* [PATCH] inetpeer: use div64_ul() and clamp_val() calculate inet_peer_threshold
@ 2021-03-01 6:05 Yejune Deng
2021-03-01 21:40 ` patchwork-bot+netdevbpf
0 siblings, 1 reply; 2+ messages in thread
From: Yejune Deng @ 2021-03-01 6:05 UTC (permalink / raw)
To: davem, yoshfuji, dsahern, kuba, eric.dumazet
Cc: netdev, linux-kernel, yejune.deng
In inet_initpeers(), struct inet_peer on IA32 uses 128 bytes in nowdays.
Get rid of the cascade and use div64_ul() and clamp_val() calculate that
will not need to be adjusted in the future as suggested by Eric Dumazet.
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Yejune Deng <yejune.deng@gmail.com>
---
net/ipv4/inetpeer.c | 21 +++++++--------------
1 file changed, 7 insertions(+), 14 deletions(-)
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index ff327a62c9ce..da21dfce24d7 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -65,7 +65,7 @@ EXPORT_SYMBOL_GPL(inet_peer_base_init);
#define PEER_MAX_GC 32
/* Exported for sysctl_net_ipv4. */
-int inet_peer_threshold __read_mostly = 65536 + 128; /* start to throw entries more
+int inet_peer_threshold __read_mostly; /* start to throw entries more
* aggressively at this stage */
int inet_peer_minttl __read_mostly = 120 * HZ; /* TTL under high load: 120 sec */
int inet_peer_maxttl __read_mostly = 10 * 60 * HZ; /* usual time to live: 10 min */
@@ -73,20 +73,13 @@ int inet_peer_maxttl __read_mostly = 10 * 60 * HZ; /* usual time to live: 10 min
/* Called from ip_output.c:ip_init */
void __init inet_initpeers(void)
{
- struct sysinfo si;
+ u64 nr_entries;
- /* Use the straight interface to information about memory. */
- si_meminfo(&si);
- /* The values below were suggested by Alexey Kuznetsov
- * <kuznet@ms2.inr.ac.ru>. I don't have any opinion about the values
- * myself. --SAW
- */
- if (si.totalram <= (32768*1024)/PAGE_SIZE)
- inet_peer_threshold >>= 1; /* max pool size about 1MB on IA32 */
- if (si.totalram <= (16384*1024)/PAGE_SIZE)
- inet_peer_threshold >>= 1; /* about 512KB */
- if (si.totalram <= (8192*1024)/PAGE_SIZE)
- inet_peer_threshold >>= 2; /* about 128KB */
+ /* 1% of physical memory */
+ nr_entries = div64_ul((u64)totalram_pages() << PAGE_SHIFT,
+ 100 * L1_CACHE_ALIGN(sizeof(struct inet_peer)));
+
+ inet_peer_threshold = clamp_val(nr_entries, 4096, 65536 + 128);
peer_cachep = kmem_cache_create("inet_peer_cache",
sizeof(struct inet_peer),
--
2.29.0
^ permalink raw reply related [flat|nested] 2+ messages in thread
* Re: [PATCH] inetpeer: use div64_ul() and clamp_val() calculate inet_peer_threshold
2021-03-01 6:05 [PATCH] inetpeer: use div64_ul() and clamp_val() calculate inet_peer_threshold Yejune Deng
@ 2021-03-01 21:40 ` patchwork-bot+netdevbpf
0 siblings, 0 replies; 2+ messages in thread
From: patchwork-bot+netdevbpf @ 2021-03-01 21:40 UTC (permalink / raw)
To: Yejune Deng
Cc: davem, yoshfuji, dsahern, kuba, eric.dumazet, netdev, linux-kernel
Hello:
This patch was applied to netdev/net.git (refs/heads/master):
On Mon, 1 Mar 2021 14:05:48 +0800 you wrote:
> In inet_initpeers(), struct inet_peer on IA32 uses 128 bytes in nowdays.
> Get rid of the cascade and use div64_ul() and clamp_val() calculate that
> will not need to be adjusted in the future as suggested by Eric Dumazet.
>
> Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
> Signed-off-by: Yejune Deng <yejune.deng@gmail.com>
>
> [...]
Here is the summary with links:
- inetpeer: use div64_ul() and clamp_val() calculate inet_peer_threshold
https://git.kernel.org/netdev/net/c/8bd2a0552734
You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2021-03-01 21:46 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-03-01 6:05 [PATCH] inetpeer: use div64_ul() and clamp_val() calculate inet_peer_threshold Yejune Deng
2021-03-01 21:40 ` patchwork-bot+netdevbpf
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).