chore: add retention policy with GB or MB limitation #1885

tests/waku_archive/test_retention_policy.nim

@@ -12,6 +12,7 @@ import
   ../../../waku/waku_archive/driver/sqlite_driver,
   ../../../waku/waku_archive/retention_policy,
   ../../../waku/waku_archive/retention_policy/retention_policy_capacity,
+  ../../../waku/waku_archive/retention_policy/retention_policy_size,
   ../testlib/common,
   ../testlib/wakucore
 
@@ -53,6 +54,38 @@ suite "Waku Archive - Retention policy":
 
     ## Cleanup
     (waitFor driver.close()).expect("driver to close")
+
+  test "size retention policy - windowed message deletion":
+    ## Given
+    let
+      # in megabytes
+      sizeLimit:float = 0.05
+      excess = 123
+
+    let driver = newTestArchiveDriver()
+
+    let retentionPolicy: RetentionPolicy = SizeRetentionPolicy.init(size=sizeLimit)
+
+    ## When
+    for i in 1..excess:
+      let msg = fakeWakuMessage(payload= @[byte i], contentTopic=DefaultContentTopic, ts=Timestamp(i))
+
+      require (waitFor driver.put(DefaultPubsubTopic, msg, computeDigest(msg), msg.timestamp)).isOk()
+      require (waitFor retentionPolicy.execute(driver)).isOk()
+    ## Then
+    # calculate the current database size
+    let pageSize = (waitFor driver.getPagesSize()).tryGet()
+    let pageCount = (waitFor driver.getPagesCount()).tryGet()
+    let sizeDB = float(pageCount * pageSize) / (1024.0 * 1024.0)
+
+    check:
+      # size of the database is used to check if the storage limit has been preserved
+      # check the current database size with the limitSize provided by the user
+      # it should be lower 
+      sizeDB <= sizeLimit
+
+    ## Cleanup
+    (waitFor driver.close()).expect("driver to close")
 
   test "store capacity should be limited":
     ## Given

waku/common/databases/db_sqlite.nim

@@ -484,4 +484,5 @@ proc performSqliteVacuum*(db: SqliteDatabase): DatabaseResult[void] =
   if resVacuum.isErr():
     return err("failed to execute vacuum: " & resVacuum.error)
 
-  debug "finished sqlite database vacuuming"
+  debug "finished sqlite database vacuuming"
+  ok()

waku/waku_archive/driver.nim

@@ -45,6 +45,15 @@ method getMessages*(driver: ArchiveDriver,
 method getMessagesCount*(driver: ArchiveDriver):
                          Future[ArchiveDriverResult[int64]] {.base, async.} = discard
 
+method getPagesCount*(driver: ArchiveDriver):
+                         Future[ArchiveDriverResult[int64]] {.base, async.} = discard
+
+method getPagesSize*(driver: ArchiveDriver):
+                         Future[ArchiveDriverResult[int64]] {.base, async.} = discard
+
+method performsSqliteVacuum*(driver: ArchiveDriver):
+              Future[ArchiveDriverResult[void]] {.base, async.} = discard
+
 method getOldestMessageTimestamp*(driver: ArchiveDriver):
                                   Future[ArchiveDriverResult[Timestamp]] {.base, async.} = discard
 

waku/waku_archive/driver/queue_driver/queue_driver.nim

@@ -280,6 +280,18 @@ method getMessagesCount*(driver: QueueDriver):
                          Future[ArchiveDriverResult[int64]] {.async} =
   return ok(int64(driver.len()))
 
+method getPagesCount*(driver: QueueDriver):
+                         Future[ArchiveDriverResult[int64]] {.async} =
+  return ok(int64(driver.len()))
+
+method getPagesSize*(driver: QueueDriver):
+                         Future[ArchiveDriverResult[int64]] {.async} =
+  return ok(int64(driver.len()))
+
+method performsSqliteVacuum*(driver: QueueDriver):
+              Future[ArchiveDriverResult[void]] {.async.} =
+  return ok()
+
 method getOldestMessageTimestamp*(driver: QueueDriver):
                                   Future[ArchiveDriverResult[Timestamp]] {.async.} =
   return driver.first().map(proc(msg: IndexedWakuMessage): Timestamp = msg.index.receiverTime)

waku/waku_archive/driver/sqlite_driver/sqlite_driver.nim

@@ -109,6 +109,18 @@ method getMessagesCount*(s: SqliteDriver):
                          Future[ArchiveDriverResult[int64]] {.async.} =
   return s.db.getMessageCount()
 
+method getPagesCount*(s: SqliteDriver):
+                         Future[ArchiveDriverResult[int64]] {.async.} =
+  return s.db.getPageCount()
+
+method getPagesSize*(s: SqliteDriver):
+                         Future[ArchiveDriverResult[int64]] {.async.} =
+  return s.db.getPageSize()
+
+method performsSqliteVacuum*(s: SqliteDriver):
+                         Future[ArchiveDriverResult[void]] {.async.} =
+  return s.db.performSqliteVacuum()
+
 method getOldestMessageTimestamp*(s: SqliteDriver):
                                   Future[ArchiveDriverResult[Timestamp]] {.async.} =
   return s.db.selectOldestReceiverTimestamp()

waku/waku_archive/retention_policy/builder.nim

@@ -11,7 +11,8 @@ import
 import
   ../retention_policy,
   ./retention_policy_time,
-  ./retention_policy_capacity
+  ./retention_policy_capacity,
+  ./retention_policy_size
 
 proc new*(T: type RetentionPolicy,
           retPolicy: string):
@@ -51,5 +52,38 @@ proc new*(T: type RetentionPolicy,
     let retPolicy: RetentionPolicy = CapacityRetentionPolicy.init(retentionCapacity)
     return ok(some(retPolicy))
 
+  elif policy == "size":
+    var retentionSize: string
+    retentionSize = policyArgs
+
+    # captures the size unit such as Gb or Mb
+    let sizeUnit = retentionSize.substr(retentionSize.len-2)
+    # captures the string type number data of the size provided  
+    let sizeQuantityStr = retentionSize.substr(0,retentionSize.len-3)
+    # to hold the numeric value data of size
+    var sizeQuantity: float
+
+    if sizeUnit in ["gb", "Gb", "GB", "gB"]:
+      # parse the actual value into integer type var
+      try:
+        sizeQuantity = parseFloat(sizeQuantityStr)
+      except ValueError:
+        return err("invalid size retention policy argument")
+      # Gb data is converted into Mb for uniform processing
+      sizeQuantity = sizeQuantity * 1024
+    elif sizeUnit in ["mb", "Mb", "MB", "mB"]:
+      try:
+        sizeQuantity = parseFloat(sizeQuantityStr)  
+      except ValueError:
+        return err("invalid size retention policy argument")
+    else:
+      return err ("""invalid size retention value unit: expected "Mb" or "Gb" but got """ & sizeUnit )
+
+    if sizeQuantity <= 0:
+          return err("invalid size retention policy argument: a non-zero value is required")
+
+    let retPolicy: RetentionPolicy = SizeRetentionPolicy.init(sizeQuantity)
+    return ok(some(retPolicy))
+
   else:
     return err("unknown retention policy")

waku/waku_archive/retention_policy/retention_policy_size.nim

@@ -0,0 +1,87 @@
+when (NimMajor, NimMinor) < (1, 4):
+  {.push raises: [Defect].}
+else:
+  {.push raises: [].}
+
+import
+  std/times,
+  stew/results,
+  chronicles,
+  chronos
+import
+  ../driver,
+  ../retention_policy
+
+logScope:
+  topics = "waku archive retention_policy"
+
+# default size is 30 Gb
+const DefaultRetentionSize*: float = 30_720
+
+# to remove 20% of the outdated data from database
+const DeleteLimit = 0.80
+
+type
+  # SizeRetentionPolicy implements auto delete as follows:
+  # - sizeLimit is the size in megabytes (Mbs) the database can grow upto
+  # to reduce the size of the databases, remove the rows/number-of-messages
+  # DeleteLimit is the total number of messages to delete beyond this limit
+  # when the database size crosses the sizeLimit, then only a fraction of messages are kept,
+  # rest of the outdated message are deleted using deleteOldestMessagesNotWithinLimit(),
+  # upon deletion process the fragmented space is retrieve back using Vacuum process. 
+  SizeRetentionPolicy* = ref object of RetentionPolicy
+      sizeLimit: float
+
+proc init*(T: type SizeRetentionPolicy, size=DefaultRetentionSize): T =
+  SizeRetentionPolicy(
+    sizeLimit: size
+  )
+
+method execute*(p: SizeRetentionPolicy,
+                driver: ArchiveDriver):
+                Future[RetentionPolicyResult[void]] {.async.} =
+  ## when db size overshoots the database limit, shread 20% of outdated messages 
+
+  # to get the size of the database, pageCount and PageSize is required
+  # get page count in "messages" database
+  var pageCountRes = await driver.getPagesCount()
+  if pageCountRes.isErr():
+    return err("failed to get Pages count: " & pageCountRes.error)
+
+  var pageCount: int64 = pageCountRes.value
+
+  # # get page size of database
+  var pageSizeRes = await driver.getPagesSize()
+  if pageSizeRes.isErr():
+    return err("failed to get Page size: " & pageSizeRes.error)
+
+  # get the page size in kilobytes Kb)
+  var pageSize: int64 = int64(pageSizeRes.value div 1024)
+
+  # database size in megabytes (Mb)
+  var totalSizeOfDB: float = float(pageSize * pageCount)/1024.0
+
+  # check if current databse size crosses the db size limit
+  if totalSizeOfDB <= p.sizeLimit:
+    return ok()
+
+  # to shread/delete messsges, get the total row/message count
+  var numMessagesRes = await driver.getMessagesCount()
+  if numMessagesRes.isErr():
+    return err("failed to get messages count: " & numMessagesRes.error)
+  var numMessages = numMessagesRes.value
+
+  # 80% of the total messages are to be kept, delete others
+  let pageDeleteWindow = int(float(numMessages) * DeleteLimit)
+
+  let res = await driver.deleteOldestMessagesNotWithinLimit(limit=pageDeleteWindow)
+  if res.isErr():
+      return err("deleting oldest messages failed: " & res.error)
+
+  # vacuum to get the deleted pages defragments to save storage space
+  # this will resize the database size
+  let resVaccum = await driver.performsSqliteVacuum()
+  if resVaccum.isErr():
+    return err("vacuumming failed: " & resVaccum.error)
+
+  return ok()