You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@kudu.apache.org by gr...@apache.org on 2019/04/12 21:51:13 UTC

[kudu] 04/04: [docs] Adjust latency and bandwidth limitations

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

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

commit 55d2faed94077ced16b736ca5e499022b0aa4789
Author: Grant Henke <gr...@apache.org>
AuthorDate: Tue Apr 9 13:43:37 2019 -0700

    [docs] Adjust latency and bandwidth limitations
    
    Adjusts the documentation for latency and bandwidth
    limitations to be a bit more conservative. Additionally,
    removes any reference to DC/AZ deployments given
    we are primarily concerned about latency and bandwidth
    as the concrete limitations.
    
    Change-Id: I42fe8a65779c3f5ad366403366e534fa28713a76
    Reviewed-on: http://gerrit.cloudera.org:8080/12970
    Reviewed-by: Will Berkeley <wd...@gmail.com>
    Tested-by: Grant Henke <gr...@apache.org>
    Reviewed-by: Alexey Serbin <as...@cloudera.com>
    Reviewed-by: Mike Percy <mp...@apache.org>
---
 docs/known_issues.adoc | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/docs/known_issues.adoc b/docs/known_issues.adoc
index bfd8709..0c3e9ac 100644
--- a/docs/known_issues.adoc
+++ b/docs/known_issues.adoc
@@ -106,11 +106,13 @@
 
 * Rolling restart is not supported.
 
-* Multi-data-center/multi-availability-zone configurations require at least 3
-  locations to maintain availability.
+* Recommended maximum point-to-point latency within a Kudu cluster is 20 milliseconds.
 
-* Multi-data-center/multi-availability-zone configurations with a network latency
-  over 100ms and bandwidth under 10 Gbps are not well tested and therefore not recommended.
+* Recommended minimum point-to-point bandwidth within a Kudu cluster is 10 Gbps.
+
+* If you intend to use the location awareness feature to place tablet servers in
+  different locations, it is recommended to measure the bandwidth and latency between servers
+  to ensure they fit within the above guidelines.
 
 == Server management