Run functional and performance tests for vhost-user mode as well. For functional tests, we add passt_vu and passt_vu_in_ns as symbolic links to their non-vhost-user counterparts, as no differences are intended but we want to distinguish them in test logs. For performance tests, instead, we add separate perf/passt_vu_tcp and perf/passt_vu_udp files, as we need longer test duration, as well as higher UDP sending bandwidths and larger TCP windows, to actually get the highest throughput vhost-user mode offers. For valgrind tests, vhost-user mode needs two extra system calls: statx and readlink. Add them as EXTRA_SYSCALLS for the valgrind target. Signed-off-by: Stefano Brivio <sbrivio(a)redhat.com> --- v2: - oops, add all the files I forgot in v1: test/perf/passt_vu_tcp, test/perf/passt_vu_udp, and symbolic links - also run the 'two_guests' case in vhost-user mode Makefile | 3 +- test/lib/perf_report | 15 +++ test/lib/setup | 77 ++++++++++++--- test/passt_vu | 1 + test/passt_vu_in_ns | 1 + test/perf/passt_vu_tcp | 211 +++++++++++++++++++++++++++++++++++++++++ test/perf/passt_vu_udp | 159 +++++++++++++++++++++++++++++++ test/run | 25 +++++ test/two_guests_vu | 1 + 9 files changed, 478 insertions(+), 15 deletions(-) create mode 120000 test/passt_vu create mode 120000 test/passt_vu_in_ns create mode 100644 test/perf/passt_vu_tcp create mode 100644 test/perf/passt_vu_udp create mode 120000 test/two_guests_vu diff --git a/Makefile b/Makefile index 74a9513..197729f 100644 --- a/Makefile +++ b/Makefile @@ -136,7 +136,8 @@ qrap: $(QRAP_SRCS) passt.h valgrind: EXTRA_SYSCALLS += rt_sigprocmask rt_sigtimedwait rt_sigaction \ rt_sigreturn getpid gettid kill clock_gettime mmap \ - mmap2 munmap open unlink gettimeofday futex + mmap2 munmap open unlink gettimeofday futex statx \ + readlink valgrind: FLAGS += -g -DVALGRIND valgrind: all diff --git a/test/lib/perf_report b/test/lib/perf_report index d1ef50b..c4ec817 100755 --- a/test/lib/perf_report +++ b/test/lib/perf_report @@ -49,6 +49,21 @@ td:empty { visibility: hidden; } __passt_tcp_LINE__ __passt_udp_LINE__ </table> +</li><li><p>passt with vhost-user support</p> +<table class="passt" width="70%"> + <tr> + <th/> + <th id="perf_passt_vu_tcp" colspan="__passt_vu_tcp_cols__">TCP, __passt_vu_tcp_threads__ at __passt_vu_tcp_freq__ GHz</th> + <th id="perf_passt_vu_udp" colspan="__passt_vu_udp_cols__">UDP, __passt_vu_udp_threads__ at __passt_vu_udp_freq__ GHz</th> + </tr> + <tr> + <td align="right">MTU:</td> + __passt_vu_tcp_header__ + __passt_vu_udp_header__ + </tr> + __passt_vu_tcp_LINE__ __passt_vu_udp_LINE__ +</table> + <style type="text/CSS"> table.pasta_local td { border: 0px solid; padding: 6px; line-height: 1; } table.pasta_local td { text-align: right; } diff --git a/test/lib/setup b/test/lib/setup index 5338393..3409bd2 100755 --- a/test/lib/setup +++ b/test/lib/setup @@ -15,8 +15,7 @@ INITRAMFS="${BASEPATH}/mbuto.img" VCPUS="$( [ $(nproc) -ge 8 ] && echo 6 || echo $(( $(nproc) / 2 + 1 )) )" -__mem_kib="$(sed -n 's/MemTotal:[ ]*\([0-9]*\) kB/\1/p' /proc/meminfo)" -VMEM="$((${__mem_kib} / 1024 / 4))" +MEM_KIB="$(sed -n 's/MemTotal:[ ]*\([0-9]*\) kB/\1/p' /proc/meminfo)" QEMU_ARCH="$(uname -m)" [ "${QEMU_ARCH}" = "i686" ] && QEMU_ARCH=i386 @@ -46,6 +45,7 @@ setup_passt() { [ ${PCAP} -eq 1 ] && __opts="${__opts} -p ${LOGDIR}/passt.pcap" [ ${DEBUG} -eq 1 ] && __opts="${__opts} -d" [ ${TRACE} -eq 1 ] && __opts="${__opts} --trace" + [ ${VHOST_USER} -eq 1 ] && __opts="${__opts} --vhost-user" context_run passt "make clean" context_run passt "make valgrind" @@ -54,16 +54,29 @@ setup_passt() { # pidfile isn't created until passt is listening wait_for [ -f "${STATESETUP}/passt.pid" ] + __vmem="$((${MEM_KIB} / 1024 / 4))" + if [ ${VHOST_USER} -eq 1 ]; then + __vmem="$(((${__vmem} + 500) / 1000))G" + __qemu_netdev=" \ + -chardev socket,id=c,path=${STATESETUP}/passt.socket \ + -netdev vhost-user,id=v,chardev=c \ + -device virtio-net,netdev=v \ + -object memory-backend-memfd,id=m,share=on,size=${__vmem} \ + -numa node,memdev=m" + else + __qemu_netdev="-device virtio-net-pci,netdev=s \ + -netdev stream,id=s,server=off,addr.type=unix,addr.path=${STATESETUP}/passt.socket" + fi + GUEST_CID=94557 context_run_bg qemu 'qemu-system-'"${QEMU_ARCH}" \ ' -machine accel=kvm' \ - ' -m '${VMEM}' -cpu host -smp '${VCPUS} \ + ' -m '${__vmem}' -cpu host -smp '${VCPUS} \ ' -kernel '"${KERNEL}" \ ' -initrd '${INITRAMFS}' -nographic -serial stdio' \ ' -nodefaults' \ ' -append "console=ttyS0 mitigations=off apparmor=0" ' \ - ' -device virtio-net-pci,netdev=s0 ' \ - " -netdev stream,id=s0,server=off,addr.type=unix,addr.path=${STATESETUP}/passt.socket " \ + " ${__qemu_netdev}" \ " -pidfile ${STATESETUP}/qemu.pid" \ " -device vhost-vsock-pci,guest-cid=$GUEST_CID" @@ -142,6 +155,7 @@ setup_passt_in_ns() { [ ${PCAP} -eq 1 ] && __opts="${__opts} -p ${LOGDIR}/passt_in_pasta.pcap" [ ${DEBUG} -eq 1 ] && __opts="${__opts} -d" [ ${TRACE} -eq 1 ] && __opts="${__opts} --trace" + [ ${VHOST_USER} -eq 1 ] && __opts="${__opts} --vhost-user" if [ ${VALGRIND} -eq 1 ]; then context_run passt "make clean" @@ -154,17 +168,30 @@ setup_passt_in_ns() { fi wait_for [ -f "${STATESETUP}/passt.pid" ] + __vmem="$((${MEM_KIB} / 1024 / 4))" + if [ ${VHOST_USER} -eq 1 ]; then + __vmem="$(((${__vmem} + 500) / 1000))G" + __qemu_netdev=" \ + -chardev socket,id=c,path=${STATESETUP}/passt.socket \ + -netdev vhost-user,id=v,chardev=c \ + -device virtio-net,netdev=v \ + -object memory-backend-memfd,id=m,share=on,size=${__vmem} \ + -numa node,memdev=m" + else + __qemu_netdev="-device virtio-net-pci,netdev=s \ + -netdev stream,id=s,server=off,addr.type=unix,addr.path=${STATESETUP}/passt.socket" + fi + GUEST_CID=94557 context_run_bg qemu 'qemu-system-'"${QEMU_ARCH}" \ ' -machine accel=kvm' \ ' -M accel=kvm:tcg' \ - ' -m '${VMEM}' -cpu host -smp '${VCPUS} \ + ' -m '${__vmem}' -cpu host -smp '${VCPUS} \ ' -kernel '"${KERNEL}" \ ' -initrd '${INITRAMFS}' -nographic -serial stdio' \ ' -nodefaults' \ ' -append "console=ttyS0 mitigations=off apparmor=0" ' \ - ' -device virtio-net-pci,netdev=s0 ' \ - " -netdev stream,id=s0,server=off,addr.type=unix,addr.path=${STATESETUP}/passt.socket " \ + " ${__qemu_netdev}" \ " -pidfile ${STATESETUP}/qemu.pid" \ " -device vhost-vsock-pci,guest-cid=$GUEST_CID" @@ -214,6 +241,7 @@ setup_two_guests() { [ ${PCAP} -eq 1 ] && __opts="${__opts} -p ${LOGDIR}/passt_1.pcap" [ ${DEBUG} -eq 1 ] && __opts="${__opts} -d" [ ${TRACE} -eq 1 ] && __opts="${__opts} --trace" + [ ${VHOST_USER} -eq 1 ] && __opts="${__opts} --vhost-user" context_run_bg passt_1 "./passt -s ${STATESETUP}/passt_1.socket -P ${STATESETUP}/passt_1.pid -f ${__opts} -t 10001 -u 10001" wait_for [ -f "${STATESETUP}/passt_1.pid" ] @@ -222,33 +250,54 @@ setup_two_guests() { [ ${PCAP} -eq 1 ] && __opts="${__opts} -p ${LOGDIR}/passt_2.pcap" [ ${DEBUG} -eq 1 ] && __opts="${__opts} -d" [ ${TRACE} -eq 1 ] && __opts="${__opts} --trace" + [ ${VHOST_USER} -eq 1 ] && __opts="${__opts} --vhost-user" context_run_bg passt_2 "./passt -s ${STATESETUP}/passt_2.socket -P ${STATESETUP}/passt_2.pid -f ${__opts} -t 10004 -u 10004" wait_for [ -f "${STATESETUP}/passt_2.pid" ] + __vmem="$((${MEM_KIB} / 1024 / 4))" + if [ ${VHOST_USER} -eq 1 ]; then + __vmem="$(((${__vmem} + 500) / 1000))G" + __qemu_netdev1=" \ + -chardev socket,id=c,path=${STATESETUP}/passt_1.socket \ + -netdev vhost-user,id=v,chardev=c \ + -device virtio-net,netdev=v \ + -object memory-backend-memfd,id=m,share=on,size=${__vmem} \ + -numa node,memdev=m" + __qemu_netdev1=" \ + -chardev socket,id=c,path=${STATESETUP}/passt_2.socket \ + -netdev vhost-user,id=v,chardev=c \ + -device virtio-net,netdev=v \ + -object memory-backend-memfd,id=m,share=on,size=${__vmem} \ + -numa node,memdev=m" + else + __qemu_netdev1="-device virtio-net-pci,netdev=s \ + -netdev stream,id=s,server=off,addr.type=unix,addr.path=${STATESETUP}/passt_1.socket" + __qemu_netdev2="-device virtio-net-pci,netdev=s \ + -netdev stream,id=s,server=off,addr.type=unix,addr.path=${STATESETUP}/passt_2.socket" + fi + GUEST_1_CID=94557 context_run_bg qemu_1 'qemu-system-'"${QEMU_ARCH}" \ ' -M accel=kvm:tcg' \ - ' -m '${VMEM}' -cpu host -smp '${VCPUS} \ + ' -m '${__vmem}' -cpu host -smp '${VCPUS} \ ' -kernel '"${KERNEL}" \ ' -initrd '${INITRAMFS}' -nographic -serial stdio' \ ' -nodefaults' \ ' -append "console=ttyS0 mitigations=off apparmor=0" ' \ - ' -device virtio-net-pci,netdev=s0 ' \ - " -netdev stream,id=s0,server=off,addr.type=unix,addr.path=${STATESETUP}/passt_1.socket " \ + " ${__qemu_netdev1}" \ " -pidfile ${STATESETUP}/qemu_1.pid" \ " -device vhost-vsock-pci,guest-cid=$GUEST_1_CID" GUEST_2_CID=94558 context_run_bg qemu_2 'qemu-system-'"${QEMU_ARCH}" \ ' -M accel=kvm:tcg' \ - ' -m '${VMEM}' -cpu host -smp '${VCPUS} \ + ' -m '${__vmem}' -cpu host -smp '${VCPUS} \ ' -kernel '"${KERNEL}" \ ' -initrd '${INITRAMFS}' -nographic -serial stdio' \ ' -nodefaults' \ ' -append "console=ttyS0 mitigations=off apparmor=0" ' \ - ' -device virtio-net-pci,netdev=s0 ' \ - " -netdev stream,id=s0,server=off,addr.type=unix,addr.path=${STATESETUP}/passt_2.socket " \ + " ${__qemu_netdev2}" \ " -pidfile ${STATESETUP}/qemu_2.pid" \ " -device vhost-vsock-pci,guest-cid=$GUEST_2_CID" diff --git a/test/passt_vu b/test/passt_vu new file mode 120000 index 0000000..22f1840 --- /dev/null +++ b/test/passt_vu @@ -0,0 +1 @@ +passt \ No newline at end of file diff --git a/test/passt_vu_in_ns b/test/passt_vu_in_ns new file mode 120000 index 0000000..3ff479e --- /dev/null +++ b/test/passt_vu_in_ns @@ -0,0 +1 @@ +passt_in_ns \ No newline at end of file diff --git a/test/perf/passt_vu_tcp b/test/perf/passt_vu_tcp new file mode 100644 index 0000000..b434008 --- /dev/null +++ b/test/perf/passt_vu_tcp @@ -0,0 +1,211 @@ +# SPDX-License-Identifier: GPL-2.0-or-later +# +# PASST - Plug A Simple Socket Transport +# for qemu/UNIX domain socket mode +# +# PASTA - Pack A Subtle Tap Abstraction +# for network namespace/tap device mode +# +# test/perf/passt_vu_tcp - Check TCP performance in passt vhost-user mode +# +# Copyright (c) 2021 Red Hat GmbH +# Author: Stefano Brivio <sbrivio(a)redhat.com> + +gtools /sbin/sysctl ip jq nproc seq sleep iperf3 tcp_rr tcp_crr # From neper +nstools /sbin/sysctl ip jq nproc seq sleep iperf3 tcp_rr tcp_crr +htools bc head sed seq + +set MAP_NS4 192.0.2.2 +set MAP_NS6 2001:db8:9a55::2 + +test passt: throughput and latency + +guest /sbin/sysctl -w net.core.rmem_max=536870912 +guest /sbin/sysctl -w net.core.wmem_max=536870912 +guest /sbin/sysctl -w net.core.rmem_default=33554432 +guest /sbin/sysctl -w net.core.wmem_default=33554432 +guest /sbin/sysctl -w net.ipv4.tcp_rmem="4096 131072 268435456" +guest /sbin/sysctl -w net.ipv4.tcp_wmem="4096 131072 268435456" +guest /sbin/sysctl -w net.ipv4.tcp_timestamps=0 + +ns /sbin/sysctl -w net.ipv4.tcp_rmem="4096 524288 134217728" +ns /sbin/sysctl -w net.ipv4.tcp_wmem="4096 524288 134217728" +ns /sbin/sysctl -w net.ipv4.tcp_timestamps=0 + +gout IFNAME ip -j link show | jq -rM '.[] | select(.link_type == "ether").ifname' + +hout FREQ_PROCFS (echo "scale=1"; sed -n 's/cpu MHz.*: \([0-9]*\)\..*$/(\1+10^2\/2)\/10^3/p' /proc/cpuinfo) | bc -l | head -n1 +hout FREQ_CPUFREQ (echo "scale=1"; printf '( %i + 10^5 / 2 ) / 10^6\n' $(cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_max_freq) ) | bc -l +hout FREQ [ -n "__FREQ_CPUFREQ__" ] && echo __FREQ_CPUFREQ__ || echo __FREQ_PROCFS__ + +set THREADS 4 +set TIME 5 +set OMIT 0.1 +set OPTS -Z -P __THREADS__ -l 1M -O__OMIT__ -N + +info Throughput in Gbps, latency in µs, __THREADS__ threads at __FREQ__ GHz +report passt_vu tcp __THREADS__ __FREQ__ + +th MTU 256B 576B 1280B 1500B 9000B 65520B + + +tr TCP throughput over IPv6: guest to host +iperf3s ns 10002 + +bw - +bw - +guest ip link set dev __IFNAME__ mtu 1280 +iperf3 BW guest __MAP_NS6__ 10002 __TIME__ __OPTS__ -w 16M +bw __BW__ 1.2 1.5 +guest ip link set dev __IFNAME__ mtu 1500 +iperf3 BW guest __MAP_NS6__ 10002 __TIME__ __OPTS__ -w 32M +bw __BW__ 1.6 1.8 +guest ip link set dev __IFNAME__ mtu 9000 +iperf3 BW guest __MAP_NS6__ 10002 __TIME__ __OPTS__ -w 64M +bw __BW__ 4.0 5.0 +guest ip link set dev __IFNAME__ mtu 65520 +iperf3 BW guest __MAP_NS6__ 10002 __TIME__ __OPTS__ -w 64M +bw __BW__ 7.0 8.0 + +iperf3k ns + +tl TCP RR latency over IPv6: guest to host +lat - +lat - +lat - +lat - +lat - +nsb tcp_rr --nolog -6 +gout LAT tcp_rr --nolog -l1 -6 -c -H __MAP_NS6__ | sed -n 's/^throughput=\(.*\)/\1/p' +lat __LAT__ 200 150 + +tl TCP CRR latency over IPv6: guest to host +lat - +lat - +lat - +lat - +lat - +nsb tcp_crr --nolog -6 +gout LAT tcp_crr --nolog -l1 -6 -c -H __MAP_NS6__ | sed -n 's/^throughput=\(.*\)/\1/p' +lat __LAT__ 500 400 + +tr TCP throughput over IPv4: guest to host +iperf3s ns 10002 + +guest ip link set dev __IFNAME__ mtu 256 +iperf3 BW guest __MAP_NS4__ 10002 __TIME__ __OPTS__ -w 2M +bw __BW__ 0.2 0.3 +guest ip link set dev __IFNAME__ mtu 576 +iperf3 BW guest __MAP_NS4__ 10002 __TIME__ __OPTS__ -w 4M +bw __BW__ 0.5 0.8 +guest ip link set dev __IFNAME__ mtu 1280 +iperf3 BW guest __MAP_NS4__ 10002 __TIME__ __OPTS__ -w 8M +bw __BW__ 1.2 1.5 +guest ip link set dev __IFNAME__ mtu 1500 +iperf3 BW guest __MAP_NS4__ 10002 __TIME__ __OPTS__ -w 16M +bw __BW__ 1.6 1.8 +guest ip link set dev __IFNAME__ mtu 9000 +iperf3 BW guest __MAP_NS4__ 10002 __TIME__ __OPTS__ -w 64M +bw __BW__ 4.0 5.0 +guest ip link set dev __IFNAME__ mtu 65520 +iperf3 BW guest __MAP_NS4__ 10002 __TIME__ __OPTS__ -w 64M +bw __BW__ 7.0 8.0 + +iperf3k ns + +# Reducing MTU below 1280 deconfigures IPv6, get our address back +guest dhclient -6 -x +guest dhclient -6 __IFNAME__ + +tl TCP RR latency over IPv4: guest to host +lat - +lat - +lat - +lat - +lat - +nsb tcp_rr --nolog -4 +gout LAT tcp_rr --nolog -l1 -4 -c -H __MAP_NS4__ | sed -n 's/^throughput=\(.*\)/\1/p' +lat __LAT__ 200 150 + +tl TCP CRR latency over IPv4: guest to host +lat - +lat - +lat - +lat - +lat - +nsb tcp_crr --nolog -4 +gout LAT tcp_crr --nolog -l1 -4 -c -H __MAP_NS4__ | sed -n 's/^throughput=\(.*\)/\1/p' +lat __LAT__ 500 400 + +tr TCP throughput over IPv6: host to guest +iperf3s guest 10001 + +bw - +bw - +bw - +bw - +bw - +iperf3 BW ns ::1 10001 __TIME__ __OPTS__ -w 32M +bw __BW__ 6.0 6.8 + +iperf3k guest + +tl TCP RR latency over IPv6: host to guest +lat - +lat - +lat - +lat - +lat - +guestb tcp_rr --nolog -P 10001 -C 10011 -6 +sleep 1 +nsout LAT tcp_rr --nolog -l1 -P 10001 -C 10011 -6 -c -H ::1 | sed -n 's/^throughput=\(.*\)/\1/p' +lat __LAT__ 200 150 + +tl TCP CRR latency over IPv6: host to guest +lat - +lat - +lat - +lat - +lat - +guestb tcp_crr --nolog -P 10001 -C 10011 -6 +sleep 1 +nsout LAT tcp_crr --nolog -l1 -P 10001 -C 10011 -6 -c -H ::1 | sed -n 's/^throughput=\(.*\)/\1/p' +lat __LAT__ 500 350 + + +tr TCP throughput over IPv4: host to guest +iperf3s guest 10001 + +bw - +bw - +bw - +bw - +bw - +iperf3 BW ns 127.0.0.1 10001 __TIME__ __OPTS__ -w 32M +bw __BW__ 6.0 6.8 + +iperf3k guest + +tl TCP RR latency over IPv4: host to guest +lat - +lat - +lat - +lat - +lat - +guestb tcp_rr --nolog -P 10001 -C 10011 -4 +sleep 1 +nsout LAT tcp_rr --nolog -l1 -P 10001 -C 10011 -4 -c -H 127.0.0.1 | sed -n 's/^throughput=\(.*\)/\1/p' +lat __LAT__ 200 150 + +tl TCP CRR latency over IPv6: host to guest +lat - +lat - +lat - +lat - +lat - +guestb tcp_crr --nolog -P 10001 -C 10011 -4 +sleep 1 +nsout LAT tcp_crr --nolog -l1 -P 10001 -C 10011 -4 -c -H 127.0.0.1 | sed -n 's/^throughput=\(.*\)/\1/p' +lat __LAT__ 500 300 + +te diff --git a/test/perf/passt_vu_udp b/test/perf/passt_vu_udp new file mode 100644 index 0000000..943ac11 --- /dev/null +++ b/test/perf/passt_vu_udp @@ -0,0 +1,159 @@ +# SPDX-License-Identifier: GPL-2.0-or-later +# +# PASST - Plug A Simple Socket Transport +# for qemu/UNIX domain socket mode +# +# PASTA - Pack A Subtle Tap Abstraction +# for network namespace/tap device mode +# +# test/perf/passt_vu_udp - Check UDP performance in passt vhost-user mode +# +# Copyright (c) 2021 Red Hat GmbH +# Author: Stefano Brivio <sbrivio(a)redhat.com> + +gtools /sbin/sysctl ip jq nproc sleep iperf3 udp_rr # From neper +nstools ip jq sleep iperf3 udp_rr +htools bc head sed + +set MAP_NS4 192.0.2.2 +set MAP_NS6 2001:db8:9a55::2 + +test passt: throughput and latency + +guest /sbin/sysctl -w net.core.rmem_max=16777216 +guest /sbin/sysctl -w net.core.wmem_max=16777216 +guest /sbin/sysctl -w net.core.rmem_default=16777216 +guest /sbin/sysctl -w net.core.wmem_default=16777216 + +hout FREQ_PROCFS (echo "scale=1"; sed -n 's/cpu MHz.*: \([0-9]*\)\..*$/(\1+10^2\/2)\/10^3/p' /proc/cpuinfo) | bc -l | head -n1 +hout FREQ_CPUFREQ (echo "scale=1"; printf '( %i + 10^5 / 2 ) / 10^6\n' $(cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_max_freq) ) | bc -l +hout FREQ [ -n "__FREQ_CPUFREQ__" ] && echo __FREQ_CPUFREQ__ || echo __FREQ_PROCFS__ + +set THREADS 2 +set TIME 1 +set OPTS -u -P __THREADS__ --pacing-timer 1000 + +info Throughput in Gbps, latency in µs, __THREADS__ threads at __FREQ__ GHz + +report passt_vu udp __THREADS__ __FREQ__ + +th pktlen 256B 576B 1280B 1500B 9000B 65520B + +tr UDP throughput over IPv6: guest to host +iperf3s ns 10002 +# (datagram size) = (packet size) - 48: 40 bytes of IPv6 header, 8 of UDP header + +bw - +bw - +iperf3 BW guest __MAP_NS6__ 10002 __TIME__ __OPTS__ -b 3G -l 1232 +bw __BW__ 0.8 1.2 +iperf3 BW guest __MAP_NS6__ 10002 __TIME__ __OPTS__ -b 4G -l 1452 +bw __BW__ 1.0 1.5 +iperf3 BW guest __MAP_NS6__ 10002 __TIME__ __OPTS__ -b 10G -l 8952 +bw __BW__ 4.0 5.0 +iperf3 BW guest __MAP_NS6__ 10002 __TIME__ __OPTS__ -b 20G -l 64372 +bw __BW__ 4.0 5.0 + +iperf3k ns + +tl UDP RR latency over IPv6: guest to host +lat - +lat - +lat - +lat - +lat - +nsb udp_rr --nolog -6 +gout LAT udp_rr --nolog -6 -c -H __MAP_NS6__ | sed -n 's/^throughput=\(.*\)/\1/p' +lat __LAT__ 200 150 + + +tr UDP throughput over IPv4: guest to host +iperf3s ns 10002 +# (datagram size) = (packet size) - 28: 20 bytes of IPv4 header, 8 of UDP header + +iperf3 BW guest __MAP_NS4__ 10002 __TIME__ __OPTS__ -b 1G -l 228 +bw __BW__ 0.0 0.0 +iperf3 BW guest __MAP_NS4__ 10002 __TIME__ __OPTS__ -b 2G -l 548 +bw __BW__ 0.4 0.6 +iperf3 BW guest __MAP_NS4__ 10002 __TIME__ __OPTS__ -b 3G -l 1252 +bw __BW__ 0.8 1.2 +iperf3 BW guest __MAP_NS4__ 10002 __TIME__ __OPTS__ -b 4G -l 1472 +bw __BW__ 1.0 1.5 +iperf3 BW guest __MAP_NS4__ 10002 __TIME__ __OPTS__ -b 10G -l 8972 +bw __BW__ 4.0 5.0 +iperf3 BW guest __MAP_NS4__ 10002 __TIME__ __OPTS__ -b 20G -l 65492 +bw __BW__ 4.0 5.0 + +iperf3k ns + +tl UDP RR latency over IPv4: guest to host +lat - +lat - +lat - +lat - +lat - +nsb udp_rr --nolog -4 +gout LAT udp_rr --nolog -4 -c -H __MAP_NS4__ | sed -n 's/^throughput=\(.*\)/\1/p' +lat __LAT__ 200 150 + + +tr UDP throughput over IPv6: host to guest +iperf3s guest 10001 +# (datagram size) = (packet size) - 48: 40 bytes of IPv6 header, 8 of UDP header + +bw - +bw - +iperf3 BW ns ::1 10001 __TIME__ __OPTS__ -b 3G -l 1232 +bw __BW__ 0.8 1.2 +iperf3 BW ns ::1 10001 __TIME__ __OPTS__ -b 4G -l 1452 +bw __BW__ 1.0 1.5 +iperf3 BW ns ::1 10001 __TIME__ __OPTS__ -b 10G -l 8952 +bw __BW__ 3.0 4.0 +iperf3 BW ns ::1 10001 __TIME__ __OPTS__ -b 20G -l 64372 +bw __BW__ 3.0 4.0 + +iperf3k guest + +tl UDP RR latency over IPv6: host to guest +lat - +lat - +lat - +lat - +lat - +guestb udp_rr --nolog -P 10001 -C 10011 -6 +sleep 1 +nsout LAT udp_rr --nolog -P 10001 -C 10011 -6 -c -H ::1 | sed -n 's/^throughput=\(.*\)/\1/p' +lat __LAT__ 200 150 + + +tr UDP throughput over IPv4: host to guest +iperf3s guest 10001 +# (datagram size) = (packet size) - 28: 20 bytes of IPv4 header, 8 of UDP header + +iperf3 BW ns 127.0.0.1 10001 __TIME__ __OPTS__ -b 1G -l 228 +bw __BW__ 0.0 0.0 +iperf3 BW ns 127.0.0.1 10001 __TIME__ __OPTS__ -b 2G -l 548 +bw __BW__ 0.4 0.6 +iperf3 BW ns 127.0.0.1 10001 __TIME__ __OPTS__ -b 3G -l 1252 +bw __BW__ 0.8 1.2 +iperf3 BW ns 127.0.0.1 10001 __TIME__ __OPTS__ -b 4G -l 1472 +bw __BW__ 1.0 1.5 +iperf3 BW ns 127.0.0.1 10001 __TIME__ __OPTS__ -b 10G -l 8972 +bw __BW__ 3.0 4.0 +iperf3 BW ns 127.0.0.1 10001 __TIME__ __OPTS__ -b 20G -l 65492 +bw __BW__ 3.0 4.0 + +iperf3k guest + +tl UDP RR latency over IPv4: host to guest +lat - +lat - +lat - +lat - +lat - +guestb udp_rr --nolog -P 10001 -C 10011 -4 +sleep 1 +nsout LAT udp_rr --nolog -P 10001 -C 10011 -4 -c -H 127.0.0.1 | sed -n 's/^throughput=\(.*\)/\1/p' +lat __LAT__ 200 150 + +te diff --git a/test/run b/test/run index 547a729..f188d8e 100755 --- a/test/run +++ b/test/run @@ -93,6 +93,7 @@ run() { test memory/passt teardown memory + VHOST_USER=0 setup passt test passt/ndp test passt/dhcp @@ -115,7 +116,22 @@ run() { test two_guests/basic teardown two_guests + VHOST_USER=1 + setup passt_in_ns + test passt_vu/ndp + test passt_vu_in_ns/dhcp + test passt_vu_in_ns/icmp + test passt_vu_in_ns/tcp + test passt_vu_in_ns/udp + test passt_vu_in_ns/shutdown + teardown passt_in_ns + + setup two_guests + test two_guests_vu/basic + teardown two_guests + VALGRIND=0 + VHOST_USER=0 setup passt_in_ns test passt/ndp test passt_in_ns/dhcp @@ -126,6 +142,15 @@ run() { test passt_in_ns/shutdown teardown passt_in_ns + VHOST_USER=1 + setup passt_in_ns + test passt_vu/ndp + test passt_vu_in_ns/dhcp + test perf/passt_vu_tcp + test perf/passt_vu_udp + test passt_vu_in_ns/shutdown + teardown passt_in_ns + # TODO: Make those faster by at least pre-installing gcc and make on # non-x86 images, then re-enable. skip_distro() { diff --git a/test/two_guests_vu b/test/two_guests_vu new file mode 120000 index 0000000..144b7ca --- /dev/null +++ b/test/two_guests_vu @@ -0,0 +1 @@ +test/two_guests \ No newline at end of file -- 2.43.0
On 01/10/2024 20:22, Stefano Brivio wrote:Run functional and performance tests for vhost-user mode as well. For functional tests, we add passt_vu and passt_vu_in_ns as symbolic links to their non-vhost-user counterparts, as no differences are intended but we want to distinguish them in test logs. For performance tests, instead, we add separate perf/passt_vu_tcp and perf/passt_vu_udp files, as we need longer test duration, as well as higher UDP sending bandwidths and larger TCP windows, to actually get the highest throughput vhost-user mode offers. For valgrind tests, vhost-user mode needs two extra system calls: statx and readlink. Add them as EXTRA_SYSCALLS for the valgrind target. Signed-off-by: Stefano Brivio <sbrivio(a)redhat.com> --- v2: - oops, add all the files I forgot in v1: test/perf/passt_vu_tcp, test/perf/passt_vu_udp, and symbolic links - also run the 'two_guests' case in vhost-user mode Makefile | 3 +- test/lib/perf_report | 15 +++ test/lib/setup | 77 ++++++++++++--- test/passt_vu | 1 + test/passt_vu_in_ns | 1 + test/perf/passt_vu_tcp | 211 +++++++++++++++++++++++++++++++++++++++++ test/perf/passt_vu_udp | 159 +++++++++++++++++++++++++++++++ test/run | 25 +++++ test/two_guests_vu | 1 + 9 files changed, 478 insertions(+), 15 deletions(-) create mode 120000 test/passt_vu create mode 120000 test/passt_vu_in_ns create mode 100644 test/perf/passt_vu_tcp create mode 100644 test/perf/passt_vu_udp create mode 120000 test/two_guests_vuSomething like this is missing: diff --git a/test/lib/setup_ugly b/test/lib/setup_ugly index 4b2a0774de1d..46089eb9834b 100755 --- a/test/lib/setup_ugly +++ b/test/lib/setup_ugly @@ -33,7 +33,7 @@ setup_memory() { pane_or_context_run guest 'qemu-system-$(uname -m)' \ ' -machine accel=kvm' \ - ' -m '${VMEM}' -cpu host -smp '${VCPUS} \ + ' -m '$((${MEM_KIB} / 1024 / 4))' -cpu host -smp '${VCPUS} \ ' -kernel ' "/boot/vmlinuz-$(uname -r)" \ ' -initrd '${INITRAMFS_MEM}' -nographic -serial stdio' \ ' -nodefaults' \ Thanks, Laurent
On Mon, 7 Oct 2024 13:57:39 +0200 Laurent Vivier <lvivier(a)redhat.com> wrote:On 01/10/2024 20:22, Stefano Brivio wrote:Oops, right, I guess I skipped that test as well while testing this change. Feel free to just change that in this patch if you carry it in your series (it looks okay to me). -- StefanoRun functional and performance tests for vhost-user mode as well. For functional tests, we add passt_vu and passt_vu_in_ns as symbolic links to their non-vhost-user counterparts, as no differences are intended but we want to distinguish them in test logs. For performance tests, instead, we add separate perf/passt_vu_tcp and perf/passt_vu_udp files, as we need longer test duration, as well as higher UDP sending bandwidths and larger TCP windows, to actually get the highest throughput vhost-user mode offers. For valgrind tests, vhost-user mode needs two extra system calls: statx and readlink. Add them as EXTRA_SYSCALLS for the valgrind target. Signed-off-by: Stefano Brivio <sbrivio(a)redhat.com> --- v2: - oops, add all the files I forgot in v1: test/perf/passt_vu_tcp, test/perf/passt_vu_udp, and symbolic links - also run the 'two_guests' case in vhost-user mode Makefile | 3 +- test/lib/perf_report | 15 +++ test/lib/setup | 77 ++++++++++++--- test/passt_vu | 1 + test/passt_vu_in_ns | 1 + test/perf/passt_vu_tcp | 211 +++++++++++++++++++++++++++++++++++++++++ test/perf/passt_vu_udp | 159 +++++++++++++++++++++++++++++++ test/run | 25 +++++ test/two_guests_vu | 1 + 9 files changed, 478 insertions(+), 15 deletions(-) create mode 120000 test/passt_vu create mode 120000 test/passt_vu_in_ns create mode 100644 test/perf/passt_vu_tcp create mode 100644 test/perf/passt_vu_udp create mode 120000 test/two_guests_vuSomething like this is missing: diff --git a/test/lib/setup_ugly b/test/lib/setup_ugly index 4b2a0774de1d..46089eb9834b 100755 --- a/test/lib/setup_ugly +++ b/test/lib/setup_ugly @@ -33,7 +33,7 @@ setup_memory() { pane_or_context_run guest 'qemu-system-$(uname -m)' \ ' -machine accel=kvm' \ - ' -m '${VMEM}' -cpu host -smp '${VCPUS} \ + ' -m '$((${MEM_KIB} / 1024 / 4))' -cpu host -smp '${VCPUS} \