rustc: Support auto-retry linking on a segfault

This is a last-ditch attempt to help our pain with dealing with #38878 on the
bots. A new environment variable is added to the compiler,
`RUSTC_RETRY_LINKER_ON_SEGFAULT`, which will instruct the compiler to
automatically retry the final linker invocation if it looks like the linker
segfaulted (up to 2 extra times).

Unfortunately there have been no successful attempts to debug #38878. The only
information seems to be that the linker (e.g. `ld` on OSX) is segfaulting
somewhere in some thread pool implementation. This appears to be spurious as
failed PRs will later merge.

The hope is that this helps the queue keep moving without clogging and delaying
PRs due to #38878.

diff --git a/.travis.yml b/.travis.yml
index fa6c9cf0748647c5d2a48593f1c2f6e127ebda8d..42684d70d36a9daa5a01b8ec37b02341f850b12e 100644 (file)
--- a/.travis.yml
+++ b/.travis.yml
@@ -44,6 +44,7 @@ matrix:
         RUST_CHECK_TARGET=check
         RUST_CONFIGURE_ARGS=--build=x86_64-apple-darwin
         SRC=.
+        RUSTC_RETRY_LINKER_ON_SEGFAULT=1
       os: osx
       osx_image: xcode8.2
       install: &osx_install_sccache >
@@ -53,6 +54,7 @@ matrix:
         RUST_CHECK_TARGET=check
         RUST_CONFIGURE_ARGS=--build=i686-apple-darwin
         SRC=.
+        RUSTC_RETRY_LINKER_ON_SEGFAULT=1
       os: osx
       osx_image: xcode8.2
       install: *osx_install_sccache
@@ -62,6 +64,7 @@ matrix:
         RUST_CONFIGURE_ARGS="--build=i686-apple-darwin --enable-extended"
         SRC=.
         DEPLOY=1
+        RUSTC_RETRY_LINKER_ON_SEGFAULT=1
       os: osx
       osx_image: xcode8.2
       install: >
@@ -74,6 +77,7 @@ matrix:
         RUST_CONFIGURE_ARGS="--target=aarch64-apple-ios,armv7-apple-ios,armv7s-apple-ios,i386-apple-ios,x86_64-apple-ios --enable-extended"
         SRC=.
         DEPLOY=1
+        RUSTC_RETRY_LINKER_ON_SEGFAULT=1
       os: osx
       osx_image: xcode8.2
       install: *osx_install_sccache
@@ -88,6 +92,7 @@ matrix:
         RUST_CONFIGURE_ARGS="--enable-extended"
         SRC=.
         DEPLOY_ALT=1
+        RUSTC_RETRY_LINKER_ON_SEGFAULT=1
       os: osx
       osx_image: xcode8.2
       install: *osx_install_sccache

diff --git a/src/librustc_trans/back/link.rs b/src/librustc_trans/back/link.rs
index b58f96033bf5b5dc2404c31657ac89dda25ea00e..a1703b1c155eb0535410d5002c3221c070721b40 100644 (file)
--- a/src/librustc_trans/back/link.rs
+++ b/src/librustc_trans/back/link.rs
@@ -752,8 +752,54 @@ fn link_natively(sess: &Session,
     sess.abort_if_errors();
 
     // Invoke the system linker
+    //
+    // Note that there's a terribly awful hack that really shouldn't be present
+    // in any compiler. Here an environment variable is supported to
+    // automatically retry the linker invocation if the linker looks like it
+    // segfaulted.
+    //
+    // Gee that seems odd, normally segfaults are things we want to know about!
+    // Unfortunately though in rust-lang/rust#38878 we're experiencing the
+    // linker segfaulting on Travis quite a bit which is causing quite a bit of
+    // pain to land PRs when they spuriously fail due to a segfault.
+    //
+    // The issue #38878 has some more debugging information on it as well, but
+    // this unfortunately looks like it's just a race condition in OSX's linker
+    // with some thread pool working in the background. It seems that no one
+    // currently knows a fix for this so in the meantime we're left with this...
     info!("{:?}", &cmd);
-    let prog = time(sess.time_passes(), "running linker", || cmd.output());
+    let retry_on_segfault = env::var("RUSTC_RETRY_LINKER_ON_SEGFAULT").is_ok();
+    let mut prog;
+    let mut i = 0;
+    loop {
+        i += 1;
+        prog = time(sess.time_passes(), "running linker", || cmd.output());
+        if !retry_on_segfault || i > 3 {
+            break
+        }
+        let output = match prog {
+            Ok(ref output) => output,
+            Err(_) => break,
+        };
+        if output.status.success() {
+            break
+        }
+        let mut out = output.stderr.clone();
+        out.extend(&output.stdout);
+        let out = String::from_utf8_lossy(&out);
+        let msg = "clang: error: unable to execute command: \
+                   Segmentation fault: 11";
+        if !out.contains(msg) {
+            break
+        }
+
+        sess.struct_warn("looks like the linker segfaulted when we tried to \
+                          call it, automatically retrying again")
+            .note(&format!("{:?}", cmd))
+            .note(&out)
+            .emit();
+    }
+
     match prog {
         Ok(prog) => {
             fn escape_string(s: &[u8]) -> String {