Add manifold check for size 0 (#1867)

Summary:
Pull Request resolved: https://github.com/facebookresearch/faiss/pull/1867

Merging code for the 1T photodna index seems to fail at

https://www.internalfb.com/phabricator/paste/view/P412975011?lines=174

with
```
terminate called after throwing an instance of 'facebook::manifold::blobstore::StorageException'
  what():  [400] Begin offset and/or length were invalid -- Begin offset must be positive and length must be non-negative. Received: offset = 2642410612, length = 0
Aborted (core dumped)
```
traces back to

https://www.internalfb.com/intern/diffusion/FBS/browsefile/master/fbcode/manifold/blobstore/BlobstoreThriftHandler.cpp?lines=671%2C700%2C732

There is a single case where we don't check if the read or write size is 0. So let's try this fix.

In the process I realized that the Manifold tests were non functional due to a name collision on common.py. Also fix this in all dependent files.

Differential Revision: D28231710

fbshipit-source-id: 700ffa6ca0c82c49e7d1eae9e76549ec5ff16332

.circleci/config.yml

@@ -174,8 +174,9 @@ jobs:
           command: |
             docker build -t faiss -f .circleci/Dockerfile.faiss_gpu .
             docker run --gpus all faiss make -C build test
-            docker run --gpus all faiss sh -c '(cd build/faiss/python; python3 setup.py install) && python3 -m unittest discover -s faiss/gpu/test -p "test_*"'
-            docker run --gpus all faiss sh -c '(cd build/faiss/python; python3 setup.py install) && python3 -m unittest discover -s faiss/gpu/test -p "torch_*.py"'
+            docker run --gpus all faiss sh -c '(pwd; find)'
+            docker run --gpus all faiss sh -c '(cd build/faiss/python; python3 setup.py install) && cp tests/common_faiss_tests.py faiss/gpu/test && python3 -m unittest discover -s faiss/gpu/test -p "test_*"'
+            docker run --gpus all faiss sh -c '(cd build/faiss/python; python3 setup.py install) && cp tests/common_faiss_tests.py faiss/gpu/test && python3 -m unittest discover -s faiss/gpu/test -p "torch_*.py"'
           no_output_timeout: 60m
 
   deploy_linux:

faiss/gpu/test/test_contrib.py

@@ -12,7 +12,7 @@ from faiss.contrib.exhaustive_search import knn_ground_truth, range_ground_truth
 from faiss.contrib import evaluation
 
 
-from common import get_dataset_2
+from common_faiss_tests import get_dataset_2
 
 
 class TestComputeGT(unittest.TestCase):

faiss/gpu/test/test_gpu_basics.py

@@ -8,7 +8,7 @@ from __future__ import absolute_import, division, print_function, unicode_litera
 import unittest
 import numpy as np
 import faiss
-from common import get_dataset_2
+from common_faiss_tests import get_dataset_2
 
 class ReferencedObject(unittest.TestCase):
 

tests/common.py

@@ -1,128 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates.
-#
-# This source code is licensed under the MIT license found in the
-# LICENSE file in the root directory of this source tree.
-
-# a few common functions for the tests
-
-from __future__ import absolute_import, division, print_function, unicode_literals
-
-import numpy as np
-import faiss
-
-# reduce number of threads to avoid excessive nb of threads in opt
-# mode (recuces runtime from 100s to 4s!)
-faiss.omp_set_num_threads(4)
-
-
-def random_unitary(n, d, seed):
-    x = faiss.randn(n * d, seed).reshape(n, d)
-    faiss.normalize_L2(x)
-    return x
-
-
-class Randu10k:
-
-    def __init__(self):
-        self.nb = 10000
-        self.nq = 1000
-        self.nt = 10000
-        self.d = 128
-
-        self.xb = random_unitary(self.nb, self.d, 1)
-        self.xt = random_unitary(self.nt, self.d, 2)
-        self.xq = random_unitary(self.nq, self.d, 3)
-
-        dotprods = np.dot(self.xq, self.xb.T)
-        self.gt = dotprods.argmax(1)
-        self.k = 100
-
-    def launch(self, name, index):
-        if not index.is_trained:
-            index.train(self.xt)
-        index.add(self.xb)
-        return index.search(self.xq, self.k)
-
-    def evalres(self, DI):
-        D, I = DI
-        e = {}
-        for rank in 1, 10, 100:
-            e[rank] = ((I[:, :rank] == self.gt.reshape(-1, 1)).sum() /
-                       float(self.nq))
-        print("1-recalls: %s" % e)
-        return e
-
-
-class Randu10kUnbalanced(Randu10k):
-
-    def __init__(self):
-        Randu10k.__init__(self)
-
-        weights = 0.95 ** np.arange(self.d)
-        rs = np.random.RandomState(123)
-        weights = weights[rs.permutation(self.d)]
-        self.xb *= weights
-        self.xb /= np.linalg.norm(self.xb, axis=1)[:, np.newaxis]
-        self.xq *= weights
-        self.xq /= np.linalg.norm(self.xq, axis=1)[:, np.newaxis]
-        self.xt *= weights
-        self.xt /= np.linalg.norm(self.xt, axis=1)[:, np.newaxis]
-
-        dotprods = np.dot(self.xq, self.xb.T)
-        self.gt = dotprods.argmax(1)
-        self.k = 100
-
-
-def get_dataset(d, nb, nt, nq):
-    rs = np.random.RandomState(123)
-    xb = rs.rand(nb, d).astype('float32')
-    xt = rs.rand(nt, d).astype('float32')
-    xq = rs.rand(nq, d).astype('float32')
-
-    return (xt, xb, xq)
-
-
-def get_dataset_2(d, nt, nb, nq):
-    """A dataset that is not completely random but still challenging to
-    index
-    """
-    d1 = 10     # intrinsic dimension (more or less)
-    n = nb + nt + nq
-    rs = np.random.RandomState(1338)
-    x = rs.normal(size=(n, d1))
-    x = np.dot(x, rs.rand(d1, d))
-    # now we have a d1-dim ellipsoid in d-dimensional space
-    # higher factor (>4) -> higher frequency -> less linear
-    x = x * (rs.rand(d) * 4 + 0.1)
-    x = np.sin(x)
-    x = x.astype('float32')
-    return x[:nt], x[nt:nt + nb], x[nt + nb:]
-
-
-def make_binary_dataset(d, nt, nb, nq):
-    assert d % 8 == 0
-    rs = np.random.RandomState(123)
-    x = rs.randint(256, size=(nb + nq + nt, int(d / 8))).astype('uint8')
-    return x[:nt], x[nt:-nq], x[-nq:]
-
-
-def compare_binary_result_lists(D1, I1, D2, I2):
-    """comparing result lists is difficult because there are many
-    ties. Here we sort by (distance, index) pairs and ignore the largest
-    distance of each result. Compatible result lists should pass this."""
-    assert D1.shape == I1.shape == D2.shape == I2.shape
-    n, k = D1.shape
-    ndiff = (D1 != D2).sum()
-    assert ndiff == 0, '%d differences in distance matrix %s' % (
-        ndiff, D1.shape)
-
-    def normalize_DI(D, I):
-        norm = I.max() + 1.0
-        Dr = D.astype('float64') + I / norm
-        # ignore -1s and elements on last column
-        Dr[I1 == -1] = 1e20
-        Dr[D == D[:, -1:]] = 1e20
-        Dr.sort(axis=1)
-        return Dr
-    ndiff = (normalize_DI(D1, I1) != normalize_DI(D2, I2)).sum()
-    assert ndiff == 0, '%d differences in normalized D matrix' % ndiff

tests/test_binary_hashindex.py

@@ -7,7 +7,7 @@ import unittest
 import numpy as np
 import faiss
 
-from common import make_binary_dataset
+from common_faiss_tests import make_binary_dataset
 
 
 def bitvec_shuffle(a, order):

tests/test_build_blocks.py

@@ -11,7 +11,7 @@ import faiss
 import unittest
 import array
 
-from common import get_dataset_2
+from common_faiss_tests import get_dataset_2
 
 
 

tests/test_clustering.py

@@ -11,7 +11,7 @@ import faiss
 import unittest
 import array
 
-from common import get_dataset_2
+from common_faiss_tests import get_dataset_2
 
 
 class TestClustering(unittest.TestCase):

tests/test_contrib.py

@@ -13,7 +13,7 @@ from faiss.contrib import inspect_tools
 from faiss.contrib import evaluation
 from faiss.contrib import ivf_tools
 
-from common import get_dataset_2
+from common_faiss_tests import get_dataset_2
 try:
     from faiss.contrib.exhaustive_search import knn_ground_truth, knn, range_ground_truth
     from faiss.contrib.exhaustive_search import range_search_max_results

tests/test_extra_distances.py

@@ -10,7 +10,7 @@ import numpy as np
 import faiss
 import unittest
 
-from common import get_dataset_2
+from common_faiss_tests import get_dataset_2
 
 import scipy.spatial.distance
 

tests/test_index.py

@@ -15,7 +15,7 @@ import os
 import re
 import warnings
 
-from common import get_dataset, get_dataset_2
+from common_faiss_tests import get_dataset, get_dataset_2
 
 class TestModuleInterface(unittest.TestCase):
 

tests/test_index_accuracy.py

@@ -11,7 +11,7 @@ import numpy as np
 import unittest
 import faiss
 
-from common import Randu10k, get_dataset_2, Randu10kUnbalanced
+from common_faiss_tests import Randu10k, get_dataset_2, Randu10kUnbalanced
 
 ev = Randu10k()
 

tests/test_index_binary.py

@@ -11,7 +11,7 @@ import numpy as np
 import unittest
 import faiss
 
-from common import compare_binary_result_lists, make_binary_dataset
+from common_faiss_tests import compare_binary_result_lists, make_binary_dataset
 
 
 

tests/test_index_composite.py

@@ -14,7 +14,7 @@ import shutil
 import tempfile
 import platform
 
-from common import get_dataset_2
+from common_faiss_tests import get_dataset_2
 
 class TestRemove(unittest.TestCase):
 

tests/test_io.py

@@ -13,7 +13,7 @@ import sys
 import pickle
 from multiprocessing.dummy import Pool as ThreadPool
 
-from common import get_dataset, get_dataset_2
+from common_faiss_tests import get_dataset, get_dataset_2
 
 
 class TestIOVariants(unittest.TestCase):

tests/test_meta_index.py

@@ -12,7 +12,7 @@ import numpy as np
 import faiss
 import unittest
 
-from common import Randu10k
+from common_faiss_tests import Randu10k
 
 ru = Randu10k()
 

tests/test_standalone_codec.py

@@ -12,7 +12,7 @@ import faiss
 import tempfile
 import os
 
-from common import get_dataset_2
+from common_faiss_tests import get_dataset_2
 
 
 class TestEncodeDecode(unittest.TestCase):