Local storage node performance enhancement
Disclosed are systems and methods for enhancing local node performance in a storage system through offloading cache replacement tasks to remote nodes. A periodic time-series analysis of CPU cycle utilization and network latency is conducted on one or more arrays to identify and/or forecast underutilized nodes in the one or more arrays. A first array detects a shortage of available cache slots in an allocation queue and identifies underutilized remote nodes in either its own array or another array. The array shares the metadata pages with the remote node. A worker thread on the remote node runs a search algorithm on the received meta data pages and creates a list of candidate replacement memory slots.
1 . A method comprising:
collecting usage data from a plurality of storage devices in one or more storage arrays;
forecasting a network latency based on the usage data of the plurality of storage devices;
determining that the forecasted network latency is below a predefined threshold, and in response:
selecting a remote storage device from the plurality of storage devices;
receiving, at a local storage device of the plurality of storage devices, a list of replacement memory slots from the remote storage device; and
offloading cache replacement tasks from the local storage device to the remote storage device.
2 . The method of claim 1 wherein forecasting the network latency includes using a time series analysis model.
3 . The method of claim 2 wherein the time series analysis model is an autoregressive integrated moving average (ARIMA) model.
4 . The method of claim 1 , wherein the local storage device and the remote storage device are within a first storage array.
5 . The method of claim 4 , further comprising offloading all cache replacement tasks to the remote storage device, wherein the list of replacement memory slots includes processed slots.
6 . The method of claim 4 , wherein the cache replacement tasks include fabric operations.
7 . The method of claim 1 , wherein the local storage device is within a first storage array and the remote storage device is within a second storage array.
8 . The method of claim 7 , wherein offloading the cache replacement tasks includes offloading a portion of the cache replacement tasks and the list of replacement memory slots includes a list of candidate replacement slots.
9 . The method of claim 1 , wherein a list of replacement memory slots is generated by a least recently used search.
10 . The method of claim 1 , further comprising transmitting metadata pages to the remote storage device.
11 . A system comprising:
a memory; and
a processor configured to perform the operations of:
collecting usage data from a plurality of storage devices in one or more storage arrays;
forecasting a network latency based on the usage data of the plurality of storage devices;
determining that the forecasted network latency is below a predefined threshold, and in response:
selecting a remote storage device from the plurality of storage devices;
receiving, at a local storage device of the plurality of storage devices, a list of replacement memory slots from the remote storage device; and
offloading cache replacement tasks from the local storage device to the remote storage device.
12 . The system of claim 11 , wherein the local storage device and the remote storage device are within a first storage array.
13 . The system of claim 12 , further comprising offloading all cache replacement tasks to the remote storage device, wherein the list of replacement memory slots includes processed slots.
14 . The system of claim 12 , wherein the cache replacement tasks include fabric operations.
15 . The system of claim 11 , wherein the local storage device is within a first storage array and the remote storage device is within a second storage array.
16 . The system of claim 15 , wherein offloading the cache replacement tasks includes offloading a portion of the cache replacement tasks and the list of replacement memory slots includes a list of candidate replacement slots.
17 . The system of claim 11 , wherein a list of replacement memory slots is generated by a least recently used search.
18 . The system of claim 11 , further comprising transmitting metadata pages to the remote storage device.
19 . A non-transitory computer-readable medium storing one or more processor-executable instructions, which when executed by a processing circuitry, further cause the processing circuitry to perform the operations of:
collecting usage data from a plurality of storage devices in one or more storage arrays;
forecasting a network latency based on the usage data of the plurality of storage devices;
determining that the forecasted network latency is below a predefined threshold, and in response:
selecting a remote storage device from the plurality of storage devices;
receiving, at a local storage device of the plurality of storage devices, a list of replacement memory slots from the remote storage device; and
offloading cache replacement tasks from the local storage device to the remote storage device.
20 . The non-transitory computer-readable medium of claim 19 wherein the list of replacement memory slots from the remote storage device is generated by a least recently used search and metadata pages are transmitted to the remote storage device.