Server time protocol messages methods

(54) Title: METHOD, EQUIPMENT AND COMPUTER PROGRAM FOR SERVER TIME PROTOCOL (30) Unionist Priority: 31/01/2007 us 60 / 887,512 (73) Holder (s): International Business Machines

CORPORATION (72) Inventor (s): denise sevigny, dennis j. dahlen, DONALD CRABTREE, JUDITH WIERBOWSKI, MICHEL HACK, NOSHIR DHONDY, Ronald Smith, Scott Carlson (74) Attorney (s): Ricardo de Andrade Bergamo da Silva (86) International Request: pct ep2008050482 of 17/01/2008 (87) International Publication: wo 2008 / 092747de 07/08/2008 (57) Summary: method, equipment and program of COMPUTER FOR SERVER TIME PROTOCOL. Server time protocol (STP) messages and exchange methods are provided to facilitate the synchronization of processing units on a jointly operated network. STP messages include time and response exchange (XTP) parameter commands and STP control and response (STC) commands. XTP message exchange processing includes: generating an XTP message command on a first processing unit including one set by the first processing unit and a time stamp receiving command that is disarmed by the first processing unit; transmit the XTP message command to a second processing unit: set the time stamp field to receive command on the XTP command with the time the XTP command is received on the second processing unit; and generating a message response from the XTP in the second processing unit, the message response including the time stamp transmitting command set by the first processing unit and the time stamp receiving command defined by the second processing unit.

<img file="BRPI0806401A2_D0001.tif" />

-1/52-

<img file="BRPI0806401A2_D0002.tif" />

METHOD, EQUIPMENT AND COMPUTER PROGRAM FOR SERVER TIME PROTOCOL

TECHNICAL FIELD

The present invention relates in general to time synchronization within and across a network of processing units, and in particular to messages and methods of the server time protocol that facilitate servers in a network operating together to synchronize. , for example, with the same main reference root time.

BACKGROUND OF THE INVENTION

For performance and data integrity reasons, systems that access shared data, such as SYSPLEX computing offered by the International Business Machines Corporation, Armonk, New York, must be able to maintain the time of day (TOD) clock synchronization with an accuracy that is best of the best communication process time between systems.

Currently, an example, to satisfy the synchronization requirements, a timer, such as the IBM ® 9037 SYSPLEX timer, is used. This timer requires expensive dedicated Timing links and a separate external box.

Other networks, such as timing network protocol (NTP), provide time synchronization, but do not meet the precision requirements of high-quality systems. NTP requires that each server has access to an external source of time that provides precision to a micro-second level in order to ensure all servers synchronize at the same time. This is an issue for systems that do not have an ability to attach to external time servers that provide that level of accuracy.

In addition, a requirement for GPS receivers or a similar attachment in each system can be considered in computational, for reasons of maintenance, safety and reliability.

-2 / 52SUMMARY OF THE INVENTION

The deficiencies of the prior art are overcome and additional advantages are provided by providing a method of exchanging messages to facilitate the synchronization of units in a processing time network. The method includes: generating a message command changes time parameters (XTP) in a first processing unit, the XTP message command, including a message command transmitting the set of timestamp fields, the first processing unit and a message command receive timestamp field which is unset by the first processing unit; transmitting the XTP message command to a second processing unit; timestamp field in the XTP command message with the time that the XTP message command is received in the second processing unit; of receiving the configuration message command and generating an XTP message response, the second processing unit, the XTP message response, including the message command transmit timestamp set by the first processing unit and the message command receive timestamp time defined by the second processing unit obtained from the XTP message command.

System and the computer program products corresponding to the methods summarized above are also described and claimed here.

Additional advantages and features are realized through techniques of the present invention. Other embodiments and aspects of the invention are described in detail here and are considered a part of the claimed invention.

BRIEF DESCRIPTION OF THE DRAWINGS

The subject that is considered as the invention is particularly noted and distinctly claimed in the claim when the specification was completed. The precedents and other objects, functionalities and advantages of

-3 / 52invention the following detailed description results in conjunction with the accompanying drawings in which:

Fig. 1A illustrates an example of a coordinated calendar mixed network to incorporate one or more aspects of the present invention,

Fig. 1B illustrates an example of an STP-only network to incorporate one or more aspects of the present invention;

Fig. 2 shows an example of a stratum-1 configuration information block, in accordance with an aspect of the present invention;

Fig. 3 illustrates an example of a new block of configuration information stratum 1, in accordance with an aspect of the present invention

Fig. 4 is a flowchart of a personification of the XTP message command processing, according to an aspect of the present invention;

Fig. 5 depicts a personification of an XTP command 15 format message, in accordance with an aspect of the present invention;

Fig. 6 is a flowchart of a message response from the XTP transformation, according to an aspect of the present invention;

Fig. 7 depicts a response format in an XTP message, in accordance with an aspect of the present invention;

Fig. 8 depicts a personification of the XTP message response data format, according to an aspect of the present invention;

Fig. 9 depicts another embodiment of the response data format of the XTP message, according to an aspect of the present invention;

Fig. 10 depicts yet another embodies an XTP data format 25 response message, in accordance with an aspect of the present invention;

-4 / 52FIGS. 11A &amp; 11B depict an XTP message command transmitting the process, in accordance with an aspect of the present invention

Fig. 12 is a flowchart of an embodied transformation associated with a response message from the XTP transmitting the procedure, in accordance with an aspect of the present invention;

Fig. 13 depicts a personification of the STP control message (STC) command format, in accordance with an aspect of the present invention;

Fig. 14 depicts a response format embodying an STC message, in accordance with an aspect of the present invention;

Fig. 15 depicts an embodiment of a new block of configuration information layer 1, in accordance with an aspect of the present invention;

Fig. 16A illustrates an example of a read-CTN response parameter in a dependent operating area format, according to an aspect of the present invention

Fig. 16B illustrates an example of a reading-CTN-parameters-general-parameters-data area format, according to an aspect of the present invention;

Fig. 17A depicts an embodiment of an STP path command in a dependent operating area format, in accordance with an aspect of the present invention to establish;

Fig. 17B depicts an embodiment of an acquisition arbitrator set response in a dependent operating area format, in accordance with an aspect of the present invention;

-5 / 52Fig. 18 depicts one embodies a processing environment to incorporate one or more aspects of the present invention;

Fig. 19 depicts more details of the memory in fig. 18, in accordance with an aspect of the present invention; and

Fig. 20 illustrates an example of a computer program product to incorporate one or more aspects of the present invention.

BEST MODE FOR CARRYING OUT THE INVENTION

In accordance with an aspect of the present invention, server time protocol (STP) messages and processing methods employing the same are provided to, for example, transfer calendar information between two servers on a calendar network to facilitate synchronization of your. Exchange time parameter (XTP) messages and STP control (STC) messages are described.

Although several networks can be configured to include a tier 1 server, one such network is a coordinated timing network (CTN). In a coordinated timing network, several different computing systems maintain time synchronization to form the coordinated timing network. Coordinate timing network systems employ a message based protocol, referred to as a Server Time

Protocol (STP), to pass timekeeping information between systems over existing, high-speed data links. This allows the time of day (TOD) clocks on each system to be synchronized with the accuracy required in today's high-end computing systems. Since the protocol makes use of technology within a computer system, precision synchronization scales as technology improves. A computer system that provides an STP mechanism is referred to as a time or server here.

-6 / 52A server defined in a CTN as a primary time server provides a primary reference time for the CTN. The server in a CTN, which determines the CST (a clock estimate (TOD) time of day for the CTN) based on information from another server, the CTN is called a secondary time server. The primary time server can obtain its time from an external time source, which provides the means to synchronize the time of day clocks on a CTN with a defined time pattern.

Servers in a CTN, which are in the synchronized state, receive a value, referred to as a stratum level, which specifies the number of servers between it and a primary time server. A primary time server operates at a stratum level of 1; Secondary time servers operate at a stratum level of 2 or higher, which increases as the number of servers in the stratum-1 increases calendar path. In general, the quality of timekeeping information decreases as stratum level increases. The server that is not synchronized is assigned a layer level of 0.

The STP facility provides the necessary procedures for transmitting, receiving and processing STP messages. STP messages are transmitted over one or more physical data links between servers. The data link that has been established between two servers is called an STP path. The STP facility provides facilities for establishing and maintaining STP paths.

STP messages include a message command and a message response. Two types of STP messages are supported. The exchange time parameters message (XTP) and the STP control message (STC). The XTP message is used to exchange the timekeeping information used to determine CST for CTN. STP control messages are used to define and modify various CTN parameters required by servers in CTN.

-7 / 52You can operate a CTN, for example, as one of two types of configurations: as a mixed CTN configuration or as a STP-only CTN configuration. In a mixed CTN configuration, the servers are configured to be part of an external time reference network (ETR) and an STP network. In a mixed CTN configuration, the CTN servers are configured with the same, non-null ETR network ID and a timer (eg, 9037 SYSPLEX timer) provides the main time reference to CTN. At least one server in the CTN is stepping the timing signals provided by the SYSPLEX timer before synchronization can occur within the CTN. Non-backup servers for the syspiex timer are secondary time servers and achieve synchronization by exchanging STP signals, as described further below.

As an example, each backup server for the SYSPLEX timer Timing signals receives the time protocol parameters and propagates the information to secondary time servers in CTN, using, for example, a CTN parameter update procedure. An example of this process is described in US Serial No. 11 / 468,352, entitled “Coordinates Timing Network Configuration parameter Update internal”, Carlson et al., Presented on August 30, 2006.

An example of a mixed CTN 100 configuration is described with reference to Fig. 1. Mixed CTN 100 configuration includes, for example, a server one (102) tied to a local area network (104), a B Server (106) tied to the local area network (104) and a Server C (108) linked to a local network (110). Each server is, for example, a complex processing center based on az / architecture ® offered by the International Business Machines Corporation. Z ® architecture is a registered trademark of International Business Machines Corporation, Armonk, New York, USA. An embodiment of z / architecture ® is described in “z / architecture, principles of operation,” IBM publication does not. SA22-7832-04, September 2005.

-8 / 52Each local area network is tied to a console 120 used to provide time synchronization within the network. In addition, local network 104 and local area network 110 are linked to each other via a wide area network 112.

Servers A and B are tied to an external time reference network 114 and servers B and C are configured to integrate a network of STP 116. Server B is at a tier 1 level and server C is at a tier 2 level. STP 118 links are used to track the installation of STP from server B with the facility of STP Server c.

In an STP-only CTN, the CTN servers are configured to be part of an STP network and none are configured to be part of an ETR network. An example of a STP 150 only network is described with reference to Fig. 1. In this example, server one (152) and server B (154) are tied to a LAN (156) and server C (158) is tied to a LAN (160). Each of the servers includes an STP 162 mechanism and each installation is coupled to each other via one or more STP 164 links.

In addition, LAN 156 is tied to a console 170 and LAN LAN is tied to a console 172. Console 170 is even more tied to an external time source (ETS) 174, such as a dial out phone time service ( for example, acts: NIST automated computers time service). In this network, there is no ETR network. Server B has a stratum level 1, and servers A and C, have a stratum level of 2.

The server that is acting as a layer 1 server active on the network, as an STP-only network, is specified as part of a layer 1 configuration defined for the network. The stratum-1 configuration is maintained on each server in the network and provides information related to the network configuration, including, for example, the type of configuration defined for the network. The network can be configured as one of several types, including, for example:

-9 / 52a) null configuration - in a null configuration, a tier 1 server is not identified. The server remains unsynchronized, until it assigns to a server that has a non-null layer 1 configuration. The stratum configuration

1 on a server that is at tier 0 level it is equal to the null setting when, for example, it is not attached to any other server and the only CEC-CTN indicator in a tier-1 configuration information block, described below, is zero.

b) the only Server definition - in a single server definition, layer 1 configuration defines a single layer 1 primary server that acts as a layer 1 active server for CTN. The loss of the primary stratum 1 server results in the synchronized time loss in the CTN until a new stratum-1 configuration is specified on the console.

A single-tier 1 server configuration may also include an indication that the specified tier-1 server is the only server (for example, electronic complex computing (CEC) or (CPC)) to CTN and that no other or additional servers will do part of the CTN. In this case, the CTN is called a single CEC CTN. When a stratum-1 configuration indicates that it is a single CEC CTN, the configuration is a valid stratum-1 configuration for the initialized state of the server after a power over reset. When a single server layer 1 configuration does not specify that it is a single CEC CTN, the configuration is not a valid layer 1 configuration for the initialized state of the server after a power over reset and the layer 1 configuration is defined in null configuration.

c) dual server configuration - in a dual server configuration, the configuration includes a primary stratum-1 server and an alternate stratum-1 server. THE

-10 / 52Using a dual server configuration provides a mechanism for an alternate server to assume the role of tier-1 active server for CTN. The tier 1 alternate server, when configured with the same connectivity to other servers, the CTN, as the tier 1 primary server, can assume as the tier-1 active without interruption for the CTN synchronization feature. The tier 1 server (primary or alternate) that is acting as the tier 1 active server for a CTN is indicated in the tier 1 configuration information block maintained on each server in the CTN, as described below. The tier-1 server that is not the active tier 1 server is defined as the inactive tier 1 server.

The inactive tier 1 server in a dual server configuration resumes the role of the tier-1 active server when it detects an active tier 1 failure. An active layer 1 failure is detected in a dual server configuration when one of the following occurs:

• an assisted console recovery procedure is performed and indicates that a stratum-1 active failure has occurred, or • stratum 1 system check signal is recognized.

The inactive tier 1 server in a dual server configuration performs assisted console recovery when the inactive tier 1 server loses the attachment to the tier-1 active server.

d) triad configuration - in a triad configuration, layer 1 configuration includes a primary layer 1 server. an alternate tier-1 server and a server

-11 / 52of the referee. The definition of a triad configuration provides a mechanism for an alternate server to be able to assume the role of stratum-1 active server for CTN, as defined for a dual server configuration. In addition, the definition of an arbitrator server, when configured with primary stratum 1 alternate stratum 1 servers and connectivity, provides a mechanism for inactive stratum-1 and arbitrator servers to communicate with each other in order to determine that an active server failure has occurred stratum-1 and that the inactive stratum-1 must assume the active stratum 1 server.

Inactive layer 1 server in a triad configuration assumes the role of layer 1 active when it recognizes a layer 1 active fault. The inactive layer 1 server recognizes an active layer 1 failure when any of the following occurs;

• a triad recovery procedure is performed and indicates that a stratum 1 active failure has occurred.

• An assisted console recovery procedure is performed and indicates that an active layer 1 failure has occurred.

The inactive layer 1 server performs the triad recovery procedure when the following conditions occur:

• The inactive tier 1 server loses the attachment to the active tier 1 server and has an attachment for the referee.

-12/5225 • The inactive tier 1 server recognizes a tier 1 active communication timeout and has an attachment for the referee.

The inactive layer 1 server performs assisted console 5 recovery, when the inactive layer 1 server loses the attachment to the active layer 1 server and does not accompany the referee.

The inactive layer 1 server performs the process of acquiring active layer 1 to assume the role of the active layer 1 server for CTN.

The tier 1 active server in a triad configuration gives the role of the tier-1 active server when it detects that it has lost the attachment to the inactive tier 1 server and the referee server. The tier 1 active server performs a tier 1 active delivery procedure to abandon the role of the tier 1 active server for the CTN.

For example, stratum-1 configuration information is kept in a control block, referred to as a stratum-1 configuration information block (SCIB), which is stored on or accessible to each server on the network. The SCIB is used to identify the layer-1 configuration for a network.

One embodies a block of configuration information of layer 1 20 200 is described with reference to Fig. 2. Stratum-1 block of configuration information 200 includes, for example, the following fields:

a) single layer 1 node descriptor 202: this field is valid when a single server, dual server or triad definition has been specified in the configuration type field of the configuration information block, described below and when valid, includes the node descriptor of primary descriptor stratum 1 node.

-13 / 52b) alternate stratum 1 node descriptor 204: this field is valid when a dual server or triad definition has been specified in the configuration type field and when valid, includes the node descriptor of the alternate stratum server node descriptor -1.

c) Referee node descriptor 206: this field is valid when a triad definition has been specified in the configuration type field and includes the node descriptor of the referee server node descriptor.

d) Stratum-1 configuration timestamp: this field includes a timestamp indicating the time at which stratum-1 configuration information in this block became current on the server.

e) type of configuration (CType) 210: this field specifies the type of configuration of layer-1, as defined below:

• null definition - none of the node descriptors are valid.

• The single server definition - only the primary layer 1 node descriptor is valid.

• Definition of dual server: the main layer 1 layer 1 and alternative node descriptors are valid.

• Triad definition: The primary stratum-1, alternative stratum-1 and arbitrator node descriptors are valid.

f) activate layer 1 (A) 212: this field is valid when a dual server or triad definition has been specified and indicates

-14 / 52 if the tier 1 primary server or the tier-1 alternate server is tier 1 active server.

g) CEC single CTN (X) 214: this field is valid when the configuration type specifies a single server definition and when one, for example, indicates the CTN is a single CEC CTN. When the field is, for example, zero, the CTN is not a single CTN. CEC)

h) recovery configuration (R) 216: this field indicates whether the layer 1 configuration described by this block is the result of a layer 1 recovery action or a console command.

i) stratum 1 maximum short term distort rate change 218: this field includes a value that specifies the maximum possible change in the skew rate of the physical Osciiador on server 1 stratum that can occur during any specified period (for example, 60 seconds). This field is used to form a value that is in the same format as the base rate of direction. On machines that are not capable of executing the switching oscillator dynamic, the value is equal to the maximum frequency drift of stratum-1 oscillator that can occur during a specified period (for example, 60 seconds). On machines that are capable of executing the Oscillator switching dynamic, the value is defined as the maximum skew tolerance range specified for the Oscillator. For example, on a machine that supports dynamic Osciiador, alternating with Osciiador skew tolerance specified at / -2 ppm nominal frequency, the value is set to the equivalent of 4 ppm. A dynamic Oscillator switch occurs when the physical Oscillator used

-15 / 52 to drive the TOD clock system is switched from one oscillator to another.

In addition to the control block above, another control block, called the new layer-1 configuration information block (NSCIB), can be used to specify a new layer-1 configuration for CTN. In addition, it can be used to specify an update to the CTN ID to occur simultaneously with the stratum-1 configuration change.

For example, the NSCIB on a server is significant when the server is configured to be part of a STP-only CTN configuration or if the migration of STP bit in the NSCIB is equal to one.

One embodies a new layer of configuration information of layer 1 300 is described with reference to Fig. 3. New block of information of configuration of layer 1 300 includes, for example, the following fields;

a) single stratum 1 descriptor node 302; this field is valid when a single, double or triad definition server has been specified in the configuration type field and includes the node descriptor of new primary descriptor stratum 1 node.

b) alternate stratum 1 node descriptor 304: this field is valid when a dual server or triad definition has been specified in the type of configuration field and includes the node descriptor of new alternative node descriptor of stratum-1.

c) Referee in descriptor 306; this field is valid when a triad definition has been specified in the configuration type field and includes the new arbitrator node descriptor node descriptor.

d) stratum 1 Update Time 308 configuration: when the server is configured to be part of a single STP CTN,

-16 / 52This field includes a timestamp that indicates when the values ​​in this block should become current for CTN. When the server is not configured to be part of a single STP CTN, the field is meaningless.

e) type of configuration (CType) 310; this camp © specifies the type of stratum-1 configuration, as defined below: · null definition - none of the node descriptors are valid.

• The single server definition - only the primary layer 1 node descriptor is valid.

• Definition of dual server; the principal stratum 1 stratum 1 and alternative descriptors are valid.

• Triad definition: The primary stratum-1, alternative stratum-1 and arbitrator node descriptors are valid.

f) activates layer 1 (A) 312; this field is valid when a dual server or triad definition has been specified and indicates whether the primary server layer 1 or the alternate server layer 1 is layer 1 active server.

g) changing the CTN ID (C) 314; when the server is configured to be part of a single STN CTN, this field indicates whether a change to the CTN ID is being requested and the CTN ID is valid. The change occurs in the layer-1 configuration update time.

The CTN identification is a value that is used to identify a

CTN. The CTN ID includes, for example, an STP network ID and an ETR network number. The STP network ID identifies the STP network, if any, that is

-17 / 52configured for the server. The ETR network number identifies the ETR network number, if any, that is configured for this server.

h) STP (S) 316 migration configuration: this field is significant when, for example, the server is not configured as a STP-only CTN. The field indicates whether a STP-only migration layer 1 configuration has been defined for the server. When the field is, for example, one, the NSCIB includes the stratum-1 configuration to become current when the CTN ID on the server is changed to an STP-only configuration. When the field is zero, a STP-only migration layer 1 setting is not defined for the server.

i) single CEC CTN (X) 318: this field is valid when the configuration type specifies a single server definition and when one, for example, indicates the CTN is a single CEC CTN. When the field is, for example, zero, the CTN is not a single CTN. CEC

j) recovery configuration (R) 320: this field indicates whether the layer 1 configuration described by this block is the result of a layer 1 recovery action or a console command.

k) stratum 1 maximum short term distort rate change 322: this field includes a value that specifies the maximum possible change in the skew rate of the physical Oscillator on the new stratum 1 server that can occur during any specified period (for example, 60 seconds).

l) new CTN ID 320: this field is valid when the CTN ID change indicator specifies a CTN ID

-18 / 52change order and a valid CTN ID. This field specifies the new CTN ID.

If the new layer of configuration information for layer 1 should not be used to specify an update to the CTN ID, then the block cannot include the change bit of the CTN ID or the new CTN ID, for example. More details on coordinated network timing and defining a layer-1 configuration for a Timing network described in the following US patent applications:

S. Carlson et al., “Facilitating synchronization of servers in a 10 coordinate timing network”, 887,584 / series no. 60; and S. Carlson, "defining a stratum configuration in a coordinated timing network", reviewed at. 60/887, 652.

As noted initially, in one aspect, provided here are time switching parameters (XTP) command and response messages, as well as server time protocol control (STC) messages for a server time protocol installation , as described above. Again, server time protocol (STP) messages are transmitted along STP paths between two servers in the form of a message command and a message response. A message command is sent from a server to an attached server; and an STP message reply is sent from a server to an attached server in response to a message command received from the attached server. The message response is sent to the server attached to the link that sent the message command. As used here, a server that sends a message command is called the message originator, while a server that receives a message command is referred to as the message recipient. A message command contains a message command code that indicates the type of message being transmitted. For example, STP message command codes can support:

-19 / 52 • Exchange time parameter messages (XTP) • STP control messages (STC)

The message response contains a response code that describes the result of trying to execute the message command. General responses are defined below. Not all responses apply to all message commands. Additional command-dependent responses can be defined for individual commands. When multiple response conditions can be detected simultaneously, the lowest numbered response code can be reported.

Command codes:

• success: The command the message was successful.

• STP not enabled: The STP facility is installed, but not enabled on the attached server.

• Busy: The message command cannot be executed at this time due to busy conditions or resource contention.

• Invalid operating parameters: The message command contains invalid parameters.

• Configuration error: The message command contains an incompatible CTN ID.

• Path not established: The path is not established on the attached server.

• CF response: indicates that the STP feature is not supported on the attached server.

-20 / 52The exchange time parameters (XTP) message is used to exchange the timestamps, while maintaining CTN parameter information between two and directly associated with servers. The information in response to the message is used by the originator of the message to calculate the round trip, offset and dispersion values, which are used by STP filtering and selection algorithms to select a clock source for the clock. It is also used to set CTN time, maintaining parameters and ensuring synchronization of attached servers.

The STP facility on the server maintains a history of the 10 date / time and time stamp, keeping the information received from XTP message responses in an XTP tracking matrix. The number of samples maintained in the matrix can vary. Transmitting XTP procedures are used to transmit XTP message commands and receiving XTP procedures are used to receive messages from XTP, as described further below.

XTP command message

As shown, the example in fig. 4, the STP facility on the server sending an XTP message command defines all fields of the message command, except for the field receiving the timestamp message-command 410. The XTP message command fields are defined by originating server the message at the time the message is sent. An XTP message command format is shown in Fig. 5. In this format, message header 510 contains information that depends on the type of data link used to implement the STP link. Command code 520 contains an indication of the XTP private message command. Format

XTP 530 contains a value that specifies the format of the space-dependent format in the message command. This value can be set to zero for message commands. CTN ID 540 is defined as the CTN ID of the server sending the message command, that is, the origin server. Command message transmit timestamp 550 is defined as the time of day clock

-21/52 (TOD) on the origin server to the date that the message is transmitted along the STP path by the server. Command message displayed timestamp 560 is defined by the receiving server, as explained below. Data dependent on the XTP 570 format is set to zero for an XTP message command.

Continuing with Fig. 4, the XTP message command is forwarded to an attached server, that is, the message recipient server 420. The command message recipient server defines the message-command-receive-timestamp field in the command message from

XTP at the time the message is received on that server 430. The message command receive timestamp field is defined from the day (TOD) of the clock on the recipient server when the message command is received. Again, at the time the XTP message command was transmitted on the origin server, the message command receiving timestamp field was undefined.

The message recipient checks for STP path errors and if detected, invokes error recovery procedures. Otherwise, the recipient server stores the incoming message data as the command message timestamp in the timestamp data for the recipient server and performs an XTP message response and transmits the procedure for generating and sending a response message. 440 (Fig. 4).

XTP reply message

Fig. 6 describes a personification of the protocol for generating and manipulating an XTP message response. The STP facility that receives the XTP message command, that is, the server originating the XTP response message, defines all message response fields at the time the response message is to be sent, except for the receive message field. message response timestamp 610.

-22 / 52Fig. 7 describes an impersonation of XTP message response format. In this format, fields are defined as follows:

• 700 message header: contains information that depends on the type of data link used to implement the STP link used.

• Response code 705: It is an integer that describes the results of trying to execute the message. Valid response codes can include:

1. success: The message command was successful.

2. STP not enabled: The STP facility is installed, but not enabled on the attached server.

3. Configuration error: The message command contains an incompatible CTN ID.

4. The path not established: The path is not established on the attached server.

5. CF response: an indication that the STP feature is not supported on the attached server.

• XTP format 710: specifies the format of the space-dependent format in the message reply, which, for example, can include valid values ​​0, 1 and 2, as explained below.

• CTN key parameter 715: indicates whether the content of the area-dependent-format has been changed. The field is only valid for STP CTNs only. In a mixed-CTN, the field is negligible and ignored. The active-stratum-1 server increments the CTN parameter key whenever it changes the format

-23 / 52used in the XTP message reply or when it changes any value in the data sent in the format-dependent data area. A secondary-time server defines the CTN 715 parameter key as the value received in the last XTP-message response from its current clock source or, if it does not have a clock source, at the same value, sent in its last response message. XTP. The initialized value is zero, and the field encapsulates zero.

• 720 layer: It is defined for the layer level of the server that sends the message response.

• Timing Mode 725: is set to the server's Timing mode code sending the message response.

• Timing State 730: it is defined for the timing-State code of the server sending the message response.

• Local clock server (L) 735: Specifies whether the server sending the message response is configured as a local clock server.

• CTN ID 740: is set to the CTN ID of the server sending the message response.

• Current PRT 745 correction director fee: contains the current PRT-correction-guidance fee for CTN. In the XTP message responses sent by server stratum 1, it contains the PRT correction direction rate that was in effect at the time the message was sent. In XTP message responses sent by secondary servers, the field is defined as the value received in the response from

-24 / 52 most recent XTP message received from the clock source to the server. The PRT-correction direction rate (PCSR) is used to correct an accumulated error between the current TOD clock on the active server-stratum-1 and the primary reference time. In a CTN joint, the PCSR is set to zero.

• Time stamp / command transmission message time 750: it is defined for the input transmit the message-command timestamp.

• Date stamp / commands received hour 755 message: it is defined for the input to receive the message as timestamp.

• Transmission timestamp / response time 760 of the message: it is set to the TOD clock of the server sends the message response at the moment the message is transmitted.

• Date / response stamp receiving message time 765: contains the time stamp of the time when the message response is received by the attached server. The field is set from the TOD clock on the server that receives the message response when the message response is received.

• Message interval 770: it is defined for the message interval output field of the associated server instead keeping the parameters defined in the sending server.

• Base director rate 775: is set to the base director rate of the server sending the message response.

-25 / 52 • Root delay 780: it is defined for the CST delay going on the server sending the message response.

• Root scatter 785: it is defined for the dispersion of CST-clock on the sending server the message response.

· Reference 790 identifier: it is defined for the identification of CST-reference on the server sending the message response.

• 795 reference timestamp: the message response is set for the CST-reference timestamp on the sending server. The STP time stamp format is the time stamp.

• Data dependent on the XTP 799 format: It is set based on the field format. Three message response format fields are described in FIGS. 8, 9 and 10.

Fig. 8 depicts a message response format 0 data (which is used to provide general CTN parameter information) and includes the general format XTP 810, the correction direction block (PCSB) 820, a new CTN ID block ( CIB) 830, a block of information of displacement of the second hop (LSOIB) 840, PRT and 850 of displacement of a total time. The format-1 data of the message response of fig. 9 are used to deliver a new layer-1 block - configuration information and if specified, a new CTN ID and includes a general format of XTP 910 and a new layer configuration information 1 block 920. The data of format 2 message response of fig. 10, which includes a general format of XTP 1010 and a time control parameter information block (TCPIB) 1020, is used to deliver a time control parameter as a time zone control parameter information block.

-26 / 52Returning to Fig. 6, the XTP message response is forwarded to a message response receiving server 620, which as noted, is the attached server originating the XTP message command. The attached server defines the message-response-receive-timestamp field in the

XTP reply message when the message reply is received 630 and invokes an XTP-message-reply-received procedure 640 (described below). As noted above, XTP transmit procedures are used to transmit an XTP 420 message command (Fig. 4) or an XTP 620 message response (Fig. 6), as explained further below.

The format used for an XTP message response by a primary-time server depends on whether an update of the CTN-parameter is in progress. If an update is in progress, then the primary-time server uses the format that contains the parameter to be updated. When a CTN-parameter update is not in progress, the response from the XTP-format message-0 can be used for all responses. The format used for an XTP message response by a secondary-time server depends on whether the server has a clock source. When the server has a clock source, it uses the same format as provided in the last valid response from the clock source. When the server does not have a clock source, it uses the 0 format response.

Transmission command message

The XTP-message-command-transmit procedure is used to transmit the message command exchange time parameters (XTP) to a specified one next to the server. The STP path that is used to transmit the message is determined using, for example, a model-dependent STP path selection process.

Initiative to issue an XTP message command is established when the message interval timer expires for an attached server. The message interval parameter for the attached server

-27 / 52Specifies the rate at which XTP message commands are sent to the attached server.

The XTP-message-command procedure builds transmit the message header, sets the message command code to the same as the XTP command code and constructs the rest of the XTP message command. Immediately before sending the message, the timestamp of transmitting the message-command in the message command is set to the current TOD clock and the command is transmitted along the selected STP path. If a non-STP10 message-delivered condition is detected, an invalid entry is added to the XTP trace array.

Transmission of the Message response

The process of transmitting response to response message is used to transmit an XTP message response upon receipt of an XTP message command. The procedure is based on the response message header, defines the message response code and constructs the rest of the XTP message response. Immediately before sending the message, the timestamp of transmitting the response message in response to the message is defined as the current time of the day value and the response is transmitted in the STP path during which the message command was received.

XTP receipt procedures

Receive XTP procedures are used to receive an XTP message command or an XTP message reply.

Reply message received FIGS. 11A &amp; 11B depict a logical embodiment implemented for XTP-message-response-receiving treatment.

-28 / 52The XTP-message-response-receive procedure is invoked whenever an XTP-message response is received on an STP path.

The procedure is initially checked for an STP 1110 path error and if an error is detected, an 1120 error recovery procedure is invoked. If no STP path error is detected, then the STP message response is added to the XTP tracking matrix and the entry code is set to 1130.

The entry code is defined as a first value of 1140, which indicates the timestamp data is invalid if any of the following conditions are true:

• any timestamp contains all zeros, or • The calendar state is in the stopped state.

If the entry code is not defined as the first value, then the entry code is defined as a second value 1150, which indicates that the timestamp data is valid, but the movement should not be used to determine a usable clock source, if any of the following conditions are true:

• indicates The Out-of-Sync Response Message Timing Status, • The Attached Server Response Message Stratum is equal to the maximum stratum parameter, or • The server stratum level is non-zero and the Message Response Stratum is greater than that value.

If the entry code is not defined as the first or second value value, then the entry code is defined as a value

-29 / 52th third 1160 (Fig. 11B), indicating that the movement contains valid time to maintain the data, and the following actions are performed:

• the time-maintenance-reference data associated with the attached server is updated from the information in response to the message.

• Clock-filtering-and-selection processes are performed.

• A clock update process is performed.

If the server is in Synchronized State, then the data in the field format-dependent data of the most recent valid time-keeping message response is checked for updates and, if detected, the data is used to update CTN parameters from the 1170 server.

Message received commands

The XTP-message-command-receive procedure is invoked whenever an XTP-message command is received on an STP path. Fig. 12 depicts a personification of a procedure. As shown, the procedure includes STP 1210 path error checking and if an error is detected, start the 1220 error recovery process. If no STP path error is detected, then the procedure stores the input-message-command data timestamp of the message command in the timestamp data for the attached server 1230. XTP-message- transmission process The response, then , is performed to send a 1240 response message.

Control message command (STC)

-30 / 5220

An STC control message an STP is used to request CTN-parameter updates, establish and remove STP paths and read configuration information from attached servers. The operation code field in the message command specifies the operation to be performed.

Fig. 13 depicts a personification of the STC message command format. The fields of this command format can be defined as follows:

• Message header 1310: The message header field contains information that depends on the type of data link used to implement the STP link.

• Command code 1320: The command code field is defined as a defined value for STC message commands.

• Operation code 1330: The operation code field contains a value that specifies the operation to be performed. Possible operations include:

Update request operations □ change of request configuration strata-1 read operations □ read node Attachment Status □ read CTN parameters notification operations establish STP Path

-31 / 52 □ remove STP Path □ set Arbiter acquisition mode □ reset Arbiter acquisition mode □ Arbiter acquisition Active Status · CTN ID 1340: contains the CTN ID of the sending server.

Timestamp / command transmission time 1350 of message: it is defined since the day (TOD) of clock in the server at the moment the message is transmitted along the path of STP by the server.

• Date / command stamp received message time 1360: is set to the time when the message command is received on the attached server. The field is defined from the clock date on the connected server when the message command is received. The moment the message command is transmitted, the field is undefined.

Operation dependent data 1370: this field contains data that depends on the operation code specified in the message command.

STC reply message

Fig. 14 depicts a personification of the STCmensagem response format, where the format fields are defined as follows:

• Message header 1410: contains the message header field. The header field of

-32 / 52message contains information that depends on the type of data link used to implement the STP links.

• Response code 1420; contains the response code, which is an integer that describes the results of trying to run the message command.

• CTN ID 1430: contains the CTN ID of the sending server.

• Timestamp / response 1440 message transmission time: it is set since the day of the server's clock sends the message response at the time the message response is transmitted.

• Date / response stamp receiving message time 1450: contains the time stamp of the time when the message response was received by the attached server. The field is defined from the clock day on the server that receives the message response when the message response is received.

• Operation dependent data 1460: this field contains data that depends on the operation code specified in the message command.

As noted above, STC operations are specified by the operation code transmitted in each STC control message. The following types of operations are supported as described below: update request operations; reading operations; and notification operations.

Update request operations

-33 l 52 An update STP request control message is sent by the secondary STP server to notify the active server-stratum-1 of a CTN-parameter update request. If the secondary-time server is directly attached to an active-layer-1 server, the secondary-time server sends the message to the active-layer-1 server. If the secondary-time server is not directly associated with an active-layer-1 server, the secondary-time server sends the message to all attached servers that have a lower layer of the layer.

A secondary-time server has the initiative to send an update request message to a console command request to update a CTN parameter or to receive an update request operation from another secondary-time server. When a secondary-time server receives an update request message, it sends the update request parameter in the message to all attached servers at a lower tier level using a new update request message.

Upon receiving an update request operation, the active server-layer-1 performs the update procedure of the CTN-parameter.

Change stratum configuration 1

The Request to change the configuration of order-strata-1 is issued by a secondary-time server to request a change in the configuration of stratum-1 for CTN. The operation is issued by a secondary-time server after accepting a console command to modify the stratum-1 configuration for CTN. A secondary-time server accepts the change-layer-1 configuration command, only when the new layer-1 configuration specifies the secondary-time server as the new active-layer-1 server. The operating area dependent on the message command is shown in Fig. 15.

-34 / 52-

<td></td><td>• Stratum 1 1500 configuration block: contains the new layer 1 configuration being requested. At Valid responses for the operation are as follows:</td>

<td> 5 5</td><td>success: The command the message was successful. o STP not enabled: STP The installation is installed, but not enabled on the attached server.</td>

<td> 10</td><td>o busy: 0 message command cannot be executed at this point due to busy conditions or resource contention.</td>

<td> 15</td><td>o Invalid operating parameters: 0 command message contains invalid parameters. the configuration error: The message command contains an incompatible CTN ID. the path not established: the path is not established on the attached server.</td>

<td> 20</td><td>o CF response: response codes indicate that the STP facility is not supported on the attached server. The operating area dependent on the message response does not contain significant data. Read operations Read commands are used to obtain the CTN parameters and configuration information for attached servers. The data that can be obtained from an attached server include :; and CTN parameters.</td>

-35 / 52Read node attachment status

The read-node-attachment state command returns the attachment state for the node descriptor provided for the dependent operation area. Valid responses for this operation again may include:

• success: The command the message was successful.

• STP not enabled: The STP facility is installed, but not enabled on the attached server.

• Busy: The message command cannot be executed at this time due to busy conditions or resource contention.

• Invalid operating parameters: The message command contains invalid parameters.

• Configuration error: The message command contains an incompatible CTN ID.

• Path not established: The path is not established on the attached server.

• CF response: an indication that the STP feature is not supported on the attached server.

When the response code is a particular value, the response-dependent operating area of ​​the message may contain an attachment status bit.

• Attached State (A): specifies the Attached State for the server described by the node descriptor provided for the message command. First, the value indicates that the specified server is not associated with the message command receiver; it is a

-36 / 52second value indicates that the specified server is attached to the message command receiver.

CTN reading parameters

The read-CTN-parameters operation reads CTN parameters from the 5 attached server. The CTN parameters, which must be returned, are specified in the operating area depending on the message command. The message command dependent operation area may include • CTN parameter Code: specifies the CTN parameters to be returned in response to the message, for example:

o general reading CTN parameters o configuration information stratum 1 new reading o reading time zone control parameters information block (TCPIB) o current reading stratum 1 confirmation information

Valid response codes for operations can be as follows:

success: The command the message was successful.

o STP not enabled: STP The installation is installed, but not enabled on the attached server.

o busy: The message command cannot be executed at this time due to busy conditions or resource contention.

o Invalid operating parameters: The message command contains invalid parameters.

-37 / 52o configuration error: The command message contains an incompatible CTN ID.

the path not established: The path is not established on the attached server.

o CF response: an indication that the STP facility is not supported on the attached server.

When returning a special response code, the operation dependent area of ​​the message response block has (in a personification) the format illustrated in Fig. 16A.

· CTN parameter code 1610: specifies the parameters

CTN, which are provided in response to the message, including:

o General CTN parameters provided in response to the message.

o Stratum-1 new configuration information block 15 provided in response to the message.

the TCPIB provided in response to the message.

o Stratum-1 current block configuration information provided in response to the message.

• CTN key parameter 1620: contains the key of the CTN20 parameter for the server.

• CTN data area parameter 1630: The content of the CTN parameter data area depends on the CTN parameter code in the message response, as shown in Fig. 16B.

-38 / 52 • PRT correction information block director (PCSIB) 1650: contains the PCSIB for the server.

• New CTN ID Information block (NCIIB) 1660: contains the new CIIB for the server.

· Jump according to block information offset (LSOIB) 1670: contains the LSOIB for the server and is used, for example, in the conversion between coordinated universal time (UTC) and STP time.

New layer 1 Configuration Information data area:

· New layer-1 configuration block: contains the new-layer-1 configuration block for the server.

TCPIB data area:

• time zone control parameter information block (TCPIB): contains the TCPIB for the server.

Current stratum 1 Configuration Information data area:

• layer-1 configuration block: contains the current layer-1 configuration information block for the server.

Notification operations

Notification operations operations are used to create or remove an STP path and for communication between the alternate-stratum-1 server and the referee during a stratum-1 acquisition.

Establishes which STP path

The STP-path (ESP) operation is performed as part of the STP-path initialization process to establish a path

-39 / 52between two servers. The operation is used to exchange and validate certain parameters associated with each of the servers in the attachment. The dependent area of ​​the message command operation has, for example, the format shown in Fig. 17A.

• Descriptor node 1710: contains the Cap node descriptor of the server sending the command.

• Stratum 1720: contains the stratum of the server to send the command.

Maximum version number 1730: specifies the highest version number of the STP supported by STP installation, send the command.

• Version number 1740 required: specifies the version number of the STP active at the time of installing the STP to send the command and is the version that must be used by the attached server for the ESP process to complete successfully. When not specified, the server sends that the command is capable of operating on any version up to and including the specified maximum version number.

• Layer 1 configuration block 1750: contains the layer-1 configuration block for the server to send the message command.

The ESP message response block does not have any operation-dependent data. The following responses are valid for the operation:

success: The message command was successful.

-40 / 52 • STP not enabled: The STP facility is installed, but not enabled on the attached server.

• Busy: The message command cannot be executed at this time due to busy conditions or resource contention.

• Invalid operating parameters: The message command contains invalid parameters.

• Configuration error: The message command contains an incompatible CTN ID.

• Error descriptor node: The node descriptor in the ESP message command is invalid. The node descriptor value provided for the message command is stored in the link information block on the receiving server.

• Do not support version: The version number required in the ESP message command does not support the receiving server. The required version number provided in the message command is stored in the link information block on the receiving server.

• Stratum 1 Configuration error: The stratum-1 configuration information block in the ESP message command is not compatible with the stratum-1 configuration on the receiving server.

• Self-coupled server: The node descriptor of the attached server is identical to the node descriptor of this server, indicating that this server is linked to itself.

-41 / 52 • Active acquisition status: The referee received an ESP command from the primary-stratum-1 server, while the referee was in the active acquisition state and the specified primary itself as the active-stratum-1 server.

• Permitted paths exceeded: The server cannot support any additional STP paths.

• CF response: response codes indicate that the STP feature is not supported on the attached server.

STP path to remove

The remove-STP-path operation removes an established STP path to an attached server. The sending server sets the path link state to not initialized as a result of the operation. The message command and the message response do not include any operation-dependent data. Valid responses for the operation include:

• success: The command the message was successful.

• STP not enabled: The STP facility is installed, but not enabled on the attached server.

• Invalid operating parameters: The message command contains invalid parameters.

• Configuration error: The command message contains an incompatible CTN ID.

• Path not established: The path is not established on the attached server.

• CF response: The response indicates that the STP feature is not supported on the attached server.

-42 / 52The sending server defines the uninitialized path state and the reason for indicating non-complete initialization as a result of the operation, regardless of the response.

Set Arbiter acquisition mode mode operation The 5 set referee acquisition is issued to the referee server by the alternate strata-1 server to place the referee in the acquisition mode. The receiving server resumes the referee acquisition status flag in the response block.

The data area dependent on the command operation cfe 10 message has the format illustrated in Fig. 17B.

• Stratum 1 active communication timeout 1780: when set, the set command arbitrators-acquisition-mode message is being issued because server 1 inactive stratum has recognized an active stratum-1 active timeout condition. When unset, the set command arbitratorsaquisition-mode message is being issued because the inactive tier 1 server has lost attachment to the active-tier-1 server.

Response codes valid for the operation include:

success: The command the message was successful.

o STP not enabled: STP The installation is installed, but not enabled on the attached servers.

o Invalid operating parameters: The message command contains invalid parameters.

the configuration error: The command message contains an incompatible CTN ID.

-43 / 52o path not established: The path is not established on the attached server.

the invalid command: The message command receiver is not a designated arbiter.

the invalid sender: The command message server is not a designated alternate-1 server.

o CF response: response codes indicate that the STP facility is not supported on the attached server.

• 1790 Acquisition Status Flag: when set, it indicates that the referee has entered the acquisition mode and is in the active acquisition state. When unset, he indicates: the arbitrator entered the acquisition mode and is the acquisition - pending the State; or the referee has not entered the acquisition mode.

Arbiter acquisition mode operation

The reset reset referee is issued to the referee server by the alternate strata-1 server to take the referee out of the acquisition mode. The message command-dependent operating area does not include any data. Valid responses for the operation include;

• success; The message command was successful.

• STP not enabled: The STP facility is installed, but not enabled on the attached server.

• Invalid operating parameters: The message command contains invalid parameters.

-44 / 52 • Configuration error: The command message contains an incompatible CTN ID.

• Path not established: The path is not established on the attached server.

· Invalid command: The message command receiver is not a designated arbiter.

• Invalid sender: The command message server is not a designated alternate-1 server.

· CF response: response codes indicate that the STP facility is not supported on the attached server.

Arbitrators acquisition of Active State

The arbitrator-active state acquisition operation is issued to the alternate-stratum-1 server by the arbitrator to notify the alternate stratum-1 server that the arbitrator has entered the active state of acquisition. The message command-dependent operating area does not include any information. Valid responses for the operation include:

• success: The command the message was successful.

• STP not enabled: The STP facility is installed, but not enabled on the attached server.

• Invalid operating parameters: The message command contains invalid parameters.

• Configuration error: The command message contains an incompatible CTN ID.

-45 / 52 • Path not established: The path is not established on the attached server.

• Invalid command: The message command server is not a designated arbiter.

• Invalid sender: The message command server is not a designated arbiter.

• CF response: response codes indicate that the STP feature is not supported on the attached server.

In one embodiment, one or more aspects of the present invention can be performed in a processing environment based on one architecture, which can be referred to as a native architecture, but which emulates the architecture of another, which can be referred to as a guest architecture . As examples, the native architecture is the Power4 or PowerPC ® architecture offered by the International Business Machines Corporation, Armonk, New York or an Intel ® architecture, offered by Intel Corporation; and the z / architecture ® guest architecture also offered by International Business Machines Corporation, Armonk, New York. Aspects of architecture / z® are described in the “z / architecture, principles of operation,” IBM publication does not. SA22-7832-04, September 2005. In such an instruction and / or logic environment, which is specified in the z / architecture ® and designed to run on a machine z / architecture ®, it is emulated to run on a different architecture than z / architecture ®. An example of this processing environment is described with reference to FIGS. 18-20.

Referring to Fig. 18, a embodiment of a processing environment for incorporating and using one or more aspects of the present invention is described. 1800's processing environment includes, for example, a 1802 native CPU, a 1804 memory (for example, the main memory) and one or more erythropic / output (I / O) 1806 devices linked to each other through, for example,

-46 / 52um or more 1808 buses and / or other connections. As an example, the 1800's processing environment may include a Power PC® processor, a pSeries® server or an xSeries® server offered by International Business Machines Corporation, Armonk, New York; an HP Superdome with Intel ® Itanium ® 2 processors offered by Hewlett-Packard Company, Paio Alto, California; and / or other machines based on architectures offered by IBM ®, Hewlett-Packard, Intel ®, Sun Microsystems or others. Poder PC ®, pSeries ® and xSeries ® are registered trademarks of International Business Machines Corporation, Armonk, New York, USA. Intel ® and Itanium ® 2 are registered trademarks of Intel Corporation, Santa Clara, California.

The 1802 native CPU includes one or more 1810 native records, such as one or more general purpose records and / or one or more special purpose files, used during processing within the environment. These records include information that represents the state of the environment at any specific time in time.

In addition, the native central processing unit 1802 executes instructions and code that are stored in memory 1804. In a specific example, the central processing unit executes 1812 emulator code stored in memory 1804. This code allows the processing environment configured in one architecture to emulate the architecture of another. For example, the 1812 emulator code allows machines based on architectures other than az / architecture, such as Power PC ® processors, pSeries ® servers, xSeries ® servers, HP Superdome ® servers or others to emulate az / architecture ® and run the software and instructions developed based on z / architecture ®.

More details regarding the 1812 emulator code are described with reference to Fig. 19. Guest instructions 1902 include software instructions (for example, machine instructions) that were developed to run on a different architecture than the native CPU

-47 / 52of 1802 (Fig. 18). For example, 1902 guest instructions may have been designed to run on the 902 z® processor architecture, but instead are being emulated on the 1802 native CPU (which may be, for example, an Intel® Itanium® 2 processor). An example, the emulator code 1812 (Fig. 18) includes an instruction seeking 1900 routine to obtain one or more 1902 guest instructions from memory 1804 and optionally provide local buffer for the obtained instruction.

Further emulator code 1812 includes a 1904 routine translation instruction to determine the type of guest instruction that has been obtained and provide one or more native 1909 instructions that correspond to the guest instruction. For example, provisioning includes creation during, for example, processing a translation, a native instruction flow for a particular guest instruction. This includes identifying the function and creating the equivalent native instructions. In yet another example, providing native instructions includes selecting a code segment in the emulator associated with the guest instruction. For example, each guest instruction with an associated code segment in the emulator, which includes a sequence of one or more native instructions, and that code segment is selected to be executed.

Further emulator code 1812 includes a 1906 emulation control routine causing the native instructions to be executed. 1906 emulation control routine can cause native 1802 CPU to execute a native instruction routine that emulate one or more previously obtained guest instructions and, upon completion of such execution, to return control to the instruction fetch routine to emulate obtaining the next guest instruction or guest instruction group. Execution of the 1909 native instructions may include loading data into a 1804 memory register; storage of data to memory in a register; or perform some kind of arithmetic or logical operation, as determined by the translation routine. Each routine is, for example, implemented in the software, which is stored in the

-48 / 52memory and executed by the native central processing unit 1802. Other examples, one or more operations or routines are implemented in the firmware, hardware, software or some combination of these. The records of the emulated guest processor can be emulated using the 1810 records of the native CPU or using locations in memory 1804. In embodiments, the guest instructions 1902, native instructions 1909 and code emulation 1812 can reside in the memory of the same or can be dispersed among different memory devices.

In yet another embodiment, data processing is a system suitable for storing and / or executing usable program code that includes at least one processor linked directly or indirectly to memory elements via a system bus. The memory elements include, for example, local memory used during the actual execution of the program code, mass storage and cache memory, which provide temporary storage of at least some program code to reduce the number of times that code must be recovered from mass storage during execution.

Input / Output or I / O devices (including, but not limited to, keyboards, monitors, pointing devices, DASD, tape, CDs, DVDs, thumb drives and other memory media, etc.), can be coupled to the system directly or through the intermediate L / O controllers. Network adapters can also be linked to the system to enable the data processing system to become linked to other data processing systems or remote printers or storage devices via private or public intermediary networks. Modems, cable modems and Ethernet cards are just a few of the available types of network adapters.

One or more aspects of the present invention can be included in an article of manufacture (for example, one or more computer program products),

-49 / 52 having, for example, the computer's usable media. The media uses, for instance, means of computer-readable program code or logic (for example, instructions, code, commands, etc.) to provide and facilitate β

capabilities of the present invention. The article of manufacture can be included as part of a system (for example, the computer system) or sold separately.

An example of an article of manufacture or a computer program product incorporating one or more aspects of the present invention is described with reference to Fig. 20. A computer program product 2000 includes, for example, one or more computer usable media 2002 for computer storage program readable code means or logic 2004 in offering and facilitating one or more aspects of the present invention. The medium can be an electronic magnetic, optical, electromagnetic, infrared, or semiconductor system (or apparatus or device) or a means of propagation. A semiconductor or solid state memory, magnetic tape, a removable computer diskette, a random access memory (RAM), a read - only memory (ROM), a hard magnetic disk and an optical disk are examples of readable media from computer. Examples of optical discs read-only compact disc (CD-ROM), compact disc read / write (CDR / W) and DVD.

A sequence of program instructions or a logic assembly of one or more interrelated modules defined by one or more computer readable program codes means or logic to direct the performance of one or more aspects of the present invention.

Described here are features that facilitate the maintenance of time synchronization by multiple different computer systems to form a coordinated timing network. Timing network servers take advantage of the server timing protocol to pass timekeeping information over existing high-speed data links between systems that

-50 / 52 provide the ability for the time of day clocks on each system to be synchronized with the accuracy required in today's high end computer systems. The use of STP over high-speed, low-latency links offers the ability to synchronize all systems in the CTN to accuracy, for example, a few microseconds based on a reference period provided by a single server.

STP provides the ability to define and maintain timekeeping information within the CTN, such as time zone, summer savings time offset and a jump seconds offset. The information can be updated within the scope of CTN in a programmed and coherent way, changes occurring all at the same time on all CTN servers. This avoids the potential system risks and disruptions that occur when these parameters are updated occasionally, creating discrepancies in time settings between computers.

CTN parameters can be defined and read by an operator via the STP console interface. CTN parameters include server connectivity, local time information, such as time zone and summer time savings and the jump seconds needed to calculate UTC. The console itself is any element that provides an operator interface for displaying and defining CTN parameters, and that is capable of communicating with the STP facility.

Although one or more examples have been provided here, they are only examples. Many variations are possible without abandoning the spirit of present invention. For example, processing environments other than the examples provided herein may include and / or benefit from one or more aspects of the present invention. For example. In addition, the required environment may not be based on z / architecture ®, but may instead be based on other architectures offered by, for example, IBM ®, Intel ®, Sun Microsystems, as well

-51 / 52 like others. Even further, the environment can include multiple processors, and / be partitioned or linked to other systems, as examples.

In addition, although several control blocks have been described, each of these control blocks may include additional, less and / or different information. The location within the control block and the size of each field within the control block can vary for different embodiments.

As used herein, the expression “obtain” includes, but is not limited to, seeking, receiving, having, providing, being provided, creating, developing, etc.

Additional details on coordinated timing networks can be found in the following US patent applications: “System and Method for TOD-Clock Steering”, Serial No. 11 / 223,886; “Synchronization Signal for TOD-Clock Steering Adjustment”. Serial No. 11 / 532,168; “Managíng · Data Access Via A Loop Only If Changed Locking Facility”, Serial No. 11 / 468,501;

"Clock Filter Dispersion", Serial No. 11 / 223,878; "Method and System for Clock Skew and Offset Estimation", Serial No. 11 / 223,876; “Use of T4 Timestamps to Calculate Clock Offset and Skew”, Serial No. 11 / 223,577; “Directly Obtaining by Application Programs Information Usable in Determining Clock Accuracy”, Serial No. 11 / 450,025; “System and Method for Calibrating to TOD Clock”, Serial No.

11 / 223,642; “Method and System for Establishing a Logical Path Between Servers in a Coordinated Timing Network”, by S. Carlson et al. Serial No. 60 / 887,576 ,; and “Channel subsystem Server Time Protocol Commands”, by S. Carlson et al „60 / 887,544.

The features of one or more aspects of the present invention can be implemented in software, firmware, hardware or some combination thereof. Program at least one machine-readable storage device provides at least one program of instructions executable by the machine to perform the capabilities of the present invention can be provided.

-52 / 52The flow diagrams mentioned here are examples only. There can be many variations on these diagrams or the steps (or operations) described without abandoning the spirit of invention. For example, steps can be performed in a different order, or steps can be added, deleted or modified. All of these variations are considered a part of the claimed invention.

Although the embodiments have been described and described in detail here, it will be apparent to those skilled in the relevant technique that various modifications, additions, substitutions and the like can be made without departing from the spirit of invention, and these are therefore considered within the scope of the invention. defined in the claims.

-1/5-