Ensuring your code is working at its utmost best can be pretty daunting if you're not sure what to pull back, and by how much. However, sometimes the stars align, and you spot a really simple fix that significantly boosts your software's speed.

As good as that is, though, not many people can claim to have sped up a process by 5% simply by moving three chunks of code down by a few lines, which is exactly what one Linux engineer achieved with kernel version 7.2.

Linux 7.2 got a 5% storage speed boost by moving three lines of code

It was a very impactful move, but a move nonetheless

As spotted by Phoronix, this change was authored by Fengnan Chang and committed by Christian Brauner. In Brauner's commit notes, he mentions the work that Chang had done to the kernel and how it helped flesh out Linux 7.2:

Skip the memset of the iomap in iomap_iter() once the iteration is done. In high-IOPS scenarios (4k randread NVMe polling via io_uring), the pointless memset wasted memory write bandwidth; this improves IOPS by about 5% on ext4 and xfs.

If you're feeling a little lost after that, IOPS stands for "Input/Output Operations Per Second" and is basically the speed at which your storage drive sends and receives data. Squeezing out a 5% speed boost from the Linux kernel is really impressive, to say the least.

Funnily enough, that's not the best part of this story. The most interesting part is how Chang fixed it. You can see the change in the image above and in the commit logs, but Chang essentially took three lines of code and moved them so they fired after the process finished rather than before. Just like that, IOPS rates went up by 5%. I wish all my debugging ventures were this easy yet significant.

Linux 7.1 just came out last weekend, so this fix won't arrive on our PCs until 7.2 releases sometime in August 2026. However, it's cool to see that 7.2 is already shaping up to be an interesting one so quickly.