From 9d12fa5e6dad5492491f4718ba7c593077d984a6 Mon Sep 17 00:00:00 2001 From: Josh Durgin Date: Tue, 10 Oct 2017 19:54:31 -0400 Subject: [PATCH] common/options: enable multiple rocksdb compaction threads for filestore One of the major benefits of rocksdb over leveldb is multithreaded compaction. The default of 1 thread does not provide much benefit, and is insufficient for heavy rgw workloads. For high-write and delete omap workloads I've seen up to 8 compaction threads be used. There's little overhead to having a higher max than are needed, so set the default to 8. Signed-off-by: Josh Durgin (cherry picked from commit 023fa810aa6b3af305e9027e3f717e54d1bb2712) Conflicts: src/common/options.cc (trivial) --- src/common/options.cc | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/common/options.cc b/src/common/options.cc index de6dc10974a23..b0e9cc8a92d2f 100644 --- a/src/common/options.cc +++ b/src/common/options.cc @@ -3650,7 +3650,7 @@ std::vector