From fa49622521b6386d8031b1e7519f087aa9d99b19 Mon Sep 17 00:00:00 2001 From: Richard Purdie Date: Wed, 30 Jun 2021 13:02:25 +0100 Subject: sstate/staging: Handle directory creation race issue The sstate code tries to be careful about racing around directory creation. In particular, the copyhardlinktree code creates the directory tree first allowing for "already exists" errors and ignoring them, then hardlinks the files in. Unfortunately the sstate removal code can race against this since it will try and remove empty directories. If there is some bad timing, a newly created directory can be removed before it was populated, leading to build failures. We could try and add locking but this would damage performance, we've been there before. It is also unclear where to actually place locks just based on the contents of a manifest file which may cover multiple sstate install locations for a given task. Instead, lets disable directory removal in the problematic "shared" core path. This could result in a few more empty directories being left on disk but those should be harmless and better than locking hurting performance or rare build races. [YOCTO #13999] [YOCTO #14379] Signed-off-by: Richard Purdie (cherry picked from commit 4f94d9296394bc7ce241439f00df86eb5912875f) Signed-off-by: Steve Sakoman --- meta/classes/sstate.bbclass | 8 +++++--- meta/classes/staging.bbclass | 6 +++--- 2 files changed, 8 insertions(+), 6 deletions(-) diff --git a/meta/classes/sstate.bbclass b/meta/classes/sstate.bbclass index 53dcfc8274..9ed0e0c139 100644 --- a/meta/classes/sstate.bbclass +++ b/meta/classes/sstate.bbclass @@ -483,7 +483,7 @@ def sstate_clean_cachefiles(d): ss = sstate_state_fromvars(ld, task) sstate_clean_cachefile(ss, ld) -def sstate_clean_manifest(manifest, d, prefix=None): +def sstate_clean_manifest(manifest, d, canrace=False, prefix=None): import oe.path mfile = open(manifest) @@ -501,7 +501,9 @@ def sstate_clean_manifest(manifest, d, prefix=None): if entry.endswith("/"): if os.path.islink(entry[:-1]): os.remove(entry[:-1]) - elif os.path.exists(entry) and len(os.listdir(entry)) == 0: + elif os.path.exists(entry) and len(os.listdir(entry)) == 0 and not canrace: + # Removing directories whilst builds are in progress exposes a race. Only + # do it in contexts where it is safe to do so. os.rmdir(entry[:-1]) else: os.remove(entry) @@ -539,7 +541,7 @@ def sstate_clean(ss, d): for lock in ss['lockfiles']: locks.append(bb.utils.lockfile(lock)) - sstate_clean_manifest(manifest, d) + sstate_clean_manifest(manifest, d, canrace=True) for lock in locks: bb.utils.unlockfile(lock) diff --git a/meta/classes/staging.bbclass b/meta/classes/staging.bbclass index 506ce0665e..78eb914921 100644 --- a/meta/classes/staging.bbclass +++ b/meta/classes/staging.bbclass @@ -408,7 +408,7 @@ python extend_recipe_sysroot() { if os.path.islink(f) and not os.path.exists(f): bb.note("%s no longer exists, removing from sysroot" % f) lnk = os.readlink(f.replace(".complete", "")) - sstate_clean_manifest(depdir + "/" + lnk, d, workdir) + sstate_clean_manifest(depdir + "/" + lnk, d, canrace=True, prefix=workdir) os.unlink(f) os.unlink(f.replace(".complete", "")) @@ -453,7 +453,7 @@ python extend_recipe_sysroot() { fl = depdir + "/" + l bb.note("Task %s no longer depends on %s, removing from sysroot" % (mytaskname, l)) lnk = os.readlink(fl) - sstate_clean_manifest(depdir + "/" + lnk, d, workdir) + sstate_clean_manifest(depdir + "/" + lnk, d, canrace=True, prefix=workdir) os.unlink(fl) os.unlink(fl + ".complete") @@ -474,7 +474,7 @@ python extend_recipe_sysroot() { continue else: bb.note("%s exists in sysroot, but is stale (%s vs. %s), removing." % (c, lnk, c + "." + taskhash)) - sstate_clean_manifest(depdir + "/" + lnk, d, workdir) + sstate_clean_manifest(depdir + "/" + lnk, d, canrace=True, prefix=workdir) os.unlink(depdir + "/" + c) if os.path.lexists(depdir + "/" + c + ".complete"): os.unlink(depdir + "/" + c + ".complete") -- cgit 1.2.3-korg