[
https://issues.apache.org/jira/browse/DRILL-5716?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16151210#comment-16151210
]
ASF GitHub Bot commented on DRILL-5716:
---------------------------------------
Github user paul-rogers commented on a diff in the pull request:
https://github.com/apache/drill/pull/928#discussion_r136665398
--- Diff:
exec/java-exec/src/main/java/org/apache/drill/exec/ExecConstants.java ---
@@ -373,13 +373,26 @@
String AVERAGE_FIELD_WIDTH_KEY = "planner.memory.average_field_width";
OptionValidator AVERAGE_FIELD_WIDTH = new
PositiveLongValidator(AVERAGE_FIELD_WIDTH_KEY, Long.MAX_VALUE);
+ // Resource management boot-time options.
+
+ String MAX_MEMORY_PER_NODE = "drill.exec.rm.memory_per_node";
+ String MAX_CPUS_PER_NODE = "drill.exec.rm.cpus_per_node";
+
+ // Resource management system run-time options.
+
+ // Enables queues. When running embedded, enables an in-process queue.
When
+ // running distributed, enables the Zookeeper-based distributed queue.
+
BooleanValidator ENABLE_QUEUE = new
BooleanValidator("exec.queue.enable");
LongValidator LARGE_QUEUE_SIZE = new
PositiveLongValidator("exec.queue.large", 1000);
LongValidator SMALL_QUEUE_SIZE = new
PositiveLongValidator("exec.queue.small", 100000);
- LongValidator QUEUE_THRESHOLD_SIZE = new
PositiveLongValidator("exec.queue.threshold",
- Long.MAX_VALUE);
- LongValidator QUEUE_TIMEOUT = new
PositiveLongValidator("exec.queue.timeout_millis",
- Long.MAX_VALUE);
+ LongValidator QUEUE_THRESHOLD_SIZE = new
PositiveLongValidator("exec.queue.threshold", Long.MAX_VALUE);
+ LongValidator QUEUE_TIMEOUT = new
PositiveLongValidator("exec.queue.timeout_millis", Long.MAX_VALUE);
+
+ // Ratio of memory for small queries vs. large queries.
+ // Each small query gets 1 unit, each large query gets
QUEUE_MEMORY_RATIO units.
+
+ DoubleValidator QUEUE_MEMORY_RATIO = new
RangeDoubleValidator("exec.queue.memory_ratio", 0.001, 1000);
--- End diff --
Sure, makes sense.
> Queue-based memory assignment for buffering operators
> -----------------------------------------------------
>
> Key: DRILL-5716
> URL: https://issues.apache.org/jira/browse/DRILL-5716
> Project: Apache Drill
> Issue Type: Improvement
> Affects Versions: 1.12.0
> Reporter: Paul Rogers
> Assignee: Paul Rogers
>
> Apache Drill already has a queueing feature based on ZK semaphores. We did a
> bit of testing to show that the feature does, in fact work. We propose to
> enhance the feature with some light revisions to make work with the "managed"
> external sort and the newly-added spilling feature for the hash agg operator.
> The key requirement is to build on what we have for now; we may want to
> tackle a larger project to create a more complete solution later.
> Existing functionality:
> * Two ZK-based queues called the “small” and “large” query queues.
> * A threshold, call it T, given as a query cost, to determine the queue into
> which a query will go.
> * Admit levels for the two queues: call them Qs and Ql.
> Basically, when a query comes in:
> * Plan the query as usual.
> * Obtain the final query cost from the planner, call this C.
> * If C<T, the query goes into the small queue, else it goes into the large
> queue.
> * Suppose the small queue. Ask ZK if the query can run.
> * ZK checks if Qs queries are already running. If so, the query waits, else
> the query runs.
> The proposed changes include:
> * Refactor the code to provide a queueing API that supports a variety of
> queuing mechanisms.
> * Provide three: the null queue (default), an in-process queue (for testing)
> and the ZK queues.
> * Modify the query profile web UI to show two new bits of information about
> queues:
> - The queue to which the query was sent.
> - The total planning cost.
> * Modify the query profile web UI to show two memory assignment numbers:
> - Total memory allocated to the query
> - Memory per sort or hash-add operator
> Then, add to the queue mechanism the ability to do memory assignment:
> * Provide a weight, W: every small query gets 1 unit, every large query gets
> W units.
> * Use the queue admit levels to determine total units: U = Qs + W * Ql.
> * Obtain total direct memory from the system. M.
> * Subtract a reserve percent R for overhead.
> * Do the math to get the memory per query for each query:
> * For the small queue: (M - R) / U
> * For the large queue: (M - R) / U * W
> * Use this memory amount as the “memory per query” number in the existing
> sort/hash-agg memory assignment (instead of the fixed 2 GB.)
> The result will be a nice incremental addition to what we already have, and
> should make it a bit easier people to actually use the feature (because they
> can see the planning numbers and see the queues used, allowing them to
> effectively tune the system.)
> The API used for the above features also allow third parties to add on a more
> robust admission control feature as needed, perhaps tying into an existing
> queueing mechanism of their choice.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
