RFR: 8317453: NMT: Performance benchmarks are needed to measure speed and memory [v10]

Johan Sjölen jsjolen at openjdk.org
Tue May 20 08:58:55 UTC 2025


On Tue, 20 May 2025 08:55:38 GMT, Johan Sjölen <jsjolen at openjdk.org> wrote:

>> I think I was more comfortable with explicit types, since they are the struct that gets written to the disk, I wanted to know exactly how they are going to be laid out on a disk to make it easier to parse the data while debugging.
>> 
>> Can this stay as is?
>
> OK, but if you're laying out the data as is then it'll differ depending on if the recording is done on a little-endian or big-endian machine. I also don't know whether `long int` is a good idea to use here, as it'll compile as a 32-bit int on Windows and a 64-bit int on Linux and Mac (see LLP64 vs LP64). We will not get recordings that you can run on different machines with this scheme.

The right thing to do here is to specify, with code, how to dump this onto disk correctly.

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

PR Review Comment: https://git.openjdk.org/jdk/pull/23786#discussion_r2097412477


More information about the hotspot-dev mailing list