DCB Capability Exchange Protocol Base Specification. Rev 1.01
|
|
|
- Corey Cobb
- 10 years ago
- Views:
Transcription
1 Task Group Data Center Bridging Revision 1.01 Author Manoj Wadekar (Qlogic), et al DCB Capability Exchange Protocol Base Specification Rev
2 Modification History Rev Originator Comment 1.0 Manoj Wadekar Initial Submitted Version 1.01 Manoj Wadekar Added Application TLV 2
3 TABLE OF CONTENTS TABLE OF CONTENTS...3 LIST OF TABLES...4 LIST OF FIGURES...4 Terminology...4 Related Documents Authors Introduction Goals Types of DCB Parameters DCBX and LLDP LLDP Modifications DCBX Operation DCBX TLV Format DCBX Control State Machine DCB Feature State Machine Manager Notifications DCB Features Priority Group Feature Priority Group Parameters Priority Group TLV Priority Group Parameter Comparison Feature Specific Behavior for Priority Group TLV Priority-based Flow Control (PFC) Feature Priority-based Flow Control Parameters Priority-based Flow Control TLV Priority-based Flow Control Parameter Comparison Feature Specific behavior for PFC TLV Application Protocol Feature Application Protocol Parameters Application Protocol TLV Application Protocol Parameter Comparison 33
4 LIST OF TABLES TABLE 1 DCBX CONTROL TLV FIELDS TABLE 2 DCBX CONTROL STATE VARIABLES TABLE 3 DCB FEATURE TLV HEADER FIELD DEFINITIONS TABLE 4 DCBX STATE VARIABLE DEFINITIONS FOR THE DCB FEATURE STATE MACHINE TABLE 5 - PRIORITY GROUP PARAMETERS TABLE 6 - PRIORITY GROUPS PARAMETER COMPARISON TABLE 7 - PRIORITY-BASED FLOW CONTROL TABLE 8 APPLICATION PROTOCOL PARAMETERS LIST OF FIGURES FIGURE 1 - DCBX DEPLOYMENT SCENARIO... 9 FIGURE 2 - TYPES OF PARAMETERS FIGURE 3 - LLDP FRAME FORMAT FIGURE 4 - INITIAL LLDP EXCHANGE DELAY ISSUE FIGURE 5 - INITIAL FAST RETRANSMISSION OF LLDP FRAMES FIGURE 6 - HIGH LEVEL DCBX TLV STRUCTURES FIGURE 7 - DCBX CONTROL TLV DEFINITION FIGURE 8 - DCBX CONTROL STATE MACHINE DIAGRAM FIGURE 9 DCB FEATURE TLV HEADER DEFINITION (DCBX_TLV_HEADER) FIGURE 10 GENERIC DCB FEATURE TLV FIGURE 11 - DCB FEATURE STATE MACHINE FIGURE 12 - PRIORITY GROUP PARAMETERS STRUCTURE FIGURE 13 - PRIORITY-BASED FLOW CONTROL PARAMETERS STRUCTURE FIGURE 14 - DCBX SPECIFIED USE OF OUI FIGURE 15 - APPLICATION PROTOCOL PARAMETERS STRUCTURE FIGURE 16 EXAMPLE APPLICATION PROTOCOL TLV WITH MULTIPLE PROTOCOLS Terminology Term BCN CM DCB DCBX LLDP LLDPDU NIC OS OUI PDU Description Backward Congestion Management Congestion Management Data Center Bridging DCB Capability Exchange Protocol Link Layer Discovery Protocol, IEEE802.1AB An LLDP PDU Network interface controller Operating System. Organizationally Unique Identifier Protocol Data Unit 4
5 Term PFC PG RX SNMP TLV TTL TX Description Priority-based Flow Control (same as Per Priority Pause or Class Based Flow Control) Priority Groups Receive Simple Network Management Protocol Type Length Value Time to Live Transmit Related Documents DCB Feature Specifications Proposal for Priority Based Flow Control pdf Packet Scheduling with Priority Grouping and Bandwidth Allocation for DCB Networks v1.01.pdf 5
6 1. Authors The following people, with company affiliations, have contributed to the preparation of this proposal: Amit Shukla Juniper Anoop Ghanwani - Brocade Anjan Cisco Anthony Faustini - Cisco Asif Hazarika Fujitsu Awais Nemat Marvell Bruce Klemin Qlogic Brice Kwan - Broadcom Claudio DeSanti- Cisco Craig W. Carlson - QLogic Dan Eisenhauer IBM Danny J. Mitzel - Brocade David Peterson Brocade Diego Crupniokoff Mellanox Dinesh Dutt - Cisco Douglas Dreyer - IBM Ed McGlaughlin Qlogic Eric Multanen - Intel Gaurav Chawla - Dell Glenn - Brocade Hemal Purohit - QLogic Hugh Barrass Cisco Ilango Ganga - Intel Irv Robinson - Intel J. R. Rivers Cisco Jeelani Syed - Juniper Jeffrey Lynch - IBM Jim Larsen - Intel Joe Pelissier - Cisco John Hufferd Brocade John Terry Brocade Krishna Doddapaneni - Cisco Manoj Wadekar Qlogic Menu Menuchehry - Marvell Mike Ko IBM Mike Krause - HP Parag Bhide - Emulex Pat Thaler - Broadcom Ravi Shenoy - Emulex Renato Recio - IBM Robert Snively - Brocade Roger Hathorn - IBM 6
7 Sanjaya Anand Qlogic Sanjay Sane Cisco Shreyas Shah - PLX Silvano Gai - Cisco Stuart Berman - Emulex Suresh Vobbilisetty - Brocade Taufik Ma - Emulex Uri Elzur - Broadcom 7
8 2. Introduction This document details the data center discovery and capability exchange protocol (DCBX) that is used by DCB devices to exchange configuration information with directly connected peers. The protocol may also be used for misconfiguration detection and for configuration of the peer. This document describes the base protocol which comprises a control state machine and a generic feature state machine. For each feature that is to be supported by DCBX, the following information must be provided: The parameters to be exchanged; How the parameters are used for detecting misconfiguration; What action needs to be taken when an error is detected; This document also lists the above information for the following features: - Priority Groups (PG) - Priority-based Flow Control (PFC) In future, it is likely that additional features may be added to DCBX. 2.1 Goals The following lists the goals of DCBX. Discovery of DCB capability in a peer: DCBX is used to know about the capabilities of the peer device. It is a means to know if the peer device supports a particular feature such as Priority Groups (PG) or Priority-based Flow Control (PFC). For example, it can be used to determine if two link peer devices support PFC. DCB feature misconfiguration detection: DCBX can be used to detect misconfiguration of a feature between the peers on a link. Misconfiguration detection is feature-specific because some features may allow asymmetric configuration. Peer configuration of DCB features: DCBX can be used by a device to perform configuration of DCB features in its link peer. The goal is to provide basic peer to peer configuration through DCBX in the initial version. Future versions of DCBX or another higher layer application can build on top of this to provide more complex configuration distribution mechanisms. Figure 1 shows a deployment scenario for a network that is using DCBX. DCBX capable links exchange DCB capability and configuration, and conflict alarms are sent to the appropriate management stations. As an example, a boundary is shown indicating which devices support PFC and which do not. 8
9 Conflict alarm DCBX Switch Management Conflict alarm DCBX DCBX DCBX DCBX DCBX DCBX DCBX DCBX DCBX PFC enabled region 3 Server Management Figure 1 - DCBX Deployment Scenario 9
10 2.2 Types of DCB Parameters Each DCB feature has a set of parameters. DCB parameters are classified into two broad categories: - Exchanged parameters: Exchanged parameters are sent to the peer. Within these parameters, there are two sub-groups: 1. Administered parameters: These are the configured parameters. 2. Operational parameters: This is the operational state of the related administered parameter. Operational state might be different than the administrative/configured state, primarily as a result of the DCBX exchange with the peer. Operational parameters accompany only those administered parameters where there is a possibility that the operational state is different from what was set by their administrator. The operational parameters are included in the the LLDP message only for informational purposes. It might be used by a device to know what is the current operational state of the peer. - Local parameters: Local parameters are not exchanged in LLDP messages. Figure 2 shows the exchanged parameters that are sent to each peer via LLDP messages. Exchanged parameters Operational parameters Local parameters DCB MIB Device A Exchanged parameters LLDP Messages Ethernet Link Exchanged parameters Operational parameters Local parameters DCB MIB Device B Figure 2 - Types of Parameters 2.3 DCBX and LLDP DCBX uses Link Layer Discovery Protocol (LLDP) to exchange parameters between two link peers. LLDP is a unidirectional protocol. It advertises connectivity and management information about the local station to adjacent stations on the same IEEE 802 LAN. LLDP PDUs carry Type Length Values (TLVs) classified as 1. Mandatory TLVs: Chassis ID, Port ID, TTL, End of LLDPDU. 2. Optional TLVs: Basic Management, and Organizationally Specific. DCB exchanged parameters are packaged into Organizationally Specific TLVs. The OUI used for the DCBX TLV is 0x001B21 (IEEE OUI will be used when it becomes available). 10
11 Depending on the amount of data required for all features, one or more TLVs, with different sub-types, are defined for DCBX. Within the DCBX TLVs, sub-tlvs are defined for each feature carried by that TLV. A device capable of any DCB feature must have DCBX enabled by default with an option for DCBX to be administratively disabled. DCBX is expected to operate over a point to point link. If multiple LLDP neighbors are detected, then DCBX behaves as if the peer s DCBX TLVs are not present until the multiple LLDP neighbor condition is no longer present. An LLDP neighbor is identified by its logical MAC Service Access Identifier (MSAP). The logical MSAP is a concatenation of the chassis ID and port ID values transmitted in the LLDPDU. LLDP gives administrator control to enable/disable the protocol independently on the Rx side and Tx side. Since DCBX is an acknowledged protocol which uses LLDP, for the protocol to operate correctly both LLDP Rx and Tx must be enabled on the interface on which DCBX runs. The behavior of DCBX is as follows with respect to LLDP Rx/Tx admin state controls: * If either of Rx or Tx is in disable state, DCBX is disabled on the interface. Neither the control nor feature state machines should run. The LLDPDU's that are generated from this interface do not have any DCBX TLVs. If the peer sends DCBX TLVs they should be ignored as far as the DCBX state machines are concerned. * When DCBX is currently running and LLDP TX is disabled, then according to the LLDP specification, a shutdown LLDPDU is sent. When the peer receives this PDU, DCBX is determined to be disabled on the peer. This is equivalent to DCBX TLV TTL expired in the Control State machine and Rx.Feature.present() = FALSE in the Feature state machine. If for some reason this frame is lost, then DCBX depends on standard rxinfottl expiry of the peer's LLDP TLV's. * When DCBX is currently running and LLDP Rx is disabled, then all DCBX TLV's including the control TLV should be withdrawn from the LLDP PDUs that the interface generates. The peer's behavior should be the same as discussed in the previous case. 11
12 DA SA Ethtype 0x88CC LLDP PDU Ethernet Frame format Chassis ID TLV Port ID TLV Time To Live Optional TLV PROTOCOL TLV End of LLDPDU TLV LLDP PDU format Type 7 bits Length 9 bits Information octets General TLV structure TLV Type=127 Length 9 bits OUI 3 octets Subtype 1 octet Information octets Organizationally Specific TLV structure Org TLV Header PROTOCOL Control Sub-TLV Feature Sub-TLV Feature Sub-TLV Feature Sub-TLV PROTCOL TLV Figure 3 - LLDP Frame Format LLDP Modifications This section lists the proposed modifications to the LLDP protocol for use with DCBX. IEEE 802.1AB REV project is currently working on these modifications. Once standard is published for IEEE 802.1AB-REV, DCBX specification will be appropriately modified Fast initial LLDP Transmissions The current LLDP protocol can result in a long delay before DCB parameters are exchanged and synchronized. LLDP transmits a frame after: - Transmit countdown timer expiration (recommended default value = 30 seconds) and txdelay expiration, OR - A condition (status or value) change in one or more objects in LLDP local system MIB. (LLDP local system MIB contains only the objects that are sent in LLDP frames. This MIB could be merely a subset of a larger MIB). After initialization, an LLDP frame is transmitted (considering the initialization as a status change). 12
13 An initial LLDP message might not be received by the peer due to different times at which their initialization completes (see Figure 4). Device A Device B PHY Link up PHY Link up LLDP initialized LLDP messages X LLDP initialized Peer parameters received Peer parameters received Figure 4 - Initial LLDP Exchange Delay Issue In order to overcome this problem, the following modification is proposed. The interval for the LLDP transmission time to refresh the timer (msgtxinterval) is set to one second for the first five transmissions after LLDP initialization and then reset to the administratively configured value. The txdelay (minimum delay between successive transmitted LLDP frames) is also set to one second as a DCBX default. This ensures that at start up both devices receive peer parameters within a short timeframe as shown in Figure 5. 13
14 Device A Device B PHY Link up PHY Link up Peer parameters received LLDP initialized LLDP Messages X X LLDP initialized Peer parameters received Figure 5 - Initial Fast Retransmission of LLDP Frames Each time LLDP is initialized, such as link up, LLDP enters this fast transmission mode. LLDP operates in its normal transmission mode at all other times. 2.4 DCBX Operation DCBX is defined as a DCBX control state machine and a set of DCB feature state machines. The DCBX control state machine handles ensuring that the two DCBX peers get in sync by exchanging LLDPDUs after link up or following a configuration change. The DCB feature state machines handle the local operational configuration for each feature by comparing and synchronizing with the peer s feature settings. 14
15 2.4.1 DCBX TLV Format Information about the DCBX control state and DCB feature configuration are exchanged with the peer in DCBX TLVs that are transmitted via LLDP PDUs. Figure 6 shows the general structure of the organizationally specific DCBX TLV. The details of each sub-tlv are covered in the remainder of the document. Figure 6 - High Level DCBX TLV Structures The DCBX Control Sub-TLV and the set of Feature Sub-TLVs can be arranged in any order within the DCBX TLV. Duplicate Sub-TLV s (such as more than one Sub-TLV for the same feature) are not allowed. Duplicates are handled as a configuration error for the feature. A duplicate DCBX Control TLV causes an error for all features. The DCBX sub-tlvs follow the same format as an LLDP TLV having type, length and information fields. The type field is meaningful within the context of a DCBX TLV and the length specifies the number of octets in the information portion of the sub-tlv. Figure 6 shows OUI=001B21 that is offered by Intel Corp. for use by all the parties using pre-standard version. Once IEEE defines the protocol, appropriate OUI needs to be used as defined by IEEE standard Bit and Octet Ordering Conventions DCBX uses the same bit and octet ordering conventions as LLDP. [The DCBX TLV] contain[s] an integral number of octets. The octets in [a DCBX TLV] are numbered starting from one and increasing in the order they are put into the LLDP frame. The bits are numbered from zero to seven, where zero is the low-order bit. When consecutive bits within an octet are used to represent a binary number, the highest bit number has the most significant value. When consecutive octets are used to represent a binary number, the lower octet number has the most significant value. All TLVs respect these bit and octet ordering conventions, thus allowing communications to take place. In the details that follow, the following data types are used to define structures which describe the elements of DCBX sub-tlvs: u32 - unsigned 32 bit integer 15
16 u16 - unsigned 16 bit integer u8 - unsigned 8 bit integer Elements listed first in a structure have lower octet numbers then subsequent elements. Bit fields within an element occupy the highest to lowest order bits of the element in the order they are listed. The following structure shows an example. struct example_tlv { u16 type :7; // high order bit field in u16 element u16 length :9; // low order bit field in u16 element u32 fielda :8; // highest order bit field in u32 element u32 fieldb :8; u32 fieldc :3; u32 fieldd :13; // lowest order bit field in u32 element }; SIZE = 6 octets DCBX Control State Machine The DCBX Control state machine uses the DCBX Control sub-tlv to exchange information with the peer. In addition, it maintains some additional local state variables to manage the state machine operation. The TLV and state variables are defined in the sections that follow DCBX Control TLV Figure 7 shows the DCBX Control TLV. Figure 7 - DCBX Control TLV Definition 16
17 The following table lists the fields in the DCBX Control TLV. Table 1 DCBX Control TLV Fields Field Field-Type Range Description Feature- Type Integer N/A Type code of the DCBX Control TLV. Length Integer N/A Length of the DCBX Control sub- TLV payload (not including the Type and Length fields). The length is less than the maximum possible value (511) as this TLV is packaged inside the DCBX TLV along with other feature TLV s. Oper Version Integer Operating version of the DCBX protocol. The system adjusts as needed to operate at the highest version supported by both link partners. Max Version Integer Highest DCBX protocol version supported by the system. Version numbers start at zero. The DCBX protocol must be backward compatible with all previous versions. SeqNo Integer 0.. (2 32 1) AckNo Integer 0.. (2 32 1) A value that changes each time an exchanged parameter in one or more of the DCB feature TLV s changes. The SeqNo value from the most recent peer DCBX TLV that has been handled. This acknowledges to the peer that a specific SeqNo has been received DCBX Control State Variables The following table lists the local state variables used to maintain the DCBX Control state machine. Table 2 DCBX Control state variables State Type Range Description Variable RcvdAckNo Integer 0.. (2 32 1) The AckNo from the most recent peer DCBX TLV that has been handled. This is an acknowledgement from the peer that a specific SeqNo 17
18 NoDCBXTLV Received DCBXFeatur eupdate has been received. Boolean TRUE/FALSE This flag is set when somethingchangedremote event is received from LLDP and Remote MIB indicates empty DCB TLVs Boolean TRUE/FALSE Indicates any change in DCBX Feature DCBX Control State Machine In addition to the TLV fields and state variables previously described, the DCBX Control state machine uses the following mechanisms: somethingchangedlocal this is an indication from the DCBX state machine to the LLDP module that there is a new DCBX TLV to transmit. somethingchangedremote this is an indication from the LLDP module to the DCBX Control state machine that there is new information from the peer (such as new DCBX TLV or data has expired). DCBXFeatureUpdate the DCBX Control state machine provides this indication to the DCB Feature state machines after it has received the somethingchangedremote indication. The SeqNo, DCBXFeatureUpdate and RcvdAckNo variables are visible to the DCB Feature state machines. Figure 8 shows the operation of the DCBX Control state machine. Note that the diagram is defined using an infinite loop model (such as no waiting). Implementations might use event waiting mechanisms as long as the function of the state machine is preserved. A few notes concerning the notations used in Figure 8: DCBX Control TLV fields and state variables are used directly such as SeqNo) Variables from the Feature state machines are identified by pre-pending Feature to the variable: For example, Feature.Syncd refers to a variable called Syncd from a Feature state machine. TLV fields received from the peer are identified as: Rx.< variable> - i.e. Rx.SeqNo. 18
19 Link up LinkUp SeqNo = 0; AckNo = 0; RcvdAckNo = 0; OperVersion = MaxVersion; UCT DWait Do Nothing; SeqNo == RcvdAckNo && Any Feature!Syncd UpdateDCBXTLV SeqNo++; somethingchangedlocal = TRUE; Capture all DCBX Feature TLVs For all Features { FeatureSyncd = FeatureSyncd!FeatureAdvertise}; UCT (SeqNo!= RcvdAckNo All Features Syncd) && somethingchangedremote && NoDCBXTLVReceived PeerNotAdvertiseDCBX SeqNo = 0; AckNo = 0; RcvdAckNo = 0; OperVersion = MaxVersion; DCBXFeatureUpdate = TRUE; UCT (SeqNo!= RcvdAckNo All Features Syncd) && somethingchangedremote &&!NoDCBXTLVReceived && OperVersion!= min(rx.maxversion, MaxVersion) (SeqNo!= RcvdAckNo All Features Syncd) && somethingchangedremote &&!NoDCBXTLVReceived && OperVersion == min(rx.maxversion, MaxVersion) && OperVersion == Rx.OperVersion AckNo == Rx.SeqNo UpdateOperVersion OperVersion = min(rx.maxversion, MaxVersion); somethingchangedlocal = TRUE; ProcessPeerTLV RcvdAckNo = Rx.AckNo; DCBXFeatureUpdate =TRUE; AckNo!= Rx.SeqNo UCT UCT AckPeer AckNo = Rx.SeqNo; somethingchangedlocal=true; Figure 8 - DCBX Control State Machine Diagram Commentary on the DCBX Control state machine diagram by reference label: UpdateDCBXTLV: Capture TLV term implies inclusion of feature TLV to be indicated to LLDP for transmission, if the feature is advertised. PeerNotAdvertiseDCBX If the DCBX TLV from the peer has expired, then the local side resets similar to a link up. This is a different case than an actual link down, which would cause this state machine to exit. AckPeer: The peer has sent a Control TLV with a new sequence number. Send a new Control TLV with an updated AckNo field. 19
20 2.4.3 DCB Feature State Machine This section defines the operation of the DCB Feature state machine. The configuration of each DCB feature is managed by that feature s DCB Feature state machine. All DCB Feature state machines operate in the same manner DCB Feature TLV Figure 9 shows the common TLV header structure used for all DCB feature sub-tlv s. Feature specific TLV parameters are pre-pended with this header. 16 bits Type Length Oper_Version Max_Version E N E W Reserved Sub_Type R EN=Enabled ER = Error W=Willing SIZE=6 Octets Figure 9 DCB Feature TLV Header Definition (DCBX_tlv_header) Figure 10 shows a generic DCB Feature TLV structure. The details of each feature specific parameter structure are defined in the upcoming DCB Feature sections. struct PROTCOL_feature_tlv { struct DCBX_tlv_header h; struct DCBX_feature_cfg desired_cfg; }; SIZE = 6 + sizeof(struct DCBX_feature_cfg) Figure 10 Generic DCB Feature TLV The following table lists the fields in the DCB Feature TLVs that are used to define the operation of the DCB Feature state machine. Table 3 DCB Feature TLV header field definitions Field Type Range Description Type Integer Type code of the DCB Feature. Following is a list of defined types: 1 DCBX Control (not a feature) 2 Priority Groups 20
21 3 Priority-based Flow Control 4 Application Protocol Length Integer N/A Length of the DCB Feature sub-tlv payload (not including the Type and Length fields). The length is less than the maximum possible value (511) as this TLV is packaged inside the DCBX TLV along with other feature TLV s. Oper Version Max Version Integer Operating version of the feature. The system adjusts to operate at the highest version supported by both link partners. Integer Highest feature version supported by the system. Version numbers start at zero. The feature must be backward compatible for all previous versions. Enable Boolean Truth value Willing Boolean Truth value Error Boolean Truth value Locally administered parameter that indicates whether the DCB feature is enabled or not. Locally administered parameter that indicates whether this feature accepts its configuration from the peer or not. When set to TRUE, the system uses the DesiredCfg supplied by a!willing peer as the OperCfg. A system set to Willing must be capable of accepting any valid DesiredCfg for the feature from the peer. If both local and remote systems have the same value for the Willing flag, then the local DesiredCfg is used and the operational outcome of the exchange is determined by the Compatible method of the feature. Indicates that an error has occurred during the configuration exchange with the peer. Error is also set to TRUE when the Compatible method for the feature fails. 21
22 The Feature turns OperMode to FALSE if either the local or remote Error flag is set to TRUE. Duplicate TLV s for the same Type/SubType or the DCBX Control TLV also causes Error to be set to TRUE. System errors are not reflected on this Error Flag. SubType Integer Some Feature TLVs may define subtypes that are specific to that feature. When subtypes are not defined by a specific feature, subtype field should be set to zero In general, the Type and SubType, taken together, identify a unique feature that is managed by an instance of the DCB Feature State Machine. NOTE: A node does not have to support 8 classes of service in order to be considered capable of accepting any valid DesiredCfg. It may fulfill the requirements of the configuration by combining priorities or priority groups requiring similar service (e.g. PFC configuration and bandwidth management) into a traffic class. Details about decision to combine various priorities in single traffic class is out of scope of this document. NOTE: The TLV always carries the DesiredCfg. A system uses its own DesiredCfg, the peer s DesiredCfg (PeerCfg) and the other bits (willing, error, etc.) to derive its OperCfg. When both sides advertise, they should be able to derive the same OperCfg DCB Feature State Variables The following table lists the additional state variables used to maintain each DCB Feature state machine. Table 4 DCBX state variable definitions for the DCB Feature state machine State Variable Type Range Description Advertise Boolean Truth Locally administered value parameter that indicates whether this feature is exchanged in the DCBX TLV. When Advertise is False, received TLVs for this feature are ignored. OperMode Boolean Truth value Operational state of the feature. FeatureSeqNo Integer 0.. When Syncd is False, this 22
23 Syncd Boolean Truth value (2 32 1) indicates the value that SeqNo must become equal to before Syncd can become True. Indicates whether the current DesiredCfg has been received by the peer. OperCfg Structure NA The actual operating configuration of the feature. Derived from either DesiredCfg or PeerCfg. PeerCfg Structure NA The DesiredCfg of the peer as received in a DCBX TLV from the peer. DesiredCfg Structure NA This represents the locally configured values of the feature specific configuration. PeerWilling Boolean Truth value LocalParamete rchange Boolean Truth Value DCB Feature State Machine The Willing state of the peer as received in a DCBX TLV from the peer. Indicates that a configurable DCB Feature TLV field or state variable has been modified on the local system. In addition to the TLV fields and state variables previously described, the DCB Feature state machine uses the following mechanisms: DCBXFeatureUpdate this represents an indication from the DCBX Control state machine that there is new information from the peer (such as a new DCBX TLV or data has expired). The Syncd variable from each DCB Feature state machine is visible to the DCBX Control state machine. Each feature has a method called Compatible which is used to compare the DesiredCfg and PeerCfg. Each feature retrieves LocalParams from non-volatile storage or sets them to default values at link up. LocalParameterChange indicates that a configurable DCB Feature TLV field or state variable has been modified on the local system. The SeqNo, DCBXFeatureUpdate and RcvdAckNo are control state machine variables that are visible to the DCB Feature state machines. Each feature has a method called SetCfg which accepts two parameters. This method is called to set operational parameters for the given feature. First parameter to this method provides configuration parameters to be used by the method. Second parameter is a Boolean. 23
24 Figure 11 shows the operation of the DCB Feature state machine. Note that the figure is defined using an infinite loop model (such as no waiting). Implementations might use event waiting mechanisms as long as the function of the state machine is preserved. A few notes concerning the notations used in Figure 11: TLV fields and state variables are used directly (e.g. SeqNo) TLV fields received from the peer are identified as: Rx.<variable> - such as Rx.SeqNo. 24
25 Link up LinkUp OperVersion = MaxVersion; OperMode = FALSE; LocalParams = Default; Error = False; UCT SetLocalParameters Syncd =!(Advertise LocalParamsAdvertise); Enabled = LocalParamsEnabled; Advertise = LocalParamsAdvertise; UCT Willing = LocalParamsWilling; DesiredCfg = LocalParamsCfg; FeatureSeqNo = SeqNo + 1; LocalParameterChange=FALSE; NoAdvertise OperCfg = SetCfg(DesiredCfg, Enabled); UCT OperMode = Enabled; Error = FALSE; PeerNotAdvertiseDCBX OperCfg = SetCfg(DesiredCfg, FALSE); OperMode = FALSE; UCT Syncd = FALSE; FeatureSeqNo = SeqNo + 1; Error = TRUE; PeerNotAdvertiseFeature OperCfg = SetCfg(DesiredCfg, FALSE); OperMode = FALSE; UCT Syncd = TRUE; Error = TRUE; UpdateOperVersion OperVersion = Min(Rx.FeatureMaxVersion, MaxVersion); UCT Syncd = FALSE; FeatureSeqNo = SeqNo + 1; PeerUpdateOperVersion UCT Syncd = TRUE; Syncd!Syncd Syncd!Syncd Syncd!Syncd Syncd!Syncd CfgNotCompatible OperCfg = SetCfg(DesiredCfg, FALSE); OperMode = FALSE; Syncd = Error; Error = TRUE; UseLocalCfg OperCfg = SetCfg(DesiredCfg,!RX.Error); OperMode =!Rx.Error; Syncd =!Error; Error = FALSE; UsePeerCfg OperCfg = SetCfg(PeerCfg,!RxError); OperMode =!Rx.Error; Syncd =!Error; Error = FALSE; FeatureDisabled OperCfg = SetCfg(DesiredCfg, FALSE); OperMode = FALSE; Syncd =!Error; Error = FALSE;!(LocalPrarmeterChange && Syncd) && Advertise && DCBFeatureUpdate && Rx.FeaturePresent() && (Syncd (RcvdAckNo == FeatureSeqNo)) &&OperVersion == min(rx.featuremaxversion, MaxVersion) &&OperVersion!= Rx.FeatureOperVersion!(LocalPrarmeterChange && Syncd) && Advertise && DCBXFeatureUpdate && Rx.FeaturePresent() && (Syncd (RcvdAckNo == FeatureSeqNo)) && OperVersion!= min(rx.featuremaxversion, MaxVersion)!(LocalPrarmeterChange && Syncd) && Advertise && DCBFeatureUpdate &&!NoDCBXTLVReceived &&!Rx.FeaturePresent() ErrorChange UCT FeatureSeqNo= SeqNo+1; FWait GetPeerCfg!(Enabled && Do Nothing; PeerCfg=Rx.FeatureCfg; Rx.FeatureEnabled) PeerWilling=Rx.FeatureWilling; Enabled && Rx.FeatureEnabled && Willing &&!PeerWilling!(LocalPrarmeterChange && Syncd) && Advertise && DCBXFeatureUpdate && Enabled && Rx.FeatureEnabled && Rx.FeaturePresent() && ((!Willing && PeerWilling) (Syncd ((Willing == PeerWilling) (RcvdAckNo == FeatureSeqNo)) && && Compatible(DesiredCfg, PeerCfg))) OperVersion == min(rx.featuremaxversion, MaxVersion) && Enabled && Rx.FeatureEnabled && OperVersion == Rx.FeatureOperVersion Willing == PeerWilling &&!Compatible(DesiredCfg, PeerCfg)!(LocalPrarmeterChange && Syncd) && Advertise && DCBFeatureUpdate && NoDCBXTLVReceived!(LocalPrarmeterChange && Syncd) &&!Advertise LocalPrarmeterChange && Syncd Figure 11 - DCB Feature State Machine 25
26 Commentary on the DCB Feature state machine by reference label: SetLocalParameters: If multiple features experience a change and set Syncd to FALSE, it is possible that the first change triggers the Control state machine to send an LLDP message. Additional pending changes do not get sent until the first change has been acknowledged (per D2 of Control state machine). In other words, the SeqNo s ratchet up and are acknowledged one value at a time. For example, the AckNo from the peer could be 9, the local SeqNo is 10, and multiple features could be pending with FeatureSeqNo at 11. A PDU with SeqNo 11 is not sent until an AckNo of 10 is received. NoAdvertise (any place OperCfg is set) The hardware configuration for the feature takes place at the point OperCfg is set and the OperMode is set. The implementation might keep track of whether or not the OperCfg and OperMode have actually changed and require an update to the hardware configuration. CfgNotCompatible Error is explicitly set to TRUE here to indicate that the two peers have a DCB configuration that is not compatible. SetCfg: When second parameter (Boolean) is set to TRUE, then configuration passed by first parameter is applied to Operational values. When second parameter is FALSE, then behavior is feature dependent and will be defined in the relevant sections for each feature Manager Notifications Implementations might choose to generate notifications when certain events occur. These types of events could include: Conditions indicating possible configuration error for example, when the Compatible method fails. Conditions where the feature is not present on the peer. This can happen when a device does not support a feature (not really an error) or if the feature s Advertise flag is off (possible configuration error). Configuration received from peer results into partial or complete mismatch. The peer stops responding as evidenced by an LLDP timeout event (delivered via the somethingchangedremote indication). Each time the Error flag is set to TRUE. 26
27 3. DCB Features This section defines the DCB Feature parameters and statistics. 3.1 Priority Group Feature This section describes the details of the Priority Group feature. The Priority Groups Specification provides configuration tables as well as a scheduling algorithm for managing bandwidth for various traffic classes on a converged link. NOTE: Although it is expected that DCB devices will eventually provide scheduling functionality as specified in the Priority Group specification (or better), legacy implementations exist. To encourage wider adoption, this Priority Group Feature allows legacy implementations to match scheduler capabilities to the behavior implied by the Priority Group specification as close as possible. All DCBX implementations must be capable of advertising the Priority Group TLV Priority Group Parameters The following table lists the Priority Group parameters. Table 5 - Priority Group Parameters Parameter Syntax Range Scope Description NumTCsSup Integer 0..7 Exchanged Number of TCs ported supported by device. Number of Priority Groups supported by a device can not be more than number of TCs supported. Priority Table Group (PG) Allocation PG ID Integer Exchanged Queue bandwidth (index) group PG Integer Exchanged Percentage of link Percentage bandwidth Priority Table Allocation Priority Integer 0..7 Exchanged (index) PG ID Integer Exchanged PG to which the priority belongs Priority Group TLV Figure 12 shows Priority Group parameters structure that is used in the Priority Group Feature TLV. 27
28 struct dcbx_pg_cfg { u8 pgid_0 :4; /* PGID of priority 0 */ u8 pgid_1 :4; /* PGID of priority 1 */ u8 pgid_2 :4; /* PGID of priority 2 */ u8 pgid_3 :4; /* PGID of priority 3 */ u8 pgid_4 :4; /* PGID of priority 4 */ u8 pgid_5 :4; /* PGID of priority 5 */ u8 pgid_6 :4; /* PGID of priority 6 */ u8 pgid_7 :4; /* PGID of priority 7 */ u8 pg_percentage[8]; /* Index is PGID */ u8 num_tcs_supported; } SIZE = 13 octets Figure 12 - Priority Group Parameters Structure Priority Group Parameter Comparison Table 6 lists how the Priority Group parameters of the local and peer nodes are compared to determine if they match or not. Table 6 - Priority Groups Parameter Comparison Parameter Priority Group (PG) Allocation PG ID (index) PG Percentage Priority Allocation Priority (index) PG ID Number of TCs Supported Comparison Does not need to match Does not need to match Does not need to match Does not need to match Does not need to match Feature Specific Behavior for Priority Group TLV Priority group has specific behavior defined for SetCfg method in feature state machine. Based on second parameter to SetCfg function, following actions shall be taken for Priority Groups feature: 28
29 - When Boolean is set to TRUE, configuration passed by first parameter to the method shall be applied to operational values. Feature shall be Enabled. - When second parameter (Boolean) is set to FALSE, local configuration (DesiredCfg) shall be applied to operational values and feature shall be Enabled. 3.2 Priority-based Flow Control (PFC) Feature This section describes the details of the Priority-based Flow Control feature. This feature is important to provide no-drop packet delivery for certain traffic classes while maintaining existing LAN behavior for other traffic classes on converged link. NOTE: Legacy implementations that do not support Priority-based Flow Control can signal this by setting "Enable" to FALSE. This effectively disables the Priority-based Flow Control feature at which time the peers fall back to configured 802.3X PAUSE behavior. All DCBX implementations must be capable of advertising the Priority-based Flow Control TLV Priority-based Flow Control Parameters Table 7 lists the Priority-based Flow Control parameters. Table 7 - Priority-based Flow Control Parameter Syntax Rang Scope Description e NumTCPFCS Integer 1..8 Exchanged Number of TCs that upported can simultaneously support PFC. PFC Config Table Priority Integer 0..7 Exchanged Priority value as (index) defined 3-bit field by 802.1Q Admin mode Integer 0..1 Exchanged Administrative PFC mode. 0: Disabled 1: Enabled PFC Enabled means that flow control in both directions (Rx and Tx) is enabled Priority-based Flow Control TLV Figure 13 shows the Priority-based Flow Control parameters structure that is used in the Priority-based Flow Control Feature TLV. struct dcbx_pfc_cfg { u8 pfc_enable; /* bitmap of priorities with PFC enabled */ u8 num_tcpfcs_supported; } 29
30 Figure 13 - Priority-based Flow Control Parameters Structure Priority-based Flow Control Parameter Comparison Local and remote parameter comparison for Admin Mode is done as follows: foreach (user_priority) { if ((localadminmode == Disabled == remoteadminmode) (localadminmode == Enabled == remoteadminmode)) { Comparison successful configuration match } else { Comparison fails configuration mismatch break } } Feature Specific behavior for PFC TLV PFC TLV has specific behavior defined for SetCfg method in feature state machine. Based on second parameter to SetCfg function, following actions shall be taken for Priority Groups feature: - When Boolean is set to TRUE, configuration passed by first parameter to the method shall be applied to operational values. Feature shall be Enabled. - When second parameter (Boolean) is set to FALSE then feature shall be Disabled. 3.3 Application Protocol Feature This TLV allows DCB node to announce upper layer protocols and associated prioritymap over DCB link. These ULPs may include L2 or L3 or L4 protocols. A DCB node can advertise multiple ULPs using a single Application Protocol TLV. Each upper level protocol is specified using a fixed size structure as shown in Figure 15 - Application Protocol Parameters Structure. The Length field of the Application Protocol TLV will include all the application protocol parameter structures specified in the TLV. For N application protocols specified in the TLV, the Length value will be sum of lengths of all the application protocol Parameters (as defined in Table 8) and the remaining Feature TLV header (except Type and Length field as defined in Table 3). There are multiple ways to specify the upper layer application protocol. One way recommended here is to use OUI specified in DCBX Base Specification 0x001B21 (Donated by Intel Corp. for use in DCBX protocol) and carry an Application Protocol ID. 30
31 This protocol ID could be EtherType (for L2 protocols) or TCP/UDP socket number for L4 protocols. Figure 14 - DCBX Specified use of OUI This proposal defines use of two least significant bits of MSB (named as SF: Selector Field) follows: 00_2: Application Protocol ID is L2 EtherType 01_2: Application Protocol ID is Socket Number (TCP/UDP) 10_2: Reserved 11_2: Reserved N OTE: E.g. FCoE protocol will be defined as follows: SF = 00_2, Application Protocol Id = 0x8906 or SF = 00_2, Application Protocol Id = 0x8914 E.g. iscsi protocol will be announced as follows: SF = 01_2, Application Protocol Id = Application Protocol Parameters Table 8 Application Protocol Parameters Parameter Syntax Range Description App Protocol Table Config App Protocol Integer 0..MAX_ Application protocol Index. Index (index 1) DCBX_A PP_PROT OCOL MAX_DCBX_APP_PROTOCOL is defined to be 15. Priority (index 2) Integer 0..7 Priority value as defined 3-bit field by 802.1Q. SF Integer x00: App Proto ID carries L2 EtherType 0x01: App Proto ID carries Socket Number (TCP/UDP) 0x10: Reserved 0x11: Reserved OUI Integer 24 Bit DCBX Protocol uses value OUI 0x001B21 Value Application Integer This two-byte field identifies Protocol Id protocol supported by DCB node Status Integer 0..1 Status of this entry 0: Disabled 31
32 1: Enabled T his Table 8 provides configuration for multiple application protocols and each application protocol configuration with multiple priorities. The table parameters are translated to the Application Protocol TLV as shown infigure 15. An application protocol using multiple priorities will use a single Application Protocol Parameter entry in the TLV with appropriate bits set in user_priority_map field Application Protocol TLV F igure 15 shows the Application Protocol parameter structure that is used in the FCoE Application Feature TLV. struct DCBXapplication_protocol { u16 application_protocol_id; u8 upper_6_bits_oui:6; /* OUI = 0x001B21 */ u8 selector_field: 2; u16 lower_16_bits_oui; /* OUI = 0x001B21*/ u8 user_priority_map :8; }; Figure 15 - Application Protocol Parameters Structure A node can announce support for multiple protocols in single Application Protocol TLV using one application protocol parameter structure for each protocol advertized. Following example shows Application Protocol TLV carrying two protocol declarations: 32
33 16 bits Type = 4 Length= 16 Oper_Version Max_Version E N E W Reserved Sub_Type = 0 R Application1_Value Application1_Value Application 1 Application1_Value Application2_Value Application2_Value Application 2 Application2_Value Figure 16 Example Application Protocol TLV with Multiple Protocols As stated earlier, multiple Application Protocol Parameters may be contained in a single Application Protocol TLV. The Enable, Willing and Error bits apply to the Application Protocol TLV as a whole. These bits have the following semantics: - The "Enable" setting applies to all of the Application Protocol Parameters. - The "Willing" setting applies to all of the Application Protocol Parameters Application Protocol Parameter Comparison For any protocol requiring bi-directional communication in the priority there needs to be intersection between priority map declared in the Application Protocol Parameter. When both peers have the same Willing value, the "Error" bit is set when there is a bitmap field mismatch in one or more Application Protocol Parameters common to both peers. When a node receives peer announcement of an Application Protocol that is not supported by it, a management notification should be issued (regardless of the Willing settings of both peers). However Error bit is not set in this case. Mismatch is expected to be notified to management entities on both sides. Further action on mismatch is beyond scope for this document. 33
Rev 1.01. Priority Grouping for DCB Networks (Enhanced Transmission Selection) Data Center Bridging Revision 1.01 Author.
Task Group Data Center Bridging Revision 1.01 Author Manoj Wadekar (Qlogic), et al Priority Grouping for DCB Networks (Enhanced Transmission Selection) Rev 1.01 1 Priority Grouping for DCB Networks (ETS)
Chapter 46 Link Layer Discovery Protocol (LLDP)
Chapter 46 Link Layer Discovery Protocol (LLDP) Introduction...46-3 LLDP Overview...46-3 Type Length Values... 46-4 Transmission and Reception... 46-5 Storing LLDP Information... 46-7 Configuring LLDP...46-9
Network Discovery Protocol LLDP and LLDP- MED
Network LLDP and LLDP- MED Prof. Vahida Z. Attar College of Engineering, Pune Wellesely Road, Shivajinagar, Pune-411 005. Maharashtra, INDIA Piyush chandwadkar College of Engineering, Pune Wellesely Road,
Network Discovery Protocol LLDP and LLDP- MED
Network LLDP and LLDP- MED Prof. Vahida Z. Attar College of Engineering, Pune Wellesely Road, Shivajinagar, Pune-411 005. Maharashtra, INDIA Piyush chandwadkar College of Engineering, Pune Wellesely Road,
How To Configure Voice Vlan On An Ip Phone
1 VLAN (Virtual Local Area Network) is used to logically divide a physical network into several broadcast domains. VLAN membership can be configured through software instead of physically relocating devices
Network Configuration Example
Network Configuration Example Configuring DCBX Application Protocol TLV Exchange Published: 2014-01-10 Juniper Networks, Inc. 1194 North Mathilda Avenue Sunnyvale, California 94089 USA 408-745-2000 www.juniper.net
802.1Qbv: Dynamic Configuration of Scheduling Windows
802.1Qbv: Dynamic Configuration of Scheduling Windows Rodney Cummings National Instruments Franz-Josef Goetz Siemens AG Agenda Need for dynamic configuration of 802.1Qbv Which existing protocol? Technical
Link Layer Discovery Protocol
12 Link Layer Discovery Protocol Contents Overview..................................................... 12-2 LLDP..................................................... 12-2 LLDP Messages............................................
Configuring LLDP, LLDP-MED, and Location Service
27 CHAPTER Configuring LLDP, LLDP-MED, and Location Service This chapter describes how to configure the Link Layer Discovery Protocol (LLDP), LLDP Media Endpoint Discovery (LLDP-MED), and Location Service
A Link Layer Discovery Protocol Fuzzer
The University of Texas at Austin, Department of Computer Sciences, Technical Report TR-07-24 A Link Layer Discovery Protocol Fuzzer Jeremy Hollander Department of Computer Sciences The University of Texas
Link Layer Discovery Protocol and MIB
Link Layer Discovery Protocol and MIB v0.0 Paul Congdon 3/7/02 Acknowledgements This document is heavily leveraged from an Internet-Draft developed for the IETF PTOPO working group. The original draft,
Accelerating Development and Troubleshooting of Data Center Bridging (DCB) Protocols Using Xgig
White Paper Accelerating Development and Troubleshooting of The new Data Center Bridging (DCB) protocols provide important mechanisms for enabling priority and managing bandwidth allocations between different
A Dell Technical White Paper Dell PowerConnect Team
Flow Control and Network Performance A Dell Technical White Paper Dell PowerConnect Team THIS WHITE PAPER IS FOR INFORMATIONAL PURPOSES ONLY, AND MAY CONTAIN TYPOGRAPHICAL ERRORS AND TECHNICAL INACCURACIES.
Data Center Bridging. IEEE 802 Tutorial 12 th November 2007
Data Center Bridging IEEE 802 Tutorial 12 th November 2007 Contributors and Supporters Hugh Barrass Jan Bialkowski Bob Brunner Craig Carlson Mukund Chavan Rao Cherukuri Uri Cummings Norman Finn Anoop Ghanwani
Ethernet Virtual Bridging Automation Use Cases
Ethernet Virtual Bridging Automation Use Cases Renato Recio, Sivakumar Krishnasamy and Rakesh Sharma Abstract Managing the Ethernet switches is a complex task in today s Data Centers, as a lot of network
Intel Ethernet Switch Converged Enhanced Ethernet (CEE) and Datacenter Bridging (DCB) Using Intel Ethernet Switch Family Switches
Intel Ethernet Switch Converged Enhanced Ethernet (CEE) and Datacenter Bridging (DCB) Using Intel Ethernet Switch Family Switches February, 2009 Legal INFORMATION IN THIS DOCUMENT IS PROVIDED IN CONNECTION
How To Switch In Sonicos Enhanced 5.7.7 (Sonicwall) On A 2400Mmi 2400Mm2 (Solarwall Nametra) (Soulwall 2400Mm1) (Network) (
You can read the recommendations in the user, the technical or the installation for SONICWALL SWITCHING NSA 2400MX IN SONICOS ENHANCED 5.7. You'll find the answers to all your questions on the SONICWALL
L2 / L3 Switches. Link Layer Discovery Protocol (LLDP) Configuration Guide
L2 / L3 Switches Link Layer Discovery Protocol (LLDP) Configuration Guide Revision 1.0 The information in this USER S MANUAL has been carefully reviewed and is believed to be accurate. The vendor assumes
iscsi Top Ten Top Ten reasons to use Emulex OneConnect iscsi adapters
W h i t e p a p e r Top Ten reasons to use Emulex OneConnect iscsi adapters Internet Small Computer System Interface (iscsi) storage has typically been viewed as a good option for small and medium sized
Can PowerConnect Switches Be Used in IP Multicast Networks?
PowerConnect Application Note #6 January 2004 Can PowerConnect Switches Be Used in IP Multicast Networks? This Application Note relates to the following Dell PowerConnect products: PowerConnect 33xx PowerConnect
Computer Network. Interconnected collection of autonomous computers that are able to exchange information
Introduction Computer Network. Interconnected collection of autonomous computers that are able to exchange information No master/slave relationship between the computers in the network Data Communications.
Cisco Datacenter 3.0. Datacenter Trends. David Gonzalez Consulting Systems Engineer Cisco
Cisco Datacenter 3.0 Datacenter Trends David Gonzalez Consulting Systems Engineer Cisco 2009 Cisco Systems, Inc. All rights reserved. Cisco Public 1 Agenda Data Center Ethernet (DCE) Fiber Channel over
CCNA R&S: Introduction to Networks. Chapter 5: Ethernet
CCNA R&S: Introduction to Networks Chapter 5: Ethernet 5.0.1.1 Introduction The OSI physical layer provides the means to transport the bits that make up a data link layer frame across the network media.
Gigabit Ethernet MAC. (1000 Mbps Ethernet MAC core with FIFO interface) PRODUCT BRIEF
Gigabit Ethernet MAC (1000 Mbps Ethernet MAC core with FIFO interface) PRODUCT BRIEF 1. INTRODUCTION This document serves as a product info for the Gigabit Ethernet MAC from Hitek Systems. The core supports
Converging Data Center Applications onto a Single 10Gb/s Ethernet Network
Converging Data Center Applications onto a Single 10Gb/s Ethernet Network Explanation of Ethernet Alliance Demonstration at SC10 Contributing Companies: Amphenol, Broadcom, Brocade, CommScope, Cisco, Dell,
IP - The Internet Protocol
Orientation IP - The Internet Protocol IP (Internet Protocol) is a Network Layer Protocol. IP s current version is Version 4 (IPv4). It is specified in RFC 891. TCP UDP Transport Layer ICMP IP IGMP Network
VXLAN: Scaling Data Center Capacity. White Paper
VXLAN: Scaling Data Center Capacity White Paper Virtual Extensible LAN (VXLAN) Overview This document provides an overview of how VXLAN works. It also provides criteria to help determine when and where
A Packet Forwarding Method for the ISCSI Virtualization Switch
Fourth International Workshop on Storage Network Architecture and Parallel I/Os A Packet Forwarding Method for the ISCSI Virtualization Switch Yi-Cheng Chung a, Stanley Lee b Network & Communications Technology,
Abstract. Avaya Solution & Interoperability Test Lab
Avaya Solution & Interoperability Test Lab Sample Configuration for using Link Layer Discovery Protocol (LLDP) with Cisco Catalyst 4500 or 3750 Switches for VLAN assignment to Avaya 4600 Series IP Telephones
G.8032 Ethernet Ring Protection Overview. March, 2008 ITU-T Q9 SG 15
G.80 Ethernet Ring Protection Overview March, 008 ITU-T Q9 SG 5 genda G.80 Recommendation Introduction G.80 Objectives and Principles G.80 Concepts G.80 Protection Switching G.80 R-PS Messages G.80 Items
Simple Network Management Protocol
56 CHAPTER Chapter Goals Discuss the SNMP Management Information Base. Describe SNMP version 1. Describe SNMP version 2. Background The (SNMP) is an application layer protocol that facilitates the exchange
Ethernet: THE Converged Network Ethernet Alliance Demonstration as SC 09
Ethernet: THE Converged Network Ethernet Alliance Demonstration as SC 09 Authors: Amphenol, Cisco, Dell, Fulcrum Microsystems, Intel, Ixia, JDSU, Mellanox, NetApp, Panduit, QLogic, Spirent, Tyco Electronics,
Objectives. The Role of Redundancy in a Switched Network. Layer 2 Loops. Broadcast Storms. More problems with Layer 2 loops
ITE I Chapter 6 2006 Cisco Systems, Inc. All rights reserved. Cisco Public 1 Objectives Implement Spanning Tree Protocols LAN Switching and Wireless Chapter 5 Explain the role of redundancy in a converged
Transport Layer Protocols
Transport Layer Protocols Version. Transport layer performs two main tasks for the application layer by using the network layer. It provides end to end communication between two applications, and implements
Ajay Gummalla-July 2001
DOCSIS Overview Ajay Gummalla Ethernet in the First Mile Study Group July 2001 Ajay Gummalla-July 2001 1 HFC Plant Topology VIDEO combiner Fiber TX Fiber Fiber RX Tap CMTS Fiber RX Fiber Fiber TX 2way
Channel Bonding in DOCSIS 3.0. Greg White Lead Architect Broadband Access CableLabs
Channel Bonding in DOCSIS 3.0 Greg White Lead Architect Broadband Access CableLabs Agenda DS Channel Bonding Protocol Receive Channel Profiles US Channel Bonding Protocol HFC Plant Topologies & Resolution
HARTING Ha-VIS Management Software
HARTING Ha-VIS Management Software People Power Partnership HARTING Management Software Network Management Automation IT - with mcon Switches from HARTING With the Ha-VIS mcon families, HARTING has expanded
Easy Smart Configuration Utility
Easy Smart Configuration Utility REV1.1.0 1910010977 CONTENTS Chapter 1 About this Guide...1 1.1 Intended Readers... 1 1.2 Conventions... 1 1.3 Overview of This Guide... 1 Chapter 2 Getting Started...4
June 2006. Bridge & Switch. Pietro Nicoletti Piero[at]studioreti.it. Bridge-Switch-Engl - 1 P. Nicoletti: see note pag. 2
Bridge & Switch Pietro Nicoletti Piero[at]studioreti.it Bridge-Switch-Engl - P. Nicoletti: see note pag. Copyright note These slides are protected by copyright and international treaties. The title and
TOP Server DNP 3.0 Suite. Background & Best Practices
TOP Server DNP 3.0 Suite Background & Best Practices Page 2 of 31 Table of Contents OVERVIEW 4 BACKGROUND 5 TECHNICAL DNP PROTOCOL INFORMATION 6 Master and Outstation Databases 6 Layering 7 Device Addressing
Protocols and Architecture. Protocol Architecture.
Protocols and Architecture Protocol Architecture. Layered structure of hardware and software to support exchange of data between systems/distributed applications Set of rules for transmission of data between
Communications and Computer Networks
SFWR 4C03: Computer Networks and Computer Security January 5-8 2004 Lecturer: Kartik Krishnan Lectures 1-3 Communications and Computer Networks The fundamental purpose of a communication system is the
(Refer Slide Time: 1:17-1:40 min)
Computer Networks Prof. S. Ghosh Department of Computer Science and Engineering Indian Institute of Technology, Kharagpur Lecture # 37 Network management Good day, so today we will talk about network management.
enetworks TM IP Quality of Service B.1 Overview of IP Prioritization
encor! enetworks TM Version A, March 2008 2010 Encore Networks, Inc. All rights reserved. IP Quality of Service The IP Quality of Service (QoS) feature allows you to assign packets a level of priority
2. IP Networks, IP Hosts and IP Ports
1. Introduction to IP... 1 2. IP Networks, IP Hosts and IP Ports... 1 3. IP Packet Structure... 2 4. IP Address Structure... 2 Network Portion... 2 Host Portion... 3 Global vs. Private IP Addresses...3
Management Software. Web Browser User s Guide AT-S106. For the AT-GS950/48 Gigabit Ethernet Smart Switch. Version 1.0.0. 613-001339 Rev.
Management Software AT-S106 Web Browser User s Guide For the AT-GS950/48 Gigabit Ethernet Smart Switch Version 1.0.0 613-001339 Rev. A Copyright 2010 Allied Telesis, Inc. All rights reserved. No part of
Data Center Converged And Virtual Ethernet Switching DC CAVES - Introduction
Data Center Converged And Virtual Ethernet Switching DC CAVES - Introduction Renato Recio Thanks to our Host - Prosper Chemouil and Orange Labs Program Committee Thanks for your help Thierry Coupaye, Orange
Data Center Bridging Plugfest
Data Center Bridging Plugfest November 2010 Page 1 Table of Contents 1 Introduction & Background Error! Bookmark not defined. 1.1 Introduction... 4 1.2 DCB Plugfest Objectives and Participants... 4 1.3
Computer Networks. Chapter 5 Transport Protocols
Computer Networks Chapter 5 Transport Protocols Transport Protocol Provides end-to-end transport Hides the network details Transport protocol or service (TS) offers: Different types of services QoS Data
Application Protocols for TCP/IP Administration
Application Protocols for TCP/IP Administration BootP, TFTP, DHCP Agenda BootP TFTP DHCP BootP, TFTP, DHCP, v4.4 2 Page 60-1 BootP (RFC 951, 1542, 2132) BootP was developed to replace RARP capabilities
The ABCs of Spanning Tree Protocol
The ABCs of Spanning Tree Protocol INTRODUCTION In an industrial automation application that relies heavily on the health of the Ethernet network that attaches all the controllers and computers together,
CHAPTER 10 LAN REDUNDANCY. Scaling Networks
CHAPTER 10 LAN REDUNDANCY Scaling Networks CHAPTER 10 10.0 Introduction 10.1 Spanning Tree Concepts 10.2 Varieties of Spanning Tree Protocols 10.3 Spanning Tree Configuration 10.4 First-Hop Redundancy
Implementing and testing tftp
CSE123 Spring 2013 Term Project Implementing and testing tftp Project Description Checkpoint: May 10, 2013 Due: May 29, 2013 For this project you will program a client/server network application in C on
Current Trends of Topology Discovery in OpenFlow-based Software Defined Networks
1 Current Trends of Topology Discovery in OpenFlow-based Software Defined Networks Leonardo Ochoa-Aday, Cristina Cervello -Pastor, Member, IEEE, and Adriana Ferna ndez-ferna ndez Abstract The explosion
Using Link Layer Discovery Protocol in Multivendor Networks
Using Link Layer Discovery Protocol in Multivendor Networks Link Layer Discovery Protocol (LLDP), standardized by the IEEE as part of 802.1ab, enables standardized discovery of nodes, which in turn facilitates
Data Center Convergence. Ahmad Zamer, Brocade
Ahmad Zamer, Brocade SNIA Legal Notice The material contained in this tutorial is copyrighted by the SNIA unless otherwise noted. Member companies and individual members may use this material in presentations
3G Converged-NICs A Platform for Server I/O to Converged Networks
White Paper 3G Converged-NICs A Platform for Server I/O to Converged Networks This document helps those responsible for connecting servers to networks achieve network convergence by providing an overview
The new frontier of the DATA acquisition using 1 and 10 Gb/s Ethernet links. Filippo Costa on behalf of the ALICE DAQ group
The new frontier of the DATA acquisition using 1 and 10 Gb/s Ethernet links Filippo Costa on behalf of the ALICE DAQ group DATE software 2 DATE (ALICE Data Acquisition and Test Environment) ALICE is a
Data Center Bridging Attributes. John Fastabend LAN Access Division, Intel Corp.
Data Center Bridging Attributes John Fastabend LAN Access Division, Intel Corp. Agenda History & Background Knowledge Use Cases (Do we need a single API) DCB Infrastructure net_device model DCB Infrastructure
Performance Evaluation of the RDMA over Ethernet (RoCE) Standard in Enterprise Data Centers Infrastructure. Abstract:
Performance Evaluation of the RDMA over Ethernet (RoCE) Standard in Enterprise Data Centers Infrastructure Motti Beck Director, Marketing [email protected] Michael Kagan Chief Technology Officer [email protected]
A Transport Protocol for Multimedia Wireless Sensor Networks
A Transport Protocol for Multimedia Wireless Sensor Networks Duarte Meneses, António Grilo, Paulo Rogério Pereira 1 NGI'2011: A Transport Protocol for Multimedia Wireless Sensor Networks Introduction Wireless
Abstract. Avaya Solution & Interoperability Test Lab
Avaya Solution & Interoperability Test Lab Sample Configuration for using Link Layer Discovery Protocol (LLDP) with Cisco Catalyst 4500 or 3750 Switches for VLAN Assignment for Avaya 9600 and 1600 Series
Ethernet. Ethernet. Network Devices
Ethernet Babak Kia Adjunct Professor Boston University College of Engineering ENG SC757 - Advanced Microprocessor Design Ethernet Ethernet is a term used to refer to a diverse set of frame based networking
Data Link Layer(1) Principal service: Transferring data from the network layer of the source machine to the one of the destination machine
Data Link Layer(1) Principal service: Transferring data from the network layer of the source machine to the one of the destination machine Virtual communication versus actual communication: Specific functions
Virtual LANs. http://www.cis.ohio-state.edu/~jain/cis788-97/ or http://www.netlab.ohio-state.edu/~jain/cis788-97/ Raj Jain
Virtual LANs Professor of Computer and Information Sciences Please download and print the handouts from: http://www.cis.ohio-state.edu/~jain/cis788-97/ or http://www.netlab.ohio-state.edu/~jain/cis788-97/
Route Discovery Protocols
Route Discovery Protocols Columbus, OH 43210 [email protected] http://www.cse.ohio-state.edu/~jain/ 1 Overview Building Routing Tables Routing Information Protocol Version 1 (RIP V1) RIP V2 OSPF
Traffic monitoring with sflow and ProCurve Manager Plus
An HP ProCurve Networking Application Note Traffic monitoring with sflow and ProCurve Manager Plus Contents 1. Introduction... 3 2. Prerequisites... 3 3. Network diagram... 3 4. About the sflow protocol...
A304a: Understanding User Needs for Field Management Stations Part 1 Object Definitions for Signal System Masters (SSM) Based on NTCIP 1210 Standard
A304a: Understanding User Needs for Field Management Stations Part 1 Object Definitions for Signal System Masters (SSM) Based on NTCIP 1210 Standard Table of Contents Introduction/Purpose... 2 SSM User
Performance Analysis and Improvement of Topology Discovery Protocols in Home Networks
Master of Science Thesis Performance Analysis and Improvement of Topology Discovery Protocols in Home Networks 13 July, 2011 Erik German Diaz Castellanos (4053265) Committee Members: Supervisors: Prof.
Chapter 7 Configuring Trunk Groups and Dynamic Link Aggregation
Chapter 7 Configuring Trunk Groups and Dynamic Link Aggregation This chapter describes how to configure trunk groups and 802.3ad link aggregation. Trunk groups are manually-configured aggregate links containing
Local Area Networks transmission system private speedy and secure kilometres shared transmission medium hardware & software
Local Area What s a LAN? A transmission system, usually private owned, very speedy and secure, covering a geographical area in the range of kilometres, comprising a shared transmission medium and a set
Fibre Channel over Ethernet: Enabling Server I/O Consolidation
WHITE PAPER Fibre Channel over Ethernet: Enabling Server I/O Consolidation Brocade is delivering industry-leading oe solutions for the data center with CNAs, top-of-rack switches, and end-of-row oe blades
Network Basics GRAPHISOFT. for connecting to a BIM Server. 2009 (version 1.0)
for connecting to a BIM Server GRAPHISOFT 2009 (version 1.0) Basic Vocabulary...3 Local Area Networks...5 Examples of Local Area Networks...5 Example 1: LAN of two computers without any other network devices...5
ADMINISTRATION GUIDE Cisco Small Business 300 Series Managed Switch Administration Guide
ADMINISTRATION GUIDE Cisco Small Business 300 Series Managed Switch Administration Guide 10/100 Switches SF 300-08, SF 302-08, SF 302-08MP, SF 302-08P, SF 300-24, SF 300-24P, SF 300-48, SF 300-48P Gigabit
Cisco Nexus 5548UP. Switch Configuration Guide for Dell PS Series SANs. A Dell Deployment and Configuration Guide
Cisco Nexus 5548UP Switch Configuration Guide for Dell PS Series SANs Dell Storage Engineering October 2015 A Dell Deployment and Configuration Guide Revisions Date February 2013 October 2013 March 2014
Chapter 3. TCP/IP Networks. 3.1 Internet Protocol version 4 (IPv4)
Chapter 3 TCP/IP Networks 3.1 Internet Protocol version 4 (IPv4) Internet Protocol version 4 is the fourth iteration of the Internet Protocol (IP) and it is the first version of the protocol to be widely
Best Practice and Deployment of the Network for iscsi, NAS and DAS in the Data Center
Best Practice and Deployment of the Network for iscsi, NAS and DAS in the Data Center Samir Sharma, Juniper Networks Author: Samir Sharma, Juniper Networks SNIA Legal Notice The material contained in this
Applications. Network Application Performance Analysis. Laboratory. Objective. Overview
Laboratory 12 Applications Network Application Performance Analysis Objective The objective of this lab is to analyze the performance of an Internet application protocol and its relation to the underlying
Configure IOS Catalyst Switches to Connect Cisco IP Phones Configuration Example
Configure IOS Catalyst Switches to Connect Cisco IP Phones Configuration Example Document ID: 69632 Introduction Prerequisites Requirements Components Used Conventions Background Information Configure
Kaseya 2. User Guide. Version R8. English
Kaseya 2 Discovery User Guide Version R8 English September 19, 2014 Agreement The purchase and use of all Software and Services is subject to the Agreement as defined in Kaseya s Click-Accept EULATOS as
Converged Data Center. Black Book. Edition 10. Converged Data Center. http://www.ixiacom.com/blackbook June 2014. PN 915-2603-01 Rev H June 2014 i
Converged Data Center Black Book Edition 10 Converged Data Center http://www.ixiacom.com/blackbook June 2014 PN 915-2603-01 Rev H June 2014 i Converged Data Center Your feedback is welcome Our goal in
Time-based Updates in OpenFlow: A Proposed Extension to the OpenFlow Protocol
CCIT Report #835, July 2013, EE Pub No. 1792, Technion, Israel 1 Time-based Updates in : A Proposed Extension to the Protocol Tal Mizrahi, Yoram Moses Department of Electrical Engineering Technion Israel
Managing Dynamic Configuration
White Paper Immediate Network Synchronization with Low Overhead: Cisco Prime Network Reduced Polling VNE Cisco Prime Network's near real-time model relies on accurate information about the managed network
CMA5000 SPECIFICATIONS. 5710 Gigabit Ethernet Module
CMA5000 5710 Gigabit Ethernet Module SPECIFICATIONS General Description The CMA5710 Gigabit Ethernet application is a single slot module that can be used in any CMA 5000. The Gigabit Ethernet test module
Exam 1 Review Questions
CSE 473 Introduction to Computer Networks Exam 1 Review Questions Jon Turner 10/2013 1. A user in St. Louis, connected to the internet via a 20 Mb/s (b=bits) connection retrieves a 250 KB (B=bytes) web
2 nd Data Center Converged And Virtual Ethernet Switching DC CAVES - Introduction
2 nd Data Center Converged And Virtual Ethernet Switching DC CAVES - Introduction Renato Recio Program Committee Thanks for your help Thierry Coupaye, Orange Labs, France Uri Elzur, Broadcom Corporation,
Modbus and ION Technology
70072-0104-14 TECHNICAL 06/2009 Modbus and ION Technology Modicon Modbus is a communications protocol widely used in process control industries such as manufacturing. PowerLogic ION meters are compatible
DEPLOYING IP TELEPHONY WITH EX SERIES ETHERNET SWITCHES
APPLICATION NOTE DEPLOYING IP TELEPHONY WITH EX SERIES ETHERNET SWITCHES Optimizing Applications with Juniper Networks Access Switches Copyright 2011, Juniper Networks, Inc. 1 Table of Contents Introduction.....................................................................................................3
JOINT TACTICAL RADIO SYSTEM - APPLICATION PROGRAMMING INTERFACES
JOINT TACTICAL RADIO SYSTEM - APPLICATION PROGRAMMING INTERFACES Cinly Magsombol, Chalena Jimenez, Donald R. Stephens Joint Program Executive Office, Joint Tactical Radio Systems Standards San Diego, CA
Dell Networking S5000: The Building Blocks of Unified Fabric and LAN/SAN Convergence. Technical Whitepaper
Dell Networking S5000: The Building Blocks of Unified Fabric and LAN/SAN Convergence Dell Technical Marketing Data Center Networking May 2013 THIS DOCUMENT IS FOR INFORMATIONAL PURPOSES ONLY AND MAY CONTAIN
Fiber Channel Over Ethernet (FCoE)
Fiber Channel Over Ethernet (FCoE) Using Intel Ethernet Switch Family White Paper November, 2008 Legal INFORMATION IN THIS DOCUMENT IS PROVIDED IN CONNECTION WITH INTEL PRODUCTS. NO LICENSE, EXPRESS OR
How To Test For 10 Gigabit Ethernet At 10 Gb/S
White Paper Testing Scenarios for Ethernet at 10 Gb/s By Guylain Barlow Introduction As a natural evolution, the typical test concepts borrowed from lower-rate Ethernet apply to 10 Gigabit Ethernet (GigE).
Ethernet Fabric Requirements for FCoE in the Data Center
Ethernet Fabric Requirements for FCoE in the Data Center Gary Lee Director of Product Marketing [email protected] February 2010 1 FCoE Market Overview FC networks are relatively high cost solutions
