From 28d6a453a9d5b1ec12a1b5ec4f21cf275f01d3d4 Mon Sep 17 00:00:00 2001 From: Szilard Nemeth Date: Mon, 15 Jul 2019 11:59:11 +0200 Subject: [PATCH] YARN-9127. Create more tests to verify GpuDeviceInformationParser. Contributed by Peter Bacsko (cherry picked from commit 18ee1092b471c5337f05809f8f01dae415e51a3a) --- ...esource-types-error-redefine-fpga-unit.xml | 45 ++ ...resource-types-error-redefine-gpu-unit.xml | 45 ++ .../resourceplugin/gpu/GpuDiscoverer.java | 2 +- .../webapp/dao/gpu/GpuDeviceInformation.java | 18 +- .../dao/gpu/GpuDeviceInformationParser.java | 48 +- .../dao/gpu/PerGpuDeviceInformation.java | 1 - .../webapp/dao/gpu/PerGpuMemoryUsage.java | 7 +- .../gpu/TestGpuDeviceInformationParser.java | 159 ++++- .../resources/nvidia-smi-output-excerpt.xml | 71 +++ .../nvidia-smi-output-missing-tags.xml | 28 + .../nvidia-smi-output-missing-tags2.xml | 61 ++ .../resources/nvidia-smi-sample-output.xml | 547 ++++++++++++++++++ .../resources/nvidia-smi-sample-xml-output | 547 ------------------ 13 files changed, 978 insertions(+), 601 deletions(-) create mode 100644 hadoop-yarn-project/hadoop-yarn/hadoop-yarn-common/src/test/resources/resource-types/resource-types-error-redefine-fpga-unit.xml create mode 100644 hadoop-yarn-project/hadoop-yarn/hadoop-yarn-common/src/test/resources/resource-types/resource-types-error-redefine-gpu-unit.xml create mode 100644 hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/test/resources/nvidia-smi-output-excerpt.xml create mode 100644 hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/test/resources/nvidia-smi-output-missing-tags.xml create mode 100644 hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/test/resources/nvidia-smi-output-missing-tags2.xml create mode 100644 hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/test/resources/nvidia-smi-sample-output.xml delete mode 100644 hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/test/resources/nvidia-smi-sample-xml-output diff --git a/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-common/src/test/resources/resource-types/resource-types-error-redefine-fpga-unit.xml b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-common/src/test/resources/resource-types/resource-types-error-redefine-fpga-unit.xml new file mode 100644 index 00000000000..72cfb9888a9 --- /dev/null +++ b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-common/src/test/resources/resource-types/resource-types-error-redefine-fpga-unit.xml @@ -0,0 +1,45 @@ + + + + + + + + + + yarn.resource-types + yarn.io/fpga + + + + yarn.resource-types.yarn.io/fpga.units + G + + + diff --git a/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-common/src/test/resources/resource-types/resource-types-error-redefine-gpu-unit.xml b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-common/src/test/resources/resource-types/resource-types-error-redefine-gpu-unit.xml new file mode 100644 index 00000000000..aa61b5f40bb --- /dev/null +++ b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-common/src/test/resources/resource-types/resource-types-error-redefine-gpu-unit.xml @@ -0,0 +1,45 @@ + + + + + + + + + + yarn.resource-types + yarn.io/gpu + + + + yarn.resource-types.yarn.io/gpu.units + G + + + diff --git a/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/java/org/apache/hadoop/yarn/server/nodemanager/containermanager/resourceplugin/gpu/GpuDiscoverer.java b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/java/org/apache/hadoop/yarn/server/nodemanager/containermanager/resourceplugin/gpu/GpuDiscoverer.java index 27a4ea1e4a1..ce767229e50 100644 --- a/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/java/org/apache/hadoop/yarn/server/nodemanager/containermanager/resourceplugin/gpu/GpuDiscoverer.java +++ b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/java/org/apache/hadoop/yarn/server/nodemanager/containermanager/resourceplugin/gpu/GpuDiscoverer.java @@ -64,7 +64,6 @@ public class GpuDiscoverer { private Configuration conf = null; private String pathOfGpuBinary = null; private Map environment = new HashMap<>(); - private GpuDeviceInformationParser parser = new GpuDeviceInformationParser(); private int numOfErrorExecutionSinceLastSucceed = 0; private GpuDeviceInformation lastDiscoveredGpuInformation = null; @@ -125,6 +124,7 @@ public class GpuDiscoverer { try { output = Shell.execCommand(environment, new String[] { pathOfGpuBinary, "-x", "-q" }, MAX_EXEC_TIMEOUT_MS); + GpuDeviceInformationParser parser = new GpuDeviceInformationParser(); lastDiscoveredGpuInformation = parser.parseXml(output); numOfErrorExecutionSinceLastSucceed = 0; return lastDiscoveredGpuInformation; diff --git a/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/java/org/apache/hadoop/yarn/server/nodemanager/webapp/dao/gpu/GpuDeviceInformation.java b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/java/org/apache/hadoop/yarn/server/nodemanager/webapp/dao/gpu/GpuDeviceInformation.java index 837d5cc99cd..c830d432a6b 100644 --- a/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/java/org/apache/hadoop/yarn/server/nodemanager/webapp/dao/gpu/GpuDeviceInformation.java +++ b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/java/org/apache/hadoop/yarn/server/nodemanager/webapp/dao/gpu/GpuDeviceInformation.java @@ -21,6 +21,7 @@ package org.apache.hadoop.yarn.server.nodemanager.webapp.dao.gpu; import org.apache.hadoop.classification.InterfaceAudience; import org.apache.hadoop.classification.InterfaceStability; +import javax.xml.bind.annotation.XmlElement; import javax.xml.bind.annotation.XmlRootElement; import java.util.List; @@ -31,14 +32,10 @@ import java.util.List; @InterfaceStability.Unstable @XmlRootElement(name = "nvidia_smi_log") public class GpuDeviceInformation { - List gpus; + private List gpus; + private String driverVersion = "N/A"; - String driverVersion = "N/A"; - - // More fields like topology information could be added when needed. - // ... - - @javax.xml.bind.annotation.XmlElement(name = "gpu") + @XmlElement(name = "gpu") public List getGpus() { return gpus; } @@ -47,7 +44,7 @@ public class GpuDeviceInformation { this.gpus = gpus; } - @javax.xml.bind.annotation.XmlElement(name = "driver_version") + @XmlElement(name = "driver_version") public String getDriverVersion() { return driverVersion; } @@ -59,8 +56,9 @@ public class GpuDeviceInformation { @Override public String toString() { StringBuilder sb = new StringBuilder(); - sb.append("=== Gpus in the system ===\n").append("\tDriver Version:").append( - getDriverVersion()).append("\n"); + sb.append("=== GPUs in the system ===\n") + .append("\tDriver Version:") + .append(getDriverVersion()).append("\n"); if (gpus != null) { for (PerGpuDeviceInformation gpu : gpus) { diff --git a/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/java/org/apache/hadoop/yarn/server/nodemanager/webapp/dao/gpu/GpuDeviceInformationParser.java b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/java/org/apache/hadoop/yarn/server/nodemanager/webapp/dao/gpu/GpuDeviceInformationParser.java index 894cb70ca61..5c166571ccc 100644 --- a/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/java/org/apache/hadoop/yarn/server/nodemanager/webapp/dao/gpu/GpuDeviceInformationParser.java +++ b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/java/org/apache/hadoop/yarn/server/nodemanager/webapp/dao/gpu/GpuDeviceInformationParser.java @@ -24,13 +24,11 @@ import org.apache.hadoop.yarn.exceptions.YarnException; import org.slf4j.Logger; import org.slf4j.LoggerFactory; import org.xml.sax.InputSource; -import org.xml.sax.SAXException; import org.xml.sax.XMLReader; import javax.xml.bind.JAXBContext; import javax.xml.bind.JAXBException; import javax.xml.bind.Unmarshaller; -import javax.xml.parsers.ParserConfigurationException; import javax.xml.parsers.SAXParserFactory; import javax.xml.transform.sax.SAXSource; import java.io.StringReader; @@ -46,39 +44,39 @@ public class GpuDeviceInformationParser { public static final String GPU_SCRIPT_REFERENCE = "GPU device detection " + "script"; - private Unmarshaller unmarshaller = null; - private XMLReader xmlReader = null; + private final Unmarshaller unmarshaller; + private final XMLReader xmlReader; - private void init() - throws SAXException, ParserConfigurationException, JAXBException { + public GpuDeviceInformationParser() throws YarnException { + try { + final SAXParserFactory parserFactory = initSaxParserFactory(); + final JAXBContext jaxbContext = JAXBContext.newInstance( + GpuDeviceInformation.class); + this.xmlReader = parserFactory.newSAXParser().getXMLReader(); + this.unmarshaller = jaxbContext.createUnmarshaller(); + } catch (Exception e) { + String msg = "Exception while initializing parser for " + + GPU_SCRIPT_REFERENCE; + LOG.error(msg, e); + throw new YarnException(msg, e); + } + } + + /** + * Disable external-dtd since by default nvidia-smi output contains + * <!DOCTYPE nvidia_smi_log SYSTEM "nvsmi_device_v8.dtd"> in header. + */ + private SAXParserFactory initSaxParserFactory() throws Exception { SAXParserFactory spf = SAXParserFactory.newInstance(); - // Disable external-dtd since by default nvidia-smi output contains - // in header spf.setFeature( "http://apache.org/xml/features/nonvalidating/load-external-dtd", false); spf.setFeature("http://xml.org/sax/features/validation", false); - - JAXBContext jaxbContext = JAXBContext.newInstance( - GpuDeviceInformation.class); - - this.xmlReader = spf.newSAXParser().getXMLReader(); - this.unmarshaller = jaxbContext.createUnmarshaller(); + return spf; } public synchronized GpuDeviceInformation parseXml(String xmlContent) throws YarnException { - if (unmarshaller == null) { - try { - init(); - } catch (SAXException | ParserConfigurationException | JAXBException e) { - String msg = "Exception while initializing parser for " + - GPU_SCRIPT_REFERENCE; - LOG.error(msg, e); - throw new YarnException(e); - } - } - InputSource inputSource = new InputSource(new StringReader(xmlContent)); SAXSource source = new SAXSource(xmlReader, inputSource); try { diff --git a/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/java/org/apache/hadoop/yarn/server/nodemanager/webapp/dao/gpu/PerGpuDeviceInformation.java b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/java/org/apache/hadoop/yarn/server/nodemanager/webapp/dao/gpu/PerGpuDeviceInformation.java index 25c2e3a1f1d..11ff2a4c49c 100644 --- a/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/java/org/apache/hadoop/yarn/server/nodemanager/webapp/dao/gpu/PerGpuDeviceInformation.java +++ b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/java/org/apache/hadoop/yarn/server/nodemanager/webapp/dao/gpu/PerGpuDeviceInformation.java @@ -33,7 +33,6 @@ import javax.xml.bind.annotation.adapters.XmlAdapter; @InterfaceStability.Unstable @XmlRootElement(name = "gpu") public class PerGpuDeviceInformation { - private String productName = "N/A"; private String uuid = "N/A"; private int minorNumber = -1; diff --git a/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/java/org/apache/hadoop/yarn/server/nodemanager/webapp/dao/gpu/PerGpuMemoryUsage.java b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/java/org/apache/hadoop/yarn/server/nodemanager/webapp/dao/gpu/PerGpuMemoryUsage.java index afc1a9679b7..1c2c0c49b84 100644 --- a/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/java/org/apache/hadoop/yarn/server/nodemanager/webapp/dao/gpu/PerGpuMemoryUsage.java +++ b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/main/java/org/apache/hadoop/yarn/server/nodemanager/webapp/dao/gpu/PerGpuMemoryUsage.java @@ -29,8 +29,8 @@ import javax.xml.bind.annotation.adapters.XmlJavaTypeAdapter; @InterfaceStability.Unstable @XmlRootElement(name = "fb_memory_usage") public class PerGpuMemoryUsage { - long usedMemoryMiB = -1L; - long availMemoryMiB = -1L; + private long usedMemoryMiB = -1L; + private long availMemoryMiB = -1L; @XmlJavaTypeAdapter(PerGpuDeviceInformation.StrToMemAdapter.class) @XmlElement(name = "used") @@ -53,6 +53,9 @@ public class PerGpuMemoryUsage { } public long getTotalMemoryMiB() { + if (usedMemoryMiB == -1 && availMemoryMiB == -1) { + return -1; + } return usedMemoryMiB + availMemoryMiB; } } diff --git a/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/test/java/org/apache/hadoop/yarn/server/nodemanager/webapp/dao/gpu/TestGpuDeviceInformationParser.java b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/test/java/org/apache/hadoop/yarn/server/nodemanager/webapp/dao/gpu/TestGpuDeviceInformationParser.java index dc96746cf5d..28e06b72bc4 100644 --- a/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/test/java/org/apache/hadoop/yarn/server/nodemanager/webapp/dao/gpu/TestGpuDeviceInformationParser.java +++ b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/test/java/org/apache/hadoop/yarn/server/nodemanager/webapp/dao/gpu/TestGpuDeviceInformationParser.java @@ -20,31 +20,160 @@ package org.apache.hadoop.yarn.server.nodemanager.webapp.dao.gpu; import org.apache.commons.io.FileUtils; import org.apache.hadoop.yarn.exceptions.YarnException; -import org.junit.Assert; +import org.junit.Rule; import org.junit.Test; +import org.junit.rules.ExpectedException; import java.io.File; import java.io.IOException; +import static org.junit.Assert.assertEquals; +import static org.junit.Assert.assertNull; + public class TestGpuDeviceInformationParser { + private static final String UTF_8 = "UTF-8"; + private static final double DELTA = 1e-6; + + @Rule + public ExpectedException expected = ExpectedException.none(); + @Test public void testParse() throws IOException, YarnException { - File f = new File("src/test/resources/nvidia-smi-sample-xml-output"); - String s = FileUtils.readFileToString(f, "UTF-8"); + File f = new File("src/test/resources/nvidia-smi-sample-output.xml"); + String s = FileUtils.readFileToString(f, UTF_8); GpuDeviceInformationParser parser = new GpuDeviceInformationParser(); - GpuDeviceInformation info = parser.parseXml(s); - Assert.assertEquals("375.66", info.getDriverVersion()); - Assert.assertEquals(2, info.getGpus().size()); - PerGpuDeviceInformation gpu1 = info.getGpus().get(1); - Assert.assertEquals("Tesla P100-PCIE-12GB", gpu1.getProductName()); - Assert.assertEquals(12193, gpu1.getGpuMemoryUsage().getTotalMemoryMiB()); - Assert.assertEquals(10.3f, - gpu1.getGpuUtilizations().getOverallGpuUtilization(), 1e-6); - Assert.assertEquals(34f, gpu1.getTemperature().getCurrentGpuTemp(), 1e-6); - Assert.assertEquals(85f, gpu1.getTemperature().getMaxGpuTemp(), 1e-6); - Assert.assertEquals(82f, gpu1.getTemperature().getSlowThresholdGpuTemp(), - 1e-6); + + assertEquals("375.66", info.getDriverVersion()); + assertEquals(2, info.getGpus().size()); + assertFirstGpu(info.getGpus().get(0)); + assertSecondGpu(info.getGpus().get(1)); + } + + @Test + public void testParseExcerpt() throws IOException, YarnException { + File f = new File("src/test/resources/nvidia-smi-output-excerpt.xml"); + String s = FileUtils.readFileToString(f, UTF_8); + + GpuDeviceInformationParser parser = new GpuDeviceInformationParser(); + GpuDeviceInformation info = parser.parseXml(s); + + assertEquals("375.66", info.getDriverVersion()); + assertEquals(2, info.getGpus().size()); + assertFirstGpu(info.getGpus().get(0)); + assertSecondGpu(info.getGpus().get(1)); + } + + @Test + public void testParseConsecutivelyWithSameParser() + throws IOException, YarnException { + File f = new File("src/test/resources/nvidia-smi-sample-output.xml"); + String s = FileUtils.readFileToString(f, UTF_8); + + for (int i = 0; i < 3; i++) { + GpuDeviceInformationParser parser = new GpuDeviceInformationParser(); + GpuDeviceInformation info = parser.parseXml(s); + + assertEquals("375.66", info.getDriverVersion()); + assertEquals(2, info.getGpus().size()); + assertFirstGpu(info.getGpus().get(0)); + assertSecondGpu(info.getGpus().get(1)); + } + } + + @Test + public void testParseEmptyString() throws YarnException { + expected.expect(YarnException.class); + GpuDeviceInformationParser parser = new GpuDeviceInformationParser(); + parser.parseXml(""); + } + + @Test + public void testParseInvalidRootElement() throws YarnException { + expected.expect(YarnException.class); + GpuDeviceInformationParser parser = new GpuDeviceInformationParser(); + parser.parseXml(" + + + + + + Wed Sep 6 21:52:51 2017 + 375.66 + 2 + + Tesla P100-PCIE-12GB + Tesla + GPU-28604e81-21ec-cc48-6759-bf2648b22e16 + 0 + + 11567 MiB + 11400 MiB + 167 MiB + + + 33.4 % + 0 % + 0 % + 0 % + + + 31 C + 80 C + 88 C + + + + + Tesla P100-PCIE-12GB_2 + Tesla + GPU-46915a82-3fd2-8e11-ae26-a80b607c04f3 + 1 + + 12290 MiB + 11800 MiB + 490 MiB + + Default + + 10.3 % + 0 % + 0 % + 0 % + + + 34 C + 85 C + 82 C + + + + \ No newline at end of file diff --git a/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/test/resources/nvidia-smi-output-missing-tags.xml b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/test/resources/nvidia-smi-output-missing-tags.xml new file mode 100644 index 00000000000..df341d36a15 --- /dev/null +++ b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/test/resources/nvidia-smi-output-missing-tags.xml @@ -0,0 +1,28 @@ + + + + + + + Wed Sep 6 21:52:51 2017 + 375.66 + 2 + + Tesla + + + \ No newline at end of file diff --git a/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/test/resources/nvidia-smi-output-missing-tags2.xml b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/test/resources/nvidia-smi-output-missing-tags2.xml new file mode 100644 index 00000000000..add92a83d7d --- /dev/null +++ b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/test/resources/nvidia-smi-output-missing-tags2.xml @@ -0,0 +1,61 @@ + + + + + + + Wed Sep 6 21:52:51 2017 + 375.66 + 2 + + Tesla P100-PCIE-12GB + Tesla + GPU-28604e81-21ec-cc48-6759-bf2648b22e16 + 0 + + + + + + + + + + Tesla P100-PCIE-12GB_2 + Tesla + GPU-46915a82-3fd2-8e11-ae26-a80b607c04f3 + 1 + + 12290 MiB + 11800 MiB + 490 MiB + + Default + + 10.3 % + 0 % + 0 % + 0 % + + + 34 C + 85 C + 82 C + + + + \ No newline at end of file diff --git a/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/test/resources/nvidia-smi-sample-output.xml b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/test/resources/nvidia-smi-sample-output.xml new file mode 100644 index 00000000000..cdd5404ea90 --- /dev/null +++ b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/test/resources/nvidia-smi-sample-output.xml @@ -0,0 +1,547 @@ + + + + + + + Wed Sep 6 21:52:51 2017 + 375.66 + 2 + + Tesla P100-PCIE-12GB + Tesla + Disabled + Disabled + Disabled + Disabled + 1920 + + N/A + N/A + + 0320717030197 + GPU-28604e81-21ec-cc48-6759-bf2648b22e16 + 0 + 86.00.3A.00.02 + No + 0x400 + 900-2H400-0110-030 + + H400.0202.00.01 + 1.1 + 4.1 + N/A + + + N/A + N/A + + + None + + + 04 + 00 + 0000 + 15F710DE + 0000:04:00.0 + 11DA10DE + + + 3 + 3 + + + 16x + 16x + + + + N/A + N/A + + 0 + 0 KB/s + 0 KB/s + + N/A + P0 + + Active + Not Active + Not Active + Not Active + Not Active + Not Active + + + 11567 MiB + 11400 MiB + 167 MiB + + + 16384 MiB + 2 MiB + 16382 MiB + + Default + + 33.4 % + 0 % + 0 % + 0 % + + + 0 + 0 + 0 ms + + + Enabled + Enabled + + + + + 0 + 0 + N/A + 0 + 0 + 0 + 0 + + + 0 + 0 + N/A + 0 + 0 + 0 + 0 + + + + + 0 + 0 + N/A + 0 + 0 + 0 + 0 + + + 0 + 0 + N/A + 0 + 0 + 0 + 0 + + + + + + 0 + + + + + 0 + + + + No + + + 31 C + 80 C + 88 C + + + P0 + Supported + 24.84 W + 250.00 W + 250.00 W + 250.00 W + 125.00 W + 250.00 W + + + 405 MHz + 405 MHz + 715 MHz + 835 MHz + + + 1189 MHz + 715 MHz + + + 1189 MHz + 715 MHz + + + 1328 MHz + 1328 MHz + 715 MHz + 1328 MHz + + + N/A + N/A + + + + 715 MHz + 1328 MHz + 1316 MHz + 1303 MHz + 1290 MHz + 1278 MHz + 1265 MHz + 1252 MHz + 1240 MHz + 1227 MHz + 1215 MHz + 1202 MHz + 1189 MHz + 1177 MHz + 1164 MHz + 1151 MHz + 1139 MHz + 1126 MHz + 1113 MHz + 1101 MHz + 1088 MHz + 1075 MHz + 1063 MHz + 1050 MHz + 1037 MHz + 1025 MHz + 1012 MHz + 999 MHz + 987 MHz + 974 MHz + 961 MHz + 949 MHz + 936 MHz + 923 MHz + 911 MHz + 898 MHz + 885 MHz + 873 MHz + 860 MHz + 847 MHz + 835 MHz + 822 MHz + 810 MHz + 797 MHz + 784 MHz + 772 MHz + 759 MHz + 746 MHz + 734 MHz + 721 MHz + 708 MHz + 696 MHz + 683 MHz + 670 MHz + 658 MHz + 645 MHz + 632 MHz + 620 MHz + 607 MHz + 594 MHz + 582 MHz + 569 MHz + 556 MHz + 544 MHz + + + + + + + + + + Tesla P100-PCIE-12GB_2 + Tesla + Disabled + Disabled + Disabled + Disabled + 1920 + + N/A + N/A + + 0320717031755 + GPU-46915a82-3fd2-8e11-ae26-a80b607c04f3 + 1 + 86.00.3A.00.02 + No + 0x8200 + 900-2H400-0110-030 + + H400.0202.00.01 + 1.1 + 4.1 + N/A + + + N/A + N/A + + + None + + + 82 + 00 + 0000 + 15F710DE + 0000:82:00.0 + 11DA10DE + + + 3 + 3 + + + 16x + 16x + + + + N/A + N/A + + 0 + 0 KB/s + 0 KB/s + + N/A + P0 + + Active + Not Active + Not Active + Not Active + Not Active + Not Active + + + 12290 MiB + 11800 MiB + 490 MiB + + + 16384 MiB + 2 MiB + 16382 MiB + + Default + + 10.3 % + 0 % + 0 % + 0 % + + + 0 + 0 + 0 ms + + + Enabled + Enabled + + + + + 0 + 0 + N/A + 0 + 0 + 0 + 0 + + + 0 + 0 + N/A + 0 + 0 + 0 + 0 + + + + + 0 + 0 + N/A + 0 + 0 + 0 + 0 + + + 0 + 0 + N/A + 0 + 0 + 0 + 0 + + + + + + 0 + + + + + 0 + + + + No + + + 34 C + 85 C + 82 C + + + P0 + Supported + 25.54 W + 250.00 W + 250.00 W + 250.00 W + 125.00 W + 250.00 W + + + 405 MHz + 405 MHz + 715 MHz + 835 MHz + + + 1189 MHz + 715 MHz + + + 1189 MHz + 715 MHz + + + 1328 MHz + 1328 MHz + 715 MHz + 1328 MHz + + + N/A + N/A + + + + 715 MHz + 1328 MHz + 1316 MHz + 1303 MHz + 1290 MHz + 1278 MHz + 1265 MHz + 1252 MHz + 1240 MHz + 1227 MHz + 1215 MHz + 1202 MHz + 1189 MHz + 1177 MHz + 1164 MHz + 1151 MHz + 1139 MHz + 1126 MHz + 1113 MHz + 1101 MHz + 1088 MHz + 1075 MHz + 1063 MHz + 1050 MHz + 1037 MHz + 1025 MHz + 1012 MHz + 999 MHz + 987 MHz + 974 MHz + 961 MHz + 949 MHz + 936 MHz + 923 MHz + 911 MHz + 898 MHz + 885 MHz + 873 MHz + 860 MHz + 847 MHz + 835 MHz + 822 MHz + 810 MHz + 797 MHz + 784 MHz + 772 MHz + 759 MHz + 746 MHz + 734 MHz + 721 MHz + 708 MHz + 696 MHz + 683 MHz + 670 MHz + 658 MHz + 645 MHz + 632 MHz + 620 MHz + 607 MHz + 594 MHz + 582 MHz + 569 MHz + 556 MHz + 544 MHz + + + + + + + + + \ No newline at end of file diff --git a/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/test/resources/nvidia-smi-sample-xml-output b/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/test/resources/nvidia-smi-sample-xml-output deleted file mode 100644 index 5ccb72265b5..00000000000 --- a/hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-nodemanager/src/test/resources/nvidia-smi-sample-xml-output +++ /dev/null @@ -1,547 +0,0 @@ - - - - - - - Wed Sep 6 21:52:51 2017 - 375.66 - 2 - - Tesla P100-PCIE-12GB - Tesla - Disabled - Disabled - Disabled - Disabled - 1920 - - N/A - N/A - - 0320717030197 - GPU-28604e81-21ec-cc48-6759-bf2648b22e16 - 0 - 86.00.3A.00.02 - No - 0x400 - 900-2H400-0110-030 - - H400.0202.00.01 - 1.1 - 4.1 - N/A - - - N/A - N/A - - - None - - - 04 - 00 - 0000 - 15F710DE - 0000:04:00.0 - 11DA10DE - - - 3 - 3 - - - 16x - 16x - - - - N/A - N/A - - 0 - 0 KB/s - 0 KB/s - - N/A - P0 - - Active - Not Active - Not Active - Not Active - Not Active - Not Active - - - 12193 MiB - 0 MiB - 12193 MiB - - - 16384 MiB - 2 MiB - 16382 MiB - - Default - - 0 % - 0 % - 0 % - 0 % - - - 0 - 0 - 0 ms - - - Enabled - Enabled - - - - - 0 - 0 - N/A - 0 - 0 - 0 - 0 - - - 0 - 0 - N/A - 0 - 0 - 0 - 0 - - - - - 0 - 0 - N/A - 0 - 0 - 0 - 0 - - - 0 - 0 - N/A - 0 - 0 - 0 - 0 - - - - - - 0 - - - - - 0 - - - - No - - - 31 C - 85 C - 82 C - - - P0 - Supported - 24.84 W - 250.00 W - 250.00 W - 250.00 W - 125.00 W - 250.00 W - - - 405 MHz - 405 MHz - 715 MHz - 835 MHz - - - 1189 MHz - 715 MHz - - - 1189 MHz - 715 MHz - - - 1328 MHz - 1328 MHz - 715 MHz - 1328 MHz - - - N/A - N/A - - - - 715 MHz - 1328 MHz - 1316 MHz - 1303 MHz - 1290 MHz - 1278 MHz - 1265 MHz - 1252 MHz - 1240 MHz - 1227 MHz - 1215 MHz - 1202 MHz - 1189 MHz - 1177 MHz - 1164 MHz - 1151 MHz - 1139 MHz - 1126 MHz - 1113 MHz - 1101 MHz - 1088 MHz - 1075 MHz - 1063 MHz - 1050 MHz - 1037 MHz - 1025 MHz - 1012 MHz - 999 MHz - 987 MHz - 974 MHz - 961 MHz - 949 MHz - 936 MHz - 923 MHz - 911 MHz - 898 MHz - 885 MHz - 873 MHz - 860 MHz - 847 MHz - 835 MHz - 822 MHz - 810 MHz - 797 MHz - 784 MHz - 772 MHz - 759 MHz - 746 MHz - 734 MHz - 721 MHz - 708 MHz - 696 MHz - 683 MHz - 670 MHz - 658 MHz - 645 MHz - 632 MHz - 620 MHz - 607 MHz - 594 MHz - 582 MHz - 569 MHz - 556 MHz - 544 MHz - - - - - - - - - - Tesla P100-PCIE-12GB - Tesla - Disabled - Disabled - Disabled - Disabled - 1920 - - N/A - N/A - - 0320717031755 - GPU-46915a82-3fd2-8e11-ae26-a80b607c04f3 - 1 - 86.00.3A.00.02 - No - 0x8200 - 900-2H400-0110-030 - - H400.0202.00.01 - 1.1 - 4.1 - N/A - - - N/A - N/A - - - None - - - 82 - 00 - 0000 - 15F710DE - 0000:82:00.0 - 11DA10DE - - - 3 - 3 - - - 16x - 16x - - - - N/A - N/A - - 0 - 0 KB/s - 0 KB/s - - N/A - P0 - - Active - Not Active - Not Active - Not Active - Not Active - Not Active - - - 12193 MiB - 0 MiB - 12193 MiB - - - 16384 MiB - 2 MiB - 16382 MiB - - Default - - 10.3 % - 0 % - 0 % - 0 % - - - 0 - 0 - 0 ms - - - Enabled - Enabled - - - - - 0 - 0 - N/A - 0 - 0 - 0 - 0 - - - 0 - 0 - N/A - 0 - 0 - 0 - 0 - - - - - 0 - 0 - N/A - 0 - 0 - 0 - 0 - - - 0 - 0 - N/A - 0 - 0 - 0 - 0 - - - - - - 0 - - - - - 0 - - - - No - - - 34 C - 85 C - 82 C - - - P0 - Supported - 25.54 W - 250.00 W - 250.00 W - 250.00 W - 125.00 W - 250.00 W - - - 405 MHz - 405 MHz - 715 MHz - 835 MHz - - - 1189 MHz - 715 MHz - - - 1189 MHz - 715 MHz - - - 1328 MHz - 1328 MHz - 715 MHz - 1328 MHz - - - N/A - N/A - - - - 715 MHz - 1328 MHz - 1316 MHz - 1303 MHz - 1290 MHz - 1278 MHz - 1265 MHz - 1252 MHz - 1240 MHz - 1227 MHz - 1215 MHz - 1202 MHz - 1189 MHz - 1177 MHz - 1164 MHz - 1151 MHz - 1139 MHz - 1126 MHz - 1113 MHz - 1101 MHz - 1088 MHz - 1075 MHz - 1063 MHz - 1050 MHz - 1037 MHz - 1025 MHz - 1012 MHz - 999 MHz - 987 MHz - 974 MHz - 961 MHz - 949 MHz - 936 MHz - 923 MHz - 911 MHz - 898 MHz - 885 MHz - 873 MHz - 860 MHz - 847 MHz - 835 MHz - 822 MHz - 810 MHz - 797 MHz - 784 MHz - 772 MHz - 759 MHz - 746 MHz - 734 MHz - 721 MHz - 708 MHz - 696 MHz - 683 MHz - 670 MHz - 658 MHz - 645 MHz - 632 MHz - 620 MHz - 607 MHz - 594 MHz - 582 MHz - 569 MHz - 556 MHz - 544 MHz - - - - - - - - - \ No newline at end of file