# HG changeset patch # User Gregory Szorc # Date 2016-01-14 21:44:01 # Node ID 2fdbf22a1b63f7b4c94393dbf45ad417da257fe0 # Parent 1d29893240cc90597b95d4ea1b18eb66b3ed4a10 streamclone: use backgroundfilecloser (issue4889) Closing files that have been appended to is slow on Windows/NTFS. CloseHandle() calls on this platform often take 1-10ms - and that's on my i7-6700K Skylake processor with a modern and fast SSD. Contrast with other I/O operations, such as writing data, which take <100us. This means that creating/appending thousands of files can add significant overhead. For example, cloning mozilla-central creates ~232,000 revlog files. Assuming 1ms per CloseHandle(), that yields 232s (3:52) of wall time waiting for file closes! The impact of this overhead can be measured most directly when applying stream clone bundles. Applying these files is effectively uncompressing a tar archive (read: it's very fast). Using a RAM disk (read: no I/O wait), the difference in wall time for a `hg debugapplystreamclonebundle` for a ~1731 MB mozilla-central bundle between Windows and Linux from the same machine is drastic: Linux: ~12.8s (128MB/s) Windows: ~352.0s (4.7MB/s) Windows is ~27.5x slower. Yikes! After this patch: Linux: ~12.8s (128MB/s) Windows: ~102.1s (16.1MB/s) Windows is now ~3.4x faster. Unfortunately, it is still ~8x slower than Linux. Profiling reveals a few hot code paths that could likely be improved. But those are for other patches. This patch introduces test-clone-uncompressed.t because existing tests of `clone --uncompressed` are scattered about and adding a variation for background thread closing to e.g. test-http.t doesn't feel correct. diff --git a/mercurial/streamclone.py b/mercurial/streamclone.py --- a/mercurial/streamclone.py +++ b/mercurial/streamclone.py @@ -298,7 +298,7 @@ def consumev1(repo, fp, filecount, bytec start = time.time() with repo.transaction('clone'): - if True: + with repo.svfs.backgroundclosing(repo.ui, expectedcount=filecount): for i in xrange(filecount): # XXX doesn't support '\n' or '\r' in filenames l = fp.readline() @@ -312,7 +312,8 @@ def consumev1(repo, fp, filecount, bytec repo.ui.debug('adding %s (%s)\n' % (name, util.bytecount(size))) # for backwards compat, name was partially encoded - with repo.svfs(store.decodedir(name), 'w') as ofp: + path = store.decodedir(name) + with repo.svfs(path, 'w', backgroundclose=True) as ofp: for chunk in util.filechunkiter(fp, limit=size): handled_bytes += len(chunk) repo.ui.progress(_('clone'), handled_bytes, diff --git a/tests/test-clone-uncompressed.t b/tests/test-clone-uncompressed.t new file mode 100644 --- /dev/null +++ b/tests/test-clone-uncompressed.t @@ -0,0 +1,48 @@ +#require serve + + $ hg init server + $ cd server + $ touch foo + $ hg -q commit -A -m initial + >>> for i in range(1024): + ... with open(str(i), 'wb') as fh: + ... fh.write(str(i)) + $ hg -q commit -A -m 'add a lot of files' + $ hg serve -p $HGPORT -d --pid-file=hg.pid + $ cat hg.pid >> $DAEMON_PIDS + $ cd .. + +Basic clone + + $ hg clone --uncompressed -U http://localhost:$HGPORT clone1 + streaming all changes + 1027 files to transfer, 96.3 KB of data + transferred 96.3 KB in * seconds (*/sec) (glob) + searching for changes + no changes found + +Clone with background file closing enabled + + $ hg --debug --config worker.backgroundclose=true --config worker.backgroundcloseminfilecount=1 clone --uncompressed -U http://localhost:$HGPORT clone-background | grep -v adding + using http://localhost:$HGPORT/ + sending capabilities command + sending branchmap command + streaming all changes + sending stream_out command + 1027 files to transfer, 96.3 KB of data + starting 4 threads for background file closing + transferred 96.3 KB in * seconds (*/sec) (glob) + query 1; heads + sending batch command + searching for changes + all remote heads known locally + no changes found + sending getbundle command + bundle2-input-bundle: with-transaction + bundle2-input-part: "listkeys" (params: 1 mandatory) supported + bundle2-input-part: "listkeys" (params: 1 mandatory) supported + bundle2-input-bundle: 1 parts total + checking for updated bookmarks + preparing listkeys for "phases" + sending listkeys command + received listkey for "phases": 58 bytes