elastic-kernel 0.0.2__py3-none-any.whl

elastic_kernel-0.0.2.dist-info/licenses/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

elastic_kernel-0.0.2.dist-info/top_level.txt

@@ -0,0 +1,2 @@
+elastic_kernel
+elastic_notebook

elastic_notebook/algorithm/baseline.py

@@ -0,0 +1,31 @@
+import numpy as np
+
+from elastic_notebook.algorithm.selector import Selector
+
+
+class MigrateAllBaseline(Selector):
+    """
+    Migrates all active VSs.
+    """
+
+    def __init__(self, migration_speed_bps=1):
+        super().__init__(migration_speed_bps)
+
+    def select_vss(self) -> set:
+        vss_to_migrate = set()
+        for vs in self.active_vss:
+            if vs.size < np.inf:
+                vss_to_migrate.add(vs)
+        return vss_to_migrate
+
+
+class RecomputeAllBaseline(Selector):
+    """
+    Recomputes all active VSs.
+    """
+
+    def __init__(self, migration_speed_bps=1):
+        super().__init__(migration_speed_bps)
+
+    def select_vss(self) -> set:
+        return set()

elastic_notebook/algorithm/optimizer_exact.py

@@ -0,0 +1,121 @@
+import networkx as nx
+import numpy as np
+from networkx.algorithms.flow import shortest_augmenting_path
+
+from elastic_notebook.algorithm.selector import Selector
+from elastic_notebook.core.graph.cell_execution import CellExecution
+from elastic_notebook.core.graph.variable_snapshot import VariableSnapshot
+
+
+class OptimizerExact(Selector):
+    """
+    The exact optimizer constructs a flow graph and runs the min-cut algorithm to exactly find the best
+    checkpointing configuration.
+    """
+
+    def __init__(self, migration_speed_bps=1):
+        super().__init__(migration_speed_bps)
+
+        # Augmented computation graph
+        self.active_oes = None
+        self.compute_graph = None
+
+        # CEs required to recompute a variables last modified by a given CE.
+        self.recomputation_ces = {}
+
+        self.idx = 0
+
+    def get_new_idx(self) -> int:
+        """
+        Get a new index number to add to compute graph.
+        """
+        idx = self.idx
+        self.idx += 1
+        return idx
+
+    def dfs(self, current: str, visited: set, recompute_ces: str):
+        """
+        Perform DFS on the Application History Graph for finding the CEs required to recompute a variable.
+        Args:
+            current (str): Name of current nodeset.
+            visited (set): Visited nodesets.
+            recompute_ces (set): Set of CEs needing re-execution to recompute the current nodeset.
+        """
+        if isinstance(current, CellExecution):
+            # Result is memoized
+            if current in self.recomputation_ces:
+                recompute_ces.update(self.recomputation_ces[current])
+            else:
+                recompute_ces.add(current)
+                for vs in current.src_vss:
+                    if vs not in self.active_vss and vs not in visited:
+                        self.dfs(vs, visited, recompute_ces)
+
+        elif isinstance(current, VariableSnapshot):
+            visited.add(current)
+            if current.output_ce not in recompute_ces:
+                self.dfs(current.output_ce, visited, recompute_ces)
+
+    def find_prerequisites(self):
+        """
+        Find the necessary (prerequisite) cell executions to rerun a cell execution.
+        """
+        self.active_vss = set(self.active_vss)
+
+        for ce in self.dependency_graph.cell_executions:
+            if ce.dst_vss.intersection(self.active_vss):
+                recompute_ces = set()
+                self.dfs(ce, set(), recompute_ces)
+                self.recomputation_ces[ce] = recompute_ces
+
+    def select_vss(
+        self, write_log_location=None, notebook_name=None, optimizer_name=None
+    ) -> set:
+        self.find_prerequisites()
+
+        # Construct flow graph for computing mincut
+        mincut_graph = nx.DiGraph()
+
+        # Add source and sink to flow graph.
+        mincut_graph.add_node("source")
+        mincut_graph.add_node("sink")
+
+        # Add all active VSs as nodes, connect them with the source with edge capacity equal to migration cost.
+        for active_vs in self.active_vss:
+            mincut_graph.add_node(active_vs)
+            mincut_graph.add_edge(
+                "source", active_vs, capacity=active_vs.size / self.migration_speed_bps
+            )
+
+        # Add all CEs as nodes, connect them with the sink with edge capacity equal to recomputation cost.
+        for ce in self.dependency_graph.cell_executions:
+            mincut_graph.add_node(ce)
+            mincut_graph.add_edge(ce, "sink", capacity=ce.cell_runtime)
+
+        # Connect each CE with its output variables and its prerequisite OEs.
+        for active_vs in self.active_vss:
+            for ce in self.recomputation_ces[active_vs.output_ce]:
+                mincut_graph.add_edge(active_vs, ce, capacity=np.inf)
+
+        # Add constraints: overlapping variables must either be migrated or recomputed together.
+        for vs_pair in self.overlapping_vss:
+            mincut_graph.add_edge(vs_pair[0], vs_pair[1], capacity=np.inf)
+            mincut_graph.add_edge(vs_pair[1], vs_pair[0], capacity=np.inf)
+
+        # Prune CEs which produce no active variables to speedup computation.
+        for ce in self.dependency_graph.cell_executions:
+            if mincut_graph.in_degree(ce) == 0:
+                mincut_graph.remove_node(ce)
+
+        # Solve min-cut with Ford-Fulkerson.
+        cut_value, partition = nx.minimum_cut(
+            mincut_graph, "source", "sink", flow_func=shortest_augmenting_path
+        )
+
+        # Determine the replication plan from the partition.
+        vss_to_migrate = set(partition[1]).intersection(self.active_vss)
+        ces_to_recompute = set(partition[0]).intersection(
+            self.dependency_graph.cell_executions
+        )
+
+        return vss_to_migrate, ces_to_recompute

elastic_notebook/algorithm/selector.py

@@ -0,0 +1,41 @@
+from enum import Enum
+
+
+class OptimizerType(Enum):
+    """
+    String representations of all implemented optimizers.
+    """
+
+    EXACT = "exact"
+    EXACT_C = "exact_c"
+    EXACT_R = "exact_r"
+    MIGRATE_ALL = "migrate_all"
+    RECOMPUTE_ALL = "recompute_all"
+
+
+class Selector:
+    """
+    The `Selector` class provides interfaces to pick a subset of active VSs to migrate based on
+        various heuristics and algorithms.
+    """
+
+    def __init__(self, migration_speed_bps=1):
+        """
+        Creates a Selector instance with a migration speed estimate. The dependency graph and active VS fields
+        must be populated prior to calling select_vss.
+        """
+        self.dependency_graph = None
+        self.active_vss = None
+        self.overlapping_vss = None
+        self.migration_speed_bps = migration_speed_bps
+
+    def select_vss(self) -> set:
+        """
+        Classes that inherit from the `Selector` class (such as `Optimizer` and various baselines)
+            should override `select_vss`.
+
+        Returns:
+            set(VariableSnapshot): a subset of active VSs selected to migrate based on various heuristics and
+            algorithms.
+        """
+        raise NotImplementedError()

elastic_notebook/core/common/checkpoint_file.py

@@ -0,0 +1,129 @@
+import json
+from typing import Dict
+
+from elastic_notebook.core.graph.graph import DependencyGraph
+
+KEY_DEPENDENCY_GRAPH = "dependencyGraph"
+KEY_VARIABLES = "variables"
+KEY_VSS_TO_MIGRATE = "vss_to_migrate"
+KEY_VSS_TO_RECOMPUTE = "vss_to_recompute"
+KEY_CES_TO_RECOMPUTE = "ces_to_recompute"
+KEY_RECOMPUTATION_CES = "recomputation_ces"
+KEY_SERIALIZATION_ORDER = "serialization_order"
+KEY_UDFS = "udfs"
+
+
+class CheckpointFile:
+    """
+    JSON representation of the notebook checkpoint.
+    """
+
+    def __init__(self):
+        # Dependency graph representation of the notebook.
+        self.dependency_graph = None
+
+        # Migrated variables.
+        self.variables = None
+
+        # Active VSs corresponding to migrated variables.
+        self.vss_to_migrate = None
+
+        # Variables to recompute post-migration.
+        self.vss_to_recompute = None
+
+        # CEs to recompute to restore non-migrated variables (vss_to_recompute).
+        self.ces_to_recompute = None
+
+        # CEs to recompute a given CE. For fault tolerance if certain VSs fail
+        # to deserialize.
+        self.recomputation_ces = None
+
+        # List of objects packed in the pickle file.
+        self.serialization_order = None
+
+        # User-declared functions in the session.
+        self.udfs = None
+
+    def with_dependency_graph(self, graph: DependencyGraph):
+        self.dependency_graph = graph
+        return self
+
+    def get_dependency_graph(self):
+        return self.dependency_graph
+
+    def with_variables(self, variables: Dict):
+        self.variables = variables
+        return self
+
+    def get_variables(self):
+        return self.variables
+
+    def with_vss_to_migrate(self, vss_to_migrate: set):
+        self.vss_to_migrate = vss_to_migrate
+        return self
+
+    def get_vss_to_migrate(self):
+        return self.vss_to_migrate
+
+    def with_vss_to_recompute(self, vss_to_recompute: set):
+        self.vss_to_recompute = vss_to_recompute
+        return self
+
+    def get_vss_to_recompute(self):
+        return self.vss_to_recompute
+
+    def with_ces_to_recompute(self, ces_to_recompute: set):
+        self.ces_to_recompute = ces_to_recompute
+        return self
+
+    def get_ces_to_recompute(self):
+        return self.ces_to_recompute
+
+    def with_recomputation_ces(self, recomputation_ces: dict):
+        self.recomputation_ces = recomputation_ces
+        return self
+
+    def get_recomputation_ces(self):
+        return self.recomputation_ces
+
+    def with_serialization_order(self, serialization_order: list):
+        self.serialization_order = serialization_order
+        return self
+
+    def get_serialization_order(self):
+        return self.serialization_order
+
+    def with_udfs(self, udfs: set):
+        self.udfs = udfs
+        return self
+
+    def get_udfs(self):
+        return self.udfs
+
+    def to_json_str(self) -> str:
+        return json.dumps(
+            {
+                KEY_DEPENDENCY_GRAPH: self.dependency_graph,
+                KEY_VARIABLES: self.variables,
+                KEY_VSS_TO_MIGRATE: self.vss_to_migrate,
+                KEY_VSS_TO_RECOMPUTE: self.vss_to_recompute,
+                KEY_CES_TO_RECOMPUTE: self.ces_to_recompute,
+                KEY_RECOMPUTATION_CES: self.recomputation_ces,
+                KEY_SERIALIZATION_ORDER: self.serialization_order,
+                KEY_UDFS: self.udfs,
+            }
+        )
+
+    @staticmethod
+    def from_json(kv: Dict):
+        return (
+            CheckpointFile()
+            .with_dependency_graph(kv[KEY_DEPENDENCY_GRAPH])
+            .with_variables(kv[KEY_VARIABLES])
+            .with_vss_to_migrate(kv[KEY_VSS_TO_MIGRATE])
+            .with_vss_to_recompute(kv[KEY_VSS_TO_RECOMPUTE])
+            .with_ces_to_recompute(kv[KEY_CES_TO_RECOMPUTE])
+            .with_recomputation_ces(kv[KEY_RECOMPUTATION_CES])
+            .with_serialization_order(kv[KEY_SERIALIZATION_ORDER])
+            .with_udfs(kv[KEY_UDFS])
+        )

elastic_notebook/core/common/profile_graph_size.py

@@ -0,0 +1,39 @@
+import sys
+
+from elastic_notebook.core.common.profile_variable_size import profile_variable_size
+from elastic_notebook.core.graph.graph import DependencyGraph
+
+
+def profile_graph_size(graph: DependencyGraph):
+    """
+    Profiles the in-memory size of a dependency graph of Elastic Notebook.
+    For experiments only.
+    Args:
+        graph (DependencyGraph): dependency graph to profile.
+    """
+
+    # Tally fields in graph
+    total_size = sys.getsizeof(graph)
+    total_size += sys.getsizeof(graph.cell_executions)
+    total_size += profile_variable_size(graph.variable_snapshots)
+
+    # Tally fields in operation events
+    for oe in graph.cell_executions:
+        total_size += sys.getsizeof(oe.cell_num)
+        total_size += sys.getsizeof(oe.cell)
+        total_size += sys.getsizeof(oe.cell_runtime)
+        total_size += sys.getsizeof(oe.start_time)
+        total_size += sys.getsizeof(oe.src_vss)
+        total_size += sys.getsizeof(oe.dst_vss)
+
+    # Tally fields in nodes
+    for vs_list in graph.variable_snapshots.values():
+        for vs in vs_list:
+            total_size += sys.getsizeof(vs.name)
+            total_size += sys.getsizeof(vs.version)
+            total_size += sys.getsizeof(vs.deleted)
+            total_size += sys.getsizeof(vs.output_ce)
+            total_size += sys.getsizeof(vs.input_ces)
+            total_size += sys.getsizeof(vs.size)
+
+    return total_size

elastic_notebook/core/common/profile_migration_speed.py

@@ -0,0 +1,69 @@
+import os
+import pickle
+import sys
+import time
+
+import numpy as np
+
+
+def profile_migration_speed(dirname: str, alpha=1) -> float:
+    """
+    The migration speed is the sum of read and write speed (since we are writing the state to disk, then
+    reading from disk to restore the notebook). The function should ideally be fast (<1 sec).
+    Args:
+        dirname: Location to profile.
+    """
+    filecount = 1
+    max_time = 0.8
+    testing_dir = os.path.join(dirname, "measure_speed")
+    os.system("rm -rf {} && mkdir {}".format(testing_dir, testing_dir))
+    total_bytes = 0
+
+    start_time = time.time()
+
+    total_read_time = 0
+    total_write_time = 0
+    for i in range(filecount):
+        # write_array_large = np.random.rand(10000, 10000)
+        write_array_large = np.random.rand(500, 500)
+        write_array_small = np.random.rand(100, 100)
+        total_bytes += sys.getsizeof(write_array_large)
+        total_bytes -= sys.getsizeof(write_array_small)
+
+        write_start = time.time()
+        out_file = open(os.path.join(testing_dir, str(i) + "large"), "wb")
+        pickle.dump(write_array_large, out_file)
+        out_file.close()
+        total_write_time += time.time() - write_start
+
+        read_start = time.time()
+        in_file = open(os.path.join(testing_dir, str(i)) + "large", "rb")
+        in_file.close()
+        total_read_time += time.time() - read_start
+
+        write_start = time.time()
+        out_file = open(os.path.join(testing_dir, str(i) + "small"), "wb")
+        pickle.dump(write_array_small, out_file)
+        out_file.close()
+        total_write_time -= time.time() - write_start
+
+        read_start = time.time()
+        in_file = open(os.path.join(testing_dir, str(i) + "small"), "rb")
+        in_file.close()
+        total_read_time -= time.time() - read_start
+
+        if time.time() - start_time > max_time:
+            break
+
+    os.system("rm -rf {}".format(testing_dir))
+
+    migration_speed_bps = total_bytes / (total_read_time + total_write_time * alpha)
+    print(
+        "migration speed (bps) (total_bytes / (total_read_time + total_write_time * alpha)):",
+        migration_speed_bps,
+    )
+    print("|- total bytes:", total_bytes)
+    print("|- total read time:", total_read_time)
+    print("|- total write time:", total_write_time)
+    print("|- alpha:", alpha)
+    return migration_speed_bps