sparkforensics-server 0.2.2 → 0.2.3

package/public/docs/assets/{tuning-reference_cluster-config.md.ZVmDGsQ3.js → tuning-reference_cluster-config.md.CD6vzYtD.js}

@@ -1 +1 @@
-import{_ as o,o as a,c as t,a5 as r}from"./chunks/framework.DSg0KOwT.js";const s="/docs/assets/container-memory.DIO0AnIm.svg",n="/docs/assets/container-memory.dark.CP-5zuCl.svg",m=JSON.parse('{"title":"Cluster Tuning","description":"","frontmatter":{"title":"Cluster Tuning"},"headers":[],"relativePath":"tuning-reference/cluster-config.md","filePath":"tuning-reference/cluster-config.md"}'),c={name:"tuning-reference/cluster-config.md"};function f(i,e,l,u,d,h){return a(),t("div",null,[...e[0]||(e[0]=[r('<h1 id="cluster-config" tabindex="-1">Cluster Tuning <a class="header-anchor" href="#cluster-config" aria-label="Permalink to &quot;Cluster Tuning {#cluster-config}&quot;">​</a></h1><h2 id="sizing-executors-and-containers" tabindex="-1">Sizing executors and containers <a class="header-anchor" href="#sizing-executors-and-containers" aria-label="Permalink to &quot;Sizing executors and containers&quot;">​</a></h2><p>Cluster tuning is the set of decisions that map an application&#39;s cores, memory, and executor count onto the underlying cluster (YARN or Kubernetes) plus a handful of related knobs (data locality, dynamic allocation, per-task CPU reservation) that all interact with that sizing decision.</p><p>The starting point is executor sizing. Working through a concrete example (a 10-node cluster with 16 cores and 64GB RAM per node), the derivation runs: assign 5 cores per executor; reserve about 1 core per node for Hadoop/YARN/OS daemons, leaving 15 usable cores per node (150 total); dividing by 5 cores per executor gives 30 executors, minus 1 reserved for the YARN ApplicationMaster (29); with 3 executors per node, memory per executor is 64GB / 3 ≈ 21GB, and after subtracting about 7% for YARN memory overhead that comes out to roughly 18GB usable, a recommended shape of 29 executors × 5 cores × 18GB<sup class="footnote-ref"><a href="#fn1" id="fnref1">[1]</a></sup>. Cloudera&#39;s own worked example, on a 6-node cluster with the same 16-core / 64GB-per-node hardware, lands on the same shape: <code>--num-executors 17 --executor-cores 5 --executor-memory 19G</code>, rather than one &quot;fat&quot; executor per node (<code>--num-executors 6 --executor-cores 15 --executor-memory 63G</code>)<sup class="footnote-ref"><a href="#fn2" id="fnref2">[2]</a></sup>. Both sources treat the resulting task count (executor-cores × num-executors) as the single most important tuning lever, since Spark cannot compensate for too little parallelism on its own<sup class="footnote-ref"><a href="#fn2" id="fnref2:1">[2:1]</a></sup>. <code>spark.executor.cores</code> is the config that controls concurrent tasks per executor; it defaults to 1 in YARN mode, or to all available cores on the worker in standalone mode<sup class="footnote-ref"><a href="#fn3" id="fnref3">[3]</a></sup>, and <code>spark.executor.memory</code> sets the JVM heap size per executor<sup class="footnote-ref"><a href="#fn2" id="fnref2:2">[2:2]</a></sup>. Independent of the sizing formula above, the Spark tuning guide recommends targeting 2–3 tasks per CPU core across the cluster<sup class="footnote-ref"><a href="#fn4" id="fnref4">[4]</a></sup>.</p><p>On top of executor memory sits container memory. Spark computes the total container/pod allocation as <code>executorMemoryMiB + memoryOverheadMiB + memoryOffHeapMiB + pysparkMemToUseMiB</code>. On YARN this is what gets allocated for the container, on Kubernetes it becomes the pod memory limit<sup class="footnote-ref"><a href="#fn5" id="fnref5">[5]</a></sup>. <code>spark.executor.memoryOverhead</code> itself defaults to <code>max(0.1 * executorMemory, 384MB)</code><sup class="footnote-ref"><a href="#fn5" id="fnref5:1">[5:1]</a></sup><sup class="footnote-ref"><a href="#fn3" id="fnref3:1">[3:1]</a></sup>.</p><img class="light-only" src="'+s+'" alt="Container memory sums executor heap, memory overhead, off-heap size, and pyspark memory into the requested container size; the resource manager grants a container of that size and OOMKills the executor when its actual runtime footprint spills past that limit."><img class="dark-only" src="'+n+'" alt="Container memory sums executor heap, memory overhead, off-heap size, and pyspark memory into the requested container size; the resource manager grants a container of that size and OOMKills the executor when its actual runtime footprint spills past that limit."><blockquote><p><strong>PySpark:</strong> <code>spark.executor.pyspark.memory</code> is only added as its own container-memory term when it&#39;s set explicitly; otherwise PySpark&#39;s memory use is folded into the general overhead budget rather than tracked separately.<sup class="footnote-ref"><a href="#fn5" id="fnref5:2">[5:2]</a></sup></p></blockquote><p>On Kubernetes specifically, <code>spark.kubernetes.executor.request.cores</code> and <code>spark.kubernetes.executor.limit.cores</code> take priority over <code>spark.executor.cores</code> for the pod&#39;s CPU request/limit sent to the Kubernetes scheduler<sup class="footnote-ref"><a href="#fn6" id="fnref6">[6]</a></sup>, while <code>spark.executor.cores</code> remains the config Spark itself uses to size the number of concurrent task slots<sup class="footnote-ref"><a href="#fn3" id="fnref3:2">[3:2]</a></sup>.</p><p>Two more knobs round out the picture. <code>spark.locality.wait</code> (default <code>3s</code>) controls how long a task waits for a data-local placement before Spark gives up and schedules it less locally, stepping through the same wait across process-local → node-local → rack-local → any; each level can be overridden independently via <code>spark.locality.wait.process</code>, <code>.node</code>, and <code>.rack</code>, all of which default to the base wait when left unset<sup class="footnote-ref"><a href="#fn3" id="fnref3:3">[3:3]</a></sup>. Dynamic allocation lets Spark add and remove executors as work changes, but it requires one of several supporting mechanisms: an external shuffle service, shuffle tracking (<code>spark.dynamicAllocation.shuffleTracking.enabled</code>, default <code>true</code> since Spark 3.0), shuffle-block decommission, or the experimental sort-IO plugin<sup class="footnote-ref"><a href="#fn3" id="fnref3:4">[3:4]</a></sup>. Removing an executor can otherwise destroy shuffle state it&#39;s holding. Finally, <code>spark.task.cpus</code> (default <code>1</code>) sets how many cores each task reserves; the number of concurrent task slots per executor is derived jointly from it and <code>spark.executor.cores</code>, roughly <code>spark.executor.cores / spark.task.cpus</code><sup class="footnote-ref"><a href="#fn3" id="fnref3:5">[3:5]</a></sup>.</p><h2 id="spotting-a-bad-sizing-decision" tabindex="-1">Spotting a bad sizing decision <a class="header-anchor" href="#spotting-a-bad-sizing-decision" aria-label="Permalink to &quot;Spotting a bad sizing decision&quot;">​</a></h2><p>Getting that sizing wrong shows up in a handful of specific symptoms. The clearest sign of an under-sized executor layout is HDFS throughput dropping under load: &quot;HDFS client has trouble with tons of concurrent threads. It was observed that HDFS achieves full write throughput with ~5 tasks per executor&quot;<sup class="footnote-ref"><a href="#fn1" id="fnref1:1">[1:1]</a></sup>. The &quot;fat executor&quot; case (one executor per node, using all 16 cores) shows the failure mode directly: &quot;with all 16 cores per executor... HDFS throughput will hurt and it&#39;ll result in excessive garbage [collection]&quot;<sup class="footnote-ref"><a href="#fn1" id="fnref1:2">[1:2]</a></sup>.</p><p>On the memory side, an executor or pod that dies with no Spark-level error is a strong signal that off-heap memory was never added into the container budget. Enabling <code>spark.memory.offHeap.enabled=true</code> with <code>spark.memory.offHeap.size=1g</code> on top of an 8G executor with default overhead (819MB) means real usage is 8192+819+1024 = 10,035MB, while the container was only granted 8192+819 = 9,011MB. The executor gets killed by YARN, or OOMKilled by the Kubernetes kubelet, with no warning from Spark itself<sup class="footnote-ref"><a href="#fn5" id="fnref5:3">[5:3]</a></sup>.</p><p>With dynamic allocation on, unexplained shuffle recomputation is a detectable symptom of executors being reclaimed mid-shuffle: &quot;In the event of stragglers... dynamic allocation may remove an executor before the shuffle completes, in which case the shuffle files written by that executor must be recomputed unnecessarily&quot;<sup class="footnote-ref"><a href="#fn6" id="fnref6:1">[6:1]</a></sup>. Jobs that abort with a serialized-result-size error are hitting the <code>spark.driver.maxResultSize</code> guardrail rather than a driver heap exhaustion: &quot;Jobs will be aborted if the total size [of serialized action results] is above this limit&quot;<sup class="footnote-ref"><a href="#fn3" id="fnref3:6">[3:6]</a></sup>. And on the resource-waste side, executors that are provisioned but never assigned work are a sign that dynamic allocation is targeting full parallelism against a workload made of many small tasks<sup class="footnote-ref"><a href="#fn3" id="fnref3:7">[3:7]</a></sup>.</p><h2 id="what-a-bad-sizing-decision-costs" tabindex="-1">What a bad sizing decision costs <a class="header-anchor" href="#what-a-bad-sizing-decision-costs" aria-label="Permalink to &quot;What a bad sizing decision costs&quot;">​</a></h2><p>Each symptom above carries a specific price tag. Task count (<code>executor-cores × num-executors</code>) is treated by both cited sources as the single most important tuning lever, since Spark cannot compensate for too little parallelism on its own<sup class="footnote-ref"><a href="#fn2" id="fnref2:3">[2:3]</a></sup>. Going the other way, cramming too many cores into one executor degrades HDFS throughput and drives up garbage collection<sup class="footnote-ref"><a href="#fn1" id="fnref1:3">[1:3]</a></sup>.</p><p>Container-memory misconfiguration matters because the failure is silent from Spark&#39;s point of view: off-heap memory that isn&#39;t accounted for in <code>spark.executor.memoryOverhead</code> causes the executor to actually use more memory than the container/pod was granted, so it gets killed externally (by YARN or the kubelet) with no Spark-level diagnostic to point at the real cause<sup class="footnote-ref"><a href="#fn5" id="fnref5:4">[5:4]</a></sup>.</p><p>Dynamic allocation&#39;s interaction with shuffle state matters because, before dynamic allocation existed, an executor exiting alongside its application meant all its state could be safely discarded; with dynamic allocation, the application keeps running after an executor is explicitly removed, so any later need for that executor&#39;s state forces a recompute<sup class="footnote-ref"><a href="#fn6" id="fnref6:2">[6:2]</a></sup>. That is exactly why Spark needs &quot;a mechanism to decommission an executor gracefully by preserving its state before removing it&quot;<sup class="footnote-ref"><a href="#fn6" id="fnref6:3">[6:3]</a></sup>. Without shuffle tracking, an external shuffle service, or shuffle-block decommission enabled, dynamic allocation either can&#39;t be turned on at all, or, if it&#39;s active regardless, an executor holding unpreserved shuffle output that gets removed forces exactly that unnecessary recompute<sup class="footnote-ref"><a href="#fn3" id="fnref3:8">[3:8]</a></sup><sup class="footnote-ref"><a href="#fn6" id="fnref6:4">[6:4]</a></sup>.</p><p>On the driver side, <code>spark.driver.maxResultSize</code> and <code>spark.driver.memory</code> are separate budgets that still interact: whether a high <code>maxResultSize</code> actually causes an out-of-memory error &quot;depends on spark.driver.memory and memory overhead of objects in JVM&quot;<sup class="footnote-ref"><a href="#fn3" id="fnref3:9">[3:9]</a></sup>. Raising one without considering the other doesn&#39;t fully protect the driver.</p><p>Finally, over-provisioning executors against a small-task workload wastes cluster resources: &quot;with small tasks this setting can waste a lot of resources due to executor allocation overhead, as some executor might not even do any work&quot;<sup class="footnote-ref"><a href="#fn3" id="fnref3:10">[3:10]</a></sup>.</p><h2 id="sizing-the-cluster-correctly" tabindex="-1">Sizing the cluster correctly <a class="header-anchor" href="#sizing-the-cluster-correctly" aria-label="Permalink to &quot;Sizing the cluster correctly&quot;">​</a></h2><p>Avoiding those costs starts from a formula, not one fat executor per node. Apply the balanced-executor formula instead; the worked examples above give shapes like 29 × 5 × 18GB for a 10-node/16-core/64GB cluster, or 17 × 5 × 19G for a 6-node cluster with the same per-node hardware<sup class="footnote-ref"><a href="#fn1" id="fnref1:4">[1:4]</a></sup><sup class="footnote-ref"><a href="#fn2" id="fnref2:4">[2:4]</a></sup>. Keep <code>--executor-cores</code> at or below roughly 5 so HDFS client concurrency stays in the range where it sustains full write throughput<sup class="footnote-ref"><a href="#fn1" id="fnref1:5">[1:5]</a></sup>.</p><p>When enabling off-heap memory, account for <code>spark.memory.offHeap.size</code> in the container/pod memory budget explicitly; <code>spark.executor.memoryOverhead</code>&#39;s default of <code>max(0.1 * executorMemory, 384MB)</code> does not include it<sup class="footnote-ref"><a href="#fn5" id="fnref5:5">[5:5]</a></sup>. If you&#39;re still referencing the older <code>spark.yarn.executor.memoryOverhead</code> name, note it was removed in Spark 3.0<sup class="footnote-ref"><a href="#fn5" id="fnref5:6">[5:6]</a></sup>.</p><p>On Kubernetes, remember that <code>spark.kubernetes.executor.request.cores</code> and <code>.limit.cores</code> govern the pod&#39;s CPU request/limit and take priority over <code>spark.executor.cores</code> for that purpose<sup class="footnote-ref"><a href="#fn6" id="fnref6:5">[6:5]</a></sup>, while <code>spark.executor.cores</code> separately governs Spark&#39;s own task-slot count<sup class="footnote-ref"><a href="#fn3" id="fnref3:11">[3:11]</a></sup>. The two need to be reasoned about together rather than assumed to be redundant.</p><p>Tune <code>spark.locality.wait</code> (and its per-level overrides) upward when tasks are long-running and locality is poor, since the default is tuned for typical workloads<sup class="footnote-ref"><a href="#fn3" id="fnref3:12">[3:12]</a></sup>; set <code>spark.locality.wait.node</code> to <code>0</code> to skip straight to rack locality when node locality isn&#39;t achievable<sup class="footnote-ref"><a href="#fn3" id="fnref3:13">[3:13]</a></sup>.</p><p>Turn on shuffle tracking (<code>spark.dynamicAllocation.shuffleTracking.enabled</code>, default <code>true</code> since Spark 3.0) or the external shuffle service so dynamic allocation can reclaim executors without losing shuffle output or forcing recomputation<sup class="footnote-ref"><a href="#fn3" id="fnref3:14">[3:14]</a></sup><sup class="footnote-ref"><a href="#fn6" id="fnref6:6">[6:6]</a></sup>. The external shuffle service additionally lets persisted RDD blocks survive executor removal when <code>spark.shuffle.service.fetch.rdd.enabled</code> is set, and executors holding cached blocks are, by default, never removed at all, tunable via <code>spark.dynamicAllocation.cachedExecutorIdleTimeout</code><sup class="footnote-ref"><a href="#fn6" id="fnref6:7">[6:7]</a></sup>.</p><p>Set <code>spark.driver.maxResultSize</code> as a guardrail on serialized action-result size, and size <code>spark.driver.memory</code> with it in mind rather than in isolation<sup class="footnote-ref"><a href="#fn3" id="fnref3:15">[3:15]</a></sup>. Use <code>spark.dynamicAllocation.executorAllocationRatio</code> (default <code>1.0</code>, added in 2.4.0) to scale down over-allocation when tasks are small; for example, a value of <code>0.5</code> halves the target executor count dynamic allocation would otherwise compute<sup class="footnote-ref"><a href="#fn3" id="fnref3:16">[3:16]</a></sup>. Raise <code>spark.task.cpus</code> above its default of <code>1</code> when a task needs more than one core; doing so proportionally reduces concurrent task slots per executor (<code>spark.executor.cores / spark.task.cpus</code>)<sup class="footnote-ref"><a href="#fn3" id="fnref3:17">[3:17]</a></sup>.</p><h2 id="sources" tabindex="-1">Sources <a class="header-anchor" href="#sources" aria-label="Permalink to &quot;Sources&quot;">​</a></h2><hr class="footnotes-sep"><section class="footnotes"><ol class="footnotes-list"><li id="fn1" class="footnote-item"><p><a href="https://raw.githubusercontent.com/spoddutur/spark-notes/master/distribution_of_executors_cores_and_memory_for_spark_application.md" target="_blank" rel="noreferrer">Distribution of Executors, Cores and Memory for a Spark Application</a> <a href="#fnref1" class="footnote-backref">↩︎</a> <a href="#fnref1:1" class="footnote-backref">↩︎</a> <a href="#fnref1:2" class="footnote-backref">↩︎</a> <a href="#fnref1:3" class="footnote-backref">↩︎</a> <a href="#fnref1:4" class="footnote-backref">↩︎</a> <a href="#fnref1:5" class="footnote-backref">↩︎</a></p></li><li id="fn2" class="footnote-item"><p><a href="https://blog.cloudera.com/how-to-tune-your-apache-spark-jobs-part-2/" target="_blank" rel="noreferrer">How to Tune Your Apache Spark Jobs (Part 2)</a> <a href="#fnref2" class="footnote-backref">↩︎</a> <a href="#fnref2:1" class="footnote-backref">↩︎</a> <a href="#fnref2:2" class="footnote-backref">↩︎</a> <a href="#fnref2:3" class="footnote-backref">↩︎</a> <a href="#fnref2:4" class="footnote-backref">↩︎</a></p></li><li id="fn3" class="footnote-item"><p><a href="https://spark.apache.org/docs/latest/configuration.html" target="_blank" rel="noreferrer">Configuration — Spark</a> <a href="#fnref3" class="footnote-backref">↩︎</a> <a href="#fnref3:1" class="footnote-backref">↩︎</a> <a href="#fnref3:2" class="footnote-backref">↩︎</a> <a href="#fnref3:3" class="footnote-backref">↩︎</a> <a href="#fnref3:4" class="footnote-backref">↩︎</a> <a href="#fnref3:5" class="footnote-backref">↩︎</a> <a href="#fnref3:6" class="footnote-backref">↩︎</a> <a href="#fnref3:7" class="footnote-backref">↩︎</a> <a href="#fnref3:8" class="footnote-backref">↩︎</a> <a href="#fnref3:9" class="footnote-backref">↩︎</a> <a href="#fnref3:10" class="footnote-backref">↩︎</a> <a href="#fnref3:11" class="footnote-backref">↩︎</a> <a href="#fnref3:12" class="footnote-backref">↩︎</a> <a href="#fnref3:13" class="footnote-backref">↩︎</a> <a href="#fnref3:14" class="footnote-backref">↩︎</a> <a href="#fnref3:15" class="footnote-backref">↩︎</a> <a href="#fnref3:16" class="footnote-backref">↩︎</a> <a href="#fnref3:17" class="footnote-backref">↩︎</a></p></li><li id="fn4" class="footnote-item"><p><a href="https://spark.apache.org/docs/latest/tuning.html" target="_blank" rel="noreferrer">Spark Tuning Guide</a> <a href="#fnref4" class="footnote-backref">↩︎</a></p></li><li id="fn5" class="footnote-item"><p><a href="https://luminousmen.com/post/dive-into-spark-memory" target="_blank" rel="noreferrer">Dive into Spark Memory</a> <a href="#fnref5" class="footnote-backref">↩︎</a> <a href="#fnref5:1" class="footnote-backref">↩︎</a> <a href="#fnref5:2" class="footnote-backref">↩︎</a> <a href="#fnref5:3" class="footnote-backref">↩︎</a> <a href="#fnref5:4" class="footnote-backref">↩︎</a> <a href="#fnref5:5" class="footnote-backref">↩︎</a> <a href="#fnref5:6" class="footnote-backref">↩︎</a></p></li><li id="fn6" class="footnote-item"><p><a href="https://spark.apache.org/docs/latest/job-scheduling.html" target="_blank" rel="noreferrer">Job Scheduling — Dynamic Resource Allocation</a> <a href="#fnref6" class="footnote-backref">↩︎</a> <a href="#fnref6:1" class="footnote-backref">↩︎</a> <a href="#fnref6:2" class="footnote-backref">↩︎</a> <a href="#fnref6:3" class="footnote-backref">↩︎</a> <a href="#fnref6:4" class="footnote-backref">↩︎</a> <a href="#fnref6:5" class="footnote-backref">↩︎</a> <a href="#fnref6:6" class="footnote-backref">↩︎</a> <a href="#fnref6:7" class="footnote-backref">↩︎</a></p></li></ol></section>',30)])])}const k=o(c,[["render",f]]);export{m as __pageData,k as default};
+import{_ as o,o as t,c as a,a5 as r}from"./chunks/framework.DSg0KOwT.js";const s="/docs/assets/container-memory.DIO0AnIm.svg",n="/docs/assets/container-memory.dark.CP-5zuCl.svg",m=JSON.parse('{"title":"Cluster Tuning","description":"","frontmatter":{"title":"Cluster Tuning"},"headers":[],"relativePath":"tuning-reference/cluster-config.md","filePath":"tuning-reference/cluster-config.md"}'),c={name:"tuning-reference/cluster-config.md"};function i(f,e,l,d,u,h){return t(),a("div",null,[...e[0]||(e[0]=[r('<h1 id="cluster-config" tabindex="-1">Cluster Tuning <a class="header-anchor" href="#cluster-config" aria-label="Permalink to &quot;Cluster Tuning {#cluster-config}&quot;">​</a></h1><h2 id="sizing-executors-and-containers" tabindex="-1">Sizing executors and containers <a class="header-anchor" href="#sizing-executors-and-containers" aria-label="Permalink to &quot;Sizing executors and containers&quot;">​</a></h2><p>Cluster tuning is the set of decisions that map an application&#39;s cores, memory, and executor count onto the underlying cluster (YARN or Kubernetes) plus a handful of related knobs (data locality, dynamic allocation, per-task CPU reservation) that all interact with that sizing decision.</p><p>The starting point is executor sizing. Working through a concrete example (a 10-node cluster with 16 cores and 64GB RAM per node), the derivation runs: assign 5 cores per executor; reserve about 1 core per node for Hadoop/YARN/OS daemons, leaving 15 usable cores per node (150 total); dividing by 5 cores per executor gives 30 executors, minus 1 reserved for the YARN ApplicationMaster (29); with 3 executors per node, memory per executor is 64GB / 3 ≈ 21GB, and after subtracting about 7% for YARN memory overhead that comes out to roughly 18GB usable, a recommended shape of 29 executors × 5 cores × 18GB<sup class="footnote-ref"><a href="#fn1" id="fnref1">[1]</a></sup>. Cloudera&#39;s own worked example, on a 6-node cluster with the same 16-core / 64GB-per-node hardware, lands on the same shape: <code>--num-executors 17 --executor-cores 5 --executor-memory 19G</code>, rather than one &quot;fat&quot; executor per node (<code>--num-executors 6 --executor-cores 15 --executor-memory 63G</code>)<sup class="footnote-ref"><a href="#fn2" id="fnref2">[2]</a></sup>. Both sources treat the resulting task count (executor-cores × num-executors) as the single most important tuning lever, since Spark cannot compensate for too little parallelism on its own<sup class="footnote-ref"><a href="#fn2" id="fnref2:1">[2:1]</a></sup>. <code>spark.executor.cores</code> is the config that controls concurrent tasks per executor; it defaults to 1 in YARN mode, or to all available cores on the worker in standalone mode<sup class="footnote-ref"><a href="#fn3" id="fnref3">[3]</a></sup>, and <code>spark.executor.memory</code> sets the JVM heap size per executor<sup class="footnote-ref"><a href="#fn2" id="fnref2:2">[2:2]</a></sup>. Independent of the sizing formula above, the Spark tuning guide recommends targeting 2–3 tasks per CPU core across the cluster<sup class="footnote-ref"><a href="#fn4" id="fnref4">[4]</a></sup>.</p><p>On top of executor memory sits container memory. Spark computes the total container/pod allocation as <code>executorMemoryMiB + memoryOverheadMiB + memoryOffHeapMiB + pysparkMemToUseMiB</code>. On YARN this is what gets allocated for the container, on Kubernetes it becomes the pod memory limit<sup class="footnote-ref"><a href="#fn5" id="fnref5">[5]</a></sup>. <code>spark.executor.memoryOverhead</code> itself defaults to <code>max(0.1 * executorMemory, 384MB)</code><sup class="footnote-ref"><a href="#fn5" id="fnref5:1">[5:1]</a></sup><sup class="footnote-ref"><a href="#fn3" id="fnref3:1">[3:1]</a></sup>.</p><img class="light-only" src="'+s+'" alt="Container memory sums executor heap, memory overhead, off-heap size, and pyspark memory into the requested container size; the resource manager grants a container of that size and OOMKills the executor when its actual runtime footprint spills past that limit."><img class="dark-only" src="'+n+'" alt="Container memory sums executor heap, memory overhead, off-heap size, and pyspark memory into the requested container size; the resource manager grants a container of that size and OOMKills the executor when its actual runtime footprint spills past that limit."><blockquote><p><strong>PySpark:</strong> <code>spark.executor.pyspark.memory</code> is only added as its own container-memory term when it&#39;s set explicitly; otherwise PySpark&#39;s memory use is folded into the general overhead budget rather than tracked separately.<sup class="footnote-ref"><a href="#fn5" id="fnref5:2">[5:2]</a></sup></p></blockquote><p>On Kubernetes specifically, <code>spark.kubernetes.executor.request.cores</code> and <code>spark.kubernetes.executor.limit.cores</code> take priority over <code>spark.executor.cores</code> for the pod&#39;s CPU request/limit sent to the Kubernetes scheduler<sup class="footnote-ref"><a href="#fn6" id="fnref6">[6]</a></sup>, while <code>spark.executor.cores</code> remains the config Spark itself uses to size the number of concurrent task slots<sup class="footnote-ref"><a href="#fn3" id="fnref3:2">[3:2]</a></sup>.</p><p>Two more knobs round out the picture. <code>spark.locality.wait</code> (default <code>3s</code>) controls how long a task waits for a data-local placement before Spark gives up and schedules it less locally, stepping through the same wait across process-local → node-local → rack-local → any; each level can be overridden independently via <code>spark.locality.wait.process</code>, <code>.node</code>, and <code>.rack</code>, all of which default to the base wait when left unset<sup class="footnote-ref"><a href="#fn3" id="fnref3:3">[3:3]</a></sup>. Dynamic allocation lets Spark add and remove executors as work changes, but it requires one of several supporting mechanisms: an external shuffle service, shuffle tracking (<code>spark.dynamicAllocation.shuffleTracking.enabled</code>, default <code>true</code> since Spark 3.0), shuffle-block decommission, or the experimental sort-IO plugin<sup class="footnote-ref"><a href="#fn3" id="fnref3:4">[3:4]</a></sup>. Removing an executor can otherwise destroy shuffle state it&#39;s holding. Finally, <code>spark.task.cpus</code> (default <code>1</code>) sets how many cores each task reserves; the number of concurrent task slots per executor is derived jointly from it and <code>spark.executor.cores</code>, roughly <code>spark.executor.cores / spark.task.cpus</code><sup class="footnote-ref"><a href="#fn3" id="fnref3:5">[3:5]</a></sup>.</p><h2 id="spotting-a-bad-sizing-decision" tabindex="-1">Spotting a bad sizing decision <a class="header-anchor" href="#spotting-a-bad-sizing-decision" aria-label="Permalink to &quot;Spotting a bad sizing decision&quot;">​</a></h2><p>Getting that sizing wrong shows up in a handful of specific symptoms. The clearest sign of an under-sized executor layout is HDFS throughput dropping under load: &quot;HDFS client has trouble with tons of concurrent threads. It was observed that HDFS achieves full write throughput with ~5 tasks per executor&quot;<sup class="footnote-ref"><a href="#fn1" id="fnref1:1">[1:1]</a></sup>. The &quot;fat executor&quot; case (one executor per node, using all 16 cores) shows the failure mode directly: &quot;with all 16 cores per executor... HDFS throughput will hurt and it&#39;ll result in excessive garbage [collection]&quot;<sup class="footnote-ref"><a href="#fn1" id="fnref1:2">[1:2]</a></sup>.</p><p>On the memory side, an executor or pod that dies with no Spark-level error is a strong signal that off-heap memory was never added into the container budget. Enabling <code>spark.memory.offHeap.enabled=true</code> with <code>spark.memory.offHeap.size=1g</code> on top of an 8G executor with default overhead (819MB) means real usage is 8192+819+1024 = 10,035MB, while the container was only granted 8192+819 = 9,011MB. The executor gets killed by YARN, or OOMKilled by the Kubernetes kubelet, with no warning from Spark itself<sup class="footnote-ref"><a href="#fn5" id="fnref5:3">[5:3]</a></sup>.</p><p>With dynamic allocation on, unexplained shuffle recomputation is a detectable symptom of executors being reclaimed mid-shuffle: &quot;In the event of stragglers... dynamic allocation may remove an executor before the shuffle completes, in which case the shuffle files written by that executor must be recomputed unnecessarily&quot;<sup class="footnote-ref"><a href="#fn6" id="fnref6:1">[6:1]</a></sup>. Jobs that abort with a serialized-result-size error are hitting the <code>spark.driver.maxResultSize</code> guardrail rather than a driver heap exhaustion: &quot;Jobs will be aborted if the total size [of serialized action results] is above this limit&quot;<sup class="footnote-ref"><a href="#fn3" id="fnref3:6">[3:6]</a></sup>. And on the resource-waste side, executors that are provisioned but never assigned work are a sign that dynamic allocation is targeting full parallelism against a workload made of many small tasks<sup class="footnote-ref"><a href="#fn3" id="fnref3:7">[3:7]</a></sup>.</p><h2 id="what-a-bad-sizing-decision-costs" tabindex="-1">What a bad sizing decision costs <a class="header-anchor" href="#what-a-bad-sizing-decision-costs" aria-label="Permalink to &quot;What a bad sizing decision costs&quot;">​</a></h2><p>Each symptom above carries a specific price tag. Task count (<code>executor-cores × num-executors</code>) is treated by both cited sources as the single most important tuning lever, since Spark cannot compensate for too little parallelism on its own<sup class="footnote-ref"><a href="#fn2" id="fnref2:3">[2:3]</a></sup>. Going the other way, cramming too many cores into one executor degrades HDFS throughput and drives up garbage collection<sup class="footnote-ref"><a href="#fn1" id="fnref1:3">[1:3]</a></sup>.</p><p>Container-memory misconfiguration matters because the failure is silent from Spark&#39;s point of view: off-heap memory that isn&#39;t accounted for in <code>spark.executor.memoryOverhead</code> causes the executor to actually use more memory than the container/pod was granted, so it gets killed externally (by YARN or the kubelet) with no Spark-level diagnostic to point at the real cause<sup class="footnote-ref"><a href="#fn5" id="fnref5:4">[5:4]</a></sup>.</p><p>Dynamic allocation&#39;s interaction with shuffle state matters because, before dynamic allocation existed, an executor exiting alongside its application meant all its state could be safely discarded; with dynamic allocation, the application keeps running after an executor is explicitly removed, so any later need for that executor&#39;s state forces a recompute<sup class="footnote-ref"><a href="#fn6" id="fnref6:2">[6:2]</a></sup>. That is exactly why Spark needs &quot;a mechanism to decommission an executor gracefully by preserving its state before removing it&quot;<sup class="footnote-ref"><a href="#fn6" id="fnref6:3">[6:3]</a></sup>. Without shuffle tracking, an external shuffle service, or shuffle-block decommission enabled, dynamic allocation either can&#39;t be turned on at all, or, if it&#39;s active regardless, an executor holding unpreserved shuffle output that gets removed forces exactly that unnecessary recompute<sup class="footnote-ref"><a href="#fn3" id="fnref3:8">[3:8]</a></sup><sup class="footnote-ref"><a href="#fn6" id="fnref6:4">[6:4]</a></sup>.</p><p>On the driver side, <code>spark.driver.maxResultSize</code> and <code>spark.driver.memory</code> are separate budgets that still interact: whether a high <code>maxResultSize</code> actually causes an out-of-memory error &quot;depends on spark.driver.memory and memory overhead of objects in JVM&quot;<sup class="footnote-ref"><a href="#fn3" id="fnref3:9">[3:9]</a></sup>. Raising one without considering the other doesn&#39;t fully protect the driver.</p><p>Finally, over-provisioning executors against a small-task workload wastes cluster resources: &quot;with small tasks this setting can waste a lot of resources due to executor allocation overhead, as some executor might not even do any work&quot;<sup class="footnote-ref"><a href="#fn3" id="fnref3:10">[3:10]</a></sup>.</p><h2 id="sizing-the-cluster-correctly" tabindex="-1">Sizing the cluster correctly <a class="header-anchor" href="#sizing-the-cluster-correctly" aria-label="Permalink to &quot;Sizing the cluster correctly&quot;">​</a></h2><p>Avoiding those costs starts from a formula, not one fat executor per node. Apply the balanced-executor formula instead; the worked examples above give shapes like 29 × 5 × 18GB for a 10-node/16-core/64GB cluster, or 17 × 5 × 19G for a 6-node cluster with the same per-node hardware<sup class="footnote-ref"><a href="#fn1" id="fnref1:4">[1:4]</a></sup><sup class="footnote-ref"><a href="#fn2" id="fnref2:4">[2:4]</a></sup>. Keep <code>--executor-cores</code> at or below roughly 5 so HDFS client concurrency stays in the range where it sustains full write throughput<sup class="footnote-ref"><a href="#fn1" id="fnref1:5">[1:5]</a></sup>.</p><p>When enabling off-heap memory, account for <code>spark.memory.offHeap.size</code> in the container/pod memory budget explicitly; <code>spark.executor.memoryOverhead</code>&#39;s default of <code>max(0.1 * executorMemory, 384MB)</code> does not include it<sup class="footnote-ref"><a href="#fn5" id="fnref5:5">[5:5]</a></sup>. If you&#39;re still referencing the older <code>spark.yarn.executor.memoryOverhead</code> name, note it was removed in Spark 3.0<sup class="footnote-ref"><a href="#fn5" id="fnref5:6">[5:6]</a></sup>.</p><p>On Kubernetes, remember that <code>spark.kubernetes.executor.request.cores</code> and <code>.limit.cores</code> govern the pod&#39;s CPU request/limit and take priority over <code>spark.executor.cores</code> for that purpose<sup class="footnote-ref"><a href="#fn6" id="fnref6:5">[6:5]</a></sup>, while <code>spark.executor.cores</code> separately governs Spark&#39;s own task-slot count<sup class="footnote-ref"><a href="#fn3" id="fnref3:11">[3:11]</a></sup>. The two need to be reasoned about together rather than assumed to be redundant.</p><p>Tune <code>spark.locality.wait</code> (and its per-level overrides) upward when tasks are long-running and locality is poor, since the default is tuned for typical workloads<sup class="footnote-ref"><a href="#fn3" id="fnref3:12">[3:12]</a></sup>; set <code>spark.locality.wait.node</code> to <code>0</code> to skip straight to rack locality when node locality isn&#39;t achievable<sup class="footnote-ref"><a href="#fn3" id="fnref3:13">[3:13]</a></sup>.</p><p>Turn on shuffle tracking (<code>spark.dynamicAllocation.shuffleTracking.enabled</code>, default <code>true</code> since Spark 3.0) or the external shuffle service so dynamic allocation can reclaim executors without losing shuffle output or forcing recomputation<sup class="footnote-ref"><a href="#fn3" id="fnref3:14">[3:14]</a></sup><sup class="footnote-ref"><a href="#fn6" id="fnref6:6">[6:6]</a></sup>. The external shuffle service additionally lets persisted RDD blocks survive executor removal when <code>spark.shuffle.service.fetch.rdd.enabled</code> is set, and executors holding cached blocks are, by default, never removed at all, tunable via <code>spark.dynamicAllocation.cachedExecutorIdleTimeout</code><sup class="footnote-ref"><a href="#fn6" id="fnref6:7">[6:7]</a></sup>.</p><p>Set <code>spark.driver.maxResultSize</code> as a guardrail on serialized action-result size, and size <code>spark.driver.memory</code> with it in mind rather than in isolation<sup class="footnote-ref"><a href="#fn3" id="fnref3:15">[3:15]</a></sup>. Use <code>spark.dynamicAllocation.executorAllocationRatio</code> (default <code>1.0</code>, added in 2.4.0) to scale down over-allocation when tasks are small; for example, a value of <code>0.5</code> halves the target executor count dynamic allocation would otherwise compute<sup class="footnote-ref"><a href="#fn3" id="fnref3:16">[3:16]</a></sup>. Raise <code>spark.task.cpus</code> above its default of <code>1</code> when a task needs more than one core; doing so proportionally reduces concurrent task slots per executor (<code>spark.executor.cores / spark.task.cpus</code>)<sup class="footnote-ref"><a href="#fn3" id="fnref3:17">[3:17]</a></sup>.</p><h2 id="bottleneck-autoscaling-churn" tabindex="-1">Autoscaling churn <a class="header-anchor" href="#bottleneck-autoscaling-churn" aria-label="Permalink to &quot;Autoscaling churn {#bottleneck-autoscaling-churn}&quot;">​</a></h2><p><span class="tag">CHRN</span> <span class="tag">EXPERIMENTAL</span></p><p>Dynamic allocation adds executors once tasks back up and frees them once they go idle<sup class="footnote-ref"><a href="#fn6" id="fnref6:8">[6:8]</a></sup>. Churn is a narrower failure mode inside that same mechanism: executors that get stood up and torn down again before they&#39;ve done much useful work, cycling through provisioning and JVM startup cost repeatedly instead of running tasks.</p><h3 id="how-it-s-detected" tabindex="-1">How it&#39;s detected <a class="header-anchor" href="#how-it-s-detected" aria-label="Permalink to &quot;How it&#39;s detected&quot;">​</a></h3><p>An executor counts as short-lived when its lifetime, from its <code>ExecutorAdded</code> event to either its <code>ExecutorRemoved</code> event or the end of the run if it was never removed, is under 2 minutes. This is evaluated once a run has added at least 5 executors, a floor that keeps a two- or three-executor job from registering on ordinary scale-down.</p><table tabindex="0"><thead><tr><th>Signal</th><th>Warning</th><th>Critical</th></tr></thead><tbody><tr><td>Share of added executors that are short-lived (&lt; 2 min lifetime)</td><td>&gt; 30%</td><td>&gt; 60%</td></tr></tbody></table><p>The 2-minute lifetime cutoff and the 30%/60% split are unvalidated heuristics rather than figures published in Spark&#39;s own documentation or benchmarks, so treat a finding here as a prompt to look at the executor timeline rather than a calibrated verdict.</p><h3 id="why-it-matters" tabindex="-1">Why it matters <a class="header-anchor" href="#why-it-matters" aria-label="Permalink to &quot;Why it matters&quot;">​</a></h3><p>Every short-lived executor pays the same provisioning and JVM-startup cost as a long-lived one, but returns little task work in exchange. A run that keeps flapping between scaling up and down spends more of its wall-clock time paying that repeated overhead than one that settles into a stable executor count.</p><h3 id="how-to-fix-it" tabindex="-1">How to fix it <a class="header-anchor" href="#how-to-fix-it" aria-label="Permalink to &quot;How to fix it&quot;">​</a></h3><ul><li>Raise <code>spark.dynamicAllocation.executorIdleTimeout</code> (default 60s<sup class="footnote-ref"><a href="#fn3" id="fnref3:18">[3:18]</a></sup>) so an executor survives a brief lull instead of being released the moment it goes idle, only to be requested again shortly after.</li><li>Widen the gap between <code>spark.dynamicAllocation.minExecutors</code> and <code>.maxExecutors</code><sup class="footnote-ref"><a href="#fn3" id="fnref3:19">[3:19]</a></sup>: bounds set too close together force Spark to repeatedly add and remove executors to track small fluctuations in the task backlog instead of settling into a stable range.</li></ul><h2 id="sources" tabindex="-1">Sources <a class="header-anchor" href="#sources" aria-label="Permalink to &quot;Sources&quot;">​</a></h2><hr class="footnotes-sep"><section class="footnotes"><ol class="footnotes-list"><li id="fn1" class="footnote-item"><p><a href="https://raw.githubusercontent.com/spoddutur/spark-notes/master/distribution_of_executors_cores_and_memory_for_spark_application.md" target="_blank" rel="noreferrer">Distribution of Executors, Cores and Memory for a Spark Application</a> <a href="#fnref1" class="footnote-backref">↩︎</a> <a href="#fnref1:1" class="footnote-backref">↩︎</a> <a href="#fnref1:2" class="footnote-backref">↩︎</a> <a href="#fnref1:3" class="footnote-backref">↩︎</a> <a href="#fnref1:4" class="footnote-backref">↩︎</a> <a href="#fnref1:5" class="footnote-backref">↩︎</a></p></li><li id="fn2" class="footnote-item"><p><a href="https://blog.cloudera.com/how-to-tune-your-apache-spark-jobs-part-2/" target="_blank" rel="noreferrer">How to Tune Your Apache Spark Jobs (Part 2)</a> <a href="#fnref2" class="footnote-backref">↩︎</a> <a href="#fnref2:1" class="footnote-backref">↩︎</a> <a href="#fnref2:2" class="footnote-backref">↩︎</a> <a href="#fnref2:3" class="footnote-backref">↩︎</a> <a href="#fnref2:4" class="footnote-backref">↩︎</a></p></li><li id="fn3" class="footnote-item"><p><a href="https://spark.apache.org/docs/latest/configuration.html" target="_blank" rel="noreferrer">Configuration — Spark</a> <a href="#fnref3" class="footnote-backref">↩︎</a> <a href="#fnref3:1" class="footnote-backref">↩︎</a> <a href="#fnref3:2" class="footnote-backref">↩︎</a> <a href="#fnref3:3" class="footnote-backref">↩︎</a> <a href="#fnref3:4" class="footnote-backref">↩︎</a> <a href="#fnref3:5" class="footnote-backref">↩︎</a> <a href="#fnref3:6" class="footnote-backref">↩︎</a> <a href="#fnref3:7" class="footnote-backref">↩︎</a> <a href="#fnref3:8" class="footnote-backref">↩︎</a> <a href="#fnref3:9" class="footnote-backref">↩︎</a> <a href="#fnref3:10" class="footnote-backref">↩︎</a> <a href="#fnref3:11" class="footnote-backref">↩︎</a> <a href="#fnref3:12" class="footnote-backref">↩︎</a> <a href="#fnref3:13" class="footnote-backref">↩︎</a> <a href="#fnref3:14" class="footnote-backref">↩︎</a> <a href="#fnref3:15" class="footnote-backref">↩︎</a> <a href="#fnref3:16" class="footnote-backref">↩︎</a> <a href="#fnref3:17" class="footnote-backref">↩︎</a> <a href="#fnref3:18" class="footnote-backref">↩︎</a> <a href="#fnref3:19" class="footnote-backref">↩︎</a></p></li><li id="fn4" class="footnote-item"><p><a href="https://spark.apache.org/docs/latest/tuning.html" target="_blank" rel="noreferrer">Spark Tuning Guide</a> <a href="#fnref4" class="footnote-backref">↩︎</a></p></li><li id="fn5" class="footnote-item"><p><a href="https://luminousmen.com/post/dive-into-spark-memory" target="_blank" rel="noreferrer">Dive into Spark Memory</a> <a href="#fnref5" class="footnote-backref">↩︎</a> <a href="#fnref5:1" class="footnote-backref">↩︎</a> <a href="#fnref5:2" class="footnote-backref">↩︎</a> <a href="#fnref5:3" class="footnote-backref">↩︎</a> <a href="#fnref5:4" class="footnote-backref">↩︎</a> <a href="#fnref5:5" class="footnote-backref">↩︎</a> <a href="#fnref5:6" class="footnote-backref">↩︎</a></p></li><li id="fn6" class="footnote-item"><p><a href="https://spark.apache.org/docs/latest/job-scheduling.html" target="_blank" rel="noreferrer">Job Scheduling — Dynamic Resource Allocation</a> <a href="#fnref6" class="footnote-backref">↩︎</a> <a href="#fnref6:1" class="footnote-backref">↩︎</a> <a href="#fnref6:2" class="footnote-backref">↩︎</a> <a href="#fnref6:3" class="footnote-backref">↩︎</a> <a href="#fnref6:4" class="footnote-backref">↩︎</a> <a href="#fnref6:5" class="footnote-backref">↩︎</a> <a href="#fnref6:6" class="footnote-backref">↩︎</a> <a href="#fnref6:7" class="footnote-backref">↩︎</a> <a href="#fnref6:8" class="footnote-backref">↩︎</a></p></li></ol></section>',41)])])}const k=o(c,[["render",i]]);export{m as __pageData,k as default};

package/public/docs/assets/{tuning-reference_cluster-config.md.ZVmDGsQ3.lean.js → tuning-reference_cluster-config.md.CD6vzYtD.lean.js}

@@ -1 +1 @@
-import{_ as o,o as a,c as t,a5 as r}from"./chunks/framework.DSg0KOwT.js";const s="/docs/assets/container-memory.DIO0AnIm.svg",n="/docs/assets/container-memory.dark.CP-5zuCl.svg",m=JSON.parse('{"title":"Cluster Tuning","description":"","frontmatter":{"title":"Cluster Tuning"},"headers":[],"relativePath":"tuning-reference/cluster-config.md","filePath":"tuning-reference/cluster-config.md"}'),c={name:"tuning-reference/cluster-config.md"};function f(i,e,l,u,d,h){return a(),t("div",null,[...e[0]||(e[0]=[r("",30)])])}const k=o(c,[["render",f]]);export{m as __pageData,k as default};
+import{_ as o,o as t,c as a,a5 as r}from"./chunks/framework.DSg0KOwT.js";const s="/docs/assets/container-memory.DIO0AnIm.svg",n="/docs/assets/container-memory.dark.CP-5zuCl.svg",m=JSON.parse('{"title":"Cluster Tuning","description":"","frontmatter":{"title":"Cluster Tuning"},"headers":[],"relativePath":"tuning-reference/cluster-config.md","filePath":"tuning-reference/cluster-config.md"}'),c={name:"tuning-reference/cluster-config.md"};function i(f,e,l,d,u,h){return t(),a("div",null,[...e[0]||(e[0]=[r("",41)])])}const k=o(c,[["render",i]]);export{m as __pageData,k as default};

package/public/docs/assets/{tuning-reference_memory-model.md.DhT-n4y3.js → tuning-reference_memory-model.md.CWhvgevP.js}

@@ -1 +1 @@
-import{_ as o,o as a,c as r,a5 as t}from"./chunks/framework.DSg0KOwT.js";const s="/docs/assets/memory-regions.XHvO7jHG.svg",n="/docs/assets/memory-regions.dark.D4TP9_08.svg",f="/docs/assets/memory-borrowing.BqQRJg0u.svg",i="/docs/assets/memory-borrowing.dark.Yhh20O9C.svg",y=JSON.parse('{"title":"Memory Management","description":"","frontmatter":{"title":"Memory Management"},"headers":[],"relativePath":"tuning-reference/memory-model.md","filePath":"tuning-reference/memory-model.md"}'),c={name:"tuning-reference/memory-model.md"};function l(h,e,d,p,u,m){return a(),r("div",null,[...e[0]||(e[0]=[t('<h1 id="memory-model" tabindex="-1">Memory Management <a class="header-anchor" href="#memory-model" aria-label="Permalink to &quot;Memory Management {#memory-model}&quot;">​</a></h1><h2 id="the-unified-memory-model" tabindex="-1">The unified memory model <a class="header-anchor" href="#the-unified-memory-model" aria-label="Permalink to &quot;The unified memory model&quot;">​</a></h2><p>Since Spark 1.6, the <code>UnifiedMemoryManager</code> has replaced the earlier static split between execution and storage memory with a single shared region, referred to as M<sup class="footnote-ref"><a href="#fn1" id="fnref1">[1]</a></sup><sup class="footnote-ref"><a href="#fn2" id="fnref2">[2]</a></sup>. M is carved out of the JVM heap after first setting aside 300 MiB of reserved system memory: <code>M = (JVM heap − 300 MiB) × spark.memory.fraction</code>, with <code>spark.memory.fraction</code> defaulting to 0.6<sup class="footnote-ref"><a href="#fn2" id="fnref2:1">[2:1]</a></sup><sup class="footnote-ref"><a href="#fn3" id="fnref3">[3]</a></sup>. Within M, <code>spark.memory.storageFraction</code> (default 0.5) marks off a subregion reserved for cached blocks that are immune to eviction; with defaults, this works out to roughly a 30%/30% on-heap split between execution and storage out of total executor memory<sup class="footnote-ref"><a href="#fn3" id="fnref3:1">[3:1]</a></sup>.</p><img class="light-only" src="'+s+'" alt="The executor memory layout showing reserved memory, the unified region split into execution and storage, and user memory inside the JVM heap, with the off-heap pool and memory overhead outside it."><img class="dark-only" src="'+n+'" alt="The executor memory layout showing reserved memory, the unified region split into execution and storage, and user memory inside the JVM heap, with the off-heap pool and memory overhead outside it."><p>Execution and storage borrow from each other dynamically rather than sitting behind a hard wall: when execution memory is unused, storage can acquire all of it, and vice versa<sup class="footnote-ref"><a href="#fn2" id="fnref2:2">[2:2]</a></sup><sup class="footnote-ref"><a href="#fn1" id="fnref1:1">[1:1]</a></sup>. The two are not equal peers, though. Execution always has priority, taking memory immediately and evicting cached storage blocks if necessary<sup class="footnote-ref"><a href="#fn3" id="fnref3:2">[3:2]</a></sup>.</p><p>The reserved 300 MB is a flat constant (<code>RESERVED_SYSTEM_MEMORY_BYTES</code> in the Spark source), not a formula, and it&#39;s hardcoded: there is no supported production configuration to change it. The only override is the internal <code>spark.testing.reservedMemory</code> property, which exists for Spark&#39;s own test suite rather than production tuning<sup class="footnote-ref"><a href="#fn3" id="fnref3:3">[3:3]</a></sup>. <code>spark.memory.fraction</code> is applied against heap minus that reserved 300 MB, not against total heap. The tuning guide is explicit that it &quot;expresses the size of M as a fraction of the (JVM heap space − 300MiB)&quot;<sup class="footnote-ref"><a href="#fn2" id="fnref2:3">[2:3]</a></sup>.</p><p>Off-heap memory extends the same model outside the JVM heap. When <code>spark.memory.offHeap.enabled=true</code>, Spark allocates raw off-heap buffers via <code>sun.misc.Unsafe</code> (routed through <code>jdk.internal.misc.Unsafe</code> on JDK 17+, which is why some builds need <code>--add-opens</code> flags), and that off-heap region is split into its own execution and storage pools, following the same borrowing rules as on-heap memory: execution has priority, storage gets evicted first<sup class="footnote-ref"><a href="#fn3" id="fnref3:4">[3:4]</a></sup>. Enabling it requires <code>spark.memory.offHeap.size</code> to be set to a positive value; leaving it enabled with the default size of <code>0</code> is a documented-invalid combination, not a supported way to run with off-heap &quot;on but empty&quot;<sup class="footnote-ref"><a href="#fn4" id="fnref4">[4]</a></sup>. The setting also &quot;has no impact on heap memory usage&quot;. Turning on off-heap memory does not shrink the JVM <code>-Xmx</code> for you, so the on-heap size has to be reduced manually to keep total footprint constant<sup class="footnote-ref"><a href="#fn4" id="fnref4:1">[4:1]</a></sup>. This off-heap execution memory underlies Project Tungsten: its compact binary row encoding, its explicit-memory-managed hash map for aggregations, and its cache-aware sort/join algorithms are all built to run against off-heap, GC-invisible memory<sup class="footnote-ref"><a href="#fn5" id="fnref5">[5]</a></sup><sup class="footnote-ref"><a href="#fn6" id="fnref6">[6]</a></sup>.</p><p>Executor memory overhead is a separate pool layered on top of M. <code>spark.executor.memoryOverhead</code> defaults to <code>executorMemory × spark.executor.memoryOverheadFactor</code>, floored at <code>spark.executor.minMemoryOverhead</code> (384 MiB)<sup class="footnote-ref"><a href="#fn4" id="fnref4:2">[4:2]</a></sup>. <code>spark.executor.memoryOverheadFactor</code> itself defaults to 0.10 for ordinary JVM executors, but Spark bumps that default to 0.40 specifically for Kubernetes non-JVM jobs, since those workloads tend to need more non-JVM heap space<sup class="footnote-ref"><a href="#fn4" id="fnref4:3">[4:3]</a></sup>. The legacy, YARN-only <code>spark.yarn.executor.memoryOverhead</code> property was removed in Spark 3.0 in favor of the cluster-manager-agnostic <code>spark.executor.memoryOverhead</code><sup class="footnote-ref"><a href="#fn3" id="fnref3:5">[3:5]</a></sup>.</p><blockquote><p><strong>PySpark:</strong> <code>spark.python.worker.memory</code> (default <code>512m</code>) is a soft spill threshold for a Python worker&#39;s own aggregation buffering, not a JVM-enforced cap. A PySpark worker runs as a separate OS process outside the JVM heap, so the JVM cannot police it directly<sup class="footnote-ref"><a href="#fn3" id="fnref3:6">[3:6]</a></sup>. The only setting that actually tries to bound PySpark memory per executor is <code>spark.executor.pyspark.memory</code>, and even that depends on Python&#39;s <code>resource</code> module, which isn&#39;t supported on Windows and doesn&#39;t actually limit anything on macOS<sup class="footnote-ref"><a href="#fn4" id="fnref4:4">[4:4]</a></sup>. Left unset, PySpark memory usage is folded into <code>spark.executor.memoryOverhead</code> by default<sup class="footnote-ref"><a href="#fn4" id="fnref4:5">[4:5]</a></sup>.</p></blockquote><h2 id="watching-eviction-and-spill" tabindex="-1">Watching eviction and spill <a class="header-anchor" href="#watching-eviction-and-spill" aria-label="Permalink to &quot;Watching eviction and spill&quot;">​</a></h2><p>That borrowing leaves a trace once eviction actually happens. Storage eviction under memory pressure follows an LRU (least recently used) policy<sup class="footnote-ref"><a href="#fn1" id="fnref1:2">[1:2]</a></sup><sup class="footnote-ref"><a href="#fn7" id="fnref7">[7]</a></sup>. The granularity is the block: the <code>BlockManager</code> tracks cached data as per-partition blocks (one block per RDD/DataFrame partition) and LRU operates at that level rather than evicting an entire RDD or cached table in one shot<sup class="footnote-ref"><a href="#fn8" id="fnref8">[8]</a></sup><sup class="footnote-ref"><a href="#fn9" id="fnref9">[9]</a></sup>. In practice this tends to evict the oldest partitions first, those materialized in the earliest job or stage, though lazy evaluation makes it hard to predict exactly which partitions will go ahead of time<sup class="footnote-ref"><a href="#fn9" id="fnref9:1">[9:1]</a></sup>.</p><p>What happens to an evicted block is visible in its downstream effect and depends on its <code>StorageLevel</code>. For <code>MEMORY_ONLY</code>, the block is simply dropped and recomputed from the RDD&#39;s lineage the next time it&#39;s needed. For a disk-backed level like <code>MEMORY_AND_DISK</code>, the evicted block is written to disk and read back from there instead of being recomputed<sup class="footnote-ref"><a href="#fn9" id="fnref9:2">[9:2]</a></sup><sup class="footnote-ref"><a href="#fn7" id="fnref7:1">[7:1]</a></sup>. Blocks can also be evicted well before you ever try to reuse them: <code>.cache()</code> does not guarantee a block stays resident, especially on busy clusters or long pipelines<sup class="footnote-ref"><a href="#fn7" id="fnref7:2">[7:2]</a></sup>.</p><p>On the execution side, each task gets its own <code>TaskMemoryManager</code>, which enforces a soft per-task cap: with <code>n</code> tasks running concurrently, each task is allowed to allocate somewhere between <code>1/(2n)</code> and <code>1/n</code> of total execution memory, and the first task to arrive on an idle executor typically grabs more than its later-arriving neighbors<sup class="footnote-ref"><a href="#fn3" id="fnref3:7">[3:7]</a></sup>.</p><p>When a sort or hash-aggregation operator keeps requesting execution-memory pages and can&#39;t get more, Spark doesn&#39;t fail immediately. It blocks the requesting task, spills that task&#39;s in-memory data structure to disk, or, in the worst case, throws an <code>OutOfMemoryError</code><sup class="footnote-ref"><a href="#fn3" id="fnref3:8">[3:8]</a></sup>. The spill path runs through Spark&#39;s map/shuffle I/O machinery: shuffle partitions created by wide transformations like <code>groupBy()</code> or <code>join()</code> <a href="./bottleneck-spill.html">spill</a> to the executors&#39; local disks at the location set by <code>spark.local.directory</code><sup class="footnote-ref"><a href="#fn6" id="fnref6:1">[6:1]</a></sup>. SQL physical operators apply the same idea with their own row-count guardrails: <code>sortMergeJoinExec</code>&#39;s in-memory buffer and the cartesian-product operator&#39;s buffer both spill once they cross a configured row threshold, which by default is set to the value of <code>spark.shuffle.spill.numElementsForceSpillThreshold</code><sup class="footnote-ref"><a href="#fn10" id="fnref10">[10]</a></sup>.</p><p>Whatever the trigger, the resulting spilled bytes are exposed on the task metrics as <code>memoryBytesSpilled</code>, visible in the Spark UI and event log. This is the concrete signal to watch for execution memory pressure<sup class="footnote-ref"><a href="#fn11" id="fnref11">[11]</a></sup>.</p><p>Memory-overhead misconfiguration shows up differently: it manifests as the container or pod being OOMKilled with a vague container-memory error rather than a Spark-level exception, since the enforcement happens at the YARN NodeManager or Kubernetes kubelet/cgroup layer, not inside the JVM<sup class="footnote-ref"><a href="#fn3" id="fnref3:9">[3:9]</a></sup>. Under the old default overhead factor of 0.10, non-JVM Kubernetes jobs commonly failed with &quot;Memory Overhead Exceeded&quot; errors, which is exactly why Spark bumped the Kubernetes non-JVM default to 0.40<sup class="footnote-ref"><a href="#fn4" id="fnref4:6">[4:6]</a></sup>.</p><h2 id="what-the-borrowing-costs-you" tabindex="-1">What the borrowing costs you <a class="header-anchor" href="#what-the-borrowing-costs-you" aria-label="Permalink to &quot;What the borrowing costs you&quot;">​</a></h2><p>None of this is free for whoever&#39;s counting on cached data staying put. Because execution always wins the tug-of-war over storage, <a href="./caching.html">caching</a> is never a guarantee; it&#39;s a best effort. As luminousmen-memory-management puts it: &quot;If Execution needs memory, it takes it. If Storage is using that space (cached RDDs, broadcasts), Spark starts evicting blocks. If Execution is idle, Storage can grow into that space, until Execution comes back.&quot;<sup class="footnote-ref"><a href="#fn3" id="fnref3:10">[3:10]</a></sup> That growth-then-shrink-back behavior is dynamic borrowing, not storage evicting execution; eviction is strictly one-directional. As spark-notes-task-memory-management summarizes the agreement between the two regions: &quot;keep acquiring execution memory and evict storage as you need more execution memory&quot;<sup class="footnote-ref"><a href="#fn1" id="fnref1:3">[1:3]</a></sup>, never the reverse. The same asymmetric rule carries over when off-heap memory is enabled: execution still has priority and storage still gets evicted first<sup class="footnote-ref"><a href="#fn3" id="fnref3:11">[3:11]</a></sup>. Practically, this means a cached DataFrame can silently lose blocks under memory pressure, forcing an expensive lineage recompute (for <code>MEMORY_ONLY</code>) or an extra disk round-trip (for <code>MEMORY_AND_DISK</code>) the next time it&#39;s touched.</p><img class="light-only" src="'+f+'" alt="How storage memory borrows idle execution space while execution reclaims its own space by evicting storage in one direction."><img class="dark-only" src="'+i+'" alt="How storage memory borrows idle execution space while execution reclaims its own space by evicting storage in one direction."><p>The <code>TaskMemoryManager</code>&#39;s soft per-task cap explains why spill behavior is workload-shape-dependent rather than a fixed threshold: with more tasks packed onto an executor, each one&#39;s guaranteed share of execution memory shrinks toward <code>1/(2n)</code>, making spills more likely under high task concurrency even when total execution memory hasn&#39;t changed<sup class="footnote-ref"><a href="#fn3" id="fnref3:12">[3:12]</a></sup>.</p><p>Off-heap memory&#39;s payoff is specifically about <a href="./bottleneck-gc.html">garbage collection</a>: because off-heap buffers sit outside the JVM heap, they are invisible to the garbage collector, so fewer and smaller live objects need to be tracked, scanned, and copied, which reduces both the frequency and duration of GC pauses<sup class="footnote-ref"><a href="#fn3" id="fnref3:13">[3:13]</a></sup>. Project Tungsten&#39;s off-heap hash map for aggregations was benchmarked at over 1 million operations per second in a single thread, with &quot;almost no performance degradation as memory utilization increases,&quot; unlike the JVM default <code>java.util.HashMap</code>, which eventually thrashes on GC<sup class="footnote-ref"><a href="#fn5" id="fnref5:1">[5:1]</a></sup><sup class="footnote-ref"><a href="#fn6" id="fnref6:2">[6:2]</a></sup>. The tradeoff is that off-heap memory removes the GC safety net along with the GC overhead: there&#39;s no garbage collector cleaning up if something goes wrong<sup class="footnote-ref"><a href="#fn3" id="fnref3:14">[3:14]</a></sup>.</p><p>Memory overhead matters because off-heap memory and (if unset) PySpark memory are not automatically folded into the overhead calculation the way heap memory is. Enabling <code>spark.memory.offHeap.size</code> without also raising <code>spark.executor.memoryOverhead</code> (or explicitly setting <code>spark.executor.pyspark.memory</code>) can push the executor&#39;s real footprint past what the cluster manager granted, and the process gets killed with a vague container-memory error instead of a Spark-level exception<sup class="footnote-ref"><a href="#fn3" id="fnref3:15">[3:15]</a></sup>. Worked example: with <code>--executor-memory=8G</code>, the default 10% overhead gives <code>max(0.1 × 8192 MB, 384 MB) = 819 MB</code>, so the total memory requested from the cluster manager is <code>8192 + 819 = 9011 MB</code><sup class="footnote-ref"><a href="#fn3" id="fnref3:16">[3:16]</a></sup>, useful to keep in mind when <a href="./cluster-config.html">sizing containers or pods</a> against a cluster&#39;s available capacity.</p><h2 id="tuning-the-memory-pools" tabindex="-1">Tuning the memory pools <a class="header-anchor" href="#tuning-the-memory-pools" aria-label="Permalink to &quot;Tuning the memory pools&quot;">​</a></h2><p>Most of this is adjustable, within limits. Tune <code>spark.memory.fraction</code> and <code>spark.memory.storageFraction</code> only if your workload&#39;s execution/storage balance genuinely needs to shift away from the ~30/30 default. But don&#39;t try to reclaim the 300 MB reserved region; it&#39;s a fixed, non-tunable constant in production<sup class="footnote-ref"><a href="#fn3" id="fnref3:17">[3:17]</a></sup>.</p><p>If losing cached partitions to eviction is costly, prefer a disk-backed <code>StorageLevel</code> such as <code>MEMORY_AND_DISK</code> over <code>MEMORY_ONLY</code>: an evicted block gets written to disk and read back rather than triggering a full lineage recompute<sup class="footnote-ref"><a href="#fn9" id="fnref9:3">[9:3]</a></sup><sup class="footnote-ref"><a href="#fn7" id="fnref7:3">[7:3]</a></sup>. Keep in mind <code>.cache()</code> alone is not a residency guarantee even with this choice<sup class="footnote-ref"><a href="#fn7" id="fnref7:4">[7:4]</a></sup>.</p><p>Watch <code>memoryBytesSpilled</code> in the Spark UI or history server to catch execution-memory pressure early<sup class="footnote-ref"><a href="#fn11" id="fnref11:1">[11:1]</a></sup>. If sort or hash-aggregation spills are heavy, consider giving the executor more memory or reducing the number of concurrently running tasks per executor, since the <code>TaskMemoryManager</code>&#39;s per-task guarantee shrinks as task concurrency <code>n</code> grows<sup class="footnote-ref"><a href="#fn3" id="fnref3:18">[3:18]</a></sup>. For SQL joins and cartesian products, <code>spark.shuffle.spill.numElementsForceSpillThreshold</code> governs when <code>sortMergeJoinExec</code> and the cartesian-product operator spill their buffers<sup class="footnote-ref"><a href="#fn10" id="fnref10:1">[10:1]</a></sup>.</p><p>Set <code>spark.executor.memoryOverhead</code> explicitly rather than relying on the default, especially on Kubernetes for non-JVM workloads (where the default factor is already bumped to 0.40) or whenever off-heap memory or heavy PySpark usage is in play: those aren&#39;t automatically folded into the overhead calculation, so an unadjusted overhead can lead to an OOMKilled container instead of a clean Spark-level error<sup class="footnote-ref"><a href="#fn3" id="fnref3:19">[3:19]</a></sup><sup class="footnote-ref"><a href="#fn4" id="fnref4:7">[4:7]</a></sup>. Use <code>spark.executor.memoryOverhead</code>, not the removed <code>spark.yarn.executor.memoryOverhead</code><sup class="footnote-ref"><a href="#fn3" id="fnref3:20">[3:20]</a></sup>. For capacity planning, remember the total requested from the cluster manager is executor memory plus overhead, e.g., <code>8192 + 819 = 9011 MB</code> for an 8 GB executor at the default 10% factor<sup class="footnote-ref"><a href="#fn3" id="fnref3:21">[3:21]</a></sup>.</p><p>When enabling off-heap memory, always pair <code>spark.memory.offHeap.enabled=true</code> with an explicit positive <code>spark.memory.offHeap.size</code> (never leave it enabled at the default size of <code>0</code><sup class="footnote-ref"><a href="#fn4" id="fnref4:8">[4:8]</a></sup>) and manually reduce the JVM <code>-Xmx</code> to compensate, since enabling off-heap memory does not shrink the heap for you<sup class="footnote-ref"><a href="#fn4" id="fnref4:9">[4:9]</a></sup>.</p><blockquote><p><strong>PySpark:</strong> if you need PySpark&#39;s own memory bounded rather than folded silently into the overhead, set <code>spark.executor.pyspark.memory</code> explicitly, though its enforcement relies on Python&#39;s <code>resource</code> module and won&#39;t work on Windows and won&#39;t actually limit anything on macOS<sup class="footnote-ref"><a href="#fn4" id="fnref4:10">[4:10]</a></sup>.</p></blockquote><h2 id="sources" tabindex="-1">Sources <a class="header-anchor" href="#sources" aria-label="Permalink to &quot;Sources&quot;">​</a></h2><hr class="footnotes-sep"><section class="footnotes"><ol class="footnotes-list"><li id="fn1" class="footnote-item"><p><a href="https://raw.githubusercontent.com/spoddutur/spark-notes/master/task_memory_management_in_spark.md" target="_blank" rel="noreferrer">Task Memory Management in Spark</a> <a href="#fnref1" class="footnote-backref">↩︎</a> <a href="#fnref1:1" class="footnote-backref">↩︎</a> <a href="#fnref1:2" class="footnote-backref">↩︎</a> <a href="#fnref1:3" class="footnote-backref">↩︎</a></p></li><li id="fn2" class="footnote-item"><p><a href="https://spark.apache.org/docs/latest/tuning.html" target="_blank" rel="noreferrer">Tuning Spark</a> <a href="#fnref2" class="footnote-backref">↩︎</a> <a href="#fnref2:1" class="footnote-backref">↩︎</a> <a href="#fnref2:2" class="footnote-backref">↩︎</a> <a href="#fnref2:3" class="footnote-backref">↩︎</a></p></li><li id="fn3" class="footnote-item"><p><a href="https://luminousmen.com/post/dive-into-spark-memory" target="_blank" rel="noreferrer">Dive into Spark Memory</a> <a href="#fnref3" class="footnote-backref">↩︎</a> <a href="#fnref3:1" class="footnote-backref">↩︎</a> <a href="#fnref3:2" class="footnote-backref">↩︎</a> <a href="#fnref3:3" class="footnote-backref">↩︎</a> <a href="#fnref3:4" class="footnote-backref">↩︎</a> <a href="#fnref3:5" class="footnote-backref">↩︎</a> <a href="#fnref3:6" class="footnote-backref">↩︎</a> <a href="#fnref3:7" class="footnote-backref">↩︎</a> <a href="#fnref3:8" class="footnote-backref">↩︎</a> <a href="#fnref3:9" class="footnote-backref">↩︎</a> <a href="#fnref3:10" class="footnote-backref">↩︎</a> <a href="#fnref3:11" class="footnote-backref">↩︎</a> <a href="#fnref3:12" class="footnote-backref">↩︎</a> <a href="#fnref3:13" class="footnote-backref">↩︎</a> <a href="#fnref3:14" class="footnote-backref">↩︎</a> <a href="#fnref3:15" class="footnote-backref">↩︎</a> <a href="#fnref3:16" class="footnote-backref">↩︎</a> <a href="#fnref3:17" class="footnote-backref">↩︎</a> <a href="#fnref3:18" class="footnote-backref">↩︎</a> <a href="#fnref3:19" class="footnote-backref">↩︎</a> <a href="#fnref3:20" class="footnote-backref">↩︎</a> <a href="#fnref3:21" class="footnote-backref">↩︎</a></p></li><li id="fn4" class="footnote-item"><p><a href="https://spark.apache.org/docs/latest/configuration.html" target="_blank" rel="noreferrer">Configuration — Spark</a> <a href="#fnref4" class="footnote-backref">↩︎</a> <a href="#fnref4:1" class="footnote-backref">↩︎</a> <a href="#fnref4:2" class="footnote-backref">↩︎</a> <a href="#fnref4:3" class="footnote-backref">↩︎</a> <a href="#fnref4:4" class="footnote-backref">↩︎</a> <a href="#fnref4:5" class="footnote-backref">↩︎</a> <a href="#fnref4:6" class="footnote-backref">↩︎</a> <a href="#fnref4:7" class="footnote-backref">↩︎</a> <a href="#fnref4:8" class="footnote-backref">↩︎</a> <a href="#fnref4:9" class="footnote-backref">↩︎</a> <a href="#fnref4:10" class="footnote-backref">↩︎</a></p></li><li id="fn5" class="footnote-item"><p><a href="https://www.databricks.com/blog/2015/04/28/project-tungsten-bringing-spark-closer-to-bare-metal.html" target="_blank" rel="noreferrer">Project Tungsten: Bringing Spark Closer to Bare Metal</a> <a href="#fnref5" class="footnote-backref">↩︎</a> <a href="#fnref5:1" class="footnote-backref">↩︎</a></p></li><li id="fn6" class="footnote-item"><p><em>Learning Spark, 2nd Edition</em>, Damji, Wenig, Das, Lee, ch. 6–7 <a href="#fnref6" class="footnote-backref">↩︎</a> <a href="#fnref6:1" class="footnote-backref">↩︎</a> <a href="#fnref6:2" class="footnote-backref">↩︎</a></p></li><li id="fn7" class="footnote-item"><p><a href="https://luminousmen.com/post/explaining-the-mechanics-of-spark-caching" target="_blank" rel="noreferrer">Explaining the Mechanics of Spark Caching</a> <a href="#fnref7" class="footnote-backref">↩︎</a> <a href="#fnref7:1" class="footnote-backref">↩︎</a> <a href="#fnref7:2" class="footnote-backref">↩︎</a> <a href="#fnref7:3" class="footnote-backref">↩︎</a> <a href="#fnref7:4" class="footnote-backref">↩︎</a></p></li><li id="fn8" class="footnote-item"><p><a href="https://spark.apache.org/docs/latest/rdd-programming-guide.html" target="_blank" rel="noreferrer">RDD Programming Guide</a> <a href="#fnref8" class="footnote-backref">↩︎</a></p></li><li id="fn9" class="footnote-item"><p><em>High Performance Spark, 2nd Edition</em>, Karau, Polak &amp; Warren, ch. 7 <a href="#fnref9" class="footnote-backref">↩︎</a> <a href="#fnref9:1" class="footnote-backref">↩︎</a> <a href="#fnref9:2" class="footnote-backref">↩︎</a> <a href="#fnref9:3" class="footnote-backref">↩︎</a></p></li><li id="fn10" class="footnote-item"><p><a href="https://raw.githubusercontent.com/apache/spark/v3.5.0/sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala" target="_blank" rel="noreferrer">SQLConf.scala</a> <a href="#fnref10" class="footnote-backref">↩︎</a> <a href="#fnref10:1" class="footnote-backref">↩︎</a></p></li><li id="fn11" class="footnote-item"><p><a href="https://spark.apache.org/docs/latest/monitoring.html#spark-history-server" target="_blank" rel="noreferrer">Monitoring and Instrumentation</a> <a href="#fnref11" class="footnote-backref">↩︎</a> <a href="#fnref11:1" class="footnote-backref">↩︎</a></p></li></ol></section>',34)])])}const k=o(c,[["render",l]]);export{y as __pageData,k as default};
+import{_ as o,o as a,c as t,a5 as r}from"./chunks/framework.DSg0KOwT.js";const s="/docs/assets/memory-regions.XHvO7jHG.svg",n="/docs/assets/memory-regions.dark.D4TP9_08.svg",i="/docs/assets/memory-borrowing.BqQRJg0u.svg",f="/docs/assets/memory-borrowing.dark.Yhh20O9C.svg",y=JSON.parse('{"title":"Memory Management","description":"","frontmatter":{"title":"Memory Management"},"headers":[],"relativePath":"tuning-reference/memory-model.md","filePath":"tuning-reference/memory-model.md"}'),c={name:"tuning-reference/memory-model.md"};function l(h,e,d,p,u,m){return a(),t("div",null,[...e[0]||(e[0]=[r('<h1 id="memory-model" tabindex="-1">Memory Management <a class="header-anchor" href="#memory-model" aria-label="Permalink to &quot;Memory Management {#memory-model}&quot;">​</a></h1><h2 id="the-unified-memory-model" tabindex="-1">The unified memory model <a class="header-anchor" href="#the-unified-memory-model" aria-label="Permalink to &quot;The unified memory model&quot;">​</a></h2><p>Since Spark 1.6, the <code>UnifiedMemoryManager</code> has replaced the earlier static split between execution and storage memory with a single shared region, referred to as M<sup class="footnote-ref"><a href="#fn1" id="fnref1">[1]</a></sup><sup class="footnote-ref"><a href="#fn2" id="fnref2">[2]</a></sup>. M is carved out of the JVM heap after first setting aside 300 MiB of reserved system memory: <code>M = (JVM heap − 300 MiB) × spark.memory.fraction</code>, with <code>spark.memory.fraction</code> defaulting to 0.6<sup class="footnote-ref"><a href="#fn2" id="fnref2:1">[2:1]</a></sup><sup class="footnote-ref"><a href="#fn3" id="fnref3">[3]</a></sup>. Within M, <code>spark.memory.storageFraction</code> (default 0.5) marks off a subregion reserved for cached blocks that are immune to eviction; with defaults, this works out to roughly a 30%/30% on-heap split between execution and storage out of total executor memory<sup class="footnote-ref"><a href="#fn3" id="fnref3:1">[3:1]</a></sup>.</p><img class="light-only" src="'+s+'" alt="The executor memory layout showing reserved memory, the unified region split into execution and storage, and user memory inside the JVM heap, with the off-heap pool and memory overhead outside it."><img class="dark-only" src="'+n+'" alt="The executor memory layout showing reserved memory, the unified region split into execution and storage, and user memory inside the JVM heap, with the off-heap pool and memory overhead outside it."><p>Execution and storage borrow from each other dynamically rather than sitting behind a hard wall: when execution memory is unused, storage can acquire all of it, and vice versa<sup class="footnote-ref"><a href="#fn2" id="fnref2:2">[2:2]</a></sup><sup class="footnote-ref"><a href="#fn1" id="fnref1:1">[1:1]</a></sup>. The two are not equal peers, though. Execution always has priority, taking memory immediately and evicting cached storage blocks if necessary<sup class="footnote-ref"><a href="#fn3" id="fnref3:2">[3:2]</a></sup>.</p><p>The reserved 300 MB is a flat constant (<code>RESERVED_SYSTEM_MEMORY_BYTES</code> in the Spark source), not a formula, and it&#39;s hardcoded: there is no supported production configuration to change it. The only override is the internal <code>spark.testing.reservedMemory</code> property, which exists for Spark&#39;s own test suite rather than production tuning<sup class="footnote-ref"><a href="#fn3" id="fnref3:3">[3:3]</a></sup>. <code>spark.memory.fraction</code> is applied against heap minus that reserved 300 MB, not against total heap. The tuning guide is explicit that it &quot;expresses the size of M as a fraction of the (JVM heap space − 300MiB)&quot;<sup class="footnote-ref"><a href="#fn2" id="fnref2:3">[2:3]</a></sup>.</p><p>Off-heap memory extends the same model outside the JVM heap. When <code>spark.memory.offHeap.enabled=true</code>, Spark allocates raw off-heap buffers via <code>sun.misc.Unsafe</code> (routed through <code>jdk.internal.misc.Unsafe</code> on JDK 17+, which is why some builds need <code>--add-opens</code> flags), and that off-heap region is split into its own execution and storage pools, following the same borrowing rules as on-heap memory: execution has priority, storage gets evicted first<sup class="footnote-ref"><a href="#fn3" id="fnref3:4">[3:4]</a></sup>. Enabling it requires <code>spark.memory.offHeap.size</code> to be set to a positive value; leaving it enabled with the default size of <code>0</code> is a documented-invalid combination, not a supported way to run with off-heap &quot;on but empty&quot;<sup class="footnote-ref"><a href="#fn4" id="fnref4">[4]</a></sup>. The setting also &quot;has no impact on heap memory usage&quot;. Turning on off-heap memory does not shrink the JVM <code>-Xmx</code> for you, so the on-heap size has to be reduced manually to keep total footprint constant<sup class="footnote-ref"><a href="#fn4" id="fnref4:1">[4:1]</a></sup>. This off-heap execution memory underlies Project Tungsten: its compact binary row encoding, its explicit-memory-managed hash map for aggregations, and its cache-aware sort/join algorithms are all built to run against off-heap, GC-invisible memory<sup class="footnote-ref"><a href="#fn5" id="fnref5">[5]</a></sup><sup class="footnote-ref"><a href="#fn6" id="fnref6">[6]</a></sup>.</p><p>Executor memory overhead is a separate pool layered on top of M. <code>spark.executor.memoryOverhead</code> defaults to <code>executorMemory × spark.executor.memoryOverheadFactor</code>, floored at <code>spark.executor.minMemoryOverhead</code> (384 MiB)<sup class="footnote-ref"><a href="#fn4" id="fnref4:2">[4:2]</a></sup>. <code>spark.executor.memoryOverheadFactor</code> itself defaults to 0.10 for ordinary JVM executors, but Spark bumps that default to 0.40 specifically for Kubernetes non-JVM jobs, since those workloads tend to need more non-JVM heap space<sup class="footnote-ref"><a href="#fn4" id="fnref4:3">[4:3]</a></sup>. The legacy, YARN-only <code>spark.yarn.executor.memoryOverhead</code> property was removed in Spark 3.0 in favor of the cluster-manager-agnostic <code>spark.executor.memoryOverhead</code><sup class="footnote-ref"><a href="#fn3" id="fnref3:5">[3:5]</a></sup>.</p><blockquote><p><strong>PySpark:</strong> <code>spark.python.worker.memory</code> (default <code>512m</code>) is a soft spill threshold for a Python worker&#39;s own aggregation buffering, not a JVM-enforced cap. A PySpark worker runs as a separate OS process outside the JVM heap, so the JVM cannot police it directly<sup class="footnote-ref"><a href="#fn3" id="fnref3:6">[3:6]</a></sup>. The only setting that actually tries to bound PySpark memory per executor is <code>spark.executor.pyspark.memory</code>, and even that depends on Python&#39;s <code>resource</code> module, which isn&#39;t supported on Windows and doesn&#39;t actually limit anything on macOS<sup class="footnote-ref"><a href="#fn4" id="fnref4:4">[4:4]</a></sup>. Left unset, PySpark memory usage is folded into <code>spark.executor.memoryOverhead</code> by default<sup class="footnote-ref"><a href="#fn4" id="fnref4:5">[4:5]</a></sup>.</p></blockquote><h2 id="watching-eviction-and-spill" tabindex="-1">Watching eviction and spill <a class="header-anchor" href="#watching-eviction-and-spill" aria-label="Permalink to &quot;Watching eviction and spill&quot;">​</a></h2><p>That borrowing leaves a trace once eviction actually happens. Storage eviction under memory pressure follows an LRU (least recently used) policy<sup class="footnote-ref"><a href="#fn1" id="fnref1:2">[1:2]</a></sup><sup class="footnote-ref"><a href="#fn7" id="fnref7">[7]</a></sup>. The granularity is the block: the <code>BlockManager</code> tracks cached data as per-partition blocks (one block per RDD/DataFrame partition) and LRU operates at that level rather than evicting an entire RDD or cached table in one shot<sup class="footnote-ref"><a href="#fn8" id="fnref8">[8]</a></sup><sup class="footnote-ref"><a href="#fn9" id="fnref9">[9]</a></sup>. In practice this tends to evict the oldest partitions first, those materialized in the earliest job or stage, though lazy evaluation makes it hard to predict exactly which partitions will go ahead of time<sup class="footnote-ref"><a href="#fn9" id="fnref9:1">[9:1]</a></sup>.</p><p>What happens to an evicted block is visible in its downstream effect and depends on its <code>StorageLevel</code>. For <code>MEMORY_ONLY</code>, the block is simply dropped and recomputed from the RDD&#39;s lineage the next time it&#39;s needed. For a disk-backed level like <code>MEMORY_AND_DISK</code>, the evicted block is written to disk and read back from there instead of being recomputed<sup class="footnote-ref"><a href="#fn9" id="fnref9:2">[9:2]</a></sup><sup class="footnote-ref"><a href="#fn7" id="fnref7:1">[7:1]</a></sup>. Blocks can also be evicted well before you ever try to reuse them: <code>.cache()</code> does not guarantee a block stays resident, especially on busy clusters or long pipelines<sup class="footnote-ref"><a href="#fn7" id="fnref7:2">[7:2]</a></sup>.</p><p>On the execution side, each task gets its own <code>TaskMemoryManager</code>, which enforces a soft per-task cap: with <code>n</code> tasks running concurrently, each task is allowed to allocate somewhere between <code>1/(2n)</code> and <code>1/n</code> of total execution memory, and the first task to arrive on an idle executor typically grabs more than its later-arriving neighbors<sup class="footnote-ref"><a href="#fn3" id="fnref3:7">[3:7]</a></sup>.</p><p>When a sort or hash-aggregation operator keeps requesting execution-memory pages and can&#39;t get more, Spark doesn&#39;t fail immediately. It blocks the requesting task, spills that task&#39;s in-memory data structure to disk, or, in the worst case, throws an <code>OutOfMemoryError</code><sup class="footnote-ref"><a href="#fn3" id="fnref3:8">[3:8]</a></sup>. The spill path runs through Spark&#39;s map/shuffle I/O machinery: shuffle partitions created by wide transformations like <code>groupBy()</code> or <code>join()</code> <a href="./bottleneck-spill.html">spill</a> to the executors&#39; local disks at the location set by <code>spark.local.directory</code><sup class="footnote-ref"><a href="#fn6" id="fnref6:1">[6:1]</a></sup>. SQL physical operators apply the same idea with their own row-count guardrails: <code>sortMergeJoinExec</code>&#39;s in-memory buffer and the cartesian-product operator&#39;s buffer both spill once they cross a configured row threshold, which by default is set to the value of <code>spark.shuffle.spill.numElementsForceSpillThreshold</code><sup class="footnote-ref"><a href="#fn10" id="fnref10">[10]</a></sup>.</p><p>Whatever the trigger, the resulting spilled bytes are exposed on the task metrics as <code>memoryBytesSpilled</code>, visible in the Spark UI and event log. This is the concrete signal to watch for execution memory pressure<sup class="footnote-ref"><a href="#fn11" id="fnref11">[11]</a></sup>.</p><p>Memory-overhead misconfiguration shows up differently: it manifests as the container or pod being OOMKilled with a vague container-memory error rather than a Spark-level exception, since the enforcement happens at the YARN NodeManager or Kubernetes kubelet/cgroup layer, not inside the JVM<sup class="footnote-ref"><a href="#fn3" id="fnref3:9">[3:9]</a></sup>. Under the old default overhead factor of 0.10, non-JVM Kubernetes jobs commonly failed with &quot;Memory Overhead Exceeded&quot; errors, which is exactly why Spark bumped the Kubernetes non-JVM default to 0.40<sup class="footnote-ref"><a href="#fn4" id="fnref4:6">[4:6]</a></sup>.</p><h2 id="what-the-borrowing-costs-you" tabindex="-1">What the borrowing costs you <a class="header-anchor" href="#what-the-borrowing-costs-you" aria-label="Permalink to &quot;What the borrowing costs you&quot;">​</a></h2><p>None of this is free for whoever&#39;s counting on cached data staying put. Because execution always wins the tug-of-war over storage, <a href="./caching.html">caching</a> is never a guarantee; it&#39;s a best effort. As luminousmen-memory-management puts it: &quot;If Execution needs memory, it takes it. If Storage is using that space (cached RDDs, broadcasts), Spark starts evicting blocks. If Execution is idle, Storage can grow into that space, until Execution comes back.&quot;<sup class="footnote-ref"><a href="#fn3" id="fnref3:10">[3:10]</a></sup> That growth-then-shrink-back behavior is dynamic borrowing, not storage evicting execution; eviction is strictly one-directional. As spark-notes-task-memory-management summarizes the agreement between the two regions: &quot;keep acquiring execution memory and evict storage as you need more execution memory&quot;<sup class="footnote-ref"><a href="#fn1" id="fnref1:3">[1:3]</a></sup>, never the reverse. The same asymmetric rule carries over when off-heap memory is enabled: execution still has priority and storage still gets evicted first<sup class="footnote-ref"><a href="#fn3" id="fnref3:11">[3:11]</a></sup>. Practically, this means a cached DataFrame can silently lose blocks under memory pressure, forcing an expensive lineage recompute (for <code>MEMORY_ONLY</code>) or an extra disk round-trip (for <code>MEMORY_AND_DISK</code>) the next time it&#39;s touched.</p><img class="light-only" src="'+i+'" alt="How storage memory borrows idle execution space while execution reclaims its own space by evicting storage in one direction."><img class="dark-only" src="'+f+'" alt="How storage memory borrows idle execution space while execution reclaims its own space by evicting storage in one direction."><p>The <code>TaskMemoryManager</code>&#39;s soft per-task cap explains why spill behavior is workload-shape-dependent rather than a fixed threshold: with more tasks packed onto an executor, each one&#39;s guaranteed share of execution memory shrinks toward <code>1/(2n)</code>, making spills more likely under high task concurrency even when total execution memory hasn&#39;t changed<sup class="footnote-ref"><a href="#fn3" id="fnref3:12">[3:12]</a></sup>.</p><p>Off-heap memory&#39;s payoff is specifically about <a href="./bottleneck-gc.html">garbage collection</a>: because off-heap buffers sit outside the JVM heap, they are invisible to the garbage collector, so fewer and smaller live objects need to be tracked, scanned, and copied, which reduces both the frequency and duration of GC pauses<sup class="footnote-ref"><a href="#fn3" id="fnref3:13">[3:13]</a></sup>. Project Tungsten&#39;s off-heap hash map for aggregations was benchmarked at over 1 million operations per second in a single thread, with &quot;almost no performance degradation as memory utilization increases,&quot; unlike the JVM default <code>java.util.HashMap</code>, which eventually thrashes on GC<sup class="footnote-ref"><a href="#fn5" id="fnref5:1">[5:1]</a></sup><sup class="footnote-ref"><a href="#fn6" id="fnref6:2">[6:2]</a></sup>. The tradeoff is that off-heap memory removes the GC safety net along with the GC overhead: there&#39;s no garbage collector cleaning up if something goes wrong<sup class="footnote-ref"><a href="#fn3" id="fnref3:14">[3:14]</a></sup>.</p><p>Memory overhead matters because off-heap memory and (if unset) PySpark memory are not automatically folded into the overhead calculation the way heap memory is. Enabling <code>spark.memory.offHeap.size</code> without also raising <code>spark.executor.memoryOverhead</code> (or explicitly setting <code>spark.executor.pyspark.memory</code>) can push the executor&#39;s real footprint past what the cluster manager granted, and the process gets killed with a vague container-memory error instead of a Spark-level exception<sup class="footnote-ref"><a href="#fn3" id="fnref3:15">[3:15]</a></sup>. Worked example: with <code>--executor-memory=8G</code>, the default 10% overhead gives <code>max(0.1 × 8192 MB, 384 MB) = 819 MB</code>, so the total memory requested from the cluster manager is <code>8192 + 819 = 9011 MB</code><sup class="footnote-ref"><a href="#fn3" id="fnref3:16">[3:16]</a></sup>, useful to keep in mind when <a href="./cluster-config.html">sizing containers or pods</a> against a cluster&#39;s available capacity.</p><h2 id="tuning-the-memory-pools" tabindex="-1">Tuning the memory pools <a class="header-anchor" href="#tuning-the-memory-pools" aria-label="Permalink to &quot;Tuning the memory pools&quot;">​</a></h2><p>Most of this is adjustable, within limits. Tune <code>spark.memory.fraction</code> and <code>spark.memory.storageFraction</code> only if your workload&#39;s execution/storage balance genuinely needs to shift away from the ~30/30 default. But don&#39;t try to reclaim the 300 MB reserved region; it&#39;s a fixed, non-tunable constant in production<sup class="footnote-ref"><a href="#fn3" id="fnref3:17">[3:17]</a></sup>.</p><p>If losing cached partitions to eviction is costly, prefer a disk-backed <code>StorageLevel</code> such as <code>MEMORY_AND_DISK</code> over <code>MEMORY_ONLY</code>: an evicted block gets written to disk and read back rather than triggering a full lineage recompute<sup class="footnote-ref"><a href="#fn9" id="fnref9:3">[9:3]</a></sup><sup class="footnote-ref"><a href="#fn7" id="fnref7:3">[7:3]</a></sup>. Keep in mind <code>.cache()</code> alone is not a residency guarantee even with this choice<sup class="footnote-ref"><a href="#fn7" id="fnref7:4">[7:4]</a></sup>.</p><p>Watch <code>memoryBytesSpilled</code> in the Spark UI or history server to catch execution-memory pressure early<sup class="footnote-ref"><a href="#fn11" id="fnref11:1">[11:1]</a></sup>. If sort or hash-aggregation spills are heavy, consider giving the executor more memory or reducing the number of concurrently running tasks per executor, since the <code>TaskMemoryManager</code>&#39;s per-task guarantee shrinks as task concurrency <code>n</code> grows<sup class="footnote-ref"><a href="#fn3" id="fnref3:18">[3:18]</a></sup>. For SQL joins and cartesian products, <code>spark.shuffle.spill.numElementsForceSpillThreshold</code> governs when <code>sortMergeJoinExec</code> and the cartesian-product operator spill their buffers<sup class="footnote-ref"><a href="#fn10" id="fnref10:1">[10:1]</a></sup>.</p><p>Set <code>spark.executor.memoryOverhead</code> explicitly rather than relying on the default, especially on Kubernetes for non-JVM workloads (where the default factor is already bumped to 0.40) or whenever off-heap memory or heavy PySpark usage is in play: those aren&#39;t automatically folded into the overhead calculation, so an unadjusted overhead can lead to an OOMKilled container instead of a clean Spark-level error<sup class="footnote-ref"><a href="#fn3" id="fnref3:19">[3:19]</a></sup><sup class="footnote-ref"><a href="#fn4" id="fnref4:7">[4:7]</a></sup>. Use <code>spark.executor.memoryOverhead</code>, not the removed <code>spark.yarn.executor.memoryOverhead</code><sup class="footnote-ref"><a href="#fn3" id="fnref3:20">[3:20]</a></sup>. For capacity planning, remember the total requested from the cluster manager is executor memory plus overhead, e.g., <code>8192 + 819 = 9011 MB</code> for an 8 GB executor at the default 10% factor<sup class="footnote-ref"><a href="#fn3" id="fnref3:21">[3:21]</a></sup>.</p><p>When enabling off-heap memory, always pair <code>spark.memory.offHeap.enabled=true</code> with an explicit positive <code>spark.memory.offHeap.size</code> (never leave it enabled at the default size of <code>0</code><sup class="footnote-ref"><a href="#fn4" id="fnref4:8">[4:8]</a></sup>) and manually reduce the JVM <code>-Xmx</code> to compensate, since enabling off-heap memory does not shrink the heap for you<sup class="footnote-ref"><a href="#fn4" id="fnref4:9">[4:9]</a></sup>.</p><blockquote><p><strong>PySpark:</strong> if you need PySpark&#39;s own memory bounded rather than folded silently into the overhead, set <code>spark.executor.pyspark.memory</code> explicitly, though its enforcement relies on Python&#39;s <code>resource</code> module and won&#39;t work on Windows and won&#39;t actually limit anything on macOS<sup class="footnote-ref"><a href="#fn4" id="fnref4:10">[4:10]</a></sup>.</p></blockquote><h2 id="bottleneck-cache-utilization" tabindex="-1">Cache utilization <a class="header-anchor" href="#bottleneck-cache-utilization" aria-label="Permalink to &quot;Cache utilization {#bottleneck-cache-utilization}&quot;">​</a></h2><p><span class="tag">CSTOR</span></p><p>Spark&#39;s event log carries no block-access or hit-rate events, so cache utilization is read from periodic per-RDD storage snapshots instead: how much of a persisted RDD is actually resident where it was asked to be.</p><h3 id="how-it-s-detected" tabindex="-1">How it&#39;s detected <a class="header-anchor" href="#how-it-s-detected" aria-label="Permalink to &quot;How it&#39;s detected&quot;">​</a></h3><p>A persisted RDD, one whose storage level requests memory and/or disk with at least one partition actually cached, is evaluated on two independent measures and can register on both at once:</p><table tabindex="0"><thead><tr><th>Signal</th><th>Info</th><th>Warning</th></tr></thead><tbody><tr><td>Cached ratio (cached partitions ÷ total partitions)</td><td>&lt; 90%</td><td>&lt; 50%</td></tr><tr><td>Disk ratio (disk bytes ÷ (memory bytes + disk bytes)), <code>MEMORY_AND_DISK*</code> levels only</td><td>&gt; 15%</td><td>&gt; 40%</td></tr></tbody></table><p>Both ratios come from a point-in-time storage snapshot taken at stage-submission events, not a runtime block-access count, so confirm against the Spark UI&#39;s Storage tab before acting. Confidence scales with the RDD&#39;s partition count: below 10 partitions the ratio is noisy enough to call low confidence, at 50 or more it&#39;s high.</p><h3 id="why-it-matters" tabindex="-1">Why it matters <a class="header-anchor" href="#why-it-matters" aria-label="Permalink to &quot;Why it matters&quot;">​</a></h3><p>A partially cached RDD still pays the recomputation cost for its evicted share on every later read, undercutting the reason it was cached in the first place. Disk spillover under a <code>MEMORY_AND_DISK*</code> level keeps that data around instead of forcing a recompute, but a disk read is still far slower than serving it out of memory.</p><h3 id="how-to-fix-it" tabindex="-1">How to fix it <a class="header-anchor" href="#how-to-fix-it" aria-label="Permalink to &quot;How to fix it&quot;">​</a></h3><ul><li>Increase executor memory, or reduce the size of the dataset being cached, so more of it fits in the storage region without eviction.</li><li>If the RDD is only cached for the occasional narrow scan, weigh whether persisting it at all is worth the partial-cache overhead, versus recomputing the slice you actually need.</li></ul><h2 id="sources" tabindex="-1">Sources <a class="header-anchor" href="#sources" aria-label="Permalink to &quot;Sources&quot;">​</a></h2><hr class="footnotes-sep"><section class="footnotes"><ol class="footnotes-list"><li id="fn1" class="footnote-item"><p><a href="https://raw.githubusercontent.com/spoddutur/spark-notes/master/task_memory_management_in_spark.md" target="_blank" rel="noreferrer">Task Memory Management in Spark</a> <a href="#fnref1" class="footnote-backref">↩︎</a> <a href="#fnref1:1" class="footnote-backref">↩︎</a> <a href="#fnref1:2" class="footnote-backref">↩︎</a> <a href="#fnref1:3" class="footnote-backref">↩︎</a></p></li><li id="fn2" class="footnote-item"><p><a href="https://spark.apache.org/docs/latest/tuning.html" target="_blank" rel="noreferrer">Tuning Spark</a> <a href="#fnref2" class="footnote-backref">↩︎</a> <a href="#fnref2:1" class="footnote-backref">↩︎</a> <a href="#fnref2:2" class="footnote-backref">↩︎</a> <a href="#fnref2:3" class="footnote-backref">↩︎</a></p></li><li id="fn3" class="footnote-item"><p><a href="https://luminousmen.com/post/dive-into-spark-memory" target="_blank" rel="noreferrer">Dive into Spark Memory</a> <a href="#fnref3" class="footnote-backref">↩︎</a> <a href="#fnref3:1" class="footnote-backref">↩︎</a> <a href="#fnref3:2" class="footnote-backref">↩︎</a> <a href="#fnref3:3" class="footnote-backref">↩︎</a> <a href="#fnref3:4" class="footnote-backref">↩︎</a> <a href="#fnref3:5" class="footnote-backref">↩︎</a> <a href="#fnref3:6" class="footnote-backref">↩︎</a> <a href="#fnref3:7" class="footnote-backref">↩︎</a> <a href="#fnref3:8" class="footnote-backref">↩︎</a> <a href="#fnref3:9" class="footnote-backref">↩︎</a> <a href="#fnref3:10" class="footnote-backref">↩︎</a> <a href="#fnref3:11" class="footnote-backref">↩︎</a> <a href="#fnref3:12" class="footnote-backref">↩︎</a> <a href="#fnref3:13" class="footnote-backref">↩︎</a> <a href="#fnref3:14" class="footnote-backref">↩︎</a> <a href="#fnref3:15" class="footnote-backref">↩︎</a> <a href="#fnref3:16" class="footnote-backref">↩︎</a> <a href="#fnref3:17" class="footnote-backref">↩︎</a> <a href="#fnref3:18" class="footnote-backref">↩︎</a> <a href="#fnref3:19" class="footnote-backref">↩︎</a> <a href="#fnref3:20" class="footnote-backref">↩︎</a> <a href="#fnref3:21" class="footnote-backref">↩︎</a></p></li><li id="fn4" class="footnote-item"><p><a href="https://spark.apache.org/docs/latest/configuration.html" target="_blank" rel="noreferrer">Configuration — Spark</a> <a href="#fnref4" class="footnote-backref">↩︎</a> <a href="#fnref4:1" class="footnote-backref">↩︎</a> <a href="#fnref4:2" class="footnote-backref">↩︎</a> <a href="#fnref4:3" class="footnote-backref">↩︎</a> <a href="#fnref4:4" class="footnote-backref">↩︎</a> <a href="#fnref4:5" class="footnote-backref">↩︎</a> <a href="#fnref4:6" class="footnote-backref">↩︎</a> <a href="#fnref4:7" class="footnote-backref">↩︎</a> <a href="#fnref4:8" class="footnote-backref">↩︎</a> <a href="#fnref4:9" class="footnote-backref">↩︎</a> <a href="#fnref4:10" class="footnote-backref">↩︎</a></p></li><li id="fn5" class="footnote-item"><p><a href="https://www.databricks.com/blog/2015/04/28/project-tungsten-bringing-spark-closer-to-bare-metal.html" target="_blank" rel="noreferrer">Project Tungsten: Bringing Spark Closer to Bare Metal</a> <a href="#fnref5" class="footnote-backref">↩︎</a> <a href="#fnref5:1" class="footnote-backref">↩︎</a></p></li><li id="fn6" class="footnote-item"><p><em>Learning Spark, 2nd Edition</em>, Damji, Wenig, Das, Lee, ch. 6–7 <a href="#fnref6" class="footnote-backref">↩︎</a> <a href="#fnref6:1" class="footnote-backref">↩︎</a> <a href="#fnref6:2" class="footnote-backref">↩︎</a></p></li><li id="fn7" class="footnote-item"><p><a href="https://luminousmen.com/post/explaining-the-mechanics-of-spark-caching" target="_blank" rel="noreferrer">Explaining the Mechanics of Spark Caching</a> <a href="#fnref7" class="footnote-backref">↩︎</a> <a href="#fnref7:1" class="footnote-backref">↩︎</a> <a href="#fnref7:2" class="footnote-backref">↩︎</a> <a href="#fnref7:3" class="footnote-backref">↩︎</a> <a href="#fnref7:4" class="footnote-backref">↩︎</a></p></li><li id="fn8" class="footnote-item"><p><a href="https://spark.apache.org/docs/latest/rdd-programming-guide.html" target="_blank" rel="noreferrer">RDD Programming Guide</a> <a href="#fnref8" class="footnote-backref">↩︎</a></p></li><li id="fn9" class="footnote-item"><p><em>High Performance Spark, 2nd Edition</em>, Karau, Polak &amp; Warren, ch. 7 <a href="#fnref9" class="footnote-backref">↩︎</a> <a href="#fnref9:1" class="footnote-backref">↩︎</a> <a href="#fnref9:2" class="footnote-backref">↩︎</a> <a href="#fnref9:3" class="footnote-backref">↩︎</a></p></li><li id="fn10" class="footnote-item"><p><a href="https://raw.githubusercontent.com/apache/spark/v3.5.0/sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala" target="_blank" rel="noreferrer">SQLConf.scala</a> <a href="#fnref10" class="footnote-backref">↩︎</a> <a href="#fnref10:1" class="footnote-backref">↩︎</a></p></li><li id="fn11" class="footnote-item"><p><a href="https://spark.apache.org/docs/latest/monitoring.html#spark-history-server" target="_blank" rel="noreferrer">Monitoring and Instrumentation</a> <a href="#fnref11" class="footnote-backref">↩︎</a> <a href="#fnref11:1" class="footnote-backref">↩︎</a></p></li></ol></section>',45)])])}const k=o(c,[["render",l]]);export{y as __pageData,k as default};

package/public/docs/assets/{tuning-reference_memory-model.md.DhT-n4y3.lean.js → tuning-reference_memory-model.md.CWhvgevP.lean.js}

@@ -1 +1 @@
-import{_ as o,o as a,c as r,a5 as t}from"./chunks/framework.DSg0KOwT.js";const s="/docs/assets/memory-regions.XHvO7jHG.svg",n="/docs/assets/memory-regions.dark.D4TP9_08.svg",f="/docs/assets/memory-borrowing.BqQRJg0u.svg",i="/docs/assets/memory-borrowing.dark.Yhh20O9C.svg",y=JSON.parse('{"title":"Memory Management","description":"","frontmatter":{"title":"Memory Management"},"headers":[],"relativePath":"tuning-reference/memory-model.md","filePath":"tuning-reference/memory-model.md"}'),c={name:"tuning-reference/memory-model.md"};function l(h,e,d,p,u,m){return a(),r("div",null,[...e[0]||(e[0]=[t("",34)])])}const k=o(c,[["render",l]]);export{y as __pageData,k as default};
+import{_ as o,o as a,c as t,a5 as r}from"./chunks/framework.DSg0KOwT.js";const s="/docs/assets/memory-regions.XHvO7jHG.svg",n="/docs/assets/memory-regions.dark.D4TP9_08.svg",i="/docs/assets/memory-borrowing.BqQRJg0u.svg",f="/docs/assets/memory-borrowing.dark.Yhh20O9C.svg",y=JSON.parse('{"title":"Memory Management","description":"","frontmatter":{"title":"Memory Management"},"headers":[],"relativePath":"tuning-reference/memory-model.md","filePath":"tuning-reference/memory-model.md"}'),c={name:"tuning-reference/memory-model.md"};function l(h,e,d,p,u,m){return a(),t("div",null,[...e[0]||(e[0]=[r("",45)])])}const k=o(c,[["render",l]]);export{y as __pageData,k as default};

package/public/docs/assets/{user-guide_mcp-tools.md.Vi3RoflJ.js → user-guide_mcp-tools.md.DGvolGzt.js}

@@ -103,7 +103,7 @@ import{_ as i,o as a,c as e,a5 as n}from"./chunks/framework.DSg0KOwT.js";const E
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">    &quot;title&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;Task skew&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">    &quot;content&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;# Task skew</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">\\n\\n</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">...&quot;</span></span>
 <span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">  }</span></span>
-<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">}</span></span></code></pre></div><p><code>tuningDoc</code> is <code>null</code> when the finding type has no vendored tuning-doc page. This isn&#39;t exhaustive, but two examples: <code>configAudit</code> (its four audited properties each have their own anchor rather than one shared page, so no single anchor resolves) and <code>incompleteRun</code> (no upstream tuning page covers this signal at all).</p><h2 id="get-reference-doc" tabindex="-1"><code>get_reference_doc</code> <a class="header-anchor" href="#get-reference-doc" aria-label="Permalink to &quot;\`get_reference_doc\`&quot;">​</a></h2><p>Full tuning-reference chapter or bottleneck markdown for one doc anchor (e.g. <code>&quot;#joins&quot;</code>, <code>&quot;#bottleneck-skew&quot;</code>, <code>&quot;#metric-task-duration&quot;</code>), independent of any run, so a client without browser access can read the same reference material the dashboard links to.</p><p>Parameters:</p><ul><li><code>anchor</code>: <code>string</code> (required): a doc anchor, with or without the leading <code>#</code></li></ul><p>Example call:</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">{ </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;name&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;get_reference_doc&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;arguments&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: { </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;anchor&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;#bottleneck-skew&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> } }</span></span></code></pre></div><p>Example response:</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">{</span></span>
+<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">}</span></span></code></pre></div><p><code>tuningDoc</code> is <code>null</code> when the finding type has no vendored tuning-doc page. This isn&#39;t exhaustive, but two examples: <code>configAudit</code> (its four audited properties each have their own anchor rather than one shared page, so no single anchor resolves) and <code>incompleteRun</code> (no upstream tuning page covers this signal at all). A type whose section lives on a general chapter rather than a bottleneck page (<code>autoscalingChurn</code> on Cluster Tuning, <code>cacheUtilization</code> on Memory Management) returns that whole chapter, with <code>anchor</code> naming the section.</p><h2 id="get-reference-doc" tabindex="-1"><code>get_reference_doc</code> <a class="header-anchor" href="#get-reference-doc" aria-label="Permalink to &quot;\`get_reference_doc\`&quot;">​</a></h2><p>Full tuning-reference chapter or bottleneck markdown for one doc anchor (e.g. <code>&quot;#joins&quot;</code>, <code>&quot;#bottleneck-skew&quot;</code>, <code>&quot;#metric-task-duration&quot;</code>), independent of any run, so a client without browser access can read the same reference material the dashboard links to.</p><p>Parameters:</p><ul><li><code>anchor</code>: <code>string</code> (required): a doc anchor, with or without the leading <code>#</code></li></ul><p>Example call:</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">{ </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;name&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;get_reference_doc&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">, </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;arguments&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: { </span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">&quot;anchor&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;#bottleneck-skew&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> } }</span></span></code></pre></div><p>Example response:</p><div class="language-json vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">json</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">{</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;anchor&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;bottleneck-skew&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;title&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;Task skew&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">,</span></span>
 <span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">  &quot;content&quot;</span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">: </span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">&quot;# Task skew</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF;">\\n\\n</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF;">...&quot;</span></span>

package/public/docs/assets/user-guide_understanding-findings.md.B29f0ucS.js

@@ -0,0 +1 @@
+import{_ as a,o as t,c as o,a5 as r}from"./chunks/framework.DSg0KOwT.js";const p=JSON.parse('{"title":"Understanding findings","description":"","frontmatter":{},"headers":[],"relativePath":"user-guide/understanding-findings.md","filePath":"user-guide/understanding-findings.md"}'),s={name:"user-guide/understanding-findings.md"};function i(n,e,l,d,c,h){return t(),o("div",null,[...e[0]||(e[0]=[r('<h1 id="understanding-findings" tabindex="-1">Understanding findings <a class="header-anchor" href="#understanding-findings" aria-label="Permalink to &quot;Understanding findings&quot;">​</a></h1><p>Every flagged problem carries a short ALL-CAPS tag. This page has one entry per tag: what it means, and what to do about it.</p><p>Turn on <a href="./getting-started.html#advanced-view">Advanced view</a> in the dashboard to see, per finding, the confidence level and a link to the same background reading collected here, opened in an in-app &quot;Reference&quot; panel next to the board. A few tags share that reading with another tag, because the underlying Spark-tuning material overlaps: <code>SFAIL</code> with <code>FAIL</code>, <code>PART</code> with <code>SHFL</code>, <code>SPEC</code> with <code>STRAG</code>, and <code>CACHE</code>/<code>LOCAL</code> with <code>UTIL</code>.</p><h2 id="per-stage" tabindex="-1">Per-stage <a class="header-anchor" href="#per-stage" aria-label="Permalink to &quot;Per-stage&quot;">​</a></h2><h3 id="skew" tabindex="-1"><code>SKEW</code>: Task skew <a class="header-anchor" href="#skew" aria-label="Permalink to &quot;`SKEW`: Task skew {#skew}&quot;">​</a></h3><p>A small number of tasks take much longer than their peers in the same stage. For join-driven skew, enable AQE skew-join handling (<code>spark.sql.adaptive.skewJoin.enabled</code>); otherwise salt the key or repartition on a better key.</p><h3 id="shfl" tabindex="-1"><code>SHFL</code>: Shuffle I/O <a class="header-anchor" href="#shfl" aria-label="Permalink to &quot;`SHFL`: Shuffle I/O {#shfl}&quot;">​</a></h3><p>Tasks move a large amount of intermediate data between stages. Raise <code>spark.sql.shuffle.partitions</code>, or add a broadcast join. Only flagged on stages that take at least 0.5% of the run.</p><h3 id="spill" tabindex="-1"><code>SPILL</code>: Memory and disk spill <a class="header-anchor" href="#spill" aria-label="Permalink to &quot;`SPILL`: Memory and disk spill {#spill}&quot;">​</a></h3><p>Tasks are writing data out of memory, which slows execution. Two spill patterns get flagged differently: skew spill, where a few heavy tasks spill while most don&#39;t (rebalance partitioning), and volume spill, where most tasks spill because the data genuinely exceeds available memory (add partitions). Only flagged on stages that take at least 0.5% of the run.</p><h3 id="gc" tabindex="-1"><code>GC</code>: Garbage collection pressure <a class="header-anchor" href="#gc" aria-label="Permalink to &quot;`GC`: Garbage collection pressure {#gc}&quot;">​</a></h3><p>Tasks spend an unusually large share of time reclaiming memory. Reduce object creation: use primitive types, avoid UDFs, or raise executor memory. A stage with very little GC gets an informational note that executor memory may be over-provisioned, only on stages that take at least 0.5% of the run.</p><h3 id="fail" tabindex="-1"><code>FAIL</code>: Failed tasks <a class="header-anchor" href="#fail" aria-label="Permalink to &quot;`FAIL`: Failed tasks {#fail}&quot;">​</a></h3><p>Tasks fail often enough to affect the stage. Failed tasks point to executor instability or data-driven errors: check driver logs for the dominant failure reason.</p><h3 id="sfail" tabindex="-1"><code>SFAIL</code>: Failed stage <a class="header-anchor" href="#sfail" aria-label="Permalink to &quot;`SFAIL`: Failed stage {#sfail}&quot;">​</a></h3><p>A stage attempt failed outright rather than losing individual tasks within it. Inspect the driver log for the failure reason and the job that triggered it.</p><h3 id="strag" tabindex="-1"><code>STRAG</code>: Straggler tasks <a class="header-anchor" href="#strag" aria-label="Permalink to &quot;`STRAG`: Straggler tasks {#strag}&quot;">​</a></h3><p>A few tasks run much slower than the rest of their stage. Rule out a GC pause or a slow shuffle fetch before assuming a hardware issue; if a skewed key is the real cause, that&#39;s a candidate for AQE&#39;s skew-join handling. Only flagged on stages that take at least 0.5% of the run.</p><h3 id="spec" tabindex="-1"><code>SPEC</code>: Speculation waste <a class="header-anchor" href="#spec" aria-label="Permalink to &quot;`SPEC`: Speculation waste {#spec}&quot;">​</a></h3><p>Speculative task attempts used a lot of executor time without confirming a genuine straggler. Self-flags a confidence that scales with how far the wasted time sits past the threshold: these thresholds are still a design spike, not yet validated against real-world runs. If task durations are just naturally variable rather than genuine stragglers, tune <code>spark.speculation.multiplier</code>/<code>spark.speculation.quantile</code>.</p><h3 id="retry" tabindex="-1"><code>RETRY</code>: Retry waste <a class="header-anchor" href="#retry" aria-label="Permalink to &quot;`RETRY`: Retry waste {#retry}&quot;">​</a></h3><p>Repeated task attempts ate into execution time even though the stage completed. Investigate executor loss or fetch failures.</p><h3 id="tiny" tabindex="-1"><code>TINY</code>: Tiny tasks <a class="header-anchor" href="#tiny" aria-label="Permalink to &quot;`TINY`: Tiny tasks {#tiny}&quot;">​</a></h3><p>Many very short tasks add scheduling overhead out of proportion to the work each one does. Repartition to fewer, larger tasks. Only flagged on stages that take at least 0.5% of the run.</p><h3 id="part" tabindex="-1"><code>PART</code>: Partition sizing <a class="header-anchor" href="#part" aria-label="Permalink to &quot;`PART`: Partition sizing {#part}&quot;">​</a></h3><p>Shuffle partitions are too large, too uneven, or too few for the work. A single shuffle partition over 5 GB, for example, will OOM or spill heavily: repartition to break it up before the stage runs.</p><h3 id="slow" tabindex="-1"><code>SLOW</code>: Stage slowness <a class="header-anchor" href="#slow" aria-label="Permalink to &quot;`SLOW`: Stage slowness {#slow}&quot;">​</a></h3><p>A stage ran long overall without a more specific cause getting flagged. Often a partition-count problem: raise parallelism via <code>spark.sql.shuffle.partitions</code> or <code>spark.default.parallelism</code>, or check for a large per-task data volume driving heavy shuffle and spill.</p><h3 id="shape" tabindex="-1"><code>SHAPE</code>: Stage shape <a class="header-anchor" href="#shape" aria-label="Permalink to &quot;`SHAPE`: Stage shape {#shape}&quot;">​</a></h3><p>The stage has an inefficient task count, output shape, or task-to-stage balance: for example, one straggler task taking a large fraction of the stage&#39;s wall-clock time. A too-low task count is only flagged on stages that take at least 0.5% of the run.</p><h3 id="host" tabindex="-1"><code>HOST</code>: Slow host <a class="header-anchor" href="#host" aria-label="Permalink to &quot;`HOST`: Slow host {#host}&quot;">​</a></h3><p>One executor is much slower than its peers. It may just hold data locality for its tasks or carry one heavy stage, rather than a hardware fault. Enable <code>spark.speculation</code> to relaunch a lagging task automatically. Only flagged on stages that take at least 0.5% of the run.</p><h2 id="app-level" tabindex="-1">App-level <a class="header-anchor" href="#app-level" aria-label="Permalink to &quot;App-level&quot;">​</a></h2><h3 id="cold" tabindex="-1"><code>COLD</code>: Executor cold start <a class="header-anchor" href="#cold" aria-label="Permalink to &quot;`COLD`: Executor cold start {#cold}&quot;">​</a></h3><p>New executors take time to become available for work. Pre-warm the cluster, or use dynamic allocation.</p><h3 id="util" tabindex="-1"><code>UTIL</code>: Low utilization <a class="header-anchor" href="#util" aria-label="Permalink to &quot;`UTIL`: Low utilization {#util}&quot;">​</a></h3><p>Allocated executors sit idle for a large share of the application run. Consider a smaller cluster, or enable dynamic allocation.</p><h3 id="mem" tabindex="-1"><code>MEM</code>: Memory utilization <a class="header-anchor" href="#mem" aria-label="Permalink to &quot;`MEM`: Memory utilization {#mem}&quot;">​</a></h3><p>Executor memory or core capacity may be over- or under-provisioned. Some detail here needs <code>spark.eventLog.logStageExecutorMetrics=true</code> on the run being analyzed; without it, per-executor memory usage can&#39;t be broken down. Review <code>spark.executor.memory</code> and executor count if allocated memory sat largely idle over the run. That idle-memory variant self-flags a confidence that scales with how far the estimated waste sits past a 1.5x buffer: it estimates waste from allocated-versus-used memory-time. Check it against the Spark UI before resizing anything.</p><h3 id="cache" tabindex="-1"><code>CACHE</code>: Caching opportunity <a class="header-anchor" href="#cache" aria-label="Permalink to &quot;`CACHE`: Caching opportunity {#cache}&quot;">​</a></h3><p>A reusable dataset (re-read via the same SQL relation more than once) may be worth persisting between stages. Self-flags a confidence that scales with how many executions reuse the same relation: reuse is only inferred, from plan-scan identity across SQL executions, so confirm the reads really do hit the same data before you cache anything.</p><h3 id="cstor" tabindex="-1"><code>CSTOR</code>: Cache storage <a class="header-anchor" href="#cstor" aria-label="Permalink to &quot;`CSTOR`: Cache storage {#cstor}&quot;">​</a></h3><p>A persisted dataset is not fully cached in memory, or is spilling to disk. Raise executor memory, or shrink the cached dataset.</p><h3 id="local" tabindex="-1"><code>LOCAL</code>: Core usage locality <a class="header-anchor" href="#local" aria-label="Permalink to &quot;`LOCAL`: Core usage locality {#local}&quot;">​</a></h3><p>Tasks run without process- or node-local data placement more often than expected. Check <code>spark.locality.wait</code> settings and executor/data colocation. Self-flags a confidence that scales with the non-local ratio and sample size: the thresholds are our own noise floor for this metric.</p><h3 id="chrn" tabindex="-1"><code>CHRN</code>: Autoscaling churn <a class="header-anchor" href="#chrn" aria-label="Permalink to &quot;`CHRN`: Autoscaling churn {#chrn}&quot;">​</a></h3><p>Executors are stood up and torn down again before they can do useful work: re-provisioning churn rather than normal scale-down. Raise <code>spark.dynamicAllocation.executorIdleTimeout</code>, or widen the <code>minExecutors</code>/<code>maxExecutors</code> bounds to reduce flapping. Self-flags a confidence that scales with how far the short-lived-executor share sits past the threshold: these thresholds are still a design spike, not yet validated against real-world runs.</p><h3 id="jobs" tabindex="-1"><code>JOBS</code>: Job failure rate <a class="header-anchor" href="#jobs" aria-label="Permalink to &quot;`JOBS`: Job failure rate {#jobs}&quot;">​</a></h3><p>A large share of completed jobs did not succeed. Inspect the driver log for the failed job(s) and the stage failures that triggered them.</p><h3 id="incmp" tabindex="-1"><code>INCMP</code>: Incomplete run <a class="header-anchor" href="#incmp" aria-label="Permalink to &quot;`INCMP`: Incomplete run {#incmp}&quot;">​</a></h3><p>This event log never recorded an <code>ApplicationEnd</code> event: capture stopped before the run finished (an in-flight job, a rotated-away log, or a cut-short capture). Every other finding and metric on the board reflects only what was captured up to that point, not the full run.</p><h2 id="configuration-scope" tabindex="-1">Configuration scope <a class="header-anchor" href="#configuration-scope" aria-label="Permalink to &quot;Configuration scope&quot;">​</a></h2><h3 id="cfg" tabindex="-1"><code>CFG</code>: Configuration audit <a class="header-anchor" href="#cfg" aria-label="Permalink to &quot;`CFG`: Configuration audit {#cfg}&quot;">​</a></h3><p>Flags configuration settings that may cause reliability or efficiency problems, independent of any one stage&#39;s behavior. Four properties are audited today:</p><ul><li><code>spark.shuffle.service.enabled</code>: flagged when dynamic allocation is on but the external shuffle service is off, since shuffle data won&#39;t survive executor removal.</li><li><code>spark.dynamicAllocation.maxExecutors</code>: flagged for inverted bounds or a missing upper bound.</li><li><code>spark.serializer</code>: flagged when still on the default Java serializer; <code>org.apache.spark.serializer.KryoSerializer</code> is faster and produces smaller buffers.</li><li><code>spark.executor.memoryOverhead</code>: flagged when set below a safe floor.</li></ul><h2 id="sql-scope" tabindex="-1">SQL scope <a class="header-anchor" href="#sql-scope" aria-label="Permalink to &quot;SQL scope&quot;">​</a></h2><h3 id="plan" tabindex="-1"><code>PLAN</code>: Plan advisor <a class="header-anchor" href="#plan" aria-label="Permalink to &quot;`PLAN`: Plan advisor {#plan}&quot;">​</a></h3><p>Flags patterns in the SQL execution plan worth reviewing. Four checks share this tag:</p><ul><li>Duplicate plan subtree: the same subtree recomputed more than once in the plan. When the repeats have the same shape but different filters, columns or tables, the finding stays informational and claims no time. Only flagged when the repeat&#39;s stages take at least 0.5% of the run.</li><li>Small files: reading an excessive number of small files.</li><li>Under-broadcast: the smaller side of a Sort Merge Join looks well under the broadcast threshold; consider a <code>broadcast()</code> hint or raising <code>spark.sql.autoBroadcastJoinThreshold</code>.</li><li>Over-broadcast: a broadcast exceeds the 1 GB threshold; check for a misapplied broadcast hint or a misconfigured <code>spark.sql.autoBroadcastJoinThreshold</code>.</li></ul>',59)])])}const f=a(s,[["render",i]]);export{p as __pageData,f as default};

package/public/docs/assets/{user-guide_understanding-findings.md.DL1UDhvR.lean.js → user-guide_understanding-findings.md.B29f0ucS.lean.js}

@@ -1 +1 @@
-import{_ as a,o as t,c as o,a5 as r}from"./chunks/framework.DSg0KOwT.js";const p=JSON.parse('{"title":"Understanding findings","description":"","frontmatter":{},"headers":[],"relativePath":"user-guide/understanding-findings.md","filePath":"user-guide/understanding-findings.md"}'),i={name:"user-guide/understanding-findings.md"};function s(n,e,l,d,c,h){return t(),o("div",null,[...e[0]||(e[0]=[r("",59)])])}const f=a(i,[["render",s]]);export{p as __pageData,f as default};
+import{_ as a,o as t,c as o,a5 as r}from"./chunks/framework.DSg0KOwT.js";const p=JSON.parse('{"title":"Understanding findings","description":"","frontmatter":{},"headers":[],"relativePath":"user-guide/understanding-findings.md","filePath":"user-guide/understanding-findings.md"}'),s={name:"user-guide/understanding-findings.md"};function i(n,e,l,d,c,h){return t(),o("div",null,[...e[0]||(e[0]=[r("",59)])])}const f=a(s,[["render",i]]);export{p as __pageData,f as default};