Abstract: Data retention for a tiered ordered event stream (OES) data storage system is disclosed. Data retention can be applied to demoted data, e.g., data demoted from a first tier to a second tier of data storage devices. The data retention disclosed can avoid demoted events, generally aggregated via a chunk object, file object, etc., from being subject to both a stream-cut operation and a retention period. In embodiments, where a stream-cut instance corresponds to events occurring later in time than a retention end time (RET), all demoted events, e.g., as aggregated by a chunk, file, etc., can be affiliated with the RET. However, where the stream-cut instance corresponds to events occurring earlier in time than the RET, then a portion of the events, e.g., those that will be truncated by performing the stream-cut instance, can be demoted and affiliated with the RET.

Abstract: The described technology is generally directed towards managing data retention policy for stream data stored in a streaming storage system. When a request to truncate a data stream from a certain position (e.g., from a request-specified stream cut) is received, an evaluation is made to determine whether the requested position is within a data retention period as specified by data retention policy. If any data prior to the stream cut position (corresponding to a stream cut time) is within the data retention period, the truncation request is blocked. Otherwise truncation from the stream cut point is allowed to proceed/is performed. Also described is handling automated (e.g., sized based) stream truncation requests with respect to data retention.

Abstract: Scaling an ordered event stream (OES) based on an information-unit (IU) metric is disclosed. The IU metric can correspond to an amount of computing resources that can be consumed to access information embodied in event data of an event of the OES. In this regard, the amount of computing resources to access the data of the stream event itself can be distinct from an amount of computing resources employed to access information embodied in the data. As such, where an external application, e.g., a reader, a writer, etc., can connect to an OES data storage system, enabling the OES to be scaled in response to burdening of computing resources accessing event information, rather than merely event data, can aid in preservation of an ordering of events accessed from the OES.

Abstract: Systems and methods are described for enabling graceful recovery of network connections in a virtual machine instance that has been migrated or temporarily halted. To prevent the virtual machine instance from attempting to reuse open connections, which might fail due to migration or halting, a host device identifies open connections just prior to halting the virtual machine instance on the host, and transmits to the virtual machine instance termination signals for the open connections. The host device may further transmit termination signals to the other parties to such connections. Each termination signal may be formatted so as to appear to originate from the other party to the connection, causing both parties to synchronize their knowledge of the connection. On reactivation, the virtual machine instance can recovery the connections without errors associated with attempted utilization of broken connections.

Abstract: Systems and methods are described for providing updating of disk images supporting serverless code execution and controlled deployment of updated disk images. A disk image can be defined as a set of layers that represent a file system include code of a serverless function and other data used by the code. A function owner can designate one layer as containing software or other data subject to update. When a new version of the layer is obtained at a serverless compute system, the system can generate a new disk image containing the updated layer. The system can then gradually transition the function to the new disk image, by dividing calls to the function among two versions of the function—one using the prior disk image, and one using the new disk image. Performance data gained from the new version of the function can be used to control the gradual transition.

Abstract: Storage of data according to mapped reliability groups (MRGs) of mapped redundant arrays of independent nodes (mapped clusters) is disclosed. Real reliability groups (RRGs) of a real cluster can provide compartmentalization that can reduce a probability of a data loss event occurring in a cluster storage system. MRGs for a mapped cluster employing the RRGs of the real cluster can provide additional compartmentalization that can further reduce a probability of a data loss event occurring. A data protection set can be stored according to a first group of MRGs and a redundant representation of the data protection set can be stored according to a second group of MRGs, wherein a network distance between the first and second group of MRGs is greater than a network distance between constituent MRGs of either the first or second group of MRGs.

Abstract: Systems and methods are described for reducing latency to service requests to execute code on an on-demand code execution system by maintaining snapshots of virtual machine instances in a ready state to execute such code. A user may submit code to the on-demand code execution system, which code depends on other software, such as an operating system or runtime. The on-demand code execution system can generate a virtual machine instance provisioned with the other software, and initialize the instance into a state at which it is ready to execute the code. The on-demand code execution system can then generate a snapshot of the state of the instance, and halt the instance. When a request to execute the code is received, the snapshot can be used to quickly restore the instance. The code can then be executed within the instance, reducing the need to initialize the instance or maintain the instance in an executing state.

Abstract: The described technology is generally directed towards fine-grained data retention management in stream-based data storage systems, which facilitates specifying retention policy at the event level. A fixed retention period corresponding to a retention end time is associated with each event, and the system keeps the longest of the retention end times for each segment of a data stream. Stream cuts are generated which divide the data stream into fragments, and are the basis for truncating the data stream. Each stream cut contains a stream cut retention end time obtained from the longest retention end time of the retention end times of the active segments. When an attempt to truncate a data stream from a stream cut is made, the attempt is blocked if the stream cut's retention end time is in the future, otherwise truncation from the stream cut point is allowed to proceed.

Abstract: Retention of events of an ordered event stream according to at least one triggered retention policy is disclosed. Expiration of events stored in a segment of an ordered event stream (OES) can be desirable. New events can be added to a head of an OES segment, and pruning events from a tail of the OES segment can be desirable. Processing applications can predicate event retention, e.g., restricting expiration of an event, on at least one triggered retention policy. In some embodiments, an additional fixed retention policy can be combined with the triggered retention. The disclosed retention can be performed at the event-level or at less granular levels, e.g., segment-level, OES-level, etc., e.g., via batching of events.

Abstract: The technology describes scanning tree data structures (trees) for multiple processes, at least partly in parallel. A service scans a tree from a beginning tree element to an ending tree element on behalf of a process; while scanning, another process can join in the scan at an intermediate tree element location (e.g., a key). For the subsequent process, the service scans the tree based on the intermediate location to the tree end, thereby visiting tree elements in parallel until the tree end, then continuing from the tree beginning element to the intermediate location for the subsequent process. The service basically completes a full carousel-type revolution for each process. One or more other processes can join an ongoing scan at any time, facilitating further parallel tree element visits, while still obtaining a full scan of the entire set of tree elements. The service handles changing tree versions during the scanning.

Abstract: Described herein, system that facilitates replication of data in a geographically distributed storage environment. According to an embodiment, a system can comprise determining whether a data storage system is in an active data storage mode or a passive data storage mode. In active data storage mode, the data storage system can accept connections from an application, permit the application to store new data objects, replicate the new data objects to other data storage systems, and accept replicated data. In passive data storage mode, the data storage system can block storage of new data objects by the application while accepting replicated data.

Abstract: The described technology is generally directed towards fine-grained data event expiration in a streaming data storage system. An event to append is given an expiration period, and the expiration time for the events in a data stream or segment of a data stream is the largest expiration time among events in the data stream or segment. Different segments can have different expiration times for their events. In a segment comprising a group of events, a subgroup of expired events prior to a stream cut are deleted by an expiration task. For a subgroup of unexpired events prior to a stream cut, the expiration task retains (does not delete) the subgroup of events. If a scaling operation is performed on a segment, the new successor segment or segments inherit the largest expiration time of the predecessor segment or segments.

Abstract: Data verification technology for ordered event stream (OES) events written into an ordered event stream storage system is disclosed. The verification technology provides perfect reliability. The verification technology further requires low storage overhead in comparison to typical checksums, storing replicated data, etc. Test event data can be generated in a reproducible manner based upon determined OES metadata. OES metadata can be determined from input received via a user interface, via characteristics of an OES storage system, etc., and can be stored for later use in data verification. The test event data can be stored to a portion of an OES storage system under test. The stored test event data can subsequently be verified by using the stored OES metadata to regenerate test event data for comparison to the stored test event data. The test event ordering can be verified via sequence information included in the stored test event data.

Abstract: Systems and methods are described for providing virtualized transaction retries in an on-demand network code execution system. A user may generate a task on the system by submitting code. The task may include a transaction that can succeed or fail depending on external factors, such as accessing a resource that other processes are also trying to access. The system may obtain success criteria for evaluating whether the transaction was successful, and may configure a virtual machine instance to execute the submitted code. The system may generate a “snapshot” or otherwise capture information regarding the state of the virtual machine instance prior to executing the code, and may then execute the code or a portion of it to attempt the transaction. The system may then apply the success criteria to determine whether the transaction was successful, and if not may retry the transaction by restoring the snapshot and re-executing the code.

Abstract: Commutative coding in a geographically diverse data storage system is disclosed. Commutative coding can achieve a same result as more conventional hierarchical erasure coding of data, but can be more efficient. Commutative coding can employ Galois Field (GF) based bit-matrix operations. The bit-matrix operations can employ a reduced GF order in associated with expanding elements of input matrixes. A reduced GF order can perform matrix operations at a lower complexity, e.g., employing AND operations for a GF(2) in contrast to XOR operations for a GF(2w), where w=4, 8, 16, etc. In an aspect, commutative coding can comprise generating a second-tier coding fragment based on applying a second erasure coding scheme, via bit-matrix operations, to a first-tier encoded fragment, wherein the first-tier encoded fragment is based on an input data fragment and a first erasure coding scheme.

Abstract: Scaling of an ordered event stream (OES) based on a characteristic of one or more writer groups is disclosed. Scaling a portion of an OES contemporaneous to writing events into that portion can conserve computing resources in contrast to more conventional scaling techniques. Moreover, scaling an OES contemporaneously with writing events thereto can enable improved management of OES scaling for applications that can both read events from an input portion of an OES and, via interim events and interim portions of an OES, write events to an output portion of an OES. An application instance can therefore simultaneously act as both a reader group and writer group and can manage data via interim OESs, such that effects of passing the data through the interim OESs can be cascaded into a scaling of the output portion of an OES based on the writer group characteristic.

Abstract: A geographically diverse data storage system that can protect data via replication of data among relevant zones according to a determined replication topology is disclosed. The replication topology can be determined based on replication times between the relevant zones. In an aspect, a tree topology can provide advantages over a star topography. In an embodiment, a tree topology can be generated, or an existing topology can be modified, via selection of a next replication task(s) based on the replication times. In an aspect, the replication times can be determined from measurable characteristics of the geographically diverse data storage system. In some embodiments, the replications times can be based on historical measurements, time limited historical measurements, inferences from machine learning, etc. A determined topology can be ranked relative to other viable topologies based on criteria such as speed, monetary cost, computing resource usage, etc.

Abstract: The described technology is generally directed towards managing data retention policy for stream data stored in a streaming storage system. When a request to truncate a data stream from a certain position (e.g., from a request-specified stream cut) is received, an evaluation is made to determine whether the requested position is within a data retention period as specified by data retention policy. If any data prior to the stream cut position (corresponding to a stream cut time) is within the data retention period, the truncation request is blocked. Otherwise truncation from the stream cut point is allowed to proceed/is performed. Also described is handling automated (e.g., sized based) stream truncation requests with respect to data retention.

Abstract: Systems and methods are described for a multi-tenant mode of a serverless code execution system. For instance, a method may include maintaining a set of execution environments, wherein each execution environment is associated with a serverless function, wherein the serverless function is associated with a software as a service (SaaS) provider that is a tenant of a cloud services provider, wherein the SaaS provider provides services to sub-tenants, wherein the set of execution environments are partitioned based on sub-tenants of the SaaS provider; receiving a call to execute a serverless function, wherein the call includes a serverless function identifier and a sub-tenant identifier; identifying a sub-tenant-specific execution environment of the set of execution environments that is associated with the sub-tenant; and in response to identifying the tenant-specific execution environment, invoking the serverless function on the sub-tenant-specific execution environment.

Abstract: The described technology is generally directed towards bulk-mode replication of data objects to a destination replication site. When replicating a group of objects, and there is enough object data to fill one or more chunk data structures, bulk-mode data replication is performed, with the destination site replicating the objects into chunk data structures and performing erasure coding to protect the data. This avoids the need for inefficient preliminary data protection scheme at the replication destination. When there are multiple objects to be replicated but not enough object data to fill a chunk data structure, bulk-mode data replication transfers the objects to the destination site for replicating as individual objects. Standard object-level replication can be used for single object replication. The technology thus facilitates high-performance data transfer to destination replication sites and efficient handling of data at the replication destination site.