From 5d4774491f2e22c763dc045a35f799302d146007 Mon Sep 17 00:00:00 2001
From: Kirill Bulatov <kirill@neon.tech>
Date: Wed, 21 Dec 2022 00:52:07 +0200
Subject: [PATCH] Exclude macOs fork files from tar processing (#3165)

When running tenant relocation tests, we use
https://github.com/neondatabase/neon/blob/main/scripts/export_import_between_pageservers.py
script to export and import basebackup between pageservers.

When pageserver runs on macOs and reuses the `tar` library for creating
the basebackup archive, it gets the fork files

https://superuser.com/questions/61185/why-do-i-get-files-like-foo-in-my-tarball-on-os-x

We might be able to fix our code to fix the issue, but if we get such
(valid) archive as an input, we
[fail](https://github.com/neondatabase/neon/pull/3013#issuecomment-1360093900).
This does not seem optimal, given that we can ignore such files.
---
 pageserver/src/import_datadir.rs | 31 ++++++++++++++-----------------
 1 file changed, 14 insertions(+), 17 deletions(-)

diff --git a/pageserver/src/import_datadir.rs b/pageserver/src/import_datadir.rs
index 642e41765b..db83bdb3a1 100644
--- a/pageserver/src/import_datadir.rs
+++ b/pageserver/src/import_datadir.rs
@@ -440,16 +440,22 @@ fn import_file<Reader: Read>(
     reader: Reader,
     len: usize,
 ) -> Result<Option<ControlFileData>> {
+    let file_name = match file_path.file_name() {
+        Some(name) => name.to_string_lossy(),
+        None => return Ok(None),
+    };
+
+    if file_name.starts_with('.') {
+        // tar archives on macOs, created without COPYFILE_DISABLE=1 env var
+        // will contain "fork files", skip them.
+        return Ok(None);
+    }
+
     if file_path.starts_with("global") {
         let spcnode = postgres_ffi::pg_constants::GLOBALTABLESPACE_OID;
         let dbnode = 0;
 
-        match file_path
-            .file_name()
-            .expect("missing filename")
-            .to_string_lossy()
-            .as_ref()
-        {
+        match file_name.as_ref() {
             "pg_control" => {
                 let bytes = read_all_bytes(reader)?;
 
@@ -485,12 +491,7 @@ fn import_file<Reader: Read>(
             .to_string_lossy()
             .parse()?;
 
-        match file_path
-            .file_name()
-            .expect("missing base filename")
-            .to_string_lossy()
-            .as_ref()
-        {
+        match file_name.as_ref() {
             "pg_filenode.map" => {
                 let bytes = read_all_bytes(reader)?;
                 modification.put_relmap_file(spcnode, dbnode, bytes)?;
@@ -520,11 +521,7 @@ fn import_file<Reader: Read>(
         import_slru(modification, slru, file_path, reader, len)?;
         debug!("imported multixact members slru");
     } else if file_path.starts_with("pg_twophase") {
-        let file_name = &file_path
-            .file_name()
-            .expect("missing twophase filename")
-            .to_string_lossy();
-        let xid = u32::from_str_radix(file_name, 16)?;
+        let xid = u32::from_str_radix(file_name.as_ref(), 16)?;
 
         let bytes = read_all_bytes(reader)?;
         modification.put_twophase_file(xid, Bytes::copy_from_slice(&bytes[..]))?;