nim-dagger/codex/sales/salesagent.nim
Eric 570a1f7b67
[marketplace] Availability improvements (#535)
## Problem
When Availabilities are created, the amount of bytes in the Availability are reserved in the repo, so those bytes on disk cannot be written to otherwise. When a request for storage is received by a node, if a previously created Availability is matched, an attempt will be made to fill a slot in the request (more accurately, the request's slots are added to the SlotQueue, and eventually those slots will be processed). During download, bytes that were reserved for the Availability were released (as they were written to disk). To prevent more bytes from being released than were reserved in the Availability, the Availability was marked as used during the download, so that no other requests would match the Availability, and therefore no new downloads (and byte releases) would begin. The unfortunate downside to this, is that the number of Availabilities a node has determines the download concurrency capacity. If, for example, a node creates a single Availability that covers all available disk space the operator is willing to use, that single Availability would mean that only one download could occur at a time, meaning the node could potentially miss out on storage opportunities.

## Solution
To alleviate the concurrency issue, each time a slot is processed, a Reservation is created, which takes size (aka reserved bytes) away from the Availability and stores them in the Reservation object. This can be done as many times as needed as long as there are enough bytes remaining in the Availability. Therefore, concurrent downloads are no longer limited by the number of Availabilities. Instead, they would more likely be limited to the SlotQueue's `maxWorkers`.

From a database design perspective, an Availability has zero or more Reservations.

Reservations are persisted in the RepoStore's metadata, along with Availabilities. The metadata store key path for Reservations is ` meta / sales / reservations / <availabilityId> / <reservationId>`, while Availabilities are stored one level up, eg `meta / sales / reservations / <availabilityId> `, allowing all Reservations for an Availability to be queried (this is not currently needed, but may be useful when work to restore Availability size is implemented, more on this later).

### Lifecycle
When a reservation is created, its size is deducted from the Availability, and when a reservation is deleted, any remaining size (bytes not written to disk) is returned to the Availability. If the request finishes, is cancelled (expired), or an error occurs, the Reservation is deleted (and any undownloaded bytes returned to the Availability). In addition, when the Sales module starts, any Reservations that are not actively being used in a filled slot, are deleted.

Having a Reservation persisted until after a storage request is completed, will allow for the originally set Availability size to be reclaimed once a request contract has been completed. This is a feature that is yet to be implemented, however the work in this PR is a step in the direction towards enabling this.

### Unknowns
Reservation size is determined by the `StorageAsk.slotSize`. If during download, more bytes than `slotSize` are attempted to be downloaded than this, then the Reservation update will fail, and the state machine will move to a `SaleErrored` state, deleting the Reservation. This will likely prevent the slot from being filled.

### Notes
Based on #514
2023-09-29 14:33:08 +10:00

110 lines
3.0 KiB
Nim

import pkg/chronos
import pkg/chronicles
import pkg/questionable
import pkg/questionable/results
import pkg/stint
import pkg/upraises
import ../contracts/requests
import ../errors
import ./statemachine
import ./salescontext
import ./salesdata
import ./reservations
export reservations
logScope:
topics = "marketplace sales"
type
SalesAgent* = ref object of Machine
context*: SalesContext
data*: SalesData
subscribed: bool
# Slot-level callbacks.
onCleanUp*: OnCleanUp
onFilled*: ?OnFilled
OnCleanUp* = proc: Future[void] {.gcsafe, upraises: [].}
OnFilled* = proc(request: StorageRequest,
slotIndex: UInt256) {.gcsafe, upraises: [].}
SalesAgentError = object of CodexError
AllSlotsFilledError* = object of SalesAgentError
func `==`*(a, b: SalesAgent): bool =
a.data.requestId == b.data.requestId and
a.data.slotIndex == b.data.slotIndex
proc newSalesAgent*(context: SalesContext,
requestId: RequestId,
slotIndex: UInt256,
request: ?StorageRequest): SalesAgent =
var agent = SalesAgent.new()
agent.context = context
agent.data = SalesData(
requestId: requestId,
slotIndex: slotIndex,
request: request)
return agent
proc retrieveRequest*(agent: SalesAgent) {.async.} =
let data = agent.data
let market = agent.context.market
if data.request.isNone:
data.request = await market.getRequest(data.requestId)
proc subscribeCancellation(agent: SalesAgent) {.async.} =
let data = agent.data
let clock = agent.context.clock
proc onCancelled() {.async.} =
without request =? data.request:
return
await clock.waitUntil(request.expiry.truncate(int64))
agent.schedule(cancelledEvent(request))
data.cancelled = onCancelled()
method onFulfilled*(agent: SalesAgent, requestId: RequestId) {.base, gcsafe, upraises: [].} =
if agent.data.requestId == requestId and
not agent.data.cancelled.isNil:
agent.data.cancelled.cancel()
method onFailed*(agent: SalesAgent, requestId: RequestId) {.base, gcsafe, upraises: [].} =
without request =? agent.data.request:
return
if agent.data.requestId == requestId:
agent.schedule(failedEvent(request))
method onSlotFilled*(agent: SalesAgent,
requestId: RequestId,
slotIndex: UInt256) {.base, gcsafe, upraises: [].} =
if agent.data.requestId == requestId and
agent.data.slotIndex == slotIndex:
agent.schedule(slotFilledEvent(requestId, slotIndex))
proc subscribe*(agent: SalesAgent) {.async.} =
if agent.subscribed:
return
await agent.subscribeCancellation()
agent.subscribed = true
proc unsubscribe*(agent: SalesAgent) {.async.} =
if not agent.subscribed:
return
let data = agent.data
if not data.cancelled.isNil and not data.cancelled.finished:
await data.cancelled.cancelAndWait()
data.cancelled = nil
agent.subscribed = false
proc stop*(agent: SalesAgent) {.async.} =
await Machine(agent).stop()
await agent.unsubscribe()