TCPM WG Aravind Prasad Sridharan INTERNET-DRAFT Shathish Muthu Venkatesan Intended Status: Informational DELL Expires: January 21, 2016 July 20, 2015 Lively TCP Connection Failure Notifications draft-aravind-tcpm-lively-failure-notifications-00 Abstract This document proposes a mechanism to provide lively notifications of TCP Connection Failures in Network. Status of this Memo This Internet-Draft is submitted to IETF in full conformance with the provisions of BCP 78 and BCP 79. Internet-Drafts are working documents of the Internet Engineering Task Force (IETF), its areas, and its working groups. Note that other groups may also distribute working documents as Internet-Drafts. Internet-Drafts are draft documents valid for a maximum of six months and may be updated, replaced, or obsoleted by other documents at any time. It is inappropriate to use Internet-Drafts as reference material or to cite them other than as "work in progress." The list of current Internet-Drafts can be accessed at http://www.ietf.org/1id-abstracts.html The list of Internet-Draft Shadow Directories can be accessed at http://www.ietf.org/shadow.html Copyright and License Notice Copyright (c) 2015 IETF Trust and the persons identified as the document authors. All rights reserved. This document is subject to BCP 78 and the IETF Trust's Legal Provisions Relating to IETF Documents (http://trustee.ietf.org/license-info) in effect on the date of publication of this document. Please review these documents carefully, as they describe your rights and restrictions with respect to this document. Code Components extracted from this document must Expires January 21, 2016 [Page 1] INTERNET DRAFT July 20, 2015 include Simplified BSD License text as described in Section 4.e of the Trust Legal Provisions and are provided without warranty as described in the Simplified BSD License. Table of Contents 1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . 2 1.1 Terminology . . . . . . . . . . . . . . . . . . . . . . . . 2 2 Solution . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 3 Useful scenarios . . . . . . . . . . . . . . . . . . . . . . . 3 4 Security Considerations . . . . . . . . . . . . . . . . . . . . 3 5 IANA Considerations . . . . . . . . . . . . . . . . . . . . . . 3 6 References . . . . . . . . . . . . . . . . . . . . . . . . . . 3 6.1 Normative References . . . . . . . . . . . . . . . . . . . 3 6.2 Informative References . . . . . . . . . . . . . . . . . . 3 Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . . 3 1 Introduction Whenever any link fails resulting in the loss of TCP connections, it takes longer time periods to detect it. In Datacenters, the failures include all the network links throughout the datacenters and also the connections between the TORs (Top of the Rack Switches) and Servers. The propagation of failure information currently takes longer periods thereby leading to wastage of kernel resources for invalid/failed TCP sessions. 1.1 Terminology The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this document are to be interpreted as described in RFC 2119 [RFC2119]. 2 Solution 1. The Network devices connected to the Servers can snoop the TCP SYN packets and can get the info of list of TCP connections established at the server. 2. Then, the Network Devices can monitor those destination subnets (IP address subnets) on which the TCP connections are made. 3. In case of network failures (if any of those subnets become unreachable), the routing protocols would determine those scenarios Expires January 21, 2016 [Page 2] INTERNET DRAFT July 20, 2015 and update the Device's IP table. 4. A Defined Timer could be used to track the failed subnets. As soon as the Network device detects the monitored subnet going down, a timer could be started and on the timer expiry, it can send a TCP RST message to the Servers connected to it so that they can tear down the corresponding sessions. If the connectivity to subnet comes up again within defined time-period, the operation of sending TCP-RST could be aborted. Further, the use of timer assists to avoid false alarms created during link flaps in case of directly connected subnets. The proposed approach is pro-active, i.e., TCP RST Messages are sent without waiting for any packet corresponding to the failed session to be received. 3 Useful Scenarios With the increased usage of persistent connections with HTTP/1.1 [RFC 7230, RFC 7231, RFC 7232, RFC 7233, RFC 7234, RFC 7235] and SIP [RFC 5923], it is possible for a number of established connections to be present at any given point of time. This leads to possibility of overloading Server with a number of open connections and may even lead to failure to open new connections. Hence, this proposal helps to close the connections quickly for which network connectivities are lost and thereby reduce the load on Server and assist in increasing the scalability. 4 Security Considerations This document does not introduce any new security concerns or any other specifications referenced in this document. 5 IANA Considerations No IANA actions required. 6 References 6.1 Normative References [RFC0793] Postel, J., "Transmission Control Protocol", STD 7, RFC 793, September 1981. Expires January 21, 2016 [Page 3] INTERNET DRAFT July 20, 2015 [RFC2119] Bradner, S., "Key words for use in RFCs to Indicate Requirement Levels", BCP 14, RFC 2119, March 1997. 6.2 Informative References [RFC7230] Fielding.R, Reschke.J, "Hypertext Transfer Protocol (HTTP/1.1): Message Syntax and Routing", June 2014. [RFC7231] Fielding.R, Reschke.J, "Hypertext Transfer Protocol (HTTP/1.1): Semantics and Content", June 2014. [RFC7232] Fielding.R, Reschke.J, "Hypertext Transfer Protocol (HTTP/1.1): Conditional Requests", June 2014. [RFC7233] Fielding.R, Reschke.J, "Hypertext Transfer Protocol (HTTP/1.1): Range Requests", June 2014. [RFC7234] Fielding.R, Reschke.J, "Hypertext Transfer Protocol (HTTP/1.1): Caching", June 2014. [RFC7235] Fielding.R, Reschke.J, "Hypertext Transfer Protocol (HTTP/1.1): Authentication", June 2014. [RFC5923] Gurbani.V, Mahy.R, Tate.B, "Connection Reuse in the Session Initiation Protocol (SIP)", June 2010 Authors' Addresses Aravind Prasad Sridharan DELL Olympia Technology Park Guindy, Chennai 600032 India Phone: +91 9884612715 Email: aravind_sridharan@dell.com Shathish Muthu Venkatesan DELL Olympia Technology Park Guindy, Chennai 600032 India Phone: +91 9994625911 Email: shathish_venkatesan@dell.com Expires January 21, 2016 [Page 4]