[PATCH] sstate: Parallelise checkstatus calls for sstate mirror

[PATCH] sstate: Parallelise checkstatus calls for sstate mirror

[Richard Purdie]

Currently the urls are checked serially which is a performance bottleneck when
looking at http:// urls in particular. This adds code to check the url status in
parallel, mirroring the way we do this elsewhere.

We need the datastore for the fetcher so we use threads, not multiprocess.

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

diff --git a/meta/classes/sstate.bbclass b/meta/classes/sstate.bbclass
index b485044..de3519a 100644
--- a/meta/classes/sstate.bbclass
+++ b/meta/classes/sstate.bbclass
@@ -715,20 +715,16 @@ def sstate_checkhashes(sq_fn, sq_task, sq_hash, sq_hashfn, d, siginfo=False):
         if localdata.getVar('BB_NO_NETWORK', True) == "1" and localdata.getVar('SSTATE_MIRROR_ALLOW_NETWORK', True) == "1":
             localdata.delVar('BB_NO_NETWORK')
 
-        for task in range(len(sq_fn)):
-            if task in ret:
-                continue
-
-            spec, extrapath, tname = getpathcomponents(task, d)
-
-            sstatefile = d.expand(extrapath + generate_sstatefn(spec, sq_hash[task], d) + "_" + tname + extension)
+        def checkstatus(arg):
+            (task, sstatefile) = arg
 
+            localdata2 = bb.data.createCopy(localdata)
             srcuri = "file://" + sstatefile
             localdata.setVar('SRC_URI', srcuri)
             bb.debug(2, "SState: Attempting to fetch %s" % srcuri)
 
             try:
-                fetcher = bb.fetch2.Fetch(srcuri.split(), localdata)
+                fetcher = bb.fetch2.Fetch(srcuri.split(), localdata2)
                 fetcher.checkstatus()
                 bb.debug(2, "SState: Successful fetch test for %s" % srcuri)
                 ret.append(task)
@@ -739,6 +735,22 @@ def sstate_checkhashes(sq_fn, sq_task, sq_hash, sq_hashfn, d, siginfo=False):
                 bb.debug(2, "SState: Unsuccessful fetch test for %s" % srcuri)
                 pass     
 
+        tasklist = []
+        for task in range(len(sq_fn)):
+            if task in ret:
+                continue
+            spec, extrapath, tname = getpathcomponents(task, d)
+            sstatefile = d.expand(extrapath + generate_sstatefn(spec, sq_hash[task], d) + "_" + tname + extension)
+            tasklist.append((task, sstatefile))
+
+        if tasklist:
+            import multiprocessing
+            nproc = min(multiprocessing.cpu_count(), len(tasklist))
+            pool = oe.utils.ThreadedPool(nproc)
+            for t in tasklist:
+                pool.add_task(checkstatus, t)
+            pool.wait_completion()
+
     inheritlist = d.getVar("INHERIT", True)
     if "toaster" in inheritlist:
         evdata = {'missed': [], 'found': []};