common/options/global.yaml.in: increase default value of bluestore_cache_trim_max_ski...

This option controls the rate of trimming of onodes and the earlier default of
64 has been seen to be too low for large clusters, leading to buildup of
onodes resulting in memory growth.

Increase the default value to 1000, since there are no known downsides to it.

Fixes: https://tracker.ceph.com/issues/50217
Signed-off-by: Neha Ojha <nojha@redhat.com>
(cherry picked from commit 26d7336d6b65f987298ede5d2c5c435191f1405c)

 Conflicts:
	src/common/options/global.yaml.in - file does not exist in pacific

diff --git a/src/common/options.cc b/src/common/options.cc
index 2c1ad531f96d159705509e0c935d6395ddc41a51..d19d27ee54054db8ac68d7f91c693da01662fb9c 100644 (file)
--- a/src/common/options.cc
+++ b/src/common/options.cc
@@ -4527,7 +4527,7 @@ std::vector<Option> get_global_options() {
     .set_description("How frequently we trim the bluestore cache"),
 
     Option("bluestore_cache_trim_max_skip_pinned", Option::TYPE_UINT, Option::LEVEL_DEV)
-    .set_default(64)
+    .set_default(1000)
     .set_description("Max pinned cache entries we consider before giving up"),
 
     Option("bluestore_cache_type", Option::TYPE_STR, Option::LEVEL_DEV)