[nvm_cache] set --nvm_cache_allocation_retry_count to 0
As it turned out, the logic of retrying NVM-based allocations in
NvmLRUCache::AllocateAndRetry() didn't serve the intended purpose.
The actual memory was deallocated only after all the retries, and
the code effectively was attempting to allocate memory again and
again on nothing-yet-freed-cache.
As a stop-gap solution, this patch sets the default value for the
--nvm_cache_allocation_retry_count flag to 0. The matter will be
properly addressed in a separate changelist.
Change-Id: If33d1a7ffdb7389a02c1b86f2f4b3b9dc362b5d9
Reviewed-on: http://gerrit.cloudera.org:8080/14497
Reviewed-by: Adar Dembo <adar@cloudera.com>
Tested-by: Kudu Jenkins
diff --git a/src/kudu/util/nvm_cache.cc b/src/kudu/util/nvm_cache.cc
index 320048b..66424e3 100644
--- a/src/kudu/util/nvm_cache.cc
+++ b/src/kudu/util/nvm_cache.cc
@@ -60,7 +60,7 @@
"The path at which the NVM cache will try to allocate its memory. "
"This can be a tmpfs or ramfs for testing purposes.");
-DEFINE_int32(nvm_cache_allocation_retry_count, 10,
+DEFINE_int32(nvm_cache_allocation_retry_count, 0,
"The number of times that the NVM cache will retry attempts to allocate "
"memory for new entries. In between attempts, a cache entry will be "
"evicted.");
