Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

roachtest: kv50/enc=false/nodes=4/cpu=96/batch=64 failed #35785

Closed
cockroach-teamcity opened this issue Mar 15, 2019 · 9 comments
Closed

roachtest: kv50/enc=false/nodes=4/cpu=96/batch=64 failed #35785

cockroach-teamcity opened this issue Mar 15, 2019 · 9 comments
Assignees
Labels
C-test-failure Broken test (automatically or manually discovered). O-roachtest O-robot Originated from a bot.
Milestone

Comments

@cockroach-teamcity
Copy link
Member

SHA: https://github.com/cockroachdb/cockroach/commits/7ce9188c6e64465d9dcb9f0ca0f113dd0e584da0

Parameters:

To repro, try:

# Don't forget to check out a clean suitable branch and experiment with the
# stress invocation until the desired results present themselves. For example,
# using stress instead of stressrace and passing the '-p' stressflag which
# controls concurrency.
./scripts/gceworker.sh start && ./scripts/gceworker.sh mosh
cd ~/go/src/github.com/cockroachdb/cockroach && \
stdbuf -oL -eL \
make stressrace TESTS=kv50/enc=false/nodes=4/cpu=96/batch=64 PKG=roachtest TESTTIMEOUT=5m STRESSFLAGS='-maxtime 20m -timeout 10m' 2>&1 | tee /tmp/stress.log

Failed test: https://teamcity.cockroachdb.com/viewLog.html?buildId=1178908&tab=buildLog

The test failed on release-2.1:
	cluster.go:1267,kv.go:69,cluster.go:1605,errgroup.go:57: /home/agent/work/.go/src/github.com/cockroachdb/cockroach/bin/roachprod run teamcity-1178908-kv50-enc-false-nodes-4-cpu-96-batch-64:5 -- ./workload run kv --init --splits=1000 --histograms=logs/stats.json --concurrency=256 --duration=10m --read-percent=50 --batch=64 {pgurl:1-4} returned:
		stderr:
		
		stdout:
		 read
		     44s        0          232.9          194.4    671.1   2080.4   2550.1   3489.7 write
		     45s        0          210.1          201.8    167.8    838.9   1208.0   1610.6 read
		     45s        0          237.1          195.4    637.5   1811.9   2952.8   4026.5 write
		     46s        0          216.0          202.1    285.2    872.4   1275.1   1744.8 read
		     46s        0          261.9          196.8    637.5   2147.5   3221.2   5368.7 write
		     47s        0          219.1          202.4    302.0    805.3   1275.1   1610.6 read
		     47s        0          227.1          197.4    704.6   1677.7   3087.0   4563.4 write
		     48s        0          121.0          200.7    260.0    838.9    939.5   1040.2 read
		     48s        0          135.0          196.1    771.8   1744.8   2147.5   2684.4 write
		     49s        0            0.0          196.7      0.0      0.0      0.0      0.0 read
		     49s        0            0.0          192.1      0.0      0.0      0.0      0.0 write
		Error: EOF
		Error:  exit status 1
		: exit status 1
	cluster.go:1626,kv.go:72,kv.go:137,test.go:1214: unexpected node event: 3: dead

@cockroach-teamcity cockroach-teamcity added this to the 19.1 milestone Mar 15, 2019
@cockroach-teamcity cockroach-teamcity added C-test-failure Broken test (automatically or manually discovered). O-roachtest O-robot Originated from a bot. labels Mar 15, 2019
@cockroach-teamcity
Copy link
Member Author

SHA: https://github.com/cockroachdb/cockroach/commits/deb08aa82922ae081c043ff7a6e85960c09910e2

Parameters:

To repro, try:

# Don't forget to check out a clean suitable branch and experiment with the
# stress invocation until the desired results present themselves. For example,
# using stress instead of stressrace and passing the '-p' stressflag which
# controls concurrency.
./scripts/gceworker.sh start && ./scripts/gceworker.sh mosh
cd ~/go/src/github.com/cockroachdb/cockroach && \
stdbuf -oL -eL \
make stressrace TESTS=kv50/enc=false/nodes=4/cpu=96/batch=64 PKG=roachtest TESTTIMEOUT=5m STRESSFLAGS='-maxtime 20m -timeout 10m' 2>&1 | tee /tmp/stress.log

Failed test: https://teamcity.cockroachdb.com/viewLog.html?buildId=1187498&tab=buildLog

The test failed on release-2.1:
	cluster.go:1267,kv.go:69,cluster.go:1605,errgroup.go:57: /home/agent/work/.go/src/github.com/cockroachdb/cockroach/bin/roachprod run teamcity-1187498-kv50-enc-false-nodes-4-cpu-96-batch-64:5 -- ./workload run kv --init --splits=1000 --histograms=logs/stats.json --concurrency=256 --duration=10m --read-percent=50 --batch=64 {pgurl:1-4} returned:
		stderr:
		
		stdout:
		 read
		     55s        0          241.1          221.2    570.4   2013.3   3221.2   4831.8 write
		     56s        0          197.0          222.9    192.9   1006.6   1610.6   2147.5 read
		     56s        0          252.0          221.8    604.0   1946.2   3087.0   3892.3 write
		     57s        0          303.0          224.3    151.0    906.0   1543.5   2684.4 read
		     57s        0          232.0          222.0    604.0   2013.3   3221.2   3355.4 write
		     58s        0          278.0          225.2    125.8    771.8   1073.7   1476.4 read
		     58s        0          251.0          222.5    604.0   1946.2   2818.6   3489.7 write
		     59s        0          216.0          225.0    125.8    805.3    973.1   2281.7 read
		     59s        0          238.0          222.7    671.1   1811.9   2684.4   3087.0 write
		    1m0s        0            0.0          221.3      0.0      0.0      0.0      0.0 read
		    1m0s        0            0.0          219.0      0.0      0.0      0.0      0.0 write
		Error: EOF
		Error:  exit status 1
		: exit status 1
	cluster.go:1626,kv.go:72,kv.go:137,test.go:1214: unexpected node event: 3: dead

@cockroach-teamcity
Copy link
Member Author

SHA: https://github.com/cockroachdb/cockroach/commits/c11656058e4a36c0c62275d7c188ef8921e02928

Parameters:

To repro, try:

# Don't forget to check out a clean suitable branch and experiment with the
# stress invocation until the desired results present themselves. For example,
# using stress instead of stressrace and passing the '-p' stressflag which
# controls concurrency.
./scripts/gceworker.sh start && ./scripts/gceworker.sh mosh
cd ~/go/src/github.com/cockroachdb/cockroach && \
stdbuf -oL -eL \
make stressrace TESTS=kv50/enc=false/nodes=4/cpu=96/batch=64 PKG=roachtest TESTTIMEOUT=5m STRESSFLAGS='-maxtime 20m -timeout 10m' 2>&1 | tee /tmp/stress.log

Failed test: https://teamcity.cockroachdb.com/viewLog.html?buildId=1191975&tab=buildLog

The test failed on release-2.1:
	cluster.go:1267,kv.go:69,cluster.go:1605,errgroup.go:57: /home/agent/work/.go/src/github.com/cockroachdb/cockroach/bin/roachprod run teamcity-1191975-kv50-enc-false-nodes-4-cpu-96-batch-64:5 -- ./workload run kv --init --splits=1000 --histograms=logs/stats.json --concurrency=256 --duration=10m --read-percent=50 --batch=64 {pgurl:1-4} returned:
		stderr:
		
		stdout:
		 read
		      3s        0          237.9          202.0    369.1    939.5   1610.6   2952.8 write
		      4s        0          117.1          176.0    771.8   1208.0   1409.3   1543.5 read
		      4s        0          122.1          182.0    570.4   1342.2   1744.8   1811.9 write
		      5s        0          171.0          175.0    906.0   1409.3   1610.6   1879.0 read
		      5s        0          188.0          183.2    503.3   2281.7   2684.4   3489.7 write
		      6s        0          246.0          186.8    570.4   1073.7   1677.7   2415.9 read
		      6s        0          196.0          185.3    318.8   1879.0   2818.6   3087.0 write
		      7s        0           42.0          166.1    536.9   1073.7   2013.3   2013.3 read
		      7s        0           55.0          166.7    285.2   1073.7   1275.1   3892.3 write
		      8s        0            0.0          145.4      0.0      0.0      0.0      0.0 read
		      8s        0            0.0          145.9      0.0      0.0      0.0      0.0 write
		Error: EOF
		Error:  exit status 1
		: exit status 1
	cluster.go:1626,kv.go:72,kv.go:137,test.go:1214: unexpected node event: 1: dead

@cockroach-teamcity
Copy link
Member Author

SHA: https://github.com/cockroachdb/cockroach/commits/df200cbf3f407dbf349aa601ff9036b4dff88e83

Parameters:

To repro, try:

# Don't forget to check out a clean suitable branch and experiment with the
# stress invocation until the desired results present themselves. For example,
# using stress instead of stressrace and passing the '-p' stressflag which
# controls concurrency.
./scripts/gceworker.sh start && ./scripts/gceworker.sh mosh
cd ~/go/src/github.com/cockroachdb/cockroach && \
stdbuf -oL -eL \
make stressrace TESTS=kv50/enc=false/nodes=4/cpu=96/batch=64 PKG=roachtest TESTTIMEOUT=5m STRESSFLAGS='-maxtime 20m -timeout 10m' 2>&1 | tee /tmp/stress.log

Failed test: https://teamcity.cockroachdb.com/viewLog.html?buildId=1252822&tab=buildLog

The test failed on release-2.1:
	cluster.go:1329,kv.go:69,cluster.go:1667,errgroup.go:57: /home/agent/work/.go/src/github.com/cockroachdb/cockroach/bin/roachprod run teamcity-1252822-kv50-enc-false-nodes-4-cpu-96-batch-64:5 -- ./workload run kv --init --splits=1000 --histograms=logs/stats.json --concurrency=256 --duration=10m --read-percent=50 --batch=64 {pgurl:1-4} returned:
		stderr:
		
		stdout:
		744.8 write
		_elapsed___errors__ops/sec(inst)___ops/sec(cum)__p50(ms)__p95(ms)__p99(ms)_pMax(ms)
		     11s        0          208.8          108.8   1409.3   1879.0   2080.4   2281.7 read
		     11s        0          199.8          110.6   1275.1   2550.1   3221.2   3489.7 write
		     12s        0          184.0          115.1    604.0   1073.7   1476.4   2147.5 read
		     12s        0          183.0          116.7    402.7   2281.7   3623.9   4295.0 write
		     13s        0          204.0          121.9    486.5   1409.3   1811.9   3355.4 read
		     13s        0          187.0          122.1    369.1   2684.4   4563.4   5905.6 write
		     14s        0          154.0          124.2    453.0   1409.3   1677.7   1811.9 read
		     14s        0          136.0          123.1    335.5   1879.0   3623.9   4831.8 write
		     15s        0            0.0          115.9      0.0      0.0      0.0      0.0 read
		     15s        0            0.0          114.9      0.0      0.0      0.0      0.0 write
		Error: EOF
		Error:  exit status 1
		: exit status 1
	cluster.go:1688,kv.go:72,kv.go:137,test.go:1237: unexpected node event: 3: dead
	cluster.go:953,context.go:89,cluster.go:942,asm_amd64.s:522,panic.go:397,test.go:785,test.go:771,cluster.go:1688,kv.go:72,kv.go:137,test.go:1237: dead node detection: /home/agent/work/.go/src/github.com/cockroachdb/cockroach/bin/roachprod monitor teamcity-1252822-kv50-enc-false-nodes-4-cpu-96-batch-64 --oneshot --ignore-empty-nodes: exit status 1 5: skipped
		2: 4681
		4: 5340
		3: dead
		1: 4552
		Error:  3: dead

@tbg
Copy link
Member

tbg commented Apr 23, 2019

Uh oh. @nvanbenschoten take a look at this. Are we maybe missing some backport for the data races you recently fixed? All failures are on 2.1.

E190421 10:37:11.545209 141697 util/log/crash_reporting.go:203  [n3,client=10.142.0.133:46312,user=root,txn=57ea2cc6] a panic has occurred!
panic: runtime error: index out of range [recovered]
	panic: runtime error: index out of range

goroutine 141697 [running]:
panic(0x2777680, 0x4260d80)
	/usr/local/go/src/runtime/panic.go:551 +0x3c1 fp=0xc42fd7e318 sp=0xc42fd7e278 pc=0x6de8e1
github.com/cockroachdb/cockroach/pkg/util/stop.(*Stopper).Recover(0xc4208f8090, 0x305d860, 0xc42be55890)
	/go/src/github.com/cockroachdb/cockroach/pkg/util/stop/stopper.go:184 +0x11f fp=0xc42fd7e378 sp=0xc42fd7e318 pc=0xf0f58f
runtime.call32(0x0, 0x2c3c328, 0xc428bf63f0, 0x1800000018)
	/usr/local/go/src/runtime/asm_amd64.s:573 +0x3b fp=0xc42fd7e3a8 sp=0xc42fd7e378 pc=0x70bc7b
panic(0x2777680, 0x4260d80)
	/usr/local/go/src/runtime/panic.go:502 +0x229 fp=0xc42fd7e448 sp=0xc42fd7e3a8 pc=0x6de749
runtime.panicindex()
	/usr/local/go/src/runtime/panic.go:28 +0x5e fp=0xc42fd7e468 sp=0xc42fd7e448 pc=0x6dd58e
github.com/cockroachdb/cockroach/pkg/roachpb.(*Value).MarshalTo(0xc42d197378, 0xc42fcb7949, 0xa, 0xa, 0xc, 0x14, 0x0)
	/go/src/github.com/cockroachdb/cockroach/pkg/roachpb/data.pb.go:1069 +0x21d fp=0xc42fd7e4c8 sp=0xc42fd7e468 pc=0xe6a17d
github.com/cockroachdb/cockroach/pkg/roachpb.(*PutRequest).MarshalTo(0xc42d197340, 0xc42fcb7935, 0x1e, 0x1e, 0x20, 0x2, 0x1)
	/go/src/github.com/cockroachdb/cockroach/pkg/roachpb/api.pb.go:6905 +0x1ba fp=0xc42fd7e528 sp=0xc42fd7e4c8 pc=0xdce06a
github.com/cockroachdb/cockroach/pkg/roachpb.(*RequestUnion_Put).MarshalTo(0xc42848a358, 0xc42fcb7933, 0x20, 0x20, 0xdf1409, 0xc42848a358, 0x22)
	/go/src/github.com/cockroachdb/cockroach/pkg/roachpb/api.pb.go:10346 +0xe1 fp=0xc42fd7e578 sp=0xc42fd7e528 pc=0xde27e1
github.com/cockroachdb/cockroach/pkg/roachpb.(*RequestUnion).MarshalTo(0xc42fd7e620, 0xc42fcb7933, 0x20, 0x20, 0x22, 0xb3, 0x0)
	/go/src/github.com/cockroachdb/cockroach/pkg/roachpb/api.pb.go:10317 +0x73 fp=0xc42fd7e5c0 sp=0xc42fd7e578 pc=0xde2563
github.com/cockroachdb/cockroach/pkg/roachpb.(*BatchRequest).MarshalTo(0xc434875100, 0xc42fcb7880, 0xd3, 0xd3, 0xd3, 0xd3, 0x2aa8a00)
	/go/src/github.com/cockroachdb/cockroach/pkg/roachpb/api.pb.go:11729 +0x245 fp=0xc42fd7e640 sp=0xc42fd7e5c0 pc=0xdea4f5
github.com/cockroachdb/cockroach/pkg/roachpb.(*BatchRequest).Marshal(0xc434875100, 0x2aa8a00, 0xc434875100, 0x7fe5af4a2650, 0xc434875100, 0xc42fd7e601)
	/go/src/github.com/cockroachdb/cockroach/pkg/roachpb/api.pb.go:11704 +0x7f fp=0xc42fd7e698 sp=0xc42fd7e640 pc=0xdea22f
github.com/cockroachdb/cockroach/vendor/google.golang.org/grpc/encoding/proto.codec.Marshal(0x2aa8a00, 0xc434875100, 0x6b6f16, 0x3, 0xc4200cc070, 0xc4200cc000, 0xc434998f58)
	/go/src/github.com/cockroachdb/cockroach/vendor/google.golang.org/grpc/encoding/proto/proto.go:70 +0x19e fp=0xc42fd7e718 sp=0xc42fd7e698 pc=0xbd60be
github.com/cockroachdb/cockroach/vendor/google.golang.org/grpc/encoding/proto.(*codec).Marshal(0x48833e8, 0x2aa8a00, 0xc434875100, 0x6de194, 0x2c3e220, 0xc42fd7e7d0, 0x10, 0xc42c768900)
	<autogenerated>:1 +0x48 fp=0xc42fd7e760 sp=0xc42fd7e718 pc=0xbd6838
github.com/cockroachdb/cockroach/vendor/google.golang.org/grpc.encode(0x7fe5af43e678, 0x48833e8, 0x2aa8a00, 0xc434875100, 0xc429f423f0, 0x0, 0xc429f423f0, 0x0, 0xbf272fd5e07dffd2)
	/go/src/github.com/cockroachdb/cockroach/vendor/google.golang.org/grpc/rpc_util.go:487 +0x61 fp=0xc42fd7e7e8 sp=0xc42fd7e760 pc=0xbee9e1
github.com/cockroachdb/cockroach/vendor/google.golang.org/grpc.(*csAttempt).sendMsg(0xc429d47ad0, 0x2aa8a00, 0xc434875100, 0x0, 0x0)
	/go/src/github.com/cockroachdb/cockroach/vendor/google.golang.org/grpc/stream.go:479 +0xc9 fp=0xc42fd7e908 sp=0xc42fd7e7e8 pc=0xbfbb99
github.com/cockroachdb/cockroach/vendor/google.golang.org/grpc.(*clientStream).SendMsg(0xc434875200, 0x2aa8a00, 0xc434875100, 0xc420a3cf00, 0x2b1f443)
	/go/src/github.com/cockroachdb/cockroach/vendor/google.golang.org/grpc/stream.go:400 +0x43 fp=0xc42fd7e940 sp=0xc42fd7e908 pc=0xbfb763
github.com/cockroachdb/cockroach/vendor/google.golang.org/grpc.invoke(0x305d860, 0xc42be55890, 0x2b1f443, 0x21, 0x2aa8a00, 0xc434875100, 0x2997ca0, 0xc420ef1d40, 0xc420a3cf00, 0xc4259d5200, ...)
	/go/src/github.com/cockroachdb/cockroach/vendor/google.golang.org/grpc/call.go:75 +0xfe fp=0xc42fd7e9c8 sp=0xc42fd7e940 pc=0xbde54e
github.com/cockroachdb/cockroach/vendor/github.com/grpc-ecosystem/grpc-opentracing/go/otgrpc.OpenTracingClientInterceptor.func1(0x305d860, 0xc42be55890, 0x2b1f443, 0x21, 0x2aa8a00, 0xc434875100, 0x2997ca0, 0xc420ef1d40, 0xc420a3cf00, 0x2c3e210, ...)
	/go/src/github.com/cockroachdb/cockroach/vendor/github.com/grpc-ecosystem/grpc-opentracing/go/otgrpc/client.go:44 +0xe28 fp=0xc42fd7ede8 sp=0xc42fd7e9c8 pc=0x14d1268
github.com/cockroachdb/cockroach/vendor/google.golang.org/grpc.(*ClientConn).Invoke(0xc420a3cf00, 0x305d860, 0xc42be55890, 0x2b1f443, 0x21, 0x2aa8a00, 0xc434875100, 0x2997ca0, 0xc420ef1d40, 0x0, ...)
	/go/src/github.com/cockroachdb/cockroach/vendor/google.golang.org/grpc/call.go:35 +0x109 fp=0xc42fd7eea0 sp=0xc42fd7ede8 pc=0xbde109
github.com/cockroachdb/cockroach/vendor/google.golang.org/grpc.Invoke(0x305d860, 0xc42be55890, 0x2b1f443, 0x21, 0x2aa8a00, 0xc434875100, 0x2997ca0, 0xc420ef1d40, 0xc420a3cf00, 0x0, ...)
	/go/src/github.com/cockroachdb/cockroach/vendor/google.golang.org/grpc/call.go:60 +0xc1 fp=0xc42fd7ef20 sp=0xc42fd7eea0 pc=0xbde421
github.com/cockroachdb/cockroach/pkg/roachpb.(*internalClient).Batch(0xc42592c7f8, 0x305d860, 0xc42be55890, 0xc434875100, 0x0, 0x0, 0x0, 0x305d860, 0xc42be55890, 0x100000002)
	/go/src/github.com/cockroachdb/cockroach/pkg/roachpb/api.pb.go:6570 +0xd2 fp=0xc42fd7efa8 sp=0xc42fd7ef20 pc=0xdcc0d2
github.com/cockroachdb/cockroach/pkg/kv.(*grpcTransport).sendBatch(0xc429f42390, 0x305d860, 0xc42be55890, 0x303a360, 0xc42592c7f8, 0x0, 0x0, 0x20000

@nvanbenschoten
Copy link
Member

None of the fixes for the data races are on 2.1 yet. I'll backport them.

It looks like we picked this up at least twice on Sentry: #34674.

@cockroach-teamcity
Copy link
Member Author

SHA: https://github.com/cockroachdb/cockroach/commits/d554884a4e474cc06213230d5ba7d757a88e9e46

Parameters:

To repro, try:

# Don't forget to check out a clean suitable branch and experiment with the
# stress invocation until the desired results present themselves. For example,
# using stress instead of stressrace and passing the '-p' stressflag which
# controls concurrency.
./scripts/gceworker.sh start && ./scripts/gceworker.sh mosh
cd ~/go/src/github.com/cockroachdb/cockroach && \
stdbuf -oL -eL \
make stressrace TESTS=kv50/enc=false/nodes=4/cpu=96/batch=64 PKG=roachtest TESTTIMEOUT=5m STRESSFLAGS='-maxtime 20m -timeout 10m' 2>&1 | tee /tmp/stress.log

Failed test: https://teamcity.cockroachdb.com/viewLog.html?buildId=1279548&tab=buildLog

The test failed on branch=release-2.1, cloud=gce:
	cluster.go:1474,kv.go:69,cluster.go:1812,errgroup.go:57: /home/agent/work/.go/src/github.com/cockroachdb/cockroach/bin/roachprod run teamcity-1279548-kv50-enc-false-nodes-4-cpu-96-batch-64:5 -- ./workload run kv --init --splits=1000 --histograms=logs/stats.json --concurrency=256 --duration=10m --read-percent=50 --batch=64 {pgurl:1-4} returned:
		stderr:
		
		stdout:
		563.4 write
		_elapsed___errors__ops/sec(inst)___ops/sec(cum)__p50(ms)__p95(ms)__p99(ms)_pMax(ms)
		     11s        0          229.9          190.1    436.2    872.4   1073.7   1543.5 read
		     11s        0          242.9          189.7    369.1   1677.7   3087.0   4831.8 write
		     12s        0          241.0          194.3    436.2    838.9   1208.0   1543.5 read
		     12s        0          241.0          194.0    369.1   1946.2   3758.1   6979.3 write
		     13s        0          215.9          196.0    419.4   1040.2   1677.7   2013.3 read
		     13s        0          235.9          197.2    402.7   1811.9   3221.2   5905.6 write
		     14s        0           82.1          187.9    385.9    973.1   1275.1   1409.3 read
		     14s        0           64.1          187.7    335.5   1476.4   1946.2   3892.3 write
		     15s        0            0.0          175.3      0.0      0.0      0.0      0.0 read
		     15s        0            0.0          175.2      0.0      0.0      0.0      0.0 write
		Error: EOF
		Error:  exit status 1
		: exit status 1
	cluster.go:1833,kv.go:72,kv.go:137,test.go:1251: unexpected node event: 3: dead
	cluster.go:1038,context.go:89,cluster.go:1027,asm_amd64.s:522,panic.go:397,test.go:788,test.go:774,cluster.go:1833,kv.go:72,kv.go:137,test.go:1251: dead node detection: /home/agent/work/.go/src/github.com/cockroachdb/cockroach/bin/roachprod monitor teamcity-1279548-kv50-enc-false-nodes-4-cpu-96-batch-64 --oneshot --ignore-empty-nodes: exit status 1 5: skipped
		2: 4768
		4: 4796
		3: dead
		1: 4842
		Error:  3: dead

@cockroach-teamcity
Copy link
Member Author

SHA: https://github.com/cockroachdb/cockroach/commits/d554884a4e474cc06213230d5ba7d757a88e9e46

Parameters:

To repro, try:

# Don't forget to check out a clean suitable branch and experiment with the
# stress invocation until the desired results present themselves. For example,
# using stress instead of stressrace and passing the '-p' stressflag which
# controls concurrency.
./scripts/gceworker.sh start && ./scripts/gceworker.sh mosh
cd ~/go/src/github.com/cockroachdb/cockroach && \
stdbuf -oL -eL \
make stressrace TESTS=kv50/enc=false/nodes=4/cpu=96/batch=64 PKG=roachtest TESTTIMEOUT=5m STRESSFLAGS='-maxtime 20m -timeout 10m' 2>&1 | tee /tmp/stress.log

Failed test: https://teamcity.cockroachdb.com/viewLog.html?buildId=1281453&tab=buildLog

The test failed on branch=release-2.1, cloud=gce:
	cluster.go:1474,kv.go:69,cluster.go:1812,errgroup.go:57: /home/agent/work/.go/src/github.com/cockroachdb/cockroach/bin/roachprod run teamcity-1281453-kv50-enc-false-nodes-4-cpu-96-batch-64:5 -- ./workload run kv --init --splits=1000 --histograms=logs/stats.json --concurrency=256 --duration=10m --read-percent=50 --batch=64 {pgurl:1-4} returned:
		stderr:
		
		stdout:
		1000 splits
		_elapsed___errors__ops/sec(inst)___ops/sec(cum)__p50(ms)__p95(ms)__p99(ms)_pMax(ms)
		      1s        0            4.5           43.0    906.0   1006.6   1006.6   1006.6 read
		      1s        0           16.7          159.0    402.7    906.0   1006.6   1006.6 write
		      2s        0          160.9          102.0   1476.4   1946.2   1946.2   2013.3 read
		      2s        0          102.9          131.0    453.0   1476.4   1610.6   1811.9 write
		      3s        0          261.9          155.3    604.0   1543.5   2080.4   2415.9 read
		      3s        0          210.9          157.6    285.2    704.6   2281.7   2415.9 write
		      4s        0          167.0          158.2    805.3   1006.6   1073.7   1140.9 read
		      4s        0          143.0          154.0    436.2    973.1   1073.7   1140.9 write
		      5s        0            0.0          126.6      0.0      0.0      0.0      0.0 read
		      5s        0            0.0          123.2      0.0      0.0      0.0      0.0 write
		Error: EOF
		Error:  exit status 1
		: exit status 1
	cluster.go:1833,kv.go:72,kv.go:137,test.go:1251: unexpected node event: 2: dead
	cluster.go:1038,context.go:89,cluster.go:1027,asm_amd64.s:522,panic.go:397,test.go:788,test.go:774,cluster.go:1833,kv.go:72,kv.go:137,test.go:1251: dead node detection: /home/agent/work/.go/src/github.com/cockroachdb/cockroach/bin/roachprod monitor teamcity-1281453-kv50-enc-false-nodes-4-cpu-96-batch-64 --oneshot --ignore-empty-nodes: exit status 1 5: skipped
		2: dead
		3: 4735
		1: 4854
		4: 4786
		Error:  2: dead

@yuzefovich yuzefovich mentioned this issue May 9, 2019
14 tasks
@cockroach-teamcity
Copy link
Member Author

SHA: https://github.com/cockroachdb/cockroach/commits/d554884a4e474cc06213230d5ba7d757a88e9e46

Parameters:

To repro, try:

# Don't forget to check out a clean suitable branch and experiment with the
# stress invocation until the desired results present themselves. For example,
# using stress instead of stressrace and passing the '-p' stressflag which
# controls concurrency.
./scripts/gceworker.sh start && ./scripts/gceworker.sh mosh
cd ~/go/src/github.com/cockroachdb/cockroach && \
stdbuf -oL -eL \
make stressrace TESTS=kv50/enc=false/nodes=4/cpu=96/batch=64 PKG=roachtest TESTTIMEOUT=5m STRESSFLAGS='-maxtime 20m -timeout 10m' 2>&1 | tee /tmp/stress.log

Failed test: https://teamcity.cockroachdb.com/viewLog.html?buildId=1286052&tab=buildLog

The test failed on branch=release-2.1, cloud=gce:
	cluster.go:1474,kv.go:69,cluster.go:1812,errgroup.go:57: /home/agent/work/.go/src/github.com/cockroachdb/cockroach/bin/roachprod run teamcity-1286052-kv50-enc-false-nodes-4-cpu-96-batch-64:5 -- ./workload run kv --init --splits=1000 --histograms=logs/stats.json --concurrency=256 --duration=10m --read-percent=50 --batch=64 {pgurl:1-4} returned:
		stderr:
		
		stdout:
		 read
		     14s        0          271.0          190.9    251.7   1946.2   3221.2   7247.8 write
		     15s        0          254.0          201.7    268.4    872.4   1342.2   1409.3 read
		     15s        0          236.0          193.9    260.0   2013.3   3758.1   4831.8 write
		     16s        0          198.0          201.4    285.2   1610.6   2281.7   2281.7 read
		     16s        0          190.0          193.7    285.2   2415.9   2818.6   4295.0 write
		     17s        0          214.0          202.2    402.7   1879.0   2684.4   2684.4 read
		     17s        0          225.0          195.5    385.9   2550.1   3623.9   6710.9 write
		     18s        0          178.0          200.8    352.3   1610.6   2684.4   3355.4 read
		     18s        0          197.0          195.6    385.9   2415.9   4831.8  12348.0 write
		     19s        0            0.0          190.3      0.0      0.0      0.0      0.0 read
		     19s        0            0.0          185.3      0.0      0.0      0.0      0.0 write
		Error: EOF
		Error:  exit status 1
		: exit status 1
	cluster.go:1833,kv.go:72,kv.go:137,test.go:1251: unexpected node event: 3: dead
	cluster.go:1038,context.go:89,cluster.go:1027,asm_amd64.s:522,panic.go:397,test.go:788,test.go:774,cluster.go:1833,kv.go:72,kv.go:137,test.go:1251: dead node detection: /home/agent/work/.go/src/github.com/cockroachdb/cockroach/bin/roachprod monitor teamcity-1286052-kv50-enc-false-nodes-4-cpu-96-batch-64 --oneshot --ignore-empty-nodes: exit status 1 5: skipped
		4: 4732
		3: dead
		1: 4928
		2: 4783
		Error:  3: dead

@nvanbenschoten
Copy link
Member

Closed by #37495.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
C-test-failure Broken test (automatically or manually discovered). O-roachtest O-robot Originated from a bot.
Projects
None yet
Development

No branches or pull requests

3 participants