From dabb2fa0683cd0f34913897e4295d3481d5e3f5d Mon Sep 17 00:00:00 2001 From: Alexander Motin Date: Tue, 26 Apr 2022 13:44:21 -0400 Subject: [PATCH] Improve log spacemap load time Previous flushing algorithm limited only total number of log blocks to the minimum of 256K and 4x number of metaslabs in the pool. As result, system with 1500 disks with 1000 metaslabs each, touching several new metaslabs each TXG could grow spacemap log to huge size without much benefits. We've observed one of such systems importing pool for about 45 minutes. This patch improves the situation from five sides: - By limiting maximum period for each metaslab to be flushed to 1000 TXGs, that effectively limits maximum number of per-TXG spacemap logs to load to the same number. - By making flushing more smooth via accounting number of metaslabs that were touched after the last flush and actually need another flush, not just ms_unflushed_txg bump. - By applying zfs_unflushed_log_block_pct to the number of metaslabs that were touched after the last flush, not all metaslabs in the pool. - By aggressively prefetching per-TXG spacemap logs up to 16 TXGs in advance, making log spacemap load process for wide HDD pool CPU-bound, accelerating it by many times. - By reducing zfs_unflushed_log_block_max from 256K to 128K, reducing single-threaded by nature log processing time from ~10 to ~5 minutes. As further optimization we could skip bumping ms_unflushed_txg for metaslabs not touched since the last flush, but that would be an incompatible change, requiring new pool feature. Reviewed-by: Matthew Ahrens Reviewed-by: Brian Behlendorf Signed-off-by: Alexander Motin Sponsored-By: iXsystems, Inc. Closes #12789 --- module/zfs/spa_log_spacemap.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/module/zfs/spa_log_spacemap.c b/module/zfs/spa_log_spacemap.c index 6871a610e62f..47a43ef9dc25 100644 --- a/module/zfs/spa_log_spacemap.c +++ b/module/zfs/spa_log_spacemap.c @@ -259,6 +259,11 @@ static ZFS_MODULE_ULONG zfs_unflushed_log_block_min = 1000; */ static ZFS_MODULE_ULONG zfs_unflushed_log_block_max = (1ULL << 18); +/* + * Also we have a hard limit in the size of the log in terms of dirty TXGs. + */ +static unsigned long zfs_unflushed_log_txg_max = 1000; + /* * Max # of rows allowed for the log_summary. The tradeoff here is accuracy and * stability of the flushing algorithm (longer summary) vs its runtime overhead