HBASE-15255 Add pointer to linkedin blog on putting jvm logs on fast disk
Project: http://git-wip-us.apache.org/repos/asf/hbase/repo Commit: http://git-wip-us.apache.org/repos/asf/hbase/commit/ab50c7c8 Tree: http://git-wip-us.apache.org/repos/asf/hbase/tree/ab50c7c8 Diff: http://git-wip-us.apache.org/repos/asf/hbase/diff/ab50c7c8 Branch: refs/heads/hbase-12439 Commit: ab50c7c8c64aa00da14167b01a9e599098afe4bc Parents: 25dfc11 Author: stack <[email protected]> Authored: Thu Feb 11 13:18:28 2016 -0800 Committer: stack <[email protected]> Committed: Thu Feb 11 13:18:28 2016 -0800 ---------------------------------------------------------------------- src/main/asciidoc/_chapters/performance.adoc | 8 ++++++++ 1 file changed, 8 insertions(+) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/hbase/blob/ab50c7c8/src/main/asciidoc/_chapters/performance.adoc ---------------------------------------------------------------------- diff --git a/src/main/asciidoc/_chapters/performance.adoc b/src/main/asciidoc/_chapters/performance.adoc index 5155f0a..ee7933c 100644 --- a/src/main/asciidoc/_chapters/performance.adoc +++ b/src/main/asciidoc/_chapters/performance.adoc @@ -48,6 +48,11 @@ Use a 64-bit platform (and 64-bit JVM). Watch out for swapping. Set `swappiness` to 0. +[[perf.os.cpu]] +=== CPU +Make sure you have set up your Hadoop to use native, hardware checksumming. +See link:[hadoop.native.lib]. + [[perf.network]] == Network @@ -137,6 +142,9 @@ It describes configurations to lower the amount of young GC during write-heavy l If you do not have HBASE-8163 installed, and you are trying to improve your young GC times, one trick to consider -- courtesy of our Liang Xie -- is to set the GC config `-XX:PretenureSizeThreshold` in _hbase-env.sh_ to be just smaller than the size of `hbase.hregion.memstore.mslab.chunksize` so MSLAB allocations happen in the tenured space directly rather than first in the young gen. You'd do this because these MSLAB allocations are going to likely make it to the old gen anyways and rather than pay the price of a copies between s0 and s1 in eden space followed by the copy up from young to old gen after the MSLABs have achieved sufficient tenure, save a bit of YGC churn and allocate in the old gen directly. +Other sources of long GCs can be the JVM itself logging. +See link:https://engineering.linkedin.com/blog/2016/02/eliminating-large-jvm-gc-pauses-caused-by-background-io-traffic[Eliminating Large JVM GC Pauses Caused by Background IO Traffic] + For more information about GC logs, see <<trouble.log.gc>>. Consider also enabling the off-heap Block Cache.
