RFR: 8373647: Avoid unnecessary fstat when opening file for write

[Alan Bateman]

On Mon, 15 Dec 2025 11:49:19 GMT, Jonas Norlinder <jnorlinder at openjdk.org> wrote:

> # Background
> 
> When Java applications uses APIs like java.io.FileOutputStream it will hook into native implementations in e.g. io_util_md.c for Unix/Linux. Java does not allow reading a directory and the implementation reflect this fact. For Unix there are three access modes O_RDONLY, O_WRONLY, O_RDWR. Moreover, on Unix it is possible to read a directory and an extra check has been added in the code to ensure that the user is trying to read a file (with O_RDONLY) and not a directory. This extra check results in an additional syscall.
> 
> This check is actually redundant in case user are using access mode O_WRONLY or O_RDWR. If one is trying to call open on a directory with these modes the specification in Unix and Linux specifies that EISDIR shall be returned. For the case of Unix standard it has been part of the standard at least since 1997 (https://pubs.opengroup.org/onlinepubs/007908799/xsh/open.html) and Linux since at least 2004 (see v 2.0 https://www.kernel.org/pub/linux/docs/man-pages/Archive/ ) to return error if user is trying to write to an directory. In OpenJDK we also include AIX and they are certified to follow the Unix standard (https://www.opengroup.org/openbrand/register/ibm.htm). I believe that it is therefore safe to assume that this is a well implemented aspect of the Unix standard by now and that this technical debt can be eliminated (assuming that this check was indeed needed at some point).
> 
> # Performance Improvements
> 
> A stress-test that opens a huge amount of files to trigger a syscall storm reveals that a removal of this redundant syscall may also improve performance during high load:
> 
> 
> JDK 27 baseline
> Benchmark            Mode   Cnt     Score    Error   Units
> FileWriteStress.test sample 8438452 3722.451 ± 2.402 ns/op
> 
> JDK 27 patched
> Benchmark            Mode   Cnt     Score    Error   Units
> FileWriteStress.test sample 4952304 3191.912 ± 4.011 ns/op
> 
> 
> ~17% performance boost.

The new APIs doesn't have this restriction but we are stuck with it for FileInputStream or when opening a file for read with RandomAccessFile. At some point we will replace the implementation of all 3 as they can be implemented on top of the new APIs.

src/java.base/unix/native/libjava/io_util_md.c line 82:

> 80:     // not a read access mode then the Unix standard
> 81:     // guarantees to have failed with EISDIR
> 82:     if (fd == -1 || ((oflag & O_ACCMODE) != O_RDONLY) != 0) {

Can you drop the "Fast-path" comment as it is confusing here. It just needs to say that there is no need to check if the file is a directory when opened for write.

src/java.base/unix/native/libjava/io_util_md.c line 86:

> 84:     }
> 85: 
> 86:     // Slow-path, while Unix allow for directories

We can replace this with a clearer comment to say that FileInputStream is specified to throw if the file is a directory?

test/micro/org/openjdk/bench/java/io/FileWriteStress.java line 26:

> 24: 
> 25: import java.io.File;
> 26: import java.io.FileNotFoundException;

Used?

test/micro/org/openjdk/bench/java/io/FileWriteStress.java line 44:

> 42: 
> 43: @Fork(value = 10)
> 44: public class FileWriteStress {

You might want to think about a better name for this as it's not really a write stress tests. It could test both FOS and RAF as the changes in the PR change both.

-------------

PR Comment: https://git.openjdk.org/jdk/pull/28823#issuecomment-3710409761
PR Review Comment: https://git.openjdk.org/jdk/pull/28823#discussion_r2661474563
PR Review Comment: https://git.openjdk.org/jdk/pull/28823#discussion_r2661479745
PR Review Comment: https://git.openjdk.org/jdk/pull/28823#discussion_r2634936021
PR Review Comment: https://git.openjdk.org/jdk/pull/28823#discussion_r2634935307