[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20231113034457.GA121324@linux.alibaba.com>
Date: Mon, 13 Nov 2023 11:44:57 +0800
From: Dust Li <dust.li@...ux.alibaba.com>
To: "D. Wythe" <alibuda@...ux.alibaba.com>, kgraul@...ux.ibm.com,
wenjia@...ux.ibm.com, jaka@...ux.ibm.com, wintera@...ux.ibm.com
Cc: kuba@...nel.org, davem@...emloft.net, netdev@...r.kernel.org,
linux-s390@...r.kernel.org, linux-rdma@...r.kernel.org
Subject: Re: [PATCH net v1] net/smc: avoid data corruption caused by decline
On Wed, Nov 08, 2023 at 05:48:29PM +0800, D. Wythe wrote:
>From: "D. Wythe" <alibuda@...ux.alibaba.com>
>
>We found a data corruption issue during testing of SMC-R on Redis
>applications.
>
>The benchmark has a low probability of reporting a strange error as
>shown below.
>
>"Error: Protocol error, got "\xe2" as reply type byte"
>
>Finally, we found that the retrieved error data was as follows:
>
>0xE2 0xD4 0xC3 0xD9 0x04 0x00 0x2C 0x20 0xA6 0x56 0x00 0x16 0x3E 0x0C
>0xCB 0x04 0x02 0x01 0x00 0x00 0x20 0x00 0x00 0x00 0x00 0x00 0x00 0x00
>0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0xE2
>
>It is quite obvious that this is a SMC DECLINE message, which means that
>the applications received SMC protocol message.
>We found that this was caused by the following situations:
>
>client server
> proposal
> ------------->
> accept
> <-------------
> confirm
> ------------->
>wait confirm
>
> failed llc confirm
> x------
>(after 2s)timeout
> wait rsp
>
>wait decline
>
>(after 1s) timeout
> (after 2s) timeout
> decline
> -------------->
> decline
> <--------------
>
>As a result, a decline message was sent in the implementation, and this
>message was read from TCP by the already-fallback connection.
>
>This patch double the client timeout as 2x of the server value,
>With this simple change, the Decline messages should never cross or
>collide (during Confirm link timeout).
>
>This issue requires an immediate solution, since the protocol updates
>involve a more long-term solution.
>
>Fixes: 0fb0b02bd6fd ("net/smc: adapt SMC client code to use the LLC flow")
>Signed-off-by: D. Wythe <alibuda@...ux.alibaba.com>
>---
> net/smc/af_smc.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
>diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
>index abd2667..5b91f55 100644
>--- a/net/smc/af_smc.c
>+++ b/net/smc/af_smc.c
>@@ -599,7 +599,7 @@ static int smcr_clnt_conf_first_link(struct smc_sock *smc)
> int rc;
>
> /* receive CONFIRM LINK request from server over RoCE fabric */
>- qentry = smc_llc_wait(link->lgr, NULL, SMC_LLC_WAIT_TIME,
>+ qentry = smc_llc_wait(link->lgr, NULL, 2 * SMC_LLC_WAIT_TIME,
> SMC_LLC_CONFIRM_LINK);
It may be difficult for people to understand why LLC_WAIT_TIME is
different, especially without any comments explaining its purpose.
People are required to use git to find the reason, which I believe is
not conducive to easy maintenance.
Best regards,
Dust
> if (!qentry) {
> struct smc_clc_msg_decline dclc;
>--
>1.8.3.1
Powered by blists - more mailing lists