netdev - Re: [PATCH net-next] tcp: remove the TCPSmallQueueFailure counter

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <31ca5dff-f69d-fc2a-64fe-145561fd18f6@gmail.com>
Date:   Tue, 30 Nov 2021 20:00:50 -0800
From:   Eric Dumazet <eric.dumazet@...il.com>
To:     Jakub Kicinski <kuba@...nel.org>, davem@...emloft.net
Cc:     netdev@...r.kernel.org, imagedong@...cent.com
Subject: Re: [PATCH net-next] tcp: remove the TCPSmallQueueFailure counter


On 11/30/21 5:51 PM, Jakub Kicinski wrote:
> This reverts commit aeeecb889165 ("net: snmp: add statistics for
> tcp small queue check").
>
> The recently added TSQ-limit-hit metric does not provide clear,
> actionable signal and can be confusing to the user as it may
> well increment under normal operation (yet it has Failure in
> its name). Menglong mentioned that the condition he was
> targetting arised due to a bug in the virtio driver.
>
> Link: https://lore.kernel.org/r/20211128060102.6504-1-imagedong@tencent.com/
> Signed-off-by: Jakub Kicinski <kuba@...nel.org>


Oops, I have seen this a bit late.


Maybe because my primary email address is edumazet@...gle.com, and that 
my @gmail.com

accounts have some lag.


Reviewed-by: Eric Dumazet <edumazet@...gle.com>


Thanks.


> ---
>   include/uapi/linux/snmp.h | 1 -
>   net/ipv4/proc.c           | 1 -
>   net/ipv4/tcp_output.c     | 5 +----
>   3 files changed, 1 insertion(+), 6 deletions(-)
>
> diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
> index e32ec6932e82..904909d020e2 100644
> --- a/include/uapi/linux/snmp.h
> +++ b/include/uapi/linux/snmp.h
> @@ -292,7 +292,6 @@ enum
>   	LINUX_MIB_TCPDSACKIGNOREDDUBIOUS,	/* TCPDSACKIgnoredDubious */
>   	LINUX_MIB_TCPMIGRATEREQSUCCESS,		/* TCPMigrateReqSuccess */
>   	LINUX_MIB_TCPMIGRATEREQFAILURE,		/* TCPMigrateReqFailure */
> -	LINUX_MIB_TCPSMALLQUEUEFAILURE,		/* TCPSmallQueueFailure */
>   	__LINUX_MIB_MAX
>   };
>   
> diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
> index 43b7a77cd6b4..f30273afb539 100644
> --- a/net/ipv4/proc.c
> +++ b/net/ipv4/proc.c
> @@ -297,7 +297,6 @@ static const struct snmp_mib snmp4_net_list[] = {
>   	SNMP_MIB_ITEM("TCPDSACKIgnoredDubious", LINUX_MIB_TCPDSACKIGNOREDDUBIOUS),
>   	SNMP_MIB_ITEM("TCPMigrateReqSuccess", LINUX_MIB_TCPMIGRATEREQSUCCESS),
>   	SNMP_MIB_ITEM("TCPMigrateReqFailure", LINUX_MIB_TCPMIGRATEREQFAILURE),
> -	SNMP_MIB_ITEM("TCPSmallQueueFailure", LINUX_MIB_TCPSMALLQUEUEFAILURE),
>   	SNMP_MIB_SENTINEL
>   };
>   
> diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
> index c4ab6c8f0c77..5079832af5c1 100644
> --- a/net/ipv4/tcp_output.c
> +++ b/net/ipv4/tcp_output.c
> @@ -2524,11 +2524,8 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
>   		 * test again the condition.
>   		 */
>   		smp_mb__after_atomic();
> -		if (refcount_read(&sk->sk_wmem_alloc) > limit) {
> -			NET_INC_STATS(sock_net(sk),
> -				      LINUX_MIB_TCPSMALLQUEUEFAILURE);
> +		if (refcount_read(&sk->sk_wmem_alloc) > limit)
>   			return true;
> -		}
>   	}
>   	return false;
>   }