tart run: introduce --net-softnet-expose (#990)

* tart run: introduce --net-softnet-expose

* --net-softnet-expose: add discussion

* --net-softnet-expose: add a note about Softnet restrictions

...and how to disable them.

* LAN → local network

* Better clarify what --net-softnet does

And how --net-softnet-allow can change that behavior.

Package.resolved

@@ -1,5 +1,5 @@
 {
-  "originHash" : "6a15657d8cb1d3e2b447f31aff5b47d6a9655d2262e48ca76476ba525435269b",
+  "originHash" : "22b3726bc4e4c6e9c04ac97cb08a82967feb39960a93d2909768a16e11576748",
   "pins" : [
     {
       "identity" : "antlr4",
@@ -55,15 +55,6 @@
         "version" : "1.5.0"
       }
     },
-    {
-      "identity" : "swift-async-algorithms",
-      "kind" : "remoteSourceControl",
-      "location" : "https://github.com/apple/swift-async-algorithms",
-      "state" : {
-        "branch" : "main",
-        "revision" : "5c8bd186f48c16af0775972700626f0b74588278"
-      }
-    },
     {
       "identity" : "swift-atomics",
       "kind" : "remoteSourceControl",
@@ -73,15 +64,6 @@
         "version" : "1.2.0"
       }
     },
-    {
-      "identity" : "swift-collections",
-      "kind" : "remoteSourceControl",
-      "location" : "https://github.com/apple/swift-collections.git",
-      "state" : {
-        "revision" : "9bf03ff58ce34478e66aaee630e491823326fd06",
-        "version" : "1.1.3"
-      }
-    },
     {
       "identity" : "swift-log",
       "kind" : "remoteSourceControl",

Package.swift

@@ -13,7 +13,6 @@ let package = Package(
     .package(url: "https://github.com/apple/swift-argument-parser", from: "1.3.1"),
     .package(url: "https://github.com/mhdhejazi/Dynamic", branch: "master"),
     .package(url: "https://github.com/apple/swift-algorithms", from: "1.2.0"),
-    .package(url: "https://github.com/apple/swift-async-algorithms", branch: "main"),
     .package(url: "https://github.com/malcommac/SwiftDate", from: "7.0.0"),
     .package(url: "https://github.com/antlr/antlr4", exact: "4.13.2"),
     .package(url: "https://github.com/apple/swift-atomics.git", .upToNextMajor(from: "1.2.0")),
@@ -29,7 +28,6 @@ let package = Package(
   targets: [
     .executableTarget(name: "tart", dependencies: [
       .product(name: "Algorithms", package: "swift-algorithms"),
-      .product(name: "AsyncAlgorithms", package: "swift-async-algorithms"),
       .product(name: "ArgumentParser", package: "swift-argument-parser"),
       .product(name: "Dynamic", package: "Dynamic"),
       .product(name: "SwiftDate", package: "SwiftDate"),

Resources/Info.plist

@@ -10,8 +10,8 @@
 	<string>org.cirruslabs.tart</string>
 	<key>CFBundleExecutable</key>
 	<string>tart</string>
-	<key>LSBackgroundOnly</key>
-	<string>1</string>
+  <key>LSApplicationCategoryType</key>
+  <string>public.app-category.developer-tools</string>
 	<key>CFBundleIconFiles</key>
 	<array>
 		<string>AppIcon.png</string>

Sources/tart/Commands/Clone.swift

@@ -71,10 +71,14 @@ struct Clone: AsyncParsableCommand {
 
       try lock.unlock()
 
-      // APFS is doing copy-on-write so the above cloning operation (just copying files on disk)
+      // APFS is doing copy-on-write, so the above cloning operation (just copying files on disk)
       // is not actually claiming new space until the VM is started and it writes something to disk.
-      // So once we clone the VM let's try to claim a little bit of space for the VM to run.
-      try Prune.reclaimIfNeeded(UInt64(sourceVM.allocatedSizeBytes()), sourceVM)
+      //
+      // So, once we clone the VM let's try to claim the rest of space for the VM to run without errors.
+      let unallocatedBytes = try sourceVM.sizeBytes() - sourceVM.allocatedSizeBytes()
+      if unallocatedBytes > 0 {
+        try Prune.reclaimIfNeeded(UInt64(unallocatedBytes), sourceVM)
+      }
     }, onCancel: {
       try? FileManager.default.removeItem(at: tmpVMDir.baseURL)
     })

Sources/tart/Commands/Pull.swift

@@ -47,8 +47,5 @@ struct Pull: AsyncParsableCommand {
     defaultLogger.appendNewLine("pulling \(remoteName)...")
 
     try await VMStorageOCI().pull(remoteName, registry: registry, concurrency: concurrency, deduplicate: deduplicate)
-
-    // to explicitly set the image as being accessed so it won't get pruned immediately
-    _ = try VMStorageOCI().open(remoteName)
   }
 }

Sources/tart/Commands/Run.swift

@@ -45,6 +45,23 @@ extension VZDiskImageSynchronizationMode {
   }
 }
 
+extension VZDiskImageCachingMode {
+  public init?(_ description: String) throws {
+    switch description {
+    case "automatic":
+      self = .automatic
+    case "cached":
+      self = .cached
+    case "uncached":
+      self = .uncached
+    case "":
+      return nil
+    default:
+      throw RuntimeError.VMConfigurationError("unsupported disk image caching mode: \"\(description)\"")
+    }
+  }
+}
+
 struct Run: AsyncParsableCommand {
   static var configuration = CommandConfiguration(abstract: "Run a VM")
 
@@ -156,6 +173,9 @@ struct Run: AsyncParsableCommand {
   """, valueName: "[name:]path[:options]"))
   var dir: [String] = []
 
+  @Flag(help: ArgumentHelp("Enable nested virtualization if possible"))
+  var nested: Bool = false
+
   @Option(help: ArgumentHelp("""
   Use bridged networking instead of the default shared (NAT) networking \n(e.g. --net-bridged=en0 or --net-bridged=\"Wi-Fi\")
   """, discussion: """
@@ -163,17 +183,46 @@ struct Run: AsyncParsableCommand {
   """, valueName: "interface name"))
   var netBridged: [String] = []
 
-  @Flag(help: ArgumentHelp("Use software networking instead of the default shared (NAT) networking",
-                           discussion: "Learn how to configure Softnet for use with Tart here: https://github.com/cirruslabs/softnet"))
+  @Flag(help: ArgumentHelp("Use software networking provided by Softnet instead of the default shared (NAT) networking",
+                           discussion: """
+                           Softnet provides better network isolation and alleviates DHCP shortage on production systems. Tart invokes Softnet when this option is specified as a sub-process and communicates with it over socketpair(2).
+
+                           It is essentially a userspace packet filter which restricts the VM networking and prevents a class of security issues, such as ARP spoofing. By default, the VM will only be able to:
+
+                           * send traffic from its own MAC-address
+                           * send traffic from the IP-address assigned to it by the DHCP
+                           * send traffic to globally routable IPv4 addresses
+                           * send traffic to gateway IP of the vmnet bridge (this would normally be \"bridge100\" interface)
+                           * receive any incoming traffic
+
+                           In addition, Softnet tunes macOS built-in DHCP server to decrease its lease time from the default 86,400 seconds (one day) to 600 seconds (10 minutes). This is especially important when you use Tart to clone and run a lot of ephemeral VMs over a period of one day.
+
+                           More on Softnet here: https://github.com/cirruslabs/softnet
+                           """))
   var netSoftnet: Bool = false
 
-  @Option(help: ArgumentHelp("Comma-separated list of CIDRs to allow the traffic to when using Softnet isolation\n(e.g. --net-softnet-allow=192.168.0.0/24)", valueName: "comma-separated CIDRs"))
+  @Option(help: ArgumentHelp("Comma-separated list of CIDRs to allow the traffic to when using Softnet isolation\n(e.g. --net-softnet-allow=192.168.0.0/24)", discussion: """
+  This option allows you bypass the private IPv4 address space restrctions imposed by --net-softnet.
+
+  For example, you can allow the VM to communicate with the local network with e.g. --net-softnet-allow=10.0.0.0/16 or to completely disable the destination based restrictions with --net-softnet-allow=0.0.0.0/0.
+  """, valueName: "comma-separated CIDRs"))
   var netSoftnetAllow: String?
 
+  @Option(help: ArgumentHelp("Comma-separated list of TCP ports to expose (e.g. --net-softnet-expose 2222:22,8080:80)", discussion: """
+  Options are comma-separated and are as follows:
+
+  * EXTERNAL_PORT:INTERNAL_PORT — forward TCP traffic from the EXTERNAL_PORT on a host's egress interface (automatically detected and could be Wi-Fi, Ethernet and a VPN interface) to the INTERNAL_PORT on guest's IP (as reported by "tart ip")
+
+  Note that your software should either listen on 0.0.0.0 inside of a VM or on an IP address assigned to that VM for the port forwarding to work correctly.
+
+  Another thing to keep in mind is that regular Softnet restrictions will still apply even to port forwarding. So if you're planning to access your VM from local network, and your local network is 192.168.0.0/24, for example, then add --net-softnet-allow=192.168.0.0/24. If you only need port forwarding, to completely disable Softnet restrictions you can use --net-softnet-allow=0.0.0.0/0.
+  """, valueName: "comma-separated port specifications"))
+  var netSoftnetExpose: String?
+
   @Flag(help: ArgumentHelp("Restrict network access to the host-only network"))
   var netHost: Bool = false
 
-  @Option(help: ArgumentHelp("Set the root disk options (e.g. --root-disk-opts=\"ro\" or --root-disk-opts=\"sync=none\")",
+  @Option(help: ArgumentHelp("Set the root disk options (e.g. --root-disk-opts=\"ro\" or --root-disk-opts=\"caching=cached,sync=none\")",
                              discussion: """
                              Options are comma-separated and are as follows:
 
@@ -184,6 +233,12 @@ struct Run: AsyncParsableCommand {
                              * sync=fsync — enable data synchronization with the permanent storage, but don't ensure that it was actually written (e.g. --root-disk-opts="sync=fsync")
 
                              * sync=full — enable data synchronization with the permanent storage and ensure that it was actually written (e.g. --root-disk-opts="sync=full")
+
+                             * caching=automatic — allows the virtualization framework to automatically determine whether to enable data caching
+
+                             * caching=cached — enabled data caching
+
+                             * caching=uncached — disables data caching
                              """, valueName: "options"))
   var rootDiskOpts: String = ""
 
@@ -221,6 +276,14 @@ struct Run: AsyncParsableCommand {
       throw ValidationError("--captures-system-keys can only be used with the default VM view")
     }
 
+    if nested {
+      if #unavailable(macOS 15) {
+        throw ValidationError("Nested virtualization is supported on hosts starting with macOS 15 (Sequia), and later.")
+      } else if !VZGenericPlatformConfiguration.isNestedVirtualizationSupported {
+        throw ValidationError("Nested virtualization is available for Mac with the M3 chip, and later.")
+      }
+    }
+
     let localStorage = VMStorageLocal()
     let vmDir = try localStorage.open(name)
     if try vmDir.state() == .Suspended {
@@ -294,9 +357,11 @@ struct Run: AsyncParsableCommand {
       directorySharingDevices: directoryShares() + rosettaDirectoryShare(),
       serialPorts: serialPorts,
       suspendable: suspendable,
+      nested: nested,
       audio: !noAudio,
       clipboard: !noClipboard,
-      sync: VZDiskImageSynchronizationMode(diskOptions.syncModeRaw)
+      sync: VZDiskImageSynchronizationMode(diskOptions.syncModeRaw),
+      caching: VZDiskImageCachingMode(diskOptions.cachingModeRaw)
     )
 
     let vncImpl: VNC? = try {
@@ -460,8 +525,10 @@ struct Run: AsyncParsableCommand {
 
     let useVNCWithoutGraphics = (vnc || vncExperimental) && !graphics
     if noGraphics || useVNCWithoutGraphics {
-      // enter the main even loop, without bringing up any UI,
-      // and just wait for the VM to exit.
+      // Enter the main event loop without bringing up any UI,
+      // waiting for the VM to exit.
+      NSApplication.shared.setActivationPolicy(.prohibited)
+
       NSApplication.shared.run()
     } else {
       runUI(suspendable, captureSystemKeys)
@@ -489,6 +556,10 @@ struct Run: AsyncParsableCommand {
       softnetExtraArguments += ["--allow", netSoftnetAllow]
     }
 
+    if let netSoftnetExpose = netSoftnetExpose {
+      softnetExtraArguments += ["--expose", netSoftnetExpose]
+    }
+
     if netSoftnet {
       let config = try VMConfig.init(fromURL: vmDir.configURL)
 
@@ -617,7 +688,7 @@ struct MainApp: App {
   static var suspendable: Bool = false
   static var capturesSystemKeys: Bool = false
 
-  @NSApplicationDelegateAdaptor private var appDelegate: MinimalMenuAppDelegate
+  @NSApplicationDelegateAdaptor private var appDelegate: AppDelegate
 
   var body: some Scene {
     WindowGroup(vm!.name) {
@@ -673,18 +744,7 @@ struct MainApp: App {
   }
 }
 
-// The only way to fully remove Edit menu item.
-class MinimalMenuAppDelegate: NSObject, NSApplicationDelegate, ObservableObject {
-  let indexOfEditMenu = 2
-
-  func applicationDidFinishLaunching(_ : Notification) {
-    NSApplication.shared.mainMenu?.removeItem(at: indexOfEditMenu)
-
-    let nsApp = NSApplication.shared
-    nsApp.setActivationPolicy(.regular)
-    nsApp.activate(ignoringOtherApps: true)
-  }
-
+class AppDelegate: NSObject, NSApplicationDelegate, ObservableObject {
   func applicationShouldTerminate(_ sender: NSApplication) -> NSApplication.TerminateReply {
     if (kill(getpid(), MainApp.suspendable ? SIGUSR1 : SIGINT) == 0) {
       return .terminateLater
@@ -737,12 +797,12 @@ struct VMView: NSViewRepresentable {
 
     machineView.capturesSystemKeys = capturesSystemKeys
 
-    // Enable automatic display reconfiguration
-    // for guests that support it
+    // If not specified, enable automatic display
+    // reconfiguration for guests that support it
     //
     // This is disabled for Linux because of poor HiDPI
     // support, which manifests in fonts being too small
-    if #available(macOS 14.0, *), vm.config.os != .linux {
+    if #available(macOS 14.0, *), vm.config.displayRefit ?? (vm.config.os != .linux) {
       machineView.automaticallyReconfiguresDisplay = true
     }
 
@@ -758,12 +818,12 @@ struct AdditionalDisk {
   let configuration: VZStorageDeviceConfiguration
 
   init(parseFrom: String) throws {
-    let (diskPath, readOnly, syncModeRaw) = Self.parseOptions(parseFrom)
+    let (diskPath, readOnly, syncModeRaw, cachingModeRaw) = Self.parseOptions(parseFrom)
 
-    self.configuration = try Self.craft(diskPath, readOnly: readOnly, syncModeRaw: syncModeRaw)
+    self.configuration = try Self.craft(diskPath, readOnly: readOnly, syncModeRaw: syncModeRaw, cachingModeRaw: cachingModeRaw)
   }
 
-  static func craft(_ diskPath: String, readOnly diskReadOnly: Bool, syncModeRaw: String) throws -> VZStorageDeviceConfiguration {
+  static func craft(_ diskPath: String, readOnly diskReadOnly: Bool, syncModeRaw: String, cachingModeRaw: String) throws -> VZStorageDeviceConfiguration {
     let diskURL = URL(string: diskPath)
 
     if (["nbd", "nbds", "nbd+unix", "nbds+unix"].contains(diskURL?.scheme)) {
@@ -840,14 +900,14 @@ struct AdditionalDisk {
     let diskImageAttachment = try VZDiskImageStorageDeviceAttachment(
       url: diskFileURL,
       readOnly: diskReadOnly,
-      cachingMode: .automatic,
+      cachingMode: try VZDiskImageCachingMode(cachingModeRaw) ?? .automatic,
       synchronizationMode: try VZDiskImageSynchronizationMode(syncModeRaw)
     )
 
     return VZVirtioBlockDeviceConfiguration(attachment: diskImageAttachment)
   }
 
-  static func parseOptions(_ parseFrom: String) -> (String, Bool, String) {
+  static func parseOptions(_ parseFrom: String) -> (String, Bool, String, String) {
     var arguments = parseFrom.split(separator: ":")
 
     let options = DiskOptions(String(arguments.last!))
@@ -855,13 +915,14 @@ struct AdditionalDisk {
       arguments.removeLast()
     }
 
-    return (arguments.joined(separator: ":"), options.readOnly, options.syncModeRaw)
+    return (arguments.joined(separator: ":"), options.readOnly, options.syncModeRaw, options.cachingModeRaw)
   }
 }
 
 struct DiskOptions {
   var readOnly: Bool = false
   var syncModeRaw: String = ""
+  var cachingModeRaw: String = ""
   var foundAtLeastOneOption: Bool = false
 
   init(_ parseFrom: String) {
@@ -875,6 +936,9 @@ struct DiskOptions {
       case option.hasPrefix("sync="):
         self.syncModeRaw = String(option.dropFirst("sync=".count))
         self.foundAtLeastOneOption = true
+      case option.hasPrefix("caching="):
+        self.cachingModeRaw = String(option.dropFirst("caching=".count))
+        self.foundAtLeastOneOption = true
       default:
         continue
       }

Sources/tart/Commands/Set.swift

@@ -17,6 +17,9 @@ struct Set: AsyncParsableCommand {
   @Option(help: "VM display resolution in a format of <width>x<height>. For example, 1200x800")
   var display: VMDisplayConfig?
 
+  @Flag(inversion: .prefixedNo, help: ArgumentHelp("Whether to automatically reconfigure the VM's display to fit the window"))
+  var displayRefit: Bool? = nil
+
   @Flag(help: ArgumentHelp("Generate a new random MAC address for the VM."))
   var randomMAC: Bool = false
 
@@ -63,6 +66,8 @@ struct Set: AsyncParsableCommand {
       }
     }
 
+    vmConfig.displayRefit = displayRefit
+
     if randomMAC {
       vmConfig.macAddress = VZMACAddress.randomLocallyAdministered()
     }

Sources/tart/Fetcher.swift

@@ -1,69 +1,6 @@
 import Foundation
-import AsyncAlgorithms
 
-fileprivate let urlSession = createURLSession()
-
-class DownloadDelegate: NSObject, URLSessionTaskDelegate {
-  let progress: Progress
-  init(_ progress: Progress) throws {
-    self.progress = progress
-  }
-
-  func urlSession(_ session: URLSession, didCreateTask task: URLSessionTask) {
-    self.progress.addChild(task.progress, withPendingUnitCount: self.progress.totalUnitCount)
-  }
-}
-
-class Fetcher {
-  static func fetch(_ request: URLRequest, viaFile: Bool = false, progress: Progress? = nil) async throws -> (AsyncThrowingChannel<Data, Error>, HTTPURLResponse) {
-    let delegate = progress != nil ? try DownloadDelegate(progress!) : nil
-
-    if viaFile {
-      return try await fetchViaFile(request, delegate: delegate)
-    }
-
-    return try await fetchViaMemory(request, delegate: delegate)
-  }
-
-  private static func fetchViaMemory(_ request: URLRequest, delegate: URLSessionTaskDelegate? = nil) async throws -> (AsyncThrowingChannel<Data, Error>, HTTPURLResponse) {
-    let dataCh = AsyncThrowingChannel<Data, Error>()
-
-    let (data, response) = try await urlSession.data(for: request, delegate: delegate)
-
-    Task {
-      await dataCh.send(data)
-
-      dataCh.finish()
-    }
-
-    return (dataCh, response as! HTTPURLResponse)
-  }
-
-  private static func fetchViaFile(_ request: URLRequest, delegate: URLSessionTaskDelegate? = nil) async throws -> (AsyncThrowingChannel<Data, Error>, HTTPURLResponse) {
-    let dataCh = AsyncThrowingChannel<Data, Error>()
-
-    let (fileURL, response) = try await urlSession.download(for: request, delegate: delegate)
-
-    // Acquire a handle to the downloaded file and then remove it.
-    //
-    // This keeps a working reference to that file, yet we don't
-    // have to deal with the cleanup any more.
-    let mappedFile = try Data(contentsOf: fileURL, options: [.alwaysMapped])
-    try FileManager.default.removeItem(at: fileURL)
-
-    Task {
-      for chunk in (0 ..< mappedFile.count).chunks(ofCount: 64 * 1024 * 1024) {
-        await dataCh.send(mappedFile.subdata(in: chunk))
-      }
-
-      dataCh.finish()
-    }
-
-    return (dataCh, response as! HTTPURLResponse)
-  }
-}
-
-fileprivate func createURLSession() -> URLSession {
+fileprivate var urlSession: URLSession = {
   let config = URLSessionConfiguration.default
 
   // Harbor expects a CSRF token to be present if the HTTP client
@@ -77,4 +14,84 @@ fileprivate func createURLSession() -> URLSession {
   config.httpShouldSetCookies = false
 
   return URLSession(configuration: config)
+}()
+
+class Fetcher {
+  static func fetch(_ request: URLRequest, viaFile: Bool = false) async throws -> (AsyncThrowingStream<Data, Error>, HTTPURLResponse) {
+    let task = urlSession.dataTask(with: request)
+
+    let delegate = Delegate()
+    task.delegate = delegate
+
+    let stream = AsyncThrowingStream<Data, Error> { continuation in
+      delegate.streamContinuation = continuation
+    }
+
+    let response = try await withCheckedThrowingContinuation { continuation in
+      delegate.responseContinuation = continuation
+      task.resume()
+    }
+
+    return (stream, response as! HTTPURLResponse)
+  }
+}
+
+fileprivate class Delegate: NSObject, URLSessionDataDelegate {
+  var responseContinuation: CheckedContinuation<URLResponse, Error>?
+  var streamContinuation: AsyncThrowingStream<Data, Error>.Continuation?
+
+  private var buffer: Data = Data()
+  private let bufferFlushSize = 16 * 1024 * 1024
+
+  func urlSession(
+    _ session: URLSession,
+    dataTask: URLSessionDataTask,
+    didReceive response: URLResponse,
+    completionHandler: @escaping (URLSession.ResponseDisposition) -> Void
+  ) {
+    // Soft-limit for the maximum buffer capacity
+    let capacity = min(response.expectedContentLength, Int64(bufferFlushSize))
+
+    // Pre-initialize buffer as we now know the capacity
+    buffer = Data(capacity: Int(capacity))
+
+    responseContinuation?.resume(returning: response)
+    responseContinuation = nil
+    completionHandler(.allow)
+  }
+
+  func urlSession(
+    _ session: URLSession,
+    dataTask: URLSessionDataTask,
+    didReceive data: Data
+  ) {
+    buffer.append(data)
+
+    if buffer.count >= bufferFlushSize {
+      streamContinuation?.yield(buffer)
+      buffer.removeAll(keepingCapacity: true)
+    }
+  }
+
+  func urlSession(
+    _ session: URLSession,
+    task: URLSessionTask,
+    didCompleteWithError error: Error?
+  ) {
+    if let error = error {
+      responseContinuation?.resume(throwing: error)
+      responseContinuation = nil
+
+      streamContinuation?.finish(throwing: error)
+      streamContinuation = nil
+    } else {
+      if !buffer.isEmpty {
+        streamContinuation?.yield(buffer)
+        buffer.removeAll(keepingCapacity: true)
+      }
+
+      streamContinuation?.finish()
+      streamContinuation = nil
+    }
+  }
 }

Sources/tart/OCI/Layerizer/DiskV2.swift

@@ -7,6 +7,21 @@ class DiskV2: Disk {
   private static let bufferSizeBytes = 4 * 1024 * 1024
   private static let layerLimitBytes = 512 * 1024 * 1024
 
+  // A zero chunk for faster than byte-by-byte comparisons
+  //
+  // Assumes that the other Data(...) is equal in size, but it's fine to get a false-negative
+  // on the last block since it costs only 4 MiB of excess data per 512 MiB layer.
+  //
+  // Some simple benchmarks ("sync && sudo purge" command was used to negate the disk caching effects):
+  // +--------------------------------------+---------------------------------------------------+
+  // | Operation                            | time(1) result                                    |
+  // +--------------------------------------+---------------------------------------------------+
+  // | Data(...) == zeroChunk               | 2.16s user 11.71s system 73% cpu 18.928 total     |
+  // | Data(...).contains(where: {$0 != 0}) | 603.68s user 12.97s system 99% cpu 10:22.85 total |
+  // +--------------------------------------+---------------------------------------------------+
+  private static let holeGranularityBytes = 4 * 1024 * 1024
+  private static let zeroChunk = Data(count: holeGranularityBytes)
+
   static func push(diskURL: URL, registry: Registry, chunkSizeMb: Int, concurrency: UInt, progress: Progress) async throws -> [OCIManifestLayer] {
     var pushedLayers: [(index: Int, pushedLayer: OCIManifestLayer)] = []
 
@@ -29,7 +44,7 @@ class DiskV2: Disk {
           let compressedData = try (data as NSData).compressed(using: .lz4) as Data
           let compressedDataDigest = Digest.hash(compressedData)
 
-          try await retry(maxAttempts: 5, backoff: .exponentialWithFullJitter(baseDelay: .seconds(5), maxDelay: .seconds(60))) {
+          try await retry(maxAttempts: 5) {
             if try await !registry.blobExists(compressedDataDigest) {
               _ = try await registry.pushBlob(fromData: compressedData, chunkSizeMb: chunkSizeMb, digest: compressedDataDigest)
             }
@@ -193,11 +208,26 @@ class DiskV2: Disk {
             diskWritingOffset = try zeroSkippingWrite(disk, rdisk, fsBlockSize, diskWritingOffset, data)
           }
 
-          try await registry.pullBlob(diskLayer.digest) { data in
-            try filter.write(data)
+          var rangeStart: Int64 = 0
 
-            // Update the progress
-            progress.completedUnitCount += Int64(data.count)
+          try await retry(maxAttempts: 5) {
+            try await registry.pullBlob(diskLayer.digest, rangeStart: rangeStart) { data in
+              try filter.write(data)
+
+              // Update the progress
+              progress.completedUnitCount += Int64(data.count)
+
+              // Update the current range start
+              rangeStart += Int64(data.count)
+            }
+          } recoverFromFailure: { error in
+            if error is URLError {
+              print("Error pulling disk layer \(index + 1): \"\(error.localizedDescription)\", attempting to re-try...")
+
+              return .retry
+            }
+
+            return .throw
           }
 
           try filter.finalize()
@@ -215,22 +245,6 @@ class DiskV2: Disk {
   }
 
   private static func zeroSkippingWrite(_ disk: FileHandle, _ rdisk: FileHandle?, _ fsBlockSize: UInt64, _ offset: UInt64, _ data: Data) throws -> UInt64 {
-    let holeGranularityBytes = 64 * 1024
-
-    // A zero chunk for faster than byte-by-byte comparisons
-    //
-    // Assumes that the other Data(...) is equal in size, but it's fine to get a false-negative
-    // on the last block since it costs only 64 KiB of excess data per 500 MB layer.
-    //
-    // Some simple benchmarks ("sync && sudo purge" command was used to negate the disk caching effects):
-    // +--------------------------------------+---------------------------------------------------+
-    // | Operation                            | time(1) result                                    |
-    // +--------------------------------------+---------------------------------------------------+
-    // | Data(...) == zeroChunk               | 2.16s user 11.71s system 73% cpu 18.928 total     |
-    // | Data(...).contains(where: {$0 != 0}) | 603.68s user 12.97s system 99% cpu 10:22.85 total |
-    // +--------------------------------------+---------------------------------------------------+
-    let zeroChunk = Data(count: holeGranularityBytes)
-
     var offset = offset
 
     for chunk in data.chunks(ofCount: holeGranularityBytes) {

Sources/tart/OCI/Registry.swift

@@ -1,6 +1,5 @@
 import Foundation
 import Algorithms
-import AsyncAlgorithms
 
 enum RegistryError: Error {
   case UnexpectedHTTPStatusCode(when: String, code: Int, details: String = "")
@@ -21,6 +20,7 @@ enum HTTPCode: Int {
   case Ok = 200
   case Created = 201
   case Accepted = 202
+  case PartialContent = 206
   case Unauthorized = 401
   case NotFound = 404
 }
@@ -29,14 +29,26 @@ extension Data {
   func asText() -> String {
     String(decoding: self, as: UTF8.self)
   }
+
+  func asTextPreview(limit: Int = 1000) -> String {
+    guard count > limit else {
+      return asText()
+    }
+
+    return "\(asText().prefix(limit))..."
+  }
 }
 
-extension AsyncThrowingChannel<Data, Error> {
-  func asData() async throws -> Data {
+extension AsyncThrowingStream<Data, Error> {
+  func asData(limitBytes: Int64? = nil) async throws -> Data {
     var result = Data()
 
     for try await chunk in self {
       result += chunk
+
+      if let limitBytes, result.count > limitBytes {
+        return result
+      }
     }
 
     return result
@@ -160,7 +172,7 @@ class Registry {
                                                  body: manifestJSON)
     if response.statusCode != HTTPCode.Created.rawValue {
       throw RegistryError.UnexpectedHTTPStatusCode(when: "pushing manifest", code: response.statusCode,
-                                                   details: data.asText())
+                                                   details: data.asTextPreview())
     }
 
     return Digest.hash(manifestJSON)
@@ -171,7 +183,7 @@ class Registry {
                                                  headers: ["Accept": ociManifestMediaType])
     if response.statusCode != HTTPCode.Ok.rawValue {
       throw RegistryError.UnexpectedHTTPStatusCode(when: "pulling manifest", code: response.statusCode,
-                                                   details: data.asText())
+                                                   details: data.asTextPreview())
     }
 
     let manifest = try OCIManifest(fromJSON: data)
@@ -197,7 +209,7 @@ class Registry {
                                                      headers: ["Content-Length": "0"])
     if postResponse.statusCode != HTTPCode.Accepted.rawValue {
       throw RegistryError.UnexpectedHTTPStatusCode(when: "pushing blob (POST)", code: postResponse.statusCode,
-                                                   details: data.asText())
+                                                   details: data.asTextPreview())
     }
 
     // Figure out where to upload the blob
@@ -218,7 +230,7 @@ class Registry {
       )
       if response.statusCode != HTTPCode.Created.rawValue {
         throw RegistryError.UnexpectedHTTPStatusCode(when: "pushing blob (PUT) to \(uploadLocation)",
-                                                     code: response.statusCode, details: data.asText())
+                                                     code: response.statusCode, details: data.asTextPreview())
       }
       return digest
     }
@@ -241,7 +253,7 @@ class Registry {
       // always accept both statuses since AWS ECR is not following specification
       if response.statusCode != HTTPCode.Created.rawValue && response.statusCode != HTTPCode.Accepted.rawValue {
         throw RegistryError.UnexpectedHTTPStatusCode(when: "streaming blob to \(uploadLocation)",
-                                                     code: response.statusCode, details: data.asText())
+                                                     code: response.statusCode, details: data.asTextPreview())
       }
       uploadedBytes += chunk.count
       // Update location for the next chunk
@@ -260,14 +272,26 @@ class Registry {
     case HTTPCode.NotFound.rawValue:
       return false
     default:
-      throw RegistryError.UnexpectedHTTPStatusCode(when: "checking blob", code: response.statusCode, details: data.asText())
+      throw RegistryError.UnexpectedHTTPStatusCode(when: "checking blob", code: response.statusCode, details: data.asTextPreview())
     }
   }
 
-  public func pullBlob(_ digest: String, handler: (Data) async throws -> Void) async throws {
-    let (channel, response) = try await channelRequest(.GET, endpointURL("\(namespace)/blobs/\(digest)"), viaFile: true)
-    if response.statusCode != HTTPCode.Ok.rawValue {
-      let body = try await channel.asData().asText()
+  public func pullBlob(_ digest: String, rangeStart: Int64 = 0, handler: (Data) async throws -> Void) async throws {
+    var expectedStatusCode = HTTPCode.Ok
+    var headers: [String: String] = [:]
+
+    // Send Range header and expect HTTP 206 in return
+    //
+    // However, do not send Range header at all when rangeStart is 0,
+    // because it makes no sense and we might get HTTP 200 in return
+    if rangeStart != 0 {
+      expectedStatusCode = HTTPCode.PartialContent
+      headers["Range"] = "bytes=\(rangeStart)-"
+    }
+
+    let (channel, response) = try await channelRequest(.GET, endpointURL("\(namespace)/blobs/\(digest)"), headers: headers, viaFile: true)
+    if response.statusCode != expectedStatusCode.rawValue {
+      let body = try await channel.asData(limitBytes: 4096).asTextPreview()
       throw RegistryError.UnexpectedHTTPStatusCode(when: "pulling blob", code: response.statusCode,
                                                    details: body)
     }
@@ -307,7 +331,7 @@ class Registry {
     body: Data? = nil,
     doAuth: Bool = true,
     viaFile: Bool = false
-  ) async throws -> (AsyncThrowingChannel<Data, Error>, HTTPURLResponse) {
+  ) async throws -> (AsyncThrowingStream<Data, Error>, HTTPURLResponse) {
     var urlComponents = urlComponents
 
     if urlComponents.queryItems == nil && !parameters.isEmpty {
@@ -330,7 +354,6 @@ class Registry {
     var (channel, response) = try await authAwareRequest(request: request, viaFile: viaFile, doAuth: doAuth)
 
     if doAuth && response.statusCode == HTTPCode.Unauthorized.rawValue {
-      _ = try await channel.asData()
       try await auth(response: response)
       (channel, response) = try await authAwareRequest(request: request, viaFile: viaFile, doAuth: doAuth)
     }
@@ -392,7 +415,7 @@ class Registry {
     let (data, response) = try await dataRequest(.GET, authenticateURL, headers: headers, doAuth: false)
     if response.statusCode != HTTPCode.Ok.rawValue {
       throw RegistryError.AuthFailed(why: "received unexpected HTTP status code \(response.statusCode) "
-        + "while retrieving an authentication token", details: data.asText())
+        + "while retrieving an authentication token", details: data.asTextPreview())
     }
 
     await authenticationKeeper.set(try TokenResponse.parse(fromData: data))
@@ -413,7 +436,7 @@ class Registry {
     return nil
   }
 
-  private func authAwareRequest(request: URLRequest, viaFile: Bool = false, doAuth: Bool) async throws -> (AsyncThrowingChannel<Data, Error>, HTTPURLResponse) {
+  private func authAwareRequest(request: URLRequest, viaFile: Bool = false, doAuth: Bool) async throws -> (AsyncThrowingStream<Data, Error>, HTTPURLResponse) {
     var request = request
 
     if doAuth {

Sources/tart/Platform/Darwin.swift

@@ -38,7 +38,7 @@ struct UnsupportedHostOSError: Error, CustomStringConvertible {
         throw DecodingError.dataCorruptedError(forKey: .hardwareModel, in: container, debugDescription: "")
       }
       guard let hardwareModel = VZMacHardwareModel.init(dataRepresentation: data) else {
-        throw DecodingError.dataCorruptedError(forKey: .hardwareModel, in: container, debugDescription: "")
+        throw UnsupportedHostOSError()
       }
       self.hardwareModel = hardwareModel
     }
@@ -58,7 +58,11 @@ struct UnsupportedHostOSError: Error, CustomStringConvertible {
       VZMacOSBootLoader()
     }
 
-    func platform(nvramURL: URL) throws -> VZPlatformConfiguration {
+    func platform(nvramURL: URL, needsNestedVirtualization: Bool) throws -> VZPlatformConfiguration {
+      if needsNestedVirtualization {
+        throw RuntimeError.VMConfigurationError("macOS virtual machines do not support nested virtualization")
+      }
+
       let result = VZMacPlatformConfiguration()
 
       result.machineIdentifier = ecid

Sources/tart/Platform/Linux.swift

@@ -14,8 +14,12 @@ struct Linux: Platform {
     return result
   }
 
-  func platform(nvramURL: URL) throws -> VZPlatformConfiguration {
-    VZGenericPlatformConfiguration()
+  func platform(nvramURL: URL, needsNestedVirtualization: Bool) throws -> VZPlatformConfiguration {
+    let config = VZGenericPlatformConfiguration()
+    if #available(macOS 15, *) {
+      config.isNestedVirtualizationEnabled = needsNestedVirtualization
+    }
+    return config
   }
 
   func graphicsDevice(vmConfig: VMConfig) -> VZGraphicsDeviceConfiguration {

Sources/tart/Platform/Platform.swift

@@ -3,7 +3,7 @@ import Virtualization
 protocol Platform: Codable {
   func os() -> OS
   func bootLoader(nvramURL: URL) throws -> VZBootLoader
-  func platform(nvramURL: URL) throws -> VZPlatformConfiguration
+  func platform(nvramURL: URL, needsNestedVirtualization: Bool) throws -> VZPlatformConfiguration
   func graphicsDevice(vmConfig: VMConfig) -> VZGraphicsDeviceConfiguration
   func keyboards() -> [VZKeyboardConfiguration]
   func pointingDevices() -> [VZPointingDeviceConfiguration]

Sources/tart/VM.swift

@@ -1,6 +1,5 @@
 import Foundation
 import Virtualization
-import AsyncAlgorithms
 import Semaphore
 
 struct UnsupportedRestoreImageError: Error {
@@ -47,9 +46,11 @@ class VM: NSObject, VZVirtualMachineDelegate, ObservableObject {
        directorySharingDevices: [VZDirectorySharingDeviceConfiguration] = [],
        serialPorts: [VZSerialPortConfiguration] = [],
        suspendable: Bool = false,
+       nested: Bool = false,
        audio: Bool = true,
        clipboard: Bool = true,
-       sync: VZDiskImageSynchronizationMode = .full
+       sync: VZDiskImageSynchronizationMode = .full,
+       caching: VZDiskImageCachingMode? = nil
   ) throws {
     name = vmDir.name
     config = try VMConfig.init(fromURL: vmDir.configURL)
@@ -66,9 +67,11 @@ class VM: NSObject, VZVirtualMachineDelegate, ObservableObject {
                                                 directorySharingDevices: directorySharingDevices,
                                                 serialPorts: serialPorts,
                                                 suspendable: suspendable,
+                                                nested: nested,
                                                 audio: audio,
                                                 clipboard: clipboard,
-                                                sync: sync
+                                                sync: sync,
+                                                caching: caching
     )
     virtualMachine = VZVirtualMachine(configuration: configuration)
 
@@ -96,16 +99,13 @@ class VM: NSObject, VZVirtualMachineDelegate, ObservableObject {
     // Download the IPSW
     defaultLogger.appendNewLine("Fetching \(remoteURL.lastPathComponent)...")
 
-    let downloadProgress = Progress(totalUnitCount: 100)
-    ProgressObserver(downloadProgress).log(defaultLogger)
-
     let request = URLRequest(url: remoteURL)
-    let (channel, response) = try await Fetcher.fetch(request, viaFile: true, progress: downloadProgress)
+    let (channel, response) = try await Fetcher.fetch(request, viaFile: true)
 
     let temporaryLocation = try Config().tartTmpDir.appendingPathComponent(UUID().uuidString + ".ipsw")
-    defaultLogger.appendNewLine("Computing digest for \(temporaryLocation.path)...")
-    let digestProgress = Progress(totalUnitCount: response.expectedContentLength)
-    ProgressObserver(digestProgress).log(defaultLogger)
+
+    let progress = Progress(totalUnitCount: response.expectedContentLength)
+    ProgressObserver(progress).log(defaultLogger)
 
     FileManager.default.createFile(atPath: temporaryLocation.path, contents: nil)
     let lock = try FileLock(lockURL: temporaryLocation)
@@ -115,10 +115,9 @@ class VM: NSObject, VZVirtualMachineDelegate, ObservableObject {
     let digest = Digest()
 
     for try await chunk in channel {
-      let chunkAsData = Data(chunk)
-      fileHandle.write(chunkAsData)
-      digest.update(chunkAsData)
-      digestProgress.completedUnitCount += Int64(chunk.count)
+      fileHandle.write(chunk)
+      digest.update(chunk)
+      progress.completedUnitCount += Int64(chunk.count)
     }
 
     try fileHandle.close()
@@ -295,9 +294,11 @@ class VM: NSObject, VZVirtualMachineDelegate, ObservableObject {
     directorySharingDevices: [VZDirectorySharingDeviceConfiguration],
     serialPorts: [VZSerialPortConfiguration],
     suspendable: Bool = false,
+    nested: Bool = false,
     audio: Bool = true,
     clipboard: Bool = true,
-    sync: VZDiskImageSynchronizationMode = .full
+    sync: VZDiskImageSynchronizationMode = .full,
+    caching: VZDiskImageCachingMode? = nil
   ) throws -> VZVirtualMachineConfiguration {
     let configuration = VZVirtualMachineConfiguration()
 
@@ -309,7 +310,7 @@ class VM: NSObject, VZVirtualMachineDelegate, ObservableObject {
     configuration.memorySize = vmConfig.memorySize
 
     // Platform
-    configuration.platform = try vmConfig.platform.platform(nvramURL: nvramURL)
+    configuration.platform = try vmConfig.platform.platform(nvramURL: nvramURL, needsNestedVirtualization: nested)
 
     // Display
     configuration.graphicsDevices = [vmConfig.platform.graphicsDevice(vmConfig: vmConfig)]
@@ -360,10 +361,15 @@ class VM: NSObject, VZVirtualMachineDelegate, ObservableObject {
     }
 
     // Storage
-    let attachment: VZDiskImageStorageDeviceAttachment = vmConfig.os == .linux ?
-      // Use "cached" caching mode for virtio drive to prevent fs corruption on linux
-      try VZDiskImageStorageDeviceAttachment(url: diskURL, readOnly: false, cachingMode: .cached, synchronizationMode: sync) :
-      try VZDiskImageStorageDeviceAttachment(url: diskURL, readOnly: false, cachingMode: .automatic, synchronizationMode: sync)
+    let attachment: VZDiskImageStorageDeviceAttachment =  try VZDiskImageStorageDeviceAttachment(
+      url: diskURL,
+      readOnly: false,
+      // When not specified, use "cached" caching mode for Linux VMs to prevent file-system corruption[1]
+      //
+      // [1]: https://github.com/cirruslabs/tart/pull/675
+      cachingMode: caching ?? (vmConfig.os == .linux ? .cached : .automatic),
+      synchronizationMode: sync
+    )
 
     var devices: [VZStorageDeviceConfiguration] = [VZVirtioBlockDeviceConfiguration(attachment: attachment)]
     devices.append(contentsOf: additionalStorageDevices)

Sources/tart/VMConfig.swift

@@ -24,6 +24,7 @@ enum CodingKeys: String, CodingKey {
   case memorySize
   case macAddress
   case display
+  case displayRefit
 
   // macOS-specific keys
   case ecid
@@ -52,6 +53,7 @@ struct VMConfig: Codable {
   private(set) var memorySize: UInt64
   var macAddress: VZMACAddress
   var display: VMDisplayConfig = VMDisplayConfig()
+  var displayRefit: Bool?
 
   init(
     platform: Platform,
@@ -121,6 +123,7 @@ struct VMConfig: Codable {
     self.macAddress = macAddress
 
     display = try container.decodeIfPresent(VMDisplayConfig.self, forKey: .display) ?? VMDisplayConfig()
+    displayRefit = try container.decodeIfPresent(Bool.self, forKey: .displayRefit)
   }
 
   func encode(to encoder: Encoder) throws {
@@ -136,6 +139,9 @@ struct VMConfig: Codable {
     try container.encode(memorySize, forKey: .memorySize)
     try container.encode(macAddress.string, forKey: .macAddress)
     try container.encode(display, forKey: .display)
+    if let displayRefit = displayRefit {
+      try container.encode(displayRefit, forKey: .displayRefit)
+    }
   }
 
   mutating func setCPU(cpuCount: Int) throws {

Sources/tart/VMStorageOCI.swift

@@ -196,7 +196,7 @@ class VMStorageOCI: PrunableStorage {
       }
 
       try await withTaskCancellationHandler(operation: {
-        try await retry(maxAttempts: 5, backoff: .exponentialWithFullJitter(baseDelay: .seconds(5), maxDelay: .seconds(60))) {
+        try await retry(maxAttempts: 5) {
           // Choose the best base image which has the most deduplication ratio
           let localLayerCache = try await chooseLocalLayerCache(name, manifest, registry)
 
@@ -212,9 +212,8 @@ class VMStorageOCI: PrunableStorage {
 
           try await tmpVMDir.pullFromRegistry(registry: registry, manifest: manifest, concurrency: concurrency, localLayerCache: localLayerCache, deduplicate: deduplicate)
         } recoverFromFailure: { error in
-          if error is Retryable {
-            print("Error: \(error.localizedDescription)")
-            print("Attempting to re-try...")
+          if error is URLError {
+            print("Error pulling image: \"\(error.localizedDescription)\", attempting to re-try...")
 
             return .retry
           }
@@ -239,6 +238,9 @@ class VMStorageOCI: PrunableStorage {
       // are excluded from garbage collection
       VMDirectory(baseURL: vmURL(name)).markExplicitlyPulled()
     }
+
+    // to explicitly set the image as being accessed so it won't get pruned immediately
+    _ = try VMStorageOCI().open(name)
   }
 
   func linked(from: RemoteName, to: RemoteName) -> Bool {

Tests/TartTests/Util/RegistryRunner.swift

@@ -31,7 +31,7 @@ class RegistryRunner {
 
   init() async throws {
     // Start container
-    let container = try Self.dockerCmd("run", "-d", "--rm", "-p", "5000", "registry:2")
+    let container = try Self.dockerCmd("run", "-d", "--rm", "-p", "127.0.0.1:0:5000", "registry:2")
       .trimmingCharacters(in: CharacterSet.newlines)
     containerID = container
 

benchmark/README.md

@@ -2,10 +2,18 @@
 
 Tart comes with a Golang-based benchmarking utility that allows one to easily compare host and guest performance.
 
-Currently, only Flexible I/O tester workloads are supported. To run them, [install Golang](https://go.dev/) and run the following command from this (`benchmark/`) directory:
+Currently, only Flexible I/O tester workloads are supported. To run them, first make sure that [passwordless sudo](https://serverfault.com/questions/160581/how-to-setup-passwordless-sudo-on-linux) is configured.
+
+Then, [install Golang](https://go.dev/). The easiest way is through [Homebrew](https://brew.sh/):
 
 ```shell
-go run cmd/main.go fio
+brew install go
+```
+
+Finally, run the following command from this (`benchmark/`) directory:
+
+```shell
+go run cmd/main.go fio --image ghcr.io/cirruslabs/macos-sonoma-base:latest --prepare 'sudo purge && sync'
 ```
 
 You can also enable the debugging output to diagnose issues:
@@ -16,6 +24,8 @@ go run cmd/main.go fio --debug
 
 ## Results
 
+### Mar 27, 2024
+
 Host:
 
 * Hardware: Mac mini (Apple M2 Pro, 8 performance and 4 efficiency cores, 32 GB RAM, `Mac14,12`)
@@ -37,3 +47,141 @@ Random writing of 100MB 	Tart    	2.0 GB/s 	493.31 kIOPS
 Random writing of 1000MB	local   	1.7 GB/s 	414.89 kIOPS  
 Random writing of 1000MB	Tart    	1.1 GB/s 	287.4 kIOPS  
 ```
+
+### Dec 2, 2024
+
+Host:
+
+* Hardware: MacBook Pro (Apple M1 Pro, 8 performance and 2 efficiency cores, 32 GB RAM, `MacBookPro18,3`)
+* OS: macOS Sequoia 15.1.1
+
+Guest:
+
+* Hardware: [Virtualization.Framework](https://developer.apple.com/documentation/virtualization)
+* OS: macOS Sonoma 14.6
+
+```
+Name                                    	Executor                                          	B/W (read)	B/W (write)	I/O (read) 	I/O (write) 	Latency (read)          	Latency (write)         	Latency (sync)      
+Single 4KiB random write process        	local                                             	0 B/s     	19 MB/s    	0 IOPS     	4.81 kIOPS  	0s ± 0s                 	203.418µs ± 155.865µs   	0s ± 0s             
+Single 4KiB random write process        	Tart                                              	0 B/s     	18 MB/s    	0 IOPS     	4.54 kIOPS  	0s ± 0s                 	213.655µs ± 188.822µs   	0s ± 0s             
+Single 4KiB random write process        	Tart (--root-disk-opts="sync=none")               	0 B/s     	19 MB/s    	0 IOPS     	4.68 kIOPS  	0s ± 0s                 	208.413µs ± 183.45µs    	0s ± 0s             
+Single 4KiB random write process        	Tart (--root-disk-opts="caching=cached")          	0 B/s     	24 MB/s    	0 IOPS     	6.11 kIOPS  	0s ± 0s                 	158.07µs ± 2.294654ms   	0s ± 0s             
+Single 4KiB random write process        	Tart (--root-disk-opts="sync=none,caching=cached")	0 B/s     	22 MB/s    	0 IOPS     	5.49 kIOPS  	0s ± 0s                 	173.414µs ± 310.213µs   	0s ± 0s             
+16 parallel 64KiB random write processes	local                                             	0 B/s     	18 GB/s    	0 IOPS     	273.76 kIOPS	0s ± 0s                 	323.423µs ± 604.999µs   	0s ± 0s             
+16 parallel 64KiB random write processes	Tart                                              	0 B/s     	16 GB/s    	0 IOPS     	273.48 kIOPS	0s ± 0s                 	335.086µs ± 7.591748ms  	0s ± 0s             
+16 parallel 64KiB random write processes	Tart (--root-disk-opts="sync=none")               	0 B/s     	18 GB/s    	0 IOPS     	281.49 kIOPS	0s ± 0s                 	326.655µs ± 7.485473ms  	0s ± 0s             
+16 parallel 64KiB random write processes	Tart (--root-disk-opts="caching=cached")          	0 B/s     	17 GB/s    	0 IOPS     	266.79 kIOPS	0s ± 0s                 	340µs ± 7.868384ms      	0s ± 0s             
+16 parallel 64KiB random write processes	Tart (--root-disk-opts="sync=none,caching=cached")	0 B/s     	16 GB/s    	0 IOPS     	251.02 kIOPS	0s ± 0s                 	355.077µs ± 8.354218ms  	0s ± 0s             
+Single 1MiB random write process        	local                                             	0 B/s     	1.3 GB/s   	0 IOPS     	1.31 kIOPS  	0s ± 0s                 	751.716µs ± 370.731µs   	0s ± 0s             
+Single 1MiB random write process        	Tart                                              	0 B/s     	1.1 GB/s   	0 IOPS     	1.1 kIOPS   	0s ± 0s                 	885.833µs ± 3.572539ms  	0s ± 0s             
+Single 1MiB random write process        	Tart (--root-disk-opts="sync=none")               	0 B/s     	1.1 GB/s   	0 IOPS     	1.08 kIOPS  	0s ± 0s                 	898.427µs ± 3.464261ms  	0s ± 0s             
+Single 1MiB random write process        	Tart (--root-disk-opts="caching=cached")          	0 B/s     	1000 MB/s  	0 IOPS     	976.47 IOPS 	0s ± 0s                 	972.491µs ± 6.87654ms   	0s ± 0s             
+Single 1MiB random write process        	Tart (--root-disk-opts="sync=none,caching=cached")	0 B/s     	1.1 GB/s   	0 IOPS     	1.03 kIOPS  	0s ± 0s                 	925.545µs ± 4.261693ms  	0s ± 0s             
+Random reads/writes (4k)                	local                                             	62 MB/s   	62 MB/s    	15.37 kIOPS	15.37 kIOPS 	2.059453ms ± 1.431822ms 	2.098761ms ± 1.445082ms 	0s ± 0s             
+Random reads/writes (4k)                	Tart                                              	38 MB/s   	38 MB/s    	9.6 kIOPS  	9.61 kIOPS  	3.30369ms ± 1.500464ms  	3.350589ms ± 1.512986ms 	0s ± 0s             
+Random reads/writes (4k)                	Tart (--root-disk-opts="sync=none")               	39 MB/s   	39 MB/s    	9.82 kIOPS 	9.83 kIOPS  	3.228106ms ± 1.367512ms 	3.27626ms ± 1.385964ms  	0s ± 0s             
+Random reads/writes (4k)                	Tart (--root-disk-opts="caching=cached")          	35 MB/s   	35 MB/s    	8.74 kIOPS 	8.76 kIOPS  	3.640772ms ± 15.472355ms	3.661779ms ± 15.264288ms	0s ± 0s             
+Random reads/writes (4k)                	Tart (--root-disk-opts="sync=none,caching=cached")	24 MB/s   	24 MB/s    	5.98 kIOPS 	5.99 kIOPS  	5.31188ms ± 4.55205ms   	5.375047ms ± 5.113847ms 	0s ± 0s             
+Random reads/writes (64k)               	local                                             	435 MB/s  	436 MB/s   	6.79 kIOPS 	6.8 kIOPS   	4.955892ms ± 2.066685ms 	4.440414ms ± 1.860036ms 	0s ± 0s             
+Random reads/writes (64k)               	Tart                                              	352 MB/s  	353 MB/s   	5.5 kIOPS  	5.51 kIOPS  	5.946067ms ± 2.041124ms 	5.658948ms ± 1.928372ms 	0s ± 0s             
+Random reads/writes (64k)               	Tart (--root-disk-opts="sync=none")               	331 MB/s  	332 MB/s   	5.16 kIOPS 	5.17 kIOPS  	6.330765ms ± 1.726782ms 	6.033862ms ± 1.671028ms 	0s ± 0s             
+Random reads/writes (64k)               	Tart (--root-disk-opts="caching=cached")          	428 MB/s  	428 MB/s   	6.68 kIOPS 	6.69 kIOPS  	4.661666ms ± 18.342779ms	4.904961ms ± 18.396772ms	0s ± 0s             
+Random reads/writes (64k)               	Tart (--root-disk-opts="sync=none,caching=cached")	297 MB/s  	298 MB/s   	4.64 kIOPS 	4.65 kIOPS  	6.591009ms ± 2.827053ms 	7.166883ms ± 3.001036ms 	0s ± 0s             
+sync test                               	local                                             	0 B/s     	48 MB/s    	0 IOPS     	21.15 kIOPS 	0s ± 0s                 	23.471µs ± 81.868µs     	23.374µs ± 6.255µs  
+sync test                               	Tart                                              	0 B/s     	24 MB/s    	0 IOPS     	10.72 kIOPS 	0s ± 0s                 	24.983µs ± 61.761µs     	67.575µs ± 76.196µs 
+sync test                               	Tart (--root-disk-opts="sync=none")               	0 B/s     	21 MB/s    	0 IOPS     	9.5 kIOPS   	0s ± 0s                 	26.973µs ± 63.935µs     	77.388µs ± 47.103µs 
+sync test                               	Tart (--root-disk-opts="caching=cached")          	0 B/s     	30 MB/s    	0 IOPS     	13.19 kIOPS 	0s ± 0s                 	11.923µs ± 25.225µs     	62.894µs ± 208.933µs
+sync test                               	Tart (--root-disk-opts="sync=none,caching=cached")	0 B/s     	38 MB/s    	0 IOPS     	17.02 kIOPS 	0s ± 0s                 	10.124µs ± 21.868µs     	47.803µs ± 33.706µs
+```
+
+### Dec 4, 2024
+
+Host:
+
+* AWS instance: `mac2.metal` + `gp3` EBS volume
+* Hardware: Mac mini (Apple M1, 4 performance and 4 efficiency cores, 16 GB RAM, `Macmini9,1`)
+* OS: macOS Sequoia 15.0
+
+Guest:
+
+* Hardware: [Virtualization.Framework](https://developer.apple.com/documentation/virtualization)
+* OS: macOS Sonoma 14.6
+
+```
+Name                                    	Executor                                          	B/W (read)	B/W (write)	I/O (read) 	I/O (write) 	Latency (read)            	Latency (write)           	Latency (sync)         
+Single 4KiB random write process        	local                                             	0 B/s     	4.4 MB/s   	0 IOPS     	1.1 kIOPS   	0s ± 0s                   	702.357µs ± 359.925µs     	0s ± 0s                
+Single 4KiB random write process        	Tart                                              	0 B/s     	2.6 MB/s   	0 IOPS     	656.37 IOPS 	0s ± 0s                   	1.140086ms ± 1.450472ms   	0s ± 0s                
+Single 4KiB random write process        	Tart (--root-disk-opts="sync=none")               	0 B/s     	2.7 MB/s   	0 IOPS     	677.07 IOPS 	0s ± 0s                   	1.179872ms ± 1.219626ms   	0s ± 0s                
+Single 4KiB random write process        	Tart (--root-disk-opts="caching=cached")          	0 B/s     	3.3 MB/s   	0 IOPS     	832.66 IOPS 	0s ± 0s                   	948.648µs ± 94.141338ms   	0s ± 0s                
+Single 4KiB random write process        	Tart (--root-disk-opts="sync=none,caching=cached")	0 B/s     	15 MB/s    	0 IOPS     	3.65 kIOPS  	0s ± 0s                   	260.717µs ± 19.977757ms   	0s ± 0s                
+16 parallel 64KiB random write processes	local                                             	0 B/s     	9.5 GB/s   	0 IOPS     	147.89 kIOPS	0s ± 0s                   	753.289µs ± 8.028974ms    	0s ± 0s                
+16 parallel 64KiB random write processes	Tart                                              	0 B/s     	10 GB/s    	0 IOPS     	176.96 kIOPS	0s ± 0s                   	429.83µs ± 33.792264ms    	0s ± 0s                
+16 parallel 64KiB random write processes	Tart (--root-disk-opts="sync=none")               	0 B/s     	12 GB/s    	0 IOPS     	180.89 kIOPS	0s ± 0s                   	383.524µs ± 17.524971ms   	0s ± 0s                
+16 parallel 64KiB random write processes	Tart (--root-disk-opts="caching=cached")          	0 B/s     	336 MB/s   	0 IOPS     	5.24 kIOPS  	0s ± 0s                   	9.970844ms ± 365.808663ms 	0s ± 0s                
+16 parallel 64KiB random write processes	Tart (--root-disk-opts="sync=none,caching=cached")	0 B/s     	9.4 GB/s   	0 IOPS     	147.04 kIOPS	0s ± 0s                   	524.139µs ± 34.100009ms   	0s ± 0s                
+Single 1MiB random write process        	local                                             	0 B/s     	178 MB/s   	0 IOPS     	173.36 IOPS 	0s ± 0s                   	3.835103ms ± 2.917977ms   	0s ± 0s                
+Single 1MiB random write process        	Tart                                              	0 B/s     	140 MB/s   	0 IOPS     	136.48 IOPS 	0s ± 0s                   	4.721178ms ± 7.744965ms   	0s ± 0s                
+Single 1MiB random write process        	Tart (--root-disk-opts="sync=none")               	0 B/s     	144 MB/s   	0 IOPS     	140.63 IOPS 	0s ± 0s                   	4.443507ms ± 11.572454ms  	0s ± 0s                
+Single 1MiB random write process        	Tart (--root-disk-opts="caching=cached")          	0 B/s     	47 MB/s    	0 IOPS     	45.55 IOPS  	0s ± 0s                   	13.267881ms ± 358.283094ms	0s ± 0s                
+Single 1MiB random write process        	Tart (--root-disk-opts="sync=none,caching=cached")	0 B/s     	196 MB/s   	0 IOPS     	191.4 IOPS  	0s ± 0s                   	4.102516ms ± 73.117503ms  	0s ± 0s                
+Random reads/writes (4k)                	local                                             	8.7 MB/s  	8.7 MB/s   	2.16 kIOPS 	2.16 kIOPS  	193.370794ms ± 42.593607ms	222.272016ms ± 56.586971ms	0s ± 0s                
+Random reads/writes (4k)                	Tart                                              	4.1 MB/s  	4.1 MB/s   	1.02 kIOPS 	1.03 kIOPS  	31.038867ms ± 13.508668ms 	31.184305ms ± 14.032766ms 	0s ± 0s                
+Random reads/writes (4k)                	Tart (--root-disk-opts="sync=none")               	4.2 MB/s  	4.2 MB/s   	1.04 kIOPS 	1.05 kIOPS  	30.368422ms ± 13.505627ms 	30.595412ms ± 13.840944ms 	0s ± 0s                
+Random reads/writes (4k)                	Tart (--root-disk-opts="caching=cached")          	2.2 MB/s  	2.2 MB/s   	545.33 IOPS	548.86 IOPS 	59.31316ms ± 716.351086ms 	57.647852ms ± 711.503882ms	0s ± 0s                
+Random reads/writes (4k)                	Tart (--root-disk-opts="sync=none,caching=cached")	6.0 MB/s  	6.0 MB/s   	1.5 kIOPS  	1.5 kIOPS   	21.244222ms ± 47.808399ms 	21.39459ms ± 44.716307ms  	0s ± 0s                
+Random reads/writes (64k)               	local                                             	121 MB/s  	121 MB/s   	1.89 kIOPS 	1.89 kIOPS  	61.894699ms ± 21.353345ms 	73.176462ms ± 13.02948ms  	0s ± 0s                
+Random reads/writes (64k)               	Tart                                              	72 MB/s   	72 MB/s    	1.12 kIOPS 	1.12 kIOPS  	27.842263ms ± 15.320781ms 	29.161858ms ± 15.765314ms 	0s ± 0s                
+Random reads/writes (64k)               	Tart (--root-disk-opts="sync=none")               	71 MB/s   	72 MB/s    	1.11 kIOPS 	1.11 kIOPS  	28.009493ms ± 16.333136ms 	29.285868ms ± 16.540589ms 	0s ± 0s                
+Random reads/writes (64k)               	Tart (--root-disk-opts="caching=cached")          	28 MB/s   	28 MB/s    	441.85 IOPS	444.81 IOPS 	71.726725ms ± 633.215756ms	72.597238ms ± 630.969305ms	0s ± 0s                
+Random reads/writes (64k)               	Tart (--root-disk-opts="sync=none,caching=cached")	81 MB/s   	81 MB/s    	1.26 kIOPS 	1.26 kIOPS  	24.872043ms ± 36.980111ms 	25.568559ms ± 37.027145ms 	0s ± 0s                
+sync test                               	local                                             	0 B/s     	1.9 MB/s   	0 IOPS     	868.08 IOPS 	0s ± 0s                   	92.08µs ± 233.598µs       	1.059033ms ± 98.751µs  
+sync test                               	Tart                                              	0 B/s     	1.5 MB/s   	0 IOPS     	649.42 IOPS 	0s ± 0s                   	146.737µs ± 434.261µs     	1.391898ms ± 699.148µs 
+sync test                               	Tart (--root-disk-opts="sync=none")               	0 B/s     	1.3 MB/s   	0 IOPS     	568.82 IOPS 	0s ± 0s                   	158.736µs ± 504.002µs     	1.59798ms ± 14.161331ms
+sync test                               	Tart (--root-disk-opts="caching=cached")          	0 B/s     	13 MB/s    	0 IOPS     	5.77 kIOPS  	0s ± 0s                   	26.596µs ± 832.169µs      	145.785µs ± 2.864048ms 
+sync test                               	Tart (--root-disk-opts="sync=none,caching=cached")	0 B/s     	19 MB/s    	0 IOPS     	8.37 kIOPS  	0s ± 0s                   	20.135µs ± 108.817µs      	98.274µs ± 239.631µs   
+```
+
+Host:
+
+* AWS instance: `mac2.metal` + `gp3` EBS volume
+* Hardware: Mac mini (Apple M1, 4 performance and 4 efficiency cores, 16 GB RAM, `Macmini9,1`)
+* OS: macOS Sequoia 15.0
+
+Guest:
+
+* Hardware: [Virtualization.Framework](https://developer.apple.com/documentation/virtualization)
+* OS: macOS Sequoia 15.1
+
+```
+Name                                    	Executor                                          	B/W (read)	B/W (write)	I/O (read) 	I/O (write) 	Latency (read)            	Latency (write)           	Latency (sync)         
+Single 4KiB random write process        	local                                             	0 B/s     	4.8 MB/s   	0 IOPS     	1.19 kIOPS  	0s ± 0s                   	690.818µs ± 326.595µs     	0s ± 0s                
+Single 4KiB random write process        	Tart                                              	0 B/s     	2.8 MB/s   	0 IOPS     	700.94 IOPS 	0s ± 0s                   	1.090362ms ± 918.444µs    	0s ± 0s                
+Single 4KiB random write process        	Tart (--root-disk-opts="sync=none")               	0 B/s     	3.0 MB/s   	0 IOPS     	746.23 IOPS 	0s ± 0s                   	1.028192ms ± 974.533µs    	0s ± 0s                
+Single 4KiB random write process        	Tart (--root-disk-opts="caching=cached")          	0 B/s     	4.2 MB/s   	0 IOPS     	1.04 kIOPS  	0s ± 0s                   	916.36µs ± 105.318323ms   	0s ± 0s                
+Single 4KiB random write process        	Tart (--root-disk-opts="sync=none,caching=cached")	0 B/s     	14 MB/s    	0 IOPS     	3.57 kIOPS  	0s ± 0s                   	269.796µs ± 22.419599ms   	0s ± 0s                
+16 parallel 64KiB random write processes	local                                             	0 B/s     	9.5 GB/s   	0 IOPS     	148.74 kIOPS	0s ± 0s                   	753.46µs ± 8.06509ms      	0s ± 0s                
+16 parallel 64KiB random write processes	Tart                                              	0 B/s     	5.2 GB/s   	0 IOPS     	81.46 kIOPS 	0s ± 0s                   	778.624µs ± 11.705178ms   	0s ± 0s                
+16 parallel 64KiB random write processes	Tart (--root-disk-opts="sync=none")               	0 B/s     	5.3 GB/s   	0 IOPS     	83.47 kIOPS 	0s ± 0s                   	865.448µs ± 38.369176ms   	0s ± 0s                
+16 parallel 64KiB random write processes	Tart (--root-disk-opts="caching=cached")          	0 B/s     	116 MB/s   	0 IOPS     	1.8 kIOPS   	0s ± 0s                   	37.601112ms ± 727.319309ms	0s ± 0s                
+16 parallel 64KiB random write processes	Tart (--root-disk-opts="sync=none,caching=cached")	0 B/s     	5.3 GB/s   	0 IOPS     	83.19 kIOPS 	0s ± 0s                   	900.751µs ± 51.223205ms   	0s ± 0s                
+Single 1MiB random write process        	local                                             	0 B/s     	177 MB/s   	0 IOPS     	173.27 IOPS 	0s ± 0s                   	3.833194ms ± 2.873871ms   	0s ± 0s                
+Single 1MiB random write process        	Tart                                              	0 B/s     	151 MB/s   	0 IOPS     	147.44 IOPS 	0s ± 0s                   	4.925853ms ± 7.793808ms   	0s ± 0s                
+Single 1MiB random write process        	Tart (--root-disk-opts="sync=none")               	0 B/s     	151 MB/s   	0 IOPS     	147.87 IOPS 	0s ± 0s                   	4.884797ms ± 7.563512ms   	0s ± 0s                
+Single 1MiB random write process        	Tart (--root-disk-opts="caching=cached")          	0 B/s     	72 MB/s    	0 IOPS     	69.9 IOPS   	0s ± 0s                   	8.909771ms ± 214.311644ms 	0s ± 0s                
+Single 1MiB random write process        	Tart (--root-disk-opts="sync=none,caching=cached")	0 B/s     	159 MB/s   	0 IOPS     	155.69 IOPS 	0s ± 0s                   	4.863448ms ± 88.965211ms  	0s ± 0s                
+Random reads/writes (4k)                	local                                             	8.7 MB/s  	8.7 MB/s   	2.16 kIOPS 	2.16 kIOPS  	193.353233ms ± 42.728494ms	222.325905ms ± 56.901372ms	0s ± 0s                
+Random reads/writes (4k)                	Tart                                              	3.5 MB/s  	3.5 MB/s   	862.89 IOPS	865.54 IOPS 	36.893229ms ± 12.644216ms 	37.143334ms ± 12.772017ms 	0s ± 0s                
+Random reads/writes (4k)                	Tart (--root-disk-opts="sync=none")               	3.6 MB/s  	3.6 MB/s   	907.4 IOPS 	911.55 IOPS 	35.048969ms ± 10.559354ms 	35.3046ms ± 10.67824ms    	0s ± 0s                
+Random reads/writes (4k)                	Tart (--root-disk-opts="caching=cached")          	2.7 MB/s  	2.8 MB/s   	684.11 IOPS	688.05 IOPS 	48.815322ms ± 687.806727ms	44.395556ms ± 635.532064ms	0s ± 0s                
+Random reads/writes (4k)                	Tart (--root-disk-opts="sync=none,caching=cached")	7.0 MB/s  	7.0 MB/s   	1.74 kIOPS 	1.74 kIOPS  	18.00448ms ± 93.784447ms  	18.617037ms ± 107.423001ms	0s ± 0s                
+Random reads/writes (64k)               	local                                             	121 MB/s  	121 MB/s   	1.89 kIOPS 	1.89 kIOPS  	61.983727ms ± 21.324782ms 	73.228597ms ± 12.730945ms 	0s ± 0s                
+Random reads/writes (64k)               	Tart                                              	75 MB/s   	75 MB/s    	1.17 kIOPS 	1.17 kIOPS  	26.830538ms ± 7.643051ms  	27.709602ms ± 7.830965ms  	0s ± 0s                
+Random reads/writes (64k)               	Tart (--root-disk-opts="sync=none")               	76 MB/s   	77 MB/s    	1.19 kIOPS 	1.19 kIOPS  	26.255337ms ± 7.302592ms  	27.256805ms ± 7.388266ms  	0s ± 0s                
+Random reads/writes (64k)               	Tart (--root-disk-opts="caching=cached")          	32 MB/s   	33 MB/s    	505.26 IOPS	508.66 IOPS 	65.170269ms ± 747.794957ms	61.062186ms ± 695.614904ms	0s ± 0s                
+Random reads/writes (64k)               	Tart (--root-disk-opts="sync=none,caching=cached")	79 MB/s   	79 MB/s    	1.23 kIOPS 	1.23 kIOPS  	25.861503ms ± 171.669777ms	25.992302ms ± 164.647788ms	0s ± 0s                
+sync test                               	local                                             	0 B/s     	1.9 MB/s   	0 IOPS     	865.16 IOPS 	0s ± 0s                   	100.95µs ± 268.722µs      	1.054051ms ± 365.377µs 
+sync test                               	Tart                                              	0 B/s     	1.6 MB/s   	0 IOPS     	704.13 IOPS 	0s ± 0s                   	133.886µs ± 390.263µs     	1.285085ms ± 575.27µs  
+sync test                               	Tart (--root-disk-opts="sync=none")               	0 B/s     	1.6 MB/s   	0 IOPS     	728.26 IOPS 	0s ± 0s                   	129.246µs ± 472.724µs     	1.242713ms ± 1.281286ms
+sync test                               	Tart (--root-disk-opts="caching=cached")          	0 B/s     	35 MB/s    	0 IOPS     	15.67 kIOPS 	0s ± 0s                   	11.319µs ± 24.771µs       	51.731µs ± 42.208µs    
+sync test                               	Tart (--root-disk-opts="sync=none,caching=cached")	0 B/s     	17 MB/s    	0 IOPS     	7.39 kIOPS  	0s ± 0s                   	21.23µs ± 81.749µs        	113.239µs ± 191.266µs  
+```

benchmark/internal/command/fio/benchmark.go

@@ -7,23 +7,63 @@ type Benchmark struct {
 
 var benchmarks = []Benchmark{
 	{
-		Name: "Random writing of 1MB",
-		Command: "fio --rw randwrite --runtime 30 --time_based --unlink 1 --output-format json " +
-			"--size 1MB --name unnamed --numjobs 1 --iodepth 1 --end_fsync 1",
+		// Ars Technica's "Single 4KiB random write process" test[1]
+		// with JSON output and created file cleanup
+		//
+		// [1]: https://arstechnica.com/gadgets/2020/02/how-fast-are-your-disks-find-out-the-open-source-way-with-fio/
+		Name: "Single 4KiB random write process",
+		Command: "fio --name=benchmark --ioengine=posixaio --rw=randwrite --bs=4k --size=4g --numjobs=1 --iodepth=1 --runtime=60 --time_based --end_fsync=1" +
+			" --output-format json --unlink 1",
 	},
 	{
-		Name: "Random writing of 10MB",
-		Command: "fio --rw randwrite --runtime 30 --time_based --unlink 1 --output-format json " +
-			"--size 10MB --name unnamed --numjobs 1 --iodepth 1 --end_fsync 1",
+		// Ars Technica's "16 parallel 64KiB random write processes" test[1]
+		// with JSON outpu, created file cleanup and group reporting (for
+		// easier analysis)
+		//
+		// [1]: https://arstechnica.com/gadgets/2020/02/how-fast-are-your-disks-find-out-the-open-source-way-with-fio/
+		Name: "16 parallel 64KiB random write processes",
+		Command: "fio --name=benchmark --ioengine=posixaio --rw=randwrite --bs=64k --size=256m --numjobs=16 --iodepth=16 --runtime=60 --time_based --end_fsync=1" +
+			" --output-format json --unlink 1 --group_reporting",
 	},
 	{
-		Name: "Random writing of 100MB",
-		Command: "fio --rw randwrite --runtime 30 --time_based --unlink 1 --output-format json " +
-			"--size 100MB --name unnamed --numjobs 1 --iodepth 1 --end_fsync 1",
+		// Ars Technica's "16 parallel 64KiB random write processes" test[1]
+		// with JSON output, created file cleanup and reduced file I/O size
+		// from 16 to 10 GB to avoid "No space left on device".
+		//
+		// [1]: https://arstechnica.com/gadgets/2020/02/how-fast-are-your-disks-find-out-the-open-source-way-with-fio/
+		Name: "Single 1MiB random write process",
+		Command: "fio --name=benchmark --ioengine=posixaio --rw=randwrite --bs=1m --size=10g --numjobs=1 --iodepth=1 --runtime=60 --time_based --end_fsync=1" +
+			" --output-format json --unlink 1",
 	},
 	{
-		Name: "Random writing of 1000MB",
-		Command: "fio --rw randwrite --runtime 30 --time_based --unlink 1 --output-format json " +
-			"--size 1000MB --name unnamed --numjobs 1 --iodepth 1 --end_fsync 1",
+		// Oracle's "Test random read/writes" (in IOPS Performance Tests[1]) category
+		// with JSON output, created file cleanup, without ETA newline, without custom
+		// file path, with file I/O size reduced from 500GB to 2GB to prevent
+		// "No space left on device" and with posixaio instead of libaio.
+		//
+		// [1]: https://docs.oracle.com/en-us/iaas/Content/Block/References/samplefiocommandslinux.htm#FIO_Commands
+		Name: "Random reads/writes (4k)",
+		Command: "fio --name=benchmark --size=2GB --direct=1 --rw=randrw --bs=4k --ioengine=posixaio --iodepth=256 --runtime=120 --numjobs=4 --time_based --group_reporting" +
+			" --output-format json --unlink 1",
+	},
+	{
+		// Oracle's "Test random read/writes" (in Throughput Performance Tests[1]) category
+		// with JSON output, created file cleanup, without ETA newline, without custom
+		// file path, with file I/O size reduced from 500GB to 2GB to prevent
+		// "No space left on device" and with posixaio instead of libaio.
+		//
+		// [1]: https://docs.oracle.com/en-us/iaas/Content/Block/References/samplefiocommandslinux.htm#Throughput_Performance_Tests
+		Name: "Random reads/writes (64k)",
+		Command: "fio --name=benchmark --size=2GB --direct=1 --rw=randrw --bs=64k --ioengine=posixaio --iodepth=64 --runtime=120 --numjobs=4 --time_based --group_reporting" +
+			" --output-format json --unlink 1",
+	},
+	{
+		// RedHat's "How can I test to see if my environment is fast enough for etcd"[1]
+		// with custom name
+		//
+		// [1]: https://access.redhat.com/solutions/5726511
+		Name: "sync test",
+		Command: "mkdir -p test-data && fio --name=benchmark --rw=write --ioengine=sync --fdatasync=1 --directory=test-data --size=22m --bs=2300" +
+			" --output-format json --unlink 1",
 	},
 }

benchmark/internal/command/fio/fio.go

@@ -1,20 +1,23 @@
 package fio
 
 import (
-	"context"
 	"encoding/json"
-	"errors"
 	"fmt"
-	"github.com/cirruslabs/tart/benchmark/internal/executor"
+	executorpkg "github.com/cirruslabs/tart/benchmark/internal/executor"
 	"github.com/cirruslabs/tart/benchmark/internal/executor/local"
 	"github.com/cirruslabs/tart/benchmark/internal/executor/tart"
 	"github.com/dustin/go-humanize"
 	"github.com/gosuri/uitable"
 	"github.com/spf13/cobra"
 	"go.uber.org/zap"
+	"go.uber.org/zap/zapio"
+	"os"
+	"os/exec"
 )
 
 var debug bool
+var image string
+var prepare string
 
 func NewCommand() *cobra.Command {
 	cmd := &cobra.Command{
@@ -24,6 +27,8 @@ func NewCommand() *cobra.Command {
 	}
 
 	cmd.Flags().BoolVar(&debug, "debug", false, "enable debug logging")
+	cmd.Flags().StringVar(&image, "image", "ghcr.io/cirruslabs/macos-sonoma-base:latest", "image to use for testing")
+	cmd.Flags().StringVar(&prepare, "prepare", "", "command to run before running each benchmark")
 
 	return cmd
 }
@@ -41,28 +46,95 @@ func run(cmd *cobra.Command, args []string) error {
 		_ = logger.Sync()
 	}()
 
-	executors, err := initializeExecutors(cmd.Context(), logger)
-	if err != nil {
-		return err
+	var executorInitializers = []struct {
+		Name string
+		Fn   func() (executorpkg.Executor, error)
+	}{
+		{
+			Name: "local",
+			Fn: func() (executorpkg.Executor, error) {
+				return local.New(logger)
+			},
+		},
+		{
+			Name: "Tart",
+			Fn: func() (executorpkg.Executor, error) {
+				return tart.New(cmd.Context(), image, nil, logger)
+			},
+		},
+		{
+			Name: "Tart (--root-disk-opts=\"sync=none\")",
+			Fn: func() (executorpkg.Executor, error) {
+				return tart.New(cmd.Context(), image, []string{
+					"--root-disk-opts",
+					"sync=none",
+				}, logger)
+			},
+		},
+		{
+			Name: "Tart (--root-disk-opts=\"caching=cached\")",
+			Fn: func() (executorpkg.Executor, error) {
+				return tart.New(cmd.Context(), image, []string{
+					"--root-disk-opts",
+					"caching=cached",
+				}, logger)
+			},
+		},
+		{
+			Name: "Tart (--root-disk-opts=\"sync=none,caching=cached\")",
+			Fn: func() (executorpkg.Executor, error) {
+				return tart.New(cmd.Context(), image, []string{
+					"--root-disk-opts",
+					"sync=none,caching=cached",
+				}, logger)
+			},
+		},
 	}
-	defer func() {
-		errs := []error{err}
-
-		for _, executor := range executors {
-			if err := executor.Close(); err != nil {
-				errs = append(errs, fmt.Errorf("failed to close executor %s: %w", executor.Name(), err))
-			}
-		}
-
-		err = errors.Join(errs...)
-	}()
 
 	table := uitable.New()
-	table.AddRow("Name", "Executor", "Bandwidth", "I/O operations")
+	table.AddRow("Name", "Executor", "B/W (read)", "B/W (write)", "I/O (read)", "I/O (write)",
+		"Latency (read)", "Latency (write)", "Latency (sync)")
 
 	for _, benchmark := range benchmarks {
-		for _, executor := range executors {
-			logger.Sugar().Infof("running benchmark %q on %s executor", benchmark.Name, executor.Name())
+		for _, executorInitializer := range executorInitializers {
+			if prepare != "" {
+				shell := "/bin/sh"
+
+				if shellFromEnv, ok := os.LookupEnv("SHELL"); ok {
+					shell = shellFromEnv
+				}
+
+				logger.Sugar().Infof("running prepare command %q using shell %q",
+					prepare, shell)
+
+				cmd := exec.CommandContext(cmd.Context(), shell, "-c", prepare)
+
+				loggerWriter := &zapio.Writer{Log: logger, Level: zap.DebugLevel}
+
+				cmd.Stdout = loggerWriter
+				cmd.Stderr = loggerWriter
+
+				if err := cmd.Run(); err != nil {
+					return fmt.Errorf("failed to run prepare command %q: %v", prepare, err)
+				}
+			}
+
+			logger.Sugar().Infof("initializing executor %s", executorInitializer.Name)
+
+			executor, err := executorInitializer.Fn()
+			if err != nil {
+				return err
+			}
+
+			logger.Sugar().Infof("installing Flexible I/O tester (fio) on executor %s",
+				executorInitializer.Name)
+
+			if _, err := executor.Run(cmd.Context(), "brew install fio"); err != nil {
+				return err
+			}
+
+			logger.Sugar().Infof("running benchmark %q on %s executor", benchmark.Name,
+				executorInitializer.Name)
 
 			stdout, err := executor.Run(cmd.Context(), benchmark.Command)
 			if err != nil {
@@ -82,12 +154,28 @@ func run(cmd *cobra.Command, args []string) error {
 
 			job := fioResult.Jobs[0]
 
+			readBandwidth := humanize.Bytes(uint64(job.Read.BW)*humanize.KByte) + "/s"
+			readIOPS := humanize.SIWithDigits(job.Read.IOPS, 2, "IOPS")
+
+			logger.Sugar().Infof("read bandwidth: %s, read IOPS: %s, read latency: %s",
+				readBandwidth, readIOPS, job.Read.LatencyNS.String())
+
 			writeBandwidth := humanize.Bytes(uint64(job.Write.BW)*humanize.KByte) + "/s"
 			writeIOPS := humanize.SIWithDigits(job.Write.IOPS, 2, "IOPS")
 
-			logger.Sugar().Infof("write bandwidth: %s, write IOPS: %s\n", writeBandwidth, writeIOPS)
+			logger.Sugar().Infof("write bandwidth: %s, write IOPS: %s, write latency: %s",
+				writeBandwidth, writeIOPS, job.Write.LatencyNS.String())
 
-			table.AddRow(benchmark.Name, executor.Name(), writeBandwidth, writeIOPS)
+			logger.Sugar().Infof("sync latency: %s", job.Sync.LatencyNS.String())
+
+			table.AddRow(benchmark.Name, executorInitializer.Name, readBandwidth, writeBandwidth,
+				readIOPS, writeIOPS, job.Read.LatencyNS.String(), job.Write.LatencyNS.String(),
+				job.Sync.LatencyNS.String())
+
+			if err := executor.Close(); err != nil {
+				return fmt.Errorf("failed to close executor %s: %w",
+					executorInitializer.Name, err)
+			}
 		}
 	}
 
@@ -95,37 +183,3 @@ func run(cmd *cobra.Command, args []string) error {
 
 	return nil
 }
-
-func initializeExecutors(ctx context.Context, logger *zap.Logger) ([]executor.Executor, error) {
-	var result []executor.Executor
-
-	logger.Info("initializing local executor")
-
-	local, err := local.New(logger)
-	if err != nil {
-		return nil, err
-	}
-	result = append(result, local)
-
-	logger.Info("local executor initialized")
-
-	logger.Info("initializing Tart executor")
-
-	tart, err := tart.New(ctx, logger)
-	if err != nil {
-		return nil, err
-	}
-	result = append(result, tart)
-
-	logger.Info("Tart executor initialized")
-
-	for _, executor := range result {
-		logger.Sugar().Infof("installing Flexible I/O tester (fio) on %s executor", executor.Name())
-
-		if _, err := executor.Run(ctx, "brew install fio"); err != nil {
-			return nil, err
-		}
-	}
-
-	return result, nil
-}

benchmark/internal/command/fio/json.go

@@ -1,15 +1,35 @@
 package fio
 
+import (
+	"fmt"
+	"time"
+)
+
 type Result struct {
 	Jobs []Job `json:"jobs"`
 }
 
 type Job struct {
 	Name  string `json:"jobname"`
-	Write Write  `json:"write"`
+	Read  Stats  `json:"read"`
+	Write Stats  `json:"write"`
+	Sync  Stats  `json:"sync"`
 }
 
-type Write struct {
-	BW   float64 `json:"bw"`
-	IOPS float64 `json:"iops"`
+type Stats struct {
+	BW        float64 `json:"bw"`
+	IOPS      float64 `json:"iops"`
+	LatencyNS Latency `json:"lat_ns"`
+}
+
+type Latency struct {
+	Mean   float64 `json:"mean"`
+	Stddev float64 `json:"stddev"`
+}
+
+func (latency Latency) String() string {
+	meanDuration := time.Duration(latency.Mean) * time.Nanosecond
+	stddevDuration := time.Duration(latency.Stddev) * time.Nanosecond
+
+	return fmt.Sprintf("%v ± %v", meanDuration, stddevDuration)
 }

benchmark/internal/executor/executor.go

@@ -5,7 +5,6 @@ import (
 )
 
 type Executor interface {
-	Name() string
 	Run(ctx context.Context, command string) ([]byte, error)
 	Close() error
 }

benchmark/internal/executor/tart/tart.go

@@ -8,14 +8,14 @@ import (
 	"github.com/avast/retry-go/v4"
 	"github.com/google/uuid"
 	"go.uber.org/zap"
+	"go.uber.org/zap/zapio"
 	"golang.org/x/crypto/ssh"
+	"io"
 	"net"
 	"strings"
 	"time"
 )
 
-const baseImage = "ghcr.io/cirruslabs/macos-sonoma-base:latest"
-
 type Tart struct {
 	vmRunCancel context.CancelFunc
 	vmName      string
@@ -23,17 +23,17 @@ type Tart struct {
 	logger      *zap.Logger
 }
 
-func New(ctx context.Context, logger *zap.Logger) (*Tart, error) {
+func New(ctx context.Context, image string, runArgsExtra []string, logger *zap.Logger) (*Tart, error) {
 	tart := &Tart{
 		vmName: fmt.Sprintf("tart-benchmark-%s", uuid.NewString()),
 		logger: logger,
 	}
 
-	if err := Cmd(ctx, tart.logger, "pull", baseImage); err != nil {
+	if err := Cmd(ctx, tart.logger, "pull", image); err != nil {
 		return nil, err
 	}
 
-	if err := Cmd(ctx, tart.logger, "clone", baseImage, tart.vmName); err != nil {
+	if err := Cmd(ctx, tart.logger, "clone", image, tart.vmName); err != nil {
 		return nil, err
 	}
 
@@ -41,7 +41,11 @@ func New(ctx context.Context, logger *zap.Logger) (*Tart, error) {
 	tart.vmRunCancel = vmRunCancel
 
 	go func() {
-		_ = Cmd(vmRunCtx, tart.logger, "run", "--no-graphics", tart.vmName)
+		runArgs := []string{"run", "--no-graphics", tart.vmName}
+
+		runArgs = append(runArgs, runArgsExtra...)
+
+		_ = Cmd(vmRunCtx, tart.logger, runArgs...)
 	}()
 
 	ip, err := CmdWithOutput(ctx, tart.logger, "ip", "--wait", "60", tart.vmName)
@@ -105,10 +109,12 @@ func (tart *Tart) Run(ctx context.Context, command string) ([]byte, error) {
 	}()
 	defer monitorCancel()
 
+	loggerWriter := &zapio.Writer{Log: tart.logger, Level: zap.DebugLevel}
 	stdoutBuf := &bytes.Buffer{}
 
 	sshSession.Stdin = bytes.NewBufferString(command)
-	sshSession.Stdout = stdoutBuf
+	sshSession.Stdout = io.MultiWriter(stdoutBuf, loggerWriter)
+	sshSession.Stderr = loggerWriter
 
 	if err := sshSession.Shell(); err != nil {
 		return nil, err

benchmark/internal/executor/tart/tart_test.go

@@ -11,7 +11,7 @@ import (
 func TestTart(t *testing.T) {
 	ctx := context.Background()
 
-	tart, err := tart.New(ctx, zap.NewNop())
+	tart, err := tart.New(ctx, "ghcr.io/cirruslabs/macos-sonoma-base:latest", nil, zap.NewNop())
 	require.NoError(t, err)
 
 	output, err := tart.Run(ctx, "echo \"this is a test\"")

docs/faq.md

@@ -5,6 +5,16 @@ title: Frequently Asked Questions
 description: Advanced configuration and troubleshooting tips for advanced configurations.
 ---
 
+## Troubleshooting crashes
+
+If you experience a crash or encounter another error while using the tart executable, you can collect debug information to assist with troubleshooting. Run the following command in a separate terminal window to gather logs from the Tart process and the macOS Virtualization subsystem:
+
+```shell
+log stream --predicate='process=="tart" OR process CONTAINS "Virtualization"' > tart.log
+```
+
+While the events are being streamed, attempt to reproduce the issue. Once the issue is reproduced, stop the streaming by pressing Ctrl+C. Then, attach the tart.log file to your report.
+
 ## VM location on disk
 
 Tart stores all its files in `~/.tart/` directory. Local images that you can run are stored in `~/.tart/vms/`.
@@ -13,12 +23,12 @@ Remote images are pulled into `~/.tart/cache/OCIs/`.
 ## Nested virtualization support?
 
 Tart is limited by functionality of Apple's `Virtualization.Framework`. At the moment `Virtualization.Framework`
-doesn't support nested virtualization.
+supports nested virtualization only on M3 or M4 chips running macOS 15 (Sequoia). By default, it is disabled, but can be enabled by passing the `--nested` flag to `tart run`.
 
 ## Connecting to a service running on host
 
 To connect from within a virtual machine to a service running on the host machine
-please first make sure that the service is binded to `0.0.0.0`.
+please first make sure that the service is bound to `0.0.0.0`.
 
 Then from within a virtual machine you can access the service using the router's IP address that you can get either from `Preferences -> Network`
 or by running the following command in the Terminal:
@@ -29,7 +39,7 @@ netstat -nr | grep default | head -n 1 | awk '{print $2}'
 
 Note: that accessing host is only possible with the default NAT network. If you are running your virtual machines with
 [Softnet](https://github.com/cirruslabs/softnet) (via `tart run --net-softnet <VM NAME>)`, then the network isolation
-is stricter and it's not only possible to access the host.
+is stricter and it's not possible to access the host.
 
 ## Changing the default NAT subnet
 
@@ -57,7 +67,15 @@ This issue is worked around automatically [when using Softnet](http://github.com
 sudo defaults write /Library/Preferences/SystemConfiguration/com.apple.InternetSharing.default.plist bootpd -dict DHCPLeaseTimeSecs -int 600
 ```
 
-Note that this tweak persists across reboots, so normally you'll only need to do it once per new host.
+This tweak persists across reboots, so normally you'll only need to do it once per new host.
+
+If that doesn't help after starting a new VM, it's possible that the `/var/db/dhcpd_leases` file is already overfilled with 86,400-second leases. You can remove it with the following command and try starting a new VM again:
+
+```shell
+sudo rm /var/db/dhcpd_leases
+```
+
+And no worries, this file will be re-created on the next `tart run`.
 
 ## Running login/clone/pull/push commands over SSH
 
@@ -89,7 +107,7 @@ or features supported. If there is some feature missing please don't hesitate to
 Instead of Anka Registry, Tart can work with any OCI-compatible container registry. This provides a much more consistent
 and scalable experience for distributing virtual machines.
 
-Tart doesn't yet have an analogue of Anka Controller for managing long living VMs but [soon will be](https://github.com/cirruslabs/tart/issues/372).
+Tart does have an analogue of Anka Controller for managing VMs across a cluster of Mac hosts called [Orchard](orchard/quick-start.md).
 
 ## Automatic pruning
 

docs/integrations/vm-management.md

@@ -7,7 +7,7 @@ description: Use Packer to build custom VM images, configure VMs and work with r
 
 ## Creating from scratch
 
-Tart supports macOS and Linux virtual machines. All commands like `run` and `pull` work the same way regarding of the underlying OS a particular VM image has.
+Tart supports macOS and Linux virtual machines. All commands like `run` and `pull` work the same way regardless of the underlying OS a particular VM image has.
 The only difference is how such VM images are created. Please check sections below for [macOS](#creating-a-macos-vm-image-from-scratch) and [Linux](#creating-a-linux-vm-image-from-scratch) instructions.
 
 ### Creating a macOS VM image from scratch

docs/orchard/deploying-controller.md

@@ -31,7 +31,13 @@ gcloud compute addresses create orchard-ip --region=us-central1
 export ORCHARD_IP=$(gcloud compute addresses describe orchard-ip --format='value(address)' --region=us-central1)
 ```
 
-Once we have the IP address, we can create a new instance with Orchard Controller running inside a container:
+Then, ensure that there exist a firewall rule targeting `https-server` tag and allowing access to TCP port 443. If that's not the case, create one:
+
+```shell
+gcloud compute firewall-rules create default-allow-https --direction=INGRESS --priority=1000 --network=default --action=ALLOW --rules=tcp:443 --source-ranges=0.0.0.0/0 --target-tags=https-server
+```
+
+Once we have the IP address and the firewall rule set up, we can create a new instance with Orchard Controller running inside a container:
 
 ```bash
 gcloud compute instances create-with-container orchard-controller \