From 9d8f841f329d81cac1929af07c55c043a5b55268 Mon Sep 17 00:00:00 2001
From: Jim Harris <james.r.harris@intel.com>
Date: Tue, 26 Apr 2022 19:51:40 +0000
Subject: [PATCH] llvm_nvme_fuzz: unaffinitize fuzzing thread

We do not want the fuzzing thread to compete with
one of the nvmf target cores - otherwise they will
keep preempting each other and drastically reducing
the operation rate.

This sped up the operation rate approximately 20x
in my test VM.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I75d8c59d75e49cafaf7ee94f4796f9184b690647
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12403
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Dong Yi <dongx.yi@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
---
 test/app/fuzz/llvm_nvme_fuzz/llvm_nvme_fuzz.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/test/app/fuzz/llvm_nvme_fuzz/llvm_nvme_fuzz.c b/test/app/fuzz/llvm_nvme_fuzz/llvm_nvme_fuzz.c
index 550364ea7..336d3e79f 100644
--- a/test/app/fuzz/llvm_nvme_fuzz/llvm_nvme_fuzz.c
+++ b/test/app/fuzz/llvm_nvme_fuzz/llvm_nvme_fuzz.c
@@ -606,6 +606,7 @@ start_fuzzer(void *ctx)
 	int argc = SPDK_COUNTOF(_argv);
 	uint32_t len;
 
+	spdk_unaffinitize_thread();
 	len = MAX_COMMANDS * g_fuzzer->bytes_per_cmd;
 	snprintf(len_str, sizeof(len_str), "-max_len=%d", len);
 	argv[argc - 3] = len_str;