diff options
| author | Stefano Brivio <sbrivio@redhat.com> | 2022-09-21 01:21:32 +0200 |
|---|---|---|
| committer | Stefano Brivio <sbrivio@redhat.com> | 2022-09-22 16:54:09 +0200 |
| commit | df29ebfe02aa0639278527b0fa2d90074263af0f (patch) | |
| tree | 035b0a97ba614114a098b0fc9d61e35813dbbc8b /test | |
| parent | 9f8b783d4a3860fa22082c57c3054fbc062def17 (diff) | |
| download | passt-df29ebfe02aa0639278527b0fa2d90074263af0f.tar passt-df29ebfe02aa0639278527b0fa2d90074263af0f.tar.gz passt-df29ebfe02aa0639278527b0fa2d90074263af0f.tar.bz2 passt-df29ebfe02aa0639278527b0fa2d90074263af0f.tar.lz passt-df29ebfe02aa0639278527b0fa2d90074263af0f.tar.xz passt-df29ebfe02aa0639278527b0fa2d90074263af0f.tar.zst passt-df29ebfe02aa0639278527b0fa2d90074263af0f.zip | |
test/perf: Disable periodic throughput reports to avoid vhost hang
It appears that if we run throughput tests with one-second periodic
reports, the sending side of the vhost channel used for SSH-based
command dispatch occasionally stops working altogether. I haven't
investigated this further, all I see is that output is truncated
at some point, and doesn't resume.
If we use gzip compression (ssh -C) this happens less frequently,
but it still happens, seemingly indicating the issue is probably
related to vhost itself.
Disable periodic reports in iperf3 clients. The -i options were
actually redundant, so remove them from both test files as well as
from test_iperf3().
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Diffstat (limited to 'test')
| -rwxr-xr-x | test/lib/test | 2 | ||||
| -rw-r--r-- | test/perf/passt_tcp | 2 | ||||
| -rw-r--r-- | test/perf/passt_udp | 2 | ||||
| -rw-r--r-- | test/perf/pasta_tcp | 2 | ||||
| -rw-r--r-- | test/perf/pasta_udp | 2 |
5 files changed, 5 insertions, 5 deletions
diff --git a/test/lib/test b/test/lib/test index b69d519..d68ade4 100755 --- a/test/lib/test +++ b/test/lib/test @@ -44,7 +44,7 @@ test_iperf3() { '(' \ ' for i in $(seq 0 '${__procs}'); do' \ ' iperf3 -c '${__dest}' -p '${__port} \ - ' -t'${__time}' -T s${i} '"${@}"' &' \ + ' -t'${__time}' -i0 -T s${i} '"${@}"' &' \ ' done;' \ ' wait' \ ')' diff --git a/test/perf/passt_tcp b/test/perf/passt_tcp index 5f0aa3a..5ba5450 100644 --- a/test/perf/passt_tcp +++ b/test/perf/passt_tcp @@ -46,7 +46,7 @@ set THREADS 1 set STREAMS 8 set TIME 10 hout OMIT echo __TIME__ / 6 | bc -l -set OPTS -Z -P __STREAMS__ -l 1M -i1 -O__OMIT__ --pacing-timer 1000000 +set OPTS -Z -P __STREAMS__ -l 1M -O__OMIT__ --pacing-timer 1000000 info Throughput in Gbps, latency in µs, one thread at __FREQ__ GHz, __STREAMS__ streams report passt tcp __THREADS__ __FREQ__ diff --git a/test/perf/passt_udp b/test/perf/passt_udp index 6bd86ff..fd2ddc1 100644 --- a/test/perf/passt_udp +++ b/test/perf/passt_udp @@ -38,7 +38,7 @@ hout FREQ [ -n "__FREQ_CPUFREQ__" ] && echo __FREQ_CPUFREQ__ || echo __FREQ_PROC set THREADS 4 set STREAMS 1 set TIME 10 -set OPTS -u -i1 -P __STREAMS__ --pacing-timer 1000 +set OPTS -u -P __STREAMS__ --pacing-timer 1000 info Throughput in Gbps, latency in µs, __THREADS__ threads at __FREQ__ GHz, one stream each diff --git a/test/perf/pasta_tcp b/test/perf/pasta_tcp index 44c5e54..1847c83 100644 --- a/test/perf/pasta_tcp +++ b/test/perf/pasta_tcp @@ -25,7 +25,7 @@ set THREADS 2 set STREAMS 2 set TIME 10 hout OMIT echo __TIME__ / 6 | bc -l -set OPTS -Z -w 4M -l 1M -P __STREAMS__ -i1 -O__OMIT__ --pacing-timer 10000 +set OPTS -Z -w 4M -l 1M -P __STREAMS__ -O__OMIT__ --pacing-timer 10000 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 diff --git a/test/perf/pasta_udp b/test/perf/pasta_udp index abb88b0..27ea724 100644 --- a/test/perf/pasta_udp +++ b/test/perf/pasta_udp @@ -23,7 +23,7 @@ hout FREQ [ -n "__FREQ_CPUFREQ__" ] && echo __FREQ_CPUFREQ__ || echo __FREQ_PROC set THREADS 1 set STREAMS 4 set TIME 10 -set OPTS -u -i1 -P __STREAMS__ +set OPTS -u -P __STREAMS__ info Throughput in Gbps, latency in µs, one thread at __FREQ__ GHz, __STREAMS__ streams |