Refactor Log Size Limit

Original Log Size Limit implementation blocked all writes in case of
limit reached until the TXG is committed and the log is freed.  It
caused huge delays and following speed spikes in application writes.

This implementation instead smoothly throttles writes, using exactly
the same mechanism as used for dirty data.

Reviewed-by: Brian Behlendorf <[email protected]>
Reviewed-by: jxdking <[email protected]>
Signed-off-by: Alexander Motin <[email protected]>
Sponsored-By: iXsystems, Inc.
Issue #12284
Closes #13476 

1 files changed, 3 insertions, 4 deletions

diff --git a/man/man4/zfs.4 b/man/man4/zfs.4
index c95fa98c5..d1ca69f80 100644
--- a/man/man4/zfs.4
+++ b/man/man4/zfs.4
@@ -1098,10 +1098,9 @@ This should be less than
 .
 .It Sy zfs_wrlog_data_max Ns = Pq int
 The upper limit of write-transaction zil log data size in bytes.
-Once it is reached, write operation is blocked, until log data is cleared out
-after transaction group sync.
-Because of some overhead, it should be set
-at least 2 times the size of
+Write operations are throttled when approaching the limit until log data is
+cleared out after transaction group sync.
+Because of some overhead, it should be set at least 2 times the size of
 .Sy zfs_dirty_data_max
 .No to prevent harming normal write throughput.
 It also should be smaller than the size of the slog device if slog is present.