This is an automated email from the ASF dual-hosted git repository.
gian pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/druid.git
The following commit(s) were added to refs/heads/master by this push:
new 2c8e4d2e33e Update basic-cluster-tuning.md to no longer suggest 24GiB
heap cap. (#17892)
2c8e4d2e33e is described below
commit 2c8e4d2e33e0b2ebeb7e6fef2b51d3b1906c6e2a
Author: Gian Merlino <[email protected]>
AuthorDate: Fri Apr 11 11:07:33 2025 -0700
Update basic-cluster-tuning.md to no longer suggest 24GiB heap cap. (#17892)
* Update basic-cluster-tuning.md to no longer suggest 24GiB heap cap.
These days, large-heap-capable garbage collectors exist, so there is
no need to constrain heap sizes based on GC concerns.
* Add ZGC to dictionary.
---
docs/operations/basic-cluster-tuning.md | 7 +++----
website/.spelling | 1 +
2 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/docs/operations/basic-cluster-tuning.md
b/docs/operations/basic-cluster-tuning.md
index 32db4863e66..4cbd9c964a7 100644
--- a/docs/operations/basic-cluster-tuning.md
+++ b/docs/operations/basic-cluster-tuning.md
@@ -40,11 +40,10 @@ The biggest contributions to heap usage on Historicals are:
- Partial unmerged query results from segments
- The stored maps for [lookups](../querying/lookups.md).
-A general rule-of-thumb for sizing the Historical heap is `(0.5GiB * number of
CPU cores)`, with an upper limit of ~24GiB.
+A general rule-of-thumb for sizing the Historical heap is `(0.5GiB * number of
CPU cores)`.
-This rule-of-thumb scales using the number of CPU cores as a convenient proxy
for hardware size and level of concurrency (note: this formula is not a hard
rule for sizing Historical heaps).
-
-Having a heap that is too large can result in excessively long GC collection
pauses, the ~24GiB upper limit is imposed to avoid this.
+This is a starting point, not a hard rule for sizing Historical heaps.
+Note that with certain garbage collectors, having a large heap can result in
excessively long GC pauses. For heaps larger than about 24GiB, we recommend
using a collector that can handle large heaps, such as Shenandoah or ZGC.
If caching is enabled on Historicals, the cache is stored on heap, sized by
`druid.cache.sizeInBytes`.
diff --git a/website/.spelling b/website/.spelling
index 2c84ee43b9c..39de8156d95 100644
--- a/website/.spelling
+++ b/website/.spelling
@@ -2414,6 +2414,7 @@ ddSketch
DDSketch
druid-ddsketch
numBins
+ZGC
- ../docs/development/extensions-contrib/spectator-histogram.md
SpectatorHistogram
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
