Thread (13 messages) 13 messages, 3 authors, 2023-05-30

Re: [PATCH v2 4/4] sock: Remove redundant cond of memcg pressure

From: Simon Horman <hidden>
Date: 2023-05-22 12:55:09
Also in: lkml

On Mon, May 22, 2023 at 03:01:22PM +0800, Abel Wu wrote:
Now with the preivous patch, __sk_mem_raise_allocated() considers
nit: s/preivous/previous/
quoted hunk ↗ jump to hunk
the memory pressure of both global and the socket's memcg on a func-
wide level, making the condition of memcg's pressure in question
redundant.

Signed-off-by: Abel Wu <redacted>
---
 net/core/sock.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/net/core/sock.c b/net/core/sock.c
index 7641d64293af..baccbb58a11a 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3029,9 +3029,14 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind)
 	if (sk_has_memory_pressure(sk)) {
 		u64 alloc;
 
-		if (!sk_under_memory_pressure(sk))
+		if (!sk_under_global_memory_pressure(sk))
 			return 1;
 		alloc = sk_sockets_allocated_read_positive(sk);
+		/*
+		 * If under global pressure, allow the sockets that are below
+		 * average memory usage to raise, trying to be fair among all
+		 * the sockets under global constrains.
+		 */
nit:
		/* Multi-line comments in networking code
		 * look like this.
		 */
 		if (sk_prot_mem_limits(sk, 2) > alloc *
 		    sk_mem_pages(sk->sk_wmem_queued +
 				 atomic_read(&sk->sk_rmem_alloc) +
-- 
2.37.3
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help