[kudu] branch branch-1.9.x updated: [docs] Add maximum tablet size recommendations

[gr...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

granthenke pushed a commit to branch branch-1.9.x
in repository https://gitbox.apache.org/repos/asf/kudu.git


The following commit(s) were added to refs/heads/branch-1.9.x by this push:
     new fdee746  [docs] Add maximum tablet size recommendations
fdee746 is described below

commit fdee7464fdb5a54151f4a925739966ccfdaf2a64
Author: Grant Henke <gr...@apache.org>
AuthorDate: Tue Apr 9 17:43:34 2019 -0700

    [docs] Add maximum tablet size recommendations
    
    Based primarily on the collective experience of many of
    the Kudu committers, this patch attempts to provide
    some guardrail limits and recomendations on tablet
    size. It doesn’t enumurate all of the issues that occur
    with very large tablets, primarily because they are
    not all known, but gives some examples of issues
    that have been seen as tablets go over the proposed
    limit of 50 GiB.
    
    I also updated existing usage of GB/TB to GiB/TiB.
    
    Change-Id: I9fe48e483334812795d124ee63a3af92f39135de
    Reviewed-on: http://gerrit.cloudera.org:8080/12979
    Tested-by: Grant Henke <gr...@apache.org>
    Reviewed-by: Mike Percy <mp...@apache.org>
    Reviewed-by: Adar Dembo <ad...@cloudera.com>
    (cherry picked from commit db71eeb25d70253d968da27bcae92fcf2a067abe)
    Reviewed-on: http://gerrit.cloudera.org:8080/13115
    Tested-by: Kudu Jenkins
    Reviewed-by: Alexey Serbin <as...@cloudera.com>
---
 docs/known_issues.adoc | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/docs/known_issues.adoc b/docs/known_issues.adoc
index eaa5159..c6f5543 100644
--- a/docs/known_issues.adoc
+++ b/docs/known_issues.adoc
@@ -118,8 +118,8 @@
 
 == Server management
 
-* Production deployments should configure a least 4GB of memory for tablet servers,
-  and ideally more than 16GB when approaching the data and tablet <<Scale>> limits.
+* Production deployments should configure a least 4 GiB of memory for tablet servers,
+  and ideally more than 16 GiB when approaching the data and tablet <<Scale>> limits.
 
 * Write ahead logs (WAL) can only be stored on one disk.
 
@@ -140,7 +140,7 @@
 * Recommended maximum number of masters is 3.
 
 * Recommended maximum amount of stored data, post-replication and post-compression,
-  per tablet server is 8TB.
+  per tablet server is 8 TiB.
 
 * The maximum number of tablets per tablet server is 2000, post-replication,
   but we recommend 1000 tablets or fewer per tablet server.
@@ -148,6 +148,10 @@
 * Maximum number of tablets per table for each tablet server is 60,
   post-replication (assuming the default replication factor of 3), at table-creation time.
 
+* Recommended maximum amount of data per tablet is 50 GiB. Going beyond this can cause
+  issues such a reduced performance, compaction issues, and slow tablet startup times.
+  The recommended target size for tablets is under 10 GiB.
+
 * When enabled, location awareness in its current implementation doesn't scale
   with the number of clients connecting to a Kudu cluster simultaneously.
   If the rate of new clients connecting is kept high (e.g., 100 request/second)