[Devel] [PATCH VZ9] fs/fuse kio: do not set RPC affinity from a workequeue worker

[Liu Kui]

A RPC's affinity shouldn't be set from a workqueue worker, otherwise
the RPC could be stuck to one cpu forever. When multiple rpcs are stuck
to the same cpu overall performance degrades significantly.

Fixes: #VSTOR-109481
https://virtuozzo.atlassian.net/browse/VSTOR-109481

Signed-off-by: Liu Kui <kui.liu at virtuozzo.com>
---
 fs/fuse/kio/pcs/pcs_rpc.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/fuse/kio/pcs/pcs_rpc.c b/fs/fuse/kio/pcs/pcs_rpc.c
index f15d0c3fb7cd..ca9c3ac5b1cc 100644
--- a/fs/fuse/kio/pcs/pcs_rpc.c
+++ b/fs/fuse/kio/pcs/pcs_rpc.c
@@ -858,6 +858,10 @@ static void pcs_rpc_cpu_select(struct pcs_rpc *ep)
 
 static void pcs_rpc_affinity(struct pcs_rpc *ep, bool was_idle)
 {
+	/* Do not set rpc affinity from a workequeue worker */
+	if (current->flags & PF_WQ_WORKER)
+		return;
+
 	switch(rpc_affinity_mode) {
 		case RPC_AFFINITY_NONE:
 			if (unlikely(ep->cpu != WORK_CPU_UNBOUND)) {
-- 
2.39.5 (Apple Git-154)