth1' interface dccp01 1 TINFO: add remote addr 10.0.0.1/24 dccp01 1 TINFO: add remote addr fd00:1:1:1::1/64 dccp01 1 TINFO: Network config (local -- remote): dccp01 1 TINFO: ltp_ns_veth2 -- ltp_ns_veth1 dccp01 1 TINFO: 10.0.0.2/24 -- 10.0.0.1/24 dccp01 1 TINFO: fd00:1:1:1::2/64 -- fd00:1:1:1::1/64 dccp01 1 TINFO: timeout per run is 0h 5m 0s dccp01 1 TINFO: run UDP dccp01 1 TINFO: run server 'netstress -T udp -D ltp_ns_veth1 -R 500000 -B /tmp/ltp-hO6iZ9evnC/LTP_dccp01.xyKb1QL595' dccp01 1 TINFO: run client 'netstress -l -T udp -H fd00:1:1:1::1 -D ltp_ns_veth2 -a 2 -r 2000 -d tst_netload.res' 5 times dccp01 1 TPASS: netstress passed, mean time '151' ms dccp01 2 TINFO: compare UDP/DCCP performance dccp01 2 TINFO: run server 'netstress -T dccp -D ltp_ns_veth1 -R 500000 -B /tmp/ltp-hO6iZ9evnC/LTP_dccp01.xyKb1QL595' dccp01 2 TINFO: run client 'netstress -l -T dccp -H fd00:1:1:1::1 -D ltp_ns_veth2 -a 2 -r 2000 -d tst_netload.res' 5 times dccp01 2 TPASS: netstress passed, mean time '498' ms dccp01 2 TFAIL: performance result is -229% < threshold -100% dccp01 3 TINFO: compare UDP/UDP-Lite performance dccp01 3 TINFO: run server 'netstress -T udp_lite -D ltp_ns_veth1 -R 500000 -B /tmp/ltp-hO6iZ9evnC/LTP_dccp01.xyKb1QL595' dccp01 3 TINFO: run client 'netstress -l -T udp_lite -H fd00:1:1:1::1 -D ltp_ns_veth2 -a 2 -r 2000 -d tst_netload.res' 5 times dccp01 3 TPASS: netstress passed, mean time '153' ms dccp01 3 TPASS: performance result is -1%, in range [-100:100]% Summary: passed 4 failed 1 skipped 0 warnings 0 <<<execution_status>>> initiation_status="ok" duration=9 termination_type=exited termination_id=1 corefile=no cutime=65 cstime=751 <<<test_end>>> [重现步骤]： 1. 安装ltp环境 git clone -b anck-5.10 https://gitee.com/anolis/ltp.git make autotools #默认会安装到/opt下 ./configure make make install /opt/ltp/runltp net.features -s dccp01 [测试环境]： 线下物理机 内核： # uname -r 5.10.134-17.git.5b174ed86.an8.x86_64+debug OS信息： # cat /etc/os-release NAME="Anolis OS" VERSION="8.6" ID="anolis" ID_LIKE="rhel fedora centos" VERSION_ID="8.6" PLATFORM_ID="platform:an8" PRETTY_NAME="Anolis OS 8.6" ANSI_COLOR="0;31" HOME_URL="https://openanolis.cn/" cpu信息： # lscpu Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian CPU(s): 96 On-line CPU(s) list: 0-95 Thread(s) per core: 2 Core(s) per socket: 24 Socket(s): 2 NUMA node(s): 1 Vendor ID: GenuineIntel BIOS Vendor ID: Intel(R) Corporation CPU family: 6 Model: 85 Model name: Intel(R) Xeon(R) Platinum 8163 CPU @ 2.50GHz BIOS Model name: Intel(R) Xeon(R) Platinum 8163 CPU @ 2.50GHz Stepping: 4 CPU MHz: 999.818 CPU max MHz: 3100.0000 CPU min MHz: 1000.0000 BogoMIPS: 5000.00 Virtualization: VT-x L1d cache: 32K L1i cache: 32K L2 cache: 1024K L3 cache: 33792K NUMA node0 CPU(s): 0-95 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 art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cdp_l3 invpcid_single pti intel_ppin ssbd mba ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm mpx rdt_a avx512f avx512dq rdseed adx smap clflushopt clwb intel_pt avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts pku ospke md_clear flush_l1d arch_capabilities 内存信息： # free -h total used free shared buff/cache available Mem: 438Gi 17Gi 420Gi 10Mi 1.5Gi 418Gi Swap: 2.0Gi 0B 2.0Gi [期望结果]： 用例执行成功 [实际结果]： 用例执行失败
alinux3-debug-x86有同样失败，此2个用例失败为今日新增； 内核：5.10.134-961.git.5b174ed86bf3.al8.x86_64+debug 失败日志如下： <<<test_output>>> dccp01 1 TINFO: initialize 'lhost' 'ltp_ns_veth2' interface dccp01 1 TINFO: add local addr 10.0.0.2/24 dccp01 1 TINFO: add local addr fd00:1:1:1::2/64 dccp01 1 TINFO: initialize 'rhost' 'ltp_ns_veth1' interface dccp01 1 TINFO: add remote addr 10.0.0.1/24 dccp01 1 TINFO: add remote addr fd00:1:1:1::1/64 dccp01 1 TINFO: Network config (local -- remote): dccp01 1 TINFO: ltp_ns_veth2 -- ltp_ns_veth1 dccp01 1 TINFO: 10.0.0.2/24 -- 10.0.0.1/24 dccp01 1 TINFO: fd00:1:1:1::2/64 -- fd00:1:1:1::1/64 dccp01 1 TINFO: timeout per run is 0h 5m 0s dccp01 1 TINFO: run UDP dccp01 1 TINFO: run server 'netstress -T udp -D ltp_ns_veth1 -R 500000 -B /tmp/ltp-ZmSDRIkOSS/LTP_dccp01.oF7Hy9TGNK' dccp01 1 TINFO: run client 'netstress -l -T udp -H 10.0.0.1 -D ltp_ns_veth2 -a 2 -r 2000 -d tst_netload.res' 5 times dccp01 1 TPASS: netstress passed, mean time '383' ms dccp01 2 TINFO: compare UDP/DCCP performance dccp01 2 TINFO: run server 'netstress -T dccp -D ltp_ns_veth1 -R 500000 -B /tmp/ltp-ZmSDRIkOSS/LTP_dccp01.oF7Hy9TGNK' dccp01 2 TINFO: run client 'netstress -l -T dccp -H 10.0.0.1 -D ltp_ns_veth2 -a 2 -r 2000 -d tst_netload.res' 5 times dccp01 2 TPASS: netstress passed, mean time '1263' ms dccp01 2 TFAIL: performance result is -229% < threshold -100% dccp01 3 TINFO: compare UDP/UDP-Lite performance dccp01 3 TINFO: run server 'netstress -T udp_lite -D ltp_ns_veth1 -R 500000 -B /tmp/ltp-ZmSDRIkOSS/LTP_dccp01.oF7Hy9TGNK' dccp01 3 TINFO: run client 'netstress -l -T udp_lite -H 10.0.0.1 -D ltp_ns_veth2 -a 2 -r 2000 -d tst_netload.res' 5 times dccp01 3 TPASS: netstress passed, mean time '376' ms dccp01 3 TPASS: performance result is 1%, in range [-100:100]% Summary: passed 4 failed 1 skipped 0 warnings 0 <<<execution_status>>> initiation_status="ok" duration=17 termination_type=exited termination_id=1 corefile=no cutime=53 cstime=1751 <<<test_end>>> <<<test_start>>> tag=dccp01_ipv6 stime=1686910854 cmdline="dccp01.sh -6" contacts="" analysis=exit <<<test_output>>> incrementing stop dccp01 1 TINFO: initialize 'lhost' 'ltp_ns_veth2' interface dccp01 1 TINFO: add local addr 10.0.0.2/24 dccp01 1 TINFO: add local addr fd00:1:1:1::2/64 dccp01 1 TINFO: initialize 'rhost' 'ltp_ns_veth1' interface dccp01 1 TINFO: add remote addr 10.0.0.1/24 dccp01 1 TINFO: add remote addr fd00:1:1:1::1/64 dccp01 1 TINFO: Network config (local -- remote): dccp01 1 TINFO: ltp_ns_veth2 -- ltp_ns_veth1 dccp01 1 TINFO: 10.0.0.2/24 -- 10.0.0.1/24 dccp01 1 TINFO: fd00:1:1:1::2/64 -- fd00:1:1:1::1/64 dccp01 1 TINFO: timeout per run is 0h 5m 0s dccp01 1 TINFO: run UDP dccp01 1 TINFO: run server 'netstress -T udp -D ltp_ns_veth1 -R 500000 -B /tmp/ltp-ZmSDRIkOSS/LTP_dccp01.J4mlmri2XP' dccp01 1 TINFO: run client 'netstress -l -T udp -H fd00:1:1:1::1 -D ltp_ns_veth2 -a 2 -r 2000 -d tst_netload.res' 5 times dccp01 1 TPASS: netstress passed, mean time '397' ms dccp01 2 TINFO: compare UDP/DCCP performance dccp01 2 TINFO: run server 'netstress -T dccp -D ltp_ns_veth1 -R 500000 -B /tmp/ltp-ZmSDRIkOSS/LTP_dccp01.J4mlmri2XP' dccp01 2 TINFO: run client 'netstress -l -T dccp -H fd00:1:1:1::1 -D ltp_ns_veth2 -a 2 -r 2000 -d tst_netload.res' 5 times dccp01 2 TPASS: netstress passed, mean time '1358' ms dccp01 2 TFAIL: performance result is -242% < threshold -100% dccp01 3 TINFO: compare UDP/UDP-Lite performance dccp01 3 TINFO: run server 'netstress -T udp_lite -D ltp_ns_veth1 -R 500000 -B /tmp/ltp-ZmSDRIkOSS/LTP_dccp01.J4mlmri2XP' dccp01 3 TINFO: run client 'netstress -l -T udp_lite -H fd00:1:1:1::1 -D ltp_ns_veth2 -a 2 -r 2000 -d tst_netload.res' 5 times dccp01 3 TPASS: netstress passed, mean time '398' ms dccp01 3 TPASS: performance result is 0%, in range [-100:100]% Summary: passed 4 failed 1 skipped 0 warnings 0 <<<execution_status>>> initiation_status="ok" duration=16 termination_type=exited termination_id=1 corefile=no cutime=53 cstime=1787 <<<test_end>>> INFO: ltp-pan reported some tests FAIL LTP Version: 20200930
我理解debug的内核，由于加了很多调试内容，性能下降很多是正常的，而且release内核是正常的，那么用户那边是不会有这个问题的。请开发同学再帮忙确认一下。给个结论。
kernel 是用 debug config 编译，然后测试性能吗？ 这么做的目的首先是什么， debug 内核里面的各种辅助功能，例如 trace function 这些都会自动打开占用热点
dccp + debug 内核测试性能优先级不高，暂时 delay
该问题不影响版本发布。