[oe-commits] Richard Purdie : lib/oe/utils: Add utils function for multiprocess execution

[git at git.openembedded.org]

Module: openembedded-core.git
Branch: master-next
Commit: 72d153a3a90d31d9f4e41d77da24e44ccb33c56e
URL:    http://git.openembedded.org/?p=openembedded-core.git&a=commit;h=72d153a3a90d31d9f4e41d77da24e44ccb33c56e

Author: Richard Purdie <richard.purdie at linuxfoundation.org>
Date:   Thu Aug 21 21:46:28 2014 +0100

lib/oe/utils: Add utils function for multiprocess execution

Our usage of multitprocessing is problematic. In particular, there is a bug
in python 2.7 multiprocessing where signals are not handled until command
completion instead of immediately.

This factors the multiprocess code into a function which is enhanced with
a workaround to ensure immediate signal handling and also better SIGINT
handling which should happen in the parent, not the children to ensure
clean exits. The workaround for the signals is being added to the core
bb.utils function so it can benefit all users.

package_manager is then converted to use the new code.

Signed-off-by: Richard Purdie <richard.purdie at linuxfoundation.org>

---

 meta/lib/oe/package_manager.py | 32 ++++----------------------------
 meta/lib/oe/utils.py           | 29 +++++++++++++++++++++++++++++
 2 files changed, 33 insertions(+), 28 deletions(-)

diff --git a/meta/lib/oe/package_manager.py b/meta/lib/oe/package_manager.py
index 8be3d41..f8fc3c2 100644
--- a/meta/lib/oe/package_manager.py
+++ b/meta/lib/oe/package_manager.py
@@ -7,6 +7,7 @@ import multiprocessing
 import re
 import bb
 import tempfile
+import oe.utils
 
 
 # this can be used by all PM backends to create the index files in parallel
@@ -116,16 +117,7 @@ class RpmIndexer(Indexer):
             bb.note("There are no packages in %s" % self.deploy_dir)
             return
 
-        nproc = multiprocessing.cpu_count()
-        pool = bb.utils.multiprocessingpool(nproc)
-        results = list(pool.imap(create_index, index_cmds))
-        pool.close()
-        pool.join()
-
-        for result in results:
-            if result is not None:
-                return(result)
-
+        oe.utils.multiprocess_exec(index_cmds, create_index)
 
 class OpkgIndexer(Indexer):
     def write_index(self):
@@ -161,15 +153,7 @@ class OpkgIndexer(Indexer):
             bb.note("There are no packages in %s!" % self.deploy_dir)
             return
 
-        nproc = multiprocessing.cpu_count()
-        pool = bb.utils.multiprocessingpool(nproc)
-        results = list(pool.imap(create_index, index_cmds))
-        pool.close()
-        pool.join()
-
-        for result in results:
-            if result is not None:
-                return(result)
+        oe.utils.multiprocess_exec(index_cmds, create_index)
 
 
 class DpkgIndexer(Indexer):
@@ -210,15 +194,7 @@ class DpkgIndexer(Indexer):
             bb.note("There are no packages in %s" % self.deploy_dir)
             return
 
-        nproc = multiprocessing.cpu_count()
-        pool = bb.utils.multiprocessingpool(nproc)
-        results = list(pool.imap(create_index, index_cmds))
-        pool.close()
-        pool.join()
-
-        for result in results:
-            if result is not None:
-                return(result)
+        oe.utils.multiprocess_exec(index_cmds, create_index)
 
 
 class PkgsList(object):
diff --git a/meta/lib/oe/utils.py b/meta/lib/oe/utils.py
index 0a1d108..92e21a4 100644
--- a/meta/lib/oe/utils.py
+++ b/meta/lib/oe/utils.py
@@ -151,3 +151,32 @@ def execute_pre_post_process(d, cmds):
         if cmd != '':
             bb.note("Executing %s ..." % cmd)
             bb.build.exec_func(cmd, d)
+
+def multiprocess_exec(commands, function):
+    import signal
+    import multiprocessing
+
+    if not commands:
+        return []
+
+    def init_worker():
+        signal.signal(signal.SIGINT, signal.SIG_IGN)
+
+    nproc = min(multiprocessing.cpu_count(), len(commands))
+    pool = bb.utils.multiprocessingpool(nproc, init_worker)
+    imap = pool.imap(function, commands)
+
+    try:
+        results = list(imap)
+        pool.close()
+        pool.join()
+        results = []
+        for result in results:
+            if result is not None:
+                results.append(result)
+        return results
+
+    except KeyboardInterrupt:
+        pool.terminate()
+        pool.join()
+        raise