[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20180118031332.32225-9-jakub.kicinski@netronome.com>
Date: Wed, 17 Jan 2018 19:13:32 -0800
From: Jakub Kicinski <jakub.kicinski@...ronome.com>
To: daniel@...earbox.net, alexei.starovoitov@...il.com
Cc: netdev@...r.kernel.org, oss-drivers@...ronome.com, tehnerd@...com,
Jakub Kicinski <jakub.kicinski@...ronome.com>
Subject: [PATCH bpf-next 8/8] nfp: bpf: add short busy wait for FW replies
Scheduling out and in for every FW message can slow us down
unnecessarily. Our experiments show that even under heavy load
the FW responds to 99.9% messages within 200 us. Add a short
busy wait before entering the wait queue.
Signed-off-by: Jakub Kicinski <jakub.kicinski@...ronome.com>
---
drivers/net/ethernet/netronome/nfp/bpf/cmsg.c | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
index 71e6586acc36..80d3aa0fc9d3 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
@@ -157,7 +157,14 @@ nfp_bpf_cmsg_wait_reply(struct nfp_app_bpf *bpf, enum nfp_bpf_cmsg_type type,
int tag)
{
struct sk_buff *skb;
- int err;
+ int i, err;
+
+ for (i = 0; i < 50; i++) {
+ udelay(4);
+ skb = nfp_bpf_reply(bpf, tag);
+ if (skb)
+ return skb;
+ }
err = wait_event_interruptible_timeout(bpf->cmsg_wq,
skb = nfp_bpf_reply(bpf, tag),
--
2.15.1
Powered by blists - more mailing lists