Package ai.platon.pulsar.skeleton.crawl
Class CoreMetrics
-
- All Implemented Interfaces:
-
ai.platon.pulsar.common.config.Parameterized,java.lang.AutoCloseable
public final class CoreMetrics implements Parameterized, AutoCloseable
-
-
Nested Class Summary
Nested Classes Modifier and Type Class Description public classCoreMetrics.Companion
-
Field Summary
Fields Modifier and Type Field Description private final InternalURLUtil.GroupModegroupModeprivate final IntegermaxHostFailureEventsprivate final InstantstartTimeprivate final DurationelapsedTimeprivate final <Error class: unknown class>elapsedSecondsprivate final ConcurrentHashMap<String, UrlStat>urlStatisticsprivate final ConcurrentSkipListSet<String>unreachableHostsprivate final ConcurrentSkipListSet<String>timeoutUrlsprivate final ConcurrentSkipListSet<String>movedUrlsprivate final ConcurrentSkipListSet<String>failedUrlsprivate final ConcurrentSkipListSet<String>deadUrlsprivate final ConcurrentHashMultiset<String>failedHostsprivate final MetermeterTotalNetworkIFsRecvMBytesprivate final MeterfetchTasksprivate final MetersuccessFetchTasksprivate final MeterfinishedFetchTasksprivate final Meterproxiesprivate final MultiMetricpersistsprivate final MultiMetriccontentPersistsprivate final MultiMetricmeterContentMBytesprivate final MultiMetricpersistContentMBytesprivate final MetermeterContentBytesprivate final HistogramhistogramContentBytesprivate final HistogrampageImagesprivate final HistogrampageAnchorsprivate final HistogrampageNumbersprivate final HistogrampageSmallTextsprivate final HistogrampageHeightsprivate final LongrealTimeNetworkIFsRecvBytesprivate final <Error class: unknown class>initNetworkIFsRecvBytesprivate LongtotalNetworkIFsRecvBytesprivate final <Error class: unknown class>networkIFsRecvBytesprivate final <Error class: unknown class>networkIFsRecvBytesPerSecondprivate final <Error class: unknown class>networkIFsRecvBytesPerPageprivate final <Error class: unknown class>fetchTasksPerSecondprivate final <Error class: unknown class>finishedFetchTasksPerSecondprivate final <Error class: unknown class>successFetchTasksPerSecondprivate BooleanenableReporterprivate final InstantlastTaskTimeprivate final InstantlastReportTimepublic final static CoreMetrics.CompanionCompanion
-
Constructor Summary
Constructors Constructor Description CoreMetrics(MiscMessageWriter messageWriter, ImmutableConfig conf)
-
Method Summary
Modifier and Type Method Description final InternalURLUtil.GroupModegetGroupMode()final IntegergetMaxHostFailureEvents()final InstantgetStartTime()The start time of the program process final DurationgetElapsedTime()final <Error class: unknown class>getElapsedSeconds()final ConcurrentHashMap<String, UrlStat>getUrlStatistics()Tracking statistics for each host final ConcurrentSkipListSet<String>getUnreachableHosts()Tracking unreachable hosts final ConcurrentSkipListSet<String>getTimeoutUrls()Tracking hosts who are failed to fetch tasks. final ConcurrentSkipListSet<String>getMovedUrls()final ConcurrentSkipListSet<String>getFailedUrls()final ConcurrentSkipListSet<String>getDeadUrls()final ConcurrentHashMultiset<String>getFailedHosts()final MetergetMeterTotalNetworkIFsRecvMBytes()final MetergetFetchTasks()The total bytes of page content of all success web pages final MetergetSuccessFetchTasks()final MetergetFinishedFetchTasks()final MetergetProxies()final MultiMetricgetPersists()final MultiMetricgetContentPersists()final MultiMetricgetMeterContentMBytes()final MultiMetricgetPersistContentMBytes()final MetergetMeterContentBytes()final HistogramgetHistogramContentBytes()final HistogramgetPageImages()final HistogramgetPageAnchors()final HistogramgetPageNumbers()final HistogramgetPageSmallTexts()final HistogramgetPageHeights()final LonggetRealTimeNetworkIFsRecvBytes()final <Error class: unknown class>getInitNetworkIFsRecvBytes()The total all bytes received by the hardware at the application startup final LonggetTotalNetworkIFsRecvBytes()The total all bytes received by the hardware last read from system final UnitsetTotalNetworkIFsRecvBytes(Long totalNetworkIFsRecvBytes)The total all bytes received by the hardware last read from system final <Error class: unknown class>getNetworkIFsRecvBytes()final <Error class: unknown class>getNetworkIFsRecvBytesPerSecond()final <Error class: unknown class>getNetworkIFsRecvBytesPerPage()final <Error class: unknown class>getFetchTasksPerSecond()final <Error class: unknown class>getFinishedFetchTasksPerSecond()final <Error class: unknown class>getSuccessFetchTasksPerSecond()final BooleangetEnableReporter()final UnitsetEnableReporter(Boolean enableReporter)final InstantgetLastTaskTime()final InstantgetLastReportTime()ParamsgetParams()final Unitstart()final BooleanisReachable(String url)final BooleanisUnreachable(String url)final BooleanisFailed(String url)final UnittrackFailedUrl(String url)final UnittrackFailedUrls(Collection<String> urls)final BooleanisTimeout(String url)final UnitmarkFetchTaskStart()final UnitmarkFetchTaskStart(Integer size)final UnittrackSuccess(WebPage page)Available hosts statistics final UnittrackTimeout(String url)final UnittrackMoved(String url)final BooleantrackHostUnreachable(String url, Integer occurrences)final IntegercountHostTasks(String host)Unitclose()final UnitupdateSystemInfo()-
-
Constructor Detail
-
CoreMetrics
CoreMetrics(MiscMessageWriter messageWriter, ImmutableConfig conf)
-
-
Method Detail
-
getGroupMode
final InternalURLUtil.GroupMode getGroupMode()
-
getMaxHostFailureEvents
final Integer getMaxHostFailureEvents()
-
getStartTime
final Instant getStartTime()
The start time of the program process
-
getElapsedTime
final Duration getElapsedTime()
-
getElapsedSeconds
final <Error class: unknown class> getElapsedSeconds()
-
getUrlStatistics
final ConcurrentHashMap<String, UrlStat> getUrlStatistics()
Tracking statistics for each host
-
getUnreachableHosts
final ConcurrentSkipListSet<String> getUnreachableHosts()
Tracking unreachable hosts
-
getTimeoutUrls
final ConcurrentSkipListSet<String> getTimeoutUrls()
Tracking hosts who are failed to fetch tasks. A host is considered to be an unreachable host if there are too many failure
-
getMovedUrls
final ConcurrentSkipListSet<String> getMovedUrls()
-
getFailedUrls
final ConcurrentSkipListSet<String> getFailedUrls()
-
getDeadUrls
final ConcurrentSkipListSet<String> getDeadUrls()
-
getFailedHosts
final ConcurrentHashMultiset<String> getFailedHosts()
-
getMeterTotalNetworkIFsRecvMBytes
final Meter getMeterTotalNetworkIFsRecvMBytes()
-
getFetchTasks
final Meter getFetchTasks()
The total bytes of page content of all success web pages
-
getSuccessFetchTasks
final Meter getSuccessFetchTasks()
-
getFinishedFetchTasks
final Meter getFinishedFetchTasks()
-
getProxies
final Meter getProxies()
-
getPersists
final MultiMetric getPersists()
-
getContentPersists
final MultiMetric getContentPersists()
-
getMeterContentMBytes
final MultiMetric getMeterContentMBytes()
-
getPersistContentMBytes
final MultiMetric getPersistContentMBytes()
-
getMeterContentBytes
final Meter getMeterContentBytes()
-
getHistogramContentBytes
final Histogram getHistogramContentBytes()
-
getPageImages
final Histogram getPageImages()
-
getPageAnchors
final Histogram getPageAnchors()
-
getPageNumbers
final Histogram getPageNumbers()
-
getPageSmallTexts
final Histogram getPageSmallTexts()
-
getPageHeights
final Histogram getPageHeights()
-
getRealTimeNetworkIFsRecvBytes
final Long getRealTimeNetworkIFsRecvBytes()
-
getInitNetworkIFsRecvBytes
final <Error class: unknown class> getInitNetworkIFsRecvBytes()
The total all bytes received by the hardware at the application startup
-
getTotalNetworkIFsRecvBytes
final Long getTotalNetworkIFsRecvBytes()
The total all bytes received by the hardware last read from system
-
setTotalNetworkIFsRecvBytes
final Unit setTotalNetworkIFsRecvBytes(Long totalNetworkIFsRecvBytes)
The total all bytes received by the hardware last read from system
-
getNetworkIFsRecvBytes
final <Error class: unknown class> getNetworkIFsRecvBytes()
-
getNetworkIFsRecvBytesPerSecond
final <Error class: unknown class> getNetworkIFsRecvBytesPerSecond()
-
getNetworkIFsRecvBytesPerPage
final <Error class: unknown class> getNetworkIFsRecvBytesPerPage()
-
getFetchTasksPerSecond
final <Error class: unknown class> getFetchTasksPerSecond()
-
getFinishedFetchTasksPerSecond
final <Error class: unknown class> getFinishedFetchTasksPerSecond()
-
getSuccessFetchTasksPerSecond
final <Error class: unknown class> getSuccessFetchTasksPerSecond()
-
getEnableReporter
final Boolean getEnableReporter()
-
setEnableReporter
final Unit setEnableReporter(Boolean enableReporter)
-
getLastTaskTime
final Instant getLastTaskTime()
-
getLastReportTime
final Instant getLastReportTime()
-
getParams
Params getParams()
-
isReachable
final Boolean isReachable(String url)
-
isUnreachable
final Boolean isUnreachable(String url)
-
trackFailedUrl
final Unit trackFailedUrl(String url)
-
trackFailedUrls
final Unit trackFailedUrls(Collection<String> urls)
-
markFetchTaskStart
final Unit markFetchTaskStart()
-
markFetchTaskStart
final Unit markFetchTaskStart(Integer size)
-
trackSuccess
final Unit trackSuccess(WebPage page)
Available hosts statistics
-
trackTimeout
final Unit trackTimeout(String url)
-
trackMoved
final Unit trackMoved(String url)
-
trackHostUnreachable
final Boolean trackHostUnreachable(String url, Integer occurrences)
- Parameters:
url- The url- Returns:
true if the host is unreachable
-
countHostTasks
final Integer countHostTasks(String host)
-
updateSystemInfo
final Unit updateSystemInfo()
-
-
-
-