mirror of
https://github.com/rustfs/rustfs.git
synced 2026-07-26 08:18:18 +00:00
073628e8be
* feat(utils): make DNS resolver cache TTL configurable via RUSTFS_DNS_CACHE_TTL_SECS The resolver cache in crates/utils/src/net.rs had a hardcoded 300s TTL with no way to tune or disable it. On orchestrated networks (Docker Swarm, Kubernetes) a peer's DNS name is its only durable identity while its container IP changes on reschedule, and the platform DNS always serves the current answer. A fixed 300s application-side cache can keep a member dialing a dead IP for up to five minutes after a peer restarts. Rust has no runtime DNS cache, so on musl images this was the only cache in the stack and the only one that could not be turned off. Read the TTL from RUSTFS_DNS_CACHE_TTL_SECS (u64, default 300), matching the existing RUSTFS_INTERNODE_* transport knobs. `0` disables caching entirely so every get_host_ip consults the system resolver. The resolved value is logged once at first use, removing an invisible cache from the triage surface. Change is backward-compatible and confined to net.rs. Also drop the two per-lookup info! logs on the resolve path: they would flood the log when caching is disabled and added hot-path noise otherwise. Co-Authored-By: heihutu <heihutu@gmail.com> * fix(helm): derive mTLS secret names from chart fullname (#4601) * fix(helm): mtls certificate for server and client hardcode * fix hardcode issue in deployment * update typo yaml file --------- Co-authored-by: heihutu <heihutu@gmail.com> Co-authored-by: majinghe <42570491+majinghe@users.noreply.github.com>