From: Eric Dumazet Date: Thu, 6 Nov 2025 20:29:35 +0000 (+0000) Subject: net: increase skb_defer_max default to 128 X-Git-Tag: v6.19-rc1~170^2~205^2 X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=b61785852ed0;p=thirdparty%2Fkernel%2Flinux.git net: increase skb_defer_max default to 128 skb_defer_max value is very conservative, and can be increased to avoid too many calls to kick_defer_list_purge(). Signed-off-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Reviewed-by: Toke Høiland-Jørgensen Reviewed-by: Jason Xing Link: https://patch.msgid.link/20251106202935.1776179-4-edumazet@google.com Signed-off-by: Jakub Kicinski --- diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst index 991773dcb9cfe..369a738a68193 100644 --- a/Documentation/admin-guide/sysctl/net.rst +++ b/Documentation/admin-guide/sysctl/net.rst @@ -355,9 +355,9 @@ skb_defer_max ------------- Max size (in skbs) of the per-cpu list of skbs being freed -by the cpu which allocated them. Used by TCP stack so far. +by the cpu which allocated them. -Default: 64 +Default: 128 optmem_max ---------- diff --git a/net/core/hotdata.c b/net/core/hotdata.c index 95d0a4df10069..dddd5c287cf08 100644 --- a/net/core/hotdata.c +++ b/net/core/hotdata.c @@ -20,7 +20,7 @@ struct net_hotdata net_hotdata __cacheline_aligned = { .dev_tx_weight = 64, .dev_rx_weight = 64, .sysctl_max_skb_frags = MAX_SKB_FRAGS, - .sysctl_skb_defer_max = 64, + .sysctl_skb_defer_max = 128, .sysctl_mem_pcpu_rsv = SK_MEMORY_PCPU_RESERVE }; EXPORT_SYMBOL(net_hotdata);