ListObjects Metadata Caching (#10648)

Design: https://gist.github.com/klauspost/025c09b48ed4a1293c917cecfabdf21c

Gist of improvements:

* Cross-server caching and listing will use the same data across servers and requests.
* Lists can be arbitrarily resumed at a constant speed.
* Metadata for all files scanned is stored for streaming retrieval.
* The existing bloom filters controlled by the crawler is used for validating caches.
* Concurrent requests for the same data (or parts of it) will not spawn additional walkers.
* Listing a subdirectory of an existing recursive cache will use the cache.
* All listing operations are fully streamable so the number of objects in a bucket no 
  longer dictates the amount of memory.
* Listings can be handled by any server within the cluster.
* Caches are cleaned up when out of date or superseded by a more recent one.
This commit is contained in:
Klaus Post
2020-10-28 09:18:35 -07:00
committed by GitHub
parent 51222cc664
commit a982baff27
65 changed files with 6328 additions and 742 deletions

View File

@@ -380,24 +380,28 @@ func TestGetRemotePeers(t *testing.T) {
testCases := []struct {
endpointArgs []string
expectedResult []string
expectedLocal string
}{
{[]string{"/d1", "/d2", "d3", "d4"}, []string{}},
{[]string{"http://localhost:9000/d1", "http://localhost:9000/d2", "http://example.org:9000/d3", "http://example.com:9000/d4"}, []string{"example.com:9000", "example.org:9000"}},
{[]string{"http://localhost:9000/d1", "http://localhost:10000/d2", "http://example.org:9000/d3", "http://example.com:9000/d4"}, []string{"example.com:9000", "example.org:9000", "localhost:10000"}},
{[]string{"http://localhost:9000/d1", "http://example.org:9000/d2", "http://example.com:9000/d3", "http://example.net:9000/d4"}, []string{"example.com:9000", "example.net:9000", "example.org:9000"}},
{[]string{"http://localhost:9000/d1", "http://localhost:9001/d2", "http://localhost:9002/d3", "http://localhost:9003/d4"}, []string{"localhost:9001", "localhost:9002", "localhost:9003"}},
{[]string{"/d1", "/d2", "d3", "d4"}, []string{}, ""},
{[]string{"http://localhost:9000/d1", "http://localhost:9000/d2", "http://example.org:9000/d3", "http://example.com:9000/d4"}, []string{"example.com:9000", "example.org:9000", "localhost:9000"}, "localhost:9000"},
{[]string{"http://localhost:9000/d1", "http://localhost:10000/d2", "http://example.org:9000/d3", "http://example.com:9000/d4"}, []string{"example.com:9000", "example.org:9000", "localhost:10000", "localhost:9000"}, "localhost:9000"},
{[]string{"http://localhost:9000/d1", "http://example.org:9000/d2", "http://example.com:9000/d3", "http://example.net:9000/d4"}, []string{"example.com:9000", "example.net:9000", "example.org:9000", "localhost:9000"}, "localhost:9000"},
{[]string{"http://localhost:9000/d1", "http://localhost:9001/d2", "http://localhost:9002/d3", "http://localhost:9003/d4"}, []string{"localhost:9000", "localhost:9001", "localhost:9002", "localhost:9003"}, "localhost:9000"},
}
for _, testCase := range testCases {
zendpoints := mustGetZoneEndpoints(testCase.endpointArgs...)
if !zendpoints[0].Endpoints[0].IsLocal {
if err := zendpoints[0].Endpoints.UpdateIsLocal(false); err != nil {
t.Fatalf("error: expected = <nil>, got = %v", err)
t.Errorf("error: expected = <nil>, got = %v", err)
}
}
remotePeers := GetRemotePeers(zendpoints)
remotePeers, local := zendpoints.peers()
if !reflect.DeepEqual(remotePeers, testCase.expectedResult) {
t.Fatalf("expected: %v, got: %v", testCase.expectedResult, remotePeers)
t.Errorf("expected: %v, got: %v", testCase.expectedResult, remotePeers)
}
if local != testCase.expectedLocal {
t.Errorf("expected: %v, got: %v", testCase.expectedLocal, local)
}
}
}