https://peng.fyi/tags/nfs/ Recent content in NFS on Hugo -- gohugo.io en map[name:Peng Zhang] map[name:Peng Zhang] Peng Zhang Mon, 09 Nov 2026 00:00:00 +0000 https://peng.fyi/post/sysfs-superblock-race/ Mon, 09 Nov 2026 00:00:00 +0000 map[name:Peng Zhang] https://peng.fyi/post/sysfs-superblock-race/ While testing Amazon EFS volumes in containers, I found that sequential reads in some runs were about 4 times slower than in others. EFS volumes are mounted with efs-utils, which turns mount -t efs into an NFSv4.1 mount through a local TLS proxy. In the slow runs, the NFS mount's read_ahead_kb was 128 instead of 15360. That symptom has a known cause. Linux 5.4 dropped the default NFS readahead from 15 times rsize, which is 15 MiB with EFS's 1 MiB rsize, to 128 KiB (NFS: Optimise the default readahead size).