From 560627b525d7abc0b25410fafc4f9fa523c3a078 Mon Sep 17 00:00:00 2001 From: Heikki Linnakangas Date: Tue, 18 Jun 2024 13:38:15 +0300 Subject: [PATCH] Replace a few references to Zenith with neon --- docs/core_changes.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/core_changes.md b/docs/core_changes.md index 6cc19d8b62..1388317728 100644 --- a/docs/core_changes.md +++ b/docs/core_changes.md @@ -156,7 +156,7 @@ index 0415df9ccb..9f9db3c8bc 100644 * crash we can lose (skip over) as many values as we pre-logged. */ -#define SEQ_LOG_VALS 32 -+/* Zenith XXX: to ensure sequence order of sequence in Zenith we need to WAL log each sequence update. */ ++/* Neon XXX: to ensure sequence order of sequence in Zenith we need to WAL log each sequence update. */ +/* #define SEQ_LOG_VALS 32 */ +#define SEQ_LOG_VALS 0 ``` @@ -485,6 +485,6 @@ Add special WAL record for setting page hints. ### Why? -Short downtime (or, in other words, fast compute node restart time) is one of the key feature of Zenith. +Short downtime (or, in other words, fast compute node restart time) is one of the key feature of Neon. But overhead of request-response round-trip for loading pages on demand can make started node warm-up quite slow. We can capture state of compute node buffer cache and send bulk request for this pages at startup.