This is an automated email from the ASF dual-hosted git repository.
domgarguilo pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/accumulo.git
commit 7f40306d968f0d76ab1d9adeadbd481ea24f099d
Merge: 816fa97cbf 960cee8d45
Author: Dom Garguilo <domgargu...@apache.org>
AuthorDate: Mon Sep 23 15:24:45 2024 -0400
Merge remote-tracking branch 'upstream/3.1'
.../org/apache/accumulo/core/metrics/Metric.java | 231 ++++++++++++---------
.../server/compaction/PausedCompactionMetrics.java | 4 +-
.../accumulo/server/metrics/ProcessMetrics.java | 7 +-
.../accumulo/server/metrics/ThriftMetrics.java | 7 +-
.../org/apache/accumulo/compactor/Compactor.java | 8 +-
.../org/apache/accumulo/gc/metrics/GcMetrics.java | 30 ++-
.../accumulo/manager/metrics/BalancerMetrics.java | 2 +-
.../apache/accumulo/tserver/BlockCacheMetrics.java | 18 +-
.../apache/accumulo/tserver/ScanServerMetrics.java | 10 +-
.../tserver/metrics/TabletServerMetrics.java | 39 ++--
.../tserver/metrics/TabletServerMinCMetrics.java | 6 +-
.../tserver/metrics/TabletServerScanMetrics.java | 35 ++--
.../tserver/metrics/TabletServerUpdateMetrics.java | 16 +-
13 files changed, 222 insertions(+), 191 deletions(-)
diff --cc core/src/main/java/org/apache/accumulo/core/metrics/Metric.java
index 7252b237ef,27b5e3bf00..d9f3791964
--- a/core/src/main/java/org/apache/accumulo/core/metrics/Metric.java
+++ b/core/src/main/java/org/apache/accumulo/core/metrics/Metric.java
@@@ -31,24 -31,14 +31,26 @@@ public enum Metric
MetricCategory.GENERAL_SERVER),
// Compactor Metrics
- COMPACTOR_MAJC_STUCK("accumulo.compactor.majc.stuck",
MetricType.LONG_TASK_TIMER, "",
- MetricCategory.COMPACTOR),
+ COMPACTOR_MAJC_STUCK("accumulo.compactor.majc.stuck",
MetricType.LONG_TASK_TIMER,
+ "Number and duration of stuck major compactions.",
MetricCategory.COMPACTOR),
COMPACTOR_ENTRIES_READ("accumulo.compactor.entries.read",
MetricType.FUNCTION_COUNTER,
- "Number of entries read by all threads performing compactions.",
MetricCategory.COMPACTOR),
+ "Number of entries read by all compactions that have run on this
compactor.",
+ MetricCategory.COMPACTOR),
COMPACTOR_ENTRIES_WRITTEN("accumulo.compactor.entries.written",
MetricType.FUNCTION_COUNTER,
- "Number of entries written by all threads performing compactions.",
MetricCategory.COMPACTOR),
+ "Number of entries written by all compactions that have run on this
compactor.",
+ MetricCategory.COMPACTOR),
+ COMPACTOR_JOB_PRIORITY_QUEUES("accumulo.compactor.queue.count",
MetricType.GAUGE,
+ "Number of priority queues for compaction jobs.",
MetricCategory.COMPACTOR),
+ COMPACTOR_JOB_PRIORITY_QUEUE_LENGTH("accumulo.compactor.queue.length",
MetricType.GAUGE, "",
+ MetricCategory.COMPACTOR),
+
COMPACTOR_JOB_PRIORITY_QUEUE_JOBS_DEQUEUED("accumulo.compactor.queue.jobs.dequeued",
+ MetricType.GAUGE, "", MetricCategory.COMPACTOR),
+
COMPACTOR_JOB_PRIORITY_QUEUE_JOBS_QUEUED("accumulo.compactor.queue.jobs.queued",
MetricType.GAUGE,
+ "", MetricCategory.COMPACTOR),
+
COMPACTOR_JOB_PRIORITY_QUEUE_JOBS_REJECTED("accumulo.compactor.queue.jobs.rejected",
+ MetricType.GAUGE, "", MetricCategory.COMPACTOR),
+
COMPACTOR_JOB_PRIORITY_QUEUE_JOBS_PRIORITY("accumulo.compactor.queue.jobs.priority",
+ MetricType.GAUGE, "", MetricCategory.COMPACTOR),
// Fate Metrics
FATE_TYPE_IN_PROGRESS("accumulo.fate.ops.in.progress.by.type",
MetricType.GAUGE,
@@@ -63,57 -56,72 +68,77 @@@
MetricCategory.FATE),
// Garbage Collection Metrics
- GC_STARTED("accumulo.gc.started", MetricType.GAUGE, "",
MetricCategory.GARBAGE_COLLECTION),
- GC_FINISHED("accumulo.gc.finished", MetricType.GAUGE, "",
MetricCategory.GARBAGE_COLLECTION),
- GC_CANDIDATES("accumulo.gc.candidates", MetricType.GAUGE, "",
MetricCategory.GARBAGE_COLLECTION),
- GC_IN_USE("accumulo.gc.in.use", MetricType.GAUGE, "",
MetricCategory.GARBAGE_COLLECTION),
- GC_DELETED("accumulo.gc.deleted", MetricType.GAUGE, "",
MetricCategory.GARBAGE_COLLECTION),
- GC_ERRORS("accumulo.gc.errors", MetricType.GAUGE, "",
MetricCategory.GARBAGE_COLLECTION),
- GC_WAL_STARTED("accumulo.gc.wal.started", MetricType.GAUGE, "",
+ GC_STARTED("accumulo.gc.started", MetricType.GAUGE, "Timestamp GC file
collection cycle started.",
+ MetricCategory.GARBAGE_COLLECTION),
+ GC_FINISHED("accumulo.gc.finished", MetricType.GAUGE, "Timestamp GC file
collect cycle finished.",
+ MetricCategory.GARBAGE_COLLECTION),
+ GC_CANDIDATES("accumulo.gc.candidates", MetricType.GAUGE,
+ "Number of files that are candidates for deletion.",
MetricCategory.GARBAGE_COLLECTION),
+ GC_IN_USE("accumulo.gc.in.use", MetricType.GAUGE, "Number of candidate
files still in use.",
MetricCategory.GARBAGE_COLLECTION),
- GC_WAL_FINISHED("accumulo.gc.wal.finished", MetricType.GAUGE, "",
+ GC_DELETED("accumulo.gc.deleted", MetricType.GAUGE, "Number of candidate
files deleted.",
MetricCategory.GARBAGE_COLLECTION),
- GC_WAL_CANDIDATES("accumulo.gc.wal.candidates", MetricType.GAUGE, "",
+ GC_ERRORS("accumulo.gc.errors", MetricType.GAUGE, "Number of candidate
deletion errors.",
MetricCategory.GARBAGE_COLLECTION),
- GC_WAL_IN_USE("accumulo.gc.wal.in.use", MetricType.GAUGE, "",
MetricCategory.GARBAGE_COLLECTION),
- GC_WAL_DELETED("accumulo.gc.wal.deleted", MetricType.GAUGE, "",
+ GC_WAL_STARTED("accumulo.gc.wal.started", MetricType.GAUGE,
+ "Timestamp GC WAL collection cycle started.",
MetricCategory.GARBAGE_COLLECTION),
+ GC_WAL_FINISHED("accumulo.gc.wal.finished", MetricType.GAUGE,
+ "Timestamp GC WAL collect cycle finished.",
MetricCategory.GARBAGE_COLLECTION),
+ GC_WAL_CANDIDATES("accumulo.gc.wal.candidates", MetricType.GAUGE,
+ "Number of files that are candidates for deletion.",
MetricCategory.GARBAGE_COLLECTION),
+ GC_WAL_IN_USE("accumulo.gc.wal.in.use", MetricType.GAUGE,
+ "Number of wal file candidates that are still in use.",
MetricCategory.GARBAGE_COLLECTION),
+ GC_WAL_DELETED("accumulo.gc.wal.deleted", MetricType.GAUGE,
+ "Number of candidate wal files deleted.",
MetricCategory.GARBAGE_COLLECTION),
+ GC_WAL_ERRORS("accumulo.gc.wal.errors", MetricType.GAUGE,
+ "Number candidate wal file deletion errors.",
MetricCategory.GARBAGE_COLLECTION),
+ GC_POST_OP_DURATION("accumulo.gc.post.op.duration", MetricType.GAUGE,
+ "GC metadata table post operation duration in milliseconds.",
MetricCategory.GARBAGE_COLLECTION),
- GC_WAL_ERRORS("accumulo.gc.wal.errors", MetricType.GAUGE, "",
MetricCategory.GARBAGE_COLLECTION),
- GC_POST_OP_DURATION("accumulo.gc.post.op.duration", MetricType.GAUGE, "",
+ GC_RUN_CYCLE("accumulo.gc.run.cycle", MetricType.GAUGE,
+ "Count of gc cycle runs. Value is reset on process start.",
MetricCategory.GARBAGE_COLLECTION),
- GC_RUN_CYCLE("accumulo.gc.run.cycle", MetricType.GAUGE, "",
MetricCategory.GARBAGE_COLLECTION),
// Tablet Server Metrics
- TSERVER_ENTRIES("accumulo.tserver.entries", MetricType.GAUGE, "",
MetricCategory.TABLET_SERVER),
- TSERVER_MEM_ENTRIES("accumulo.tserver.entries.mem", MetricType.GAUGE, "",
- MetricCategory.TABLET_SERVER),
- TSERVER_MINC_QUEUED("accumulo.tserver.minc.queued", MetricType.GAUGE, "",
- MetricCategory.TABLET_SERVER),
- TSERVER_MINC_RUNNING("accumulo.tserver.minc.running", MetricType.GAUGE, "",
- MetricCategory.TABLET_SERVER),
- TSERVER_MINC_TOTAL("accumulo.tserver.minc.total", MetricType.GAUGE, "",
- MetricCategory.TABLET_SERVER),
- TSERVER_TABLETS_ONLINE("accumulo.tserver.tablets.online", MetricType.GAUGE,
"",
- MetricCategory.TABLET_SERVER),
+ TSERVER_ENTRIES("accumulo.tserver.entries", MetricType.GAUGE, "Number of
entries.",
+ MetricCategory.TABLET_SERVER),
+ TSERVER_MEM_ENTRIES("accumulo.tserver.entries.mem", MetricType.GAUGE,
+ "Number of entries in memory.", MetricCategory.TABLET_SERVER),
+ TSERVER_MAJC_RUNNING("accumulo.tserver.majc.running", MetricType.GAUGE,
+ "Number of active major compactions.", MetricCategory.TABLET_SERVER),
+ TSERVER_MAJC_STUCK("accumulo.tserver.majc.stuck", MetricType.GAUGE,
+ "Number and duration of stuck major compactions.",
MetricCategory.TABLET_SERVER),
+ TSERVER_MAJC_QUEUED("accumulo.tserver.majc.queued", MetricType.GAUGE,
+ "Number of queued major compactions.", MetricCategory.TABLET_SERVER),
+ TSERVER_MINC_QUEUED("accumulo.tserver.minc.queued", MetricType.GAUGE,
+ "Number of queued minor compactions.", MetricCategory.TABLET_SERVER),
+ TSERVER_MINC_RUNNING("accumulo.tserver.minc.running", MetricType.GAUGE,
+ "Number of active minor compactions.", MetricCategory.TABLET_SERVER),
+ TSERVER_MINC_TOTAL("accumulo.tserver.minc.total", MetricType.GAUGE,
+ "Total number of minor compactions performed.",
MetricCategory.TABLET_SERVER),
+ TSERVER_TABLETS_ONLINE("accumulo.tserver.tablets.online", MetricType.GAUGE,
+ "Number of online tablets.", MetricCategory.TABLET_SERVER),
TSERVER_TABLETS_LONG_ASSIGNMENTS("accumulo.tserver.tablets.assignments.warning",
MetricType.GAUGE,
- "", MetricCategory.TABLET_SERVER),
- TSERVER_TABLETS_OPENING("accumulo.tserver.tablets.opening",
MetricType.GAUGE, "",
- MetricCategory.TABLET_SERVER),
- TSERVER_TABLETS_UNOPENED("accumulo.tserver.tablets.unopened",
MetricType.GAUGE, "",
- MetricCategory.TABLET_SERVER),
- TSERVER_TABLETS_FILES("accumulo.tserver.tablets.files", MetricType.GAUGE,
"",
- MetricCategory.TABLET_SERVER),
+ "Number of tablet assignments that are taking longer than the
configured warning duration.",
+ MetricCategory.TABLET_SERVER),
+ TSERVER_TABLETS_OPENING("accumulo.tserver.tablets.opening",
MetricType.GAUGE,
+ "Number of opening tablets.", MetricCategory.TABLET_SERVER),
+ TSERVER_TABLETS_UNOPENED("accumulo.tserver.tablets.unopened",
MetricType.GAUGE,
+ "Number of unopened tablets.", MetricCategory.TABLET_SERVER),
+ TSERVER_TABLETS_FILES("accumulo.tserver.tablets.files", MetricType.GAUGE,
+ "Number of files per tablet.", MetricCategory.TABLET_SERVER),
TSERVER_INGEST_MUTATIONS("accumulo.tserver.ingest.mutations",
MetricType.GAUGE,
- "Prior to 2.1.0 this metric was reported as a rate, it is now the count
and the rate can be derived.",
+ "Ingest mutation count. The rate can be derived from this metric.",
MetricCategory.TABLET_SERVER),
TSERVER_INGEST_BYTES("accumulo.tserver.ingest.bytes", MetricType.GAUGE,
- "Prior to 2.1.0 this metric was reported as a rate, it is now the count
and the rate can be derived.",
- MetricCategory.TABLET_SERVER),
- TSERVER_HOLD("accumulo.tserver.hold", MetricType.GAUGE, "",
MetricCategory.TABLET_SERVER),
- TSERVER_TABLETS_ONLINE_ONDEMAND("accumulo.tserver.tablets.ondemand.online",
MetricType.GAUGE, "",
- MetricCategory.TABLET_SERVER),
+ "Ingest byte count. The rate can be derived from this metric.",
MetricCategory.TABLET_SERVER),
+ TSERVER_HOLD("accumulo.tserver.hold", MetricType.GAUGE,
+ "Duration for which commits have been held in milliseconds.",
MetricCategory.TABLET_SERVER),
++ TSERVER_TABLETS_ONLINE_ONDEMAND("accumulo.tserver.tablets.ondemand.online",
MetricType.GAUGE,
++ "Number of online on-demand tablets", MetricCategory.TABLET_SERVER),
+
TSERVER_TABLETS_ONDEMAND_UNLOADED_FOR_MEM("accumulo.tserver.tablets.ondemand.unloaded.lowmem",
- MetricType.GAUGE, "", MetricCategory.TABLET_SERVER),
++ MetricType.GAUGE, "Number of online on-demand tablets unloaded due to
low memory",
++ MetricCategory.TABLET_SERVER),
// Scan Metrics
SCAN_RESERVATION_TOTAL_TIMER("accumulo.scan.reservation.total.timer",
MetricType.TIMER,
diff --cc
server/tserver/src/main/java/org/apache/accumulo/tserver/metrics/TabletServerMetrics.java
index 76753b2c54,134c604a67..68798e6d67
---
a/server/tserver/src/main/java/org/apache/accumulo/tserver/metrics/TabletServerMetrics.java
+++
b/server/tserver/src/main/java/org/apache/accumulo/tserver/metrics/TabletServerMetrics.java
@@@ -72,41 -71,37 +71,39 @@@ public class TabletServerMetrics implem
FunctionCounter
.builder(COMPACTOR_ENTRIES_WRITTEN.getName(), this,
TabletServerMetrics::getTotalEntriesWritten)
- .description("Number of entries written by all compactions that have
run on this tserver")
- .register(registry);
+
.description(COMPACTOR_ENTRIES_WRITTEN.getDescription()).register(registry);
- LongTaskTimer timer = LongTaskTimer.builder(TSERVER_MAJC_STUCK.getName())
- .description(TSERVER_MAJC_STUCK.getDescription()).register(registry);
+ LongTaskTimer timer =
LongTaskTimer.builder(COMPACTOR_MAJC_STUCK.getName())
- .description("Number and duration of stuck major
compactions").register(registry);
++
.description(COMPACTOR_MAJC_STUCK.getDescription()).register(registry);
CompactionWatcher.setTimer(timer);
+
Gauge
.builder(TSERVER_TABLETS_LONG_ASSIGNMENTS.getName(), util,
TabletServerMetricsUtil::getLongTabletAssignments)
- .description("Number of tablet assignments that are taking a long
time").register(registry);
+
.description(TSERVER_TABLETS_LONG_ASSIGNMENTS.getDescription()).register(registry);
Gauge.builder(TSERVER_ENTRIES.getName(), util,
TabletServerMetricsUtil::getEntries)
- .description("Number of entries").register(registry);
+ .description(TSERVER_ENTRIES.getDescription()).register(registry);
Gauge.builder(TSERVER_MEM_ENTRIES.getName(), util,
TabletServerMetricsUtil::getEntriesInMemory)
- .description("Number of entries in memory").register(registry);
+ .description(TSERVER_MEM_ENTRIES.getDescription()).register(registry);
- Gauge
- .builder(TSERVER_MAJC_RUNNING.getName(), util,
TabletServerMetricsUtil::getMajorCompactions)
-
.description(TSERVER_MAJC_RUNNING.getDescription()).register(registry);
- Gauge
- .builder(TSERVER_MAJC_QUEUED.getName(), util,
- TabletServerMetricsUtil::getMajorCompactionsQueued)
- .description(TSERVER_MINC_QUEUED.getDescription()).register(registry);
Gauge
.builder(TSERVER_MINC_RUNNING.getName(), util,
TabletServerMetricsUtil::getMinorCompactions)
- .description("Number of active minor compactions").register(registry);
+
.description(TSERVER_MINC_RUNNING.getDescription()).register(registry);
Gauge
.builder(TSERVER_MINC_QUEUED.getName(), util,
TabletServerMetricsUtil::getMinorCompactionsQueued)
- .description("Number of queued minor compactions").register(registry);
+ .description(TSERVER_MINC_QUEUED.getDescription()).register(registry);
+ Gauge
+ .builder(TSERVER_TABLETS_ONLINE_ONDEMAND.getName(), util,
+ TabletServerMetricsUtil::getOnDemandOnlineCount)
- .description("Number of online on-demand tablets").register(registry);
++
.description(TSERVER_TABLETS_ONLINE_ONDEMAND.getDescription()).register(registry);
+ Gauge
+ .builder(TSERVER_TABLETS_ONDEMAND_UNLOADED_FOR_MEM.getName(), util,
+ TabletServerMetricsUtil::getOnDemandUnloadedLowMem)
- .description("Number of online on-demand tablets unloaded due to low
memory")
- .register(registry);
++
.description(TSERVER_TABLETS_ONDEMAND_UNLOADED_FOR_MEM.getDescription()).register(registry);
Gauge.builder(TSERVER_TABLETS_ONLINE.getName(), util,
TabletServerMetricsUtil::getOnlineCount)
- .description("Number of online tablets").register(registry);
+
.description(TSERVER_TABLETS_ONLINE.getDescription()).register(registry);
Gauge.builder(TSERVER_TABLETS_OPENING.getName(), util,
TabletServerMetricsUtil::getOpeningCount)
- .description("Number of opening tablets").register(registry);
+
.description(TSERVER_TABLETS_OPENING.getDescription()).register(registry);
Gauge
.builder(TSERVER_TABLETS_UNOPENED.getName(), util,
TabletServerMetricsUtil::getUnopenedCount)
