local TCP connections should be expediently purged from TIME_WAIT
An individual was running an HTTP-based benchmark locally in a native smartos zone. Due to the high transaction rate, TCP connections were piling up in TIME_WAIT state. Even with the best-case localhost behavior being fired every TCP_TIME_WAIT_DELAY (5s), we're left with a maximum connection rate of ~6500/s.
Since these connections are all local to the host (over localhost for this specific example), it should be safe to immediately purge the connection instead of letting it languish in TIME_WAIT.
Updated by Electric Monk over 6 years ago
- Status changed from New to Closed
commit 2404c9e6b54f427b32dd0a2d46940d6a4c5299bc Author: Patrick Mooney <firstname.lastname@example.org> Date: 2016-06-09T20:31:42.000Z 7062 Connections remain in TIME_WAIT too long 7061 local TCP connections should be expediently purged from TIME_WAIT Reviewed by: Jerry Jelinek <email@example.com> Reviewed by: Robert Mustacchi <firstname.lastname@example.org> Reviewed by: Garrett D'Amore <email@example.com> Approved by: Dan McDonald <firstname.lastname@example.org>