c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2026-05-22 18:40:43 +03:00
Code Issues Packages Projects Releases Wiki Activity

make zil max block size tunable

Browse Source 
We've observed that on some highly fragmented pools, most metaslab
allocations are small (~2-8KB), but there are some large, 128K
allocations.  The large allocations are for ZIL blocks.  If there is a
lot of fragmentation, the large allocations can be hard to satisfy.

The most common impact of this is that we need to check (and thus load)
lots of metaslabs from the ZIL allocation code path, causing sync writes
to wait for metaslabs to load, which can take a second or more.  In the
worst case, we may not be able to satisfy the allocation, in which case
the ZIL will resort to txg_wait_synced() to ensure the change is on
disk.

To provide a workaround for this, this change adds a tunable that can
reduce the size of ZIL blocks.

External-issue: DLPX-61719
Reviewed-by: George Wilson <george.wilson@delphix.com>
Reviewed-by: Paul Dagnelie <pcd@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Closes #8865
This commit is contained in:
Matthew Ahrens
2019-06-10 11:48:42 -07:00
committed by Brian Behlendorf
parent 5a902f5aaa
commit b8738257c2
7 changed files with 96 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/sys/zil.h
+4 -1
View File
@@ -20,7 +20,7 @@
*/
/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
* Copyright (c) 2012, 2017 by Delphix. All rights reserved.
* Copyright (c) 2012, 2018 by Delphix. All rights reserved.
*/
/* Portions Copyright 2010 Robert Milkowski */
@@ -515,6 +515,9 @@ extern void zil_set_sync(zilog_t *zilog, uint64_t syncval);
extern void zil_set_logbias(zilog_t *zilog, uint64_t slogval);
extern uint64_t zil_max_copied_data(zilog_t *zilog);
extern uint64_t zil_max_log_data(zilog_t *zilog);
extern int zil_replay_disable;
#ifdef __cplusplus
include/sys/zil_impl.h
+8 -21
View File
@@ -20,7 +20,7 @@
*/
/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
* Copyright (c) 2012, 2017 by Delphix. All rights reserved.
* Copyright (c) 2012, 2018 by Delphix. All rights reserved.
*/
/* Portions Copyright 2010 Robert Milkowski */
@@ -209,6 +209,13 @@ struct zilog {
uint_t zl_prev_rotor; /* rotor for zl_prev[] */
txg_node_t zl_dirty_link; /* protected by dp_dirty_zilogs list */
uint64_t zl_dirty_max_txg; /* highest txg used to dirty zilog */
/*
* Max block size for this ZIL. Note that this can not be changed
* while the ZIL is in use because consumers (ZPL/zvol) need to take
* this into account when deciding between WR_COPIED and WR_NEED_COPY
* (see zil_max_copied_data()).
*/
uint64_t zl_max_block_size;
};
typedef struct zil_bp_node {
@@ -216,26 +223,6 @@ typedef struct zil_bp_node {
avl_node_t zn_node;
} zil_bp_node_t;
/*
* Maximum amount of write data that can be put into single log block.
*/
#define ZIL_MAX_LOG_DATA (SPA_OLD_MAXBLOCKSIZE - sizeof (zil_chain_t) - \
sizeof (lr_write_t))
/*
* Maximum amount of log space we agree to waste to reduce number of
* WR_NEED_COPY chunks to reduce zl_get_data() overhead (~12%).
*/
#define ZIL_MAX_WASTE_SPACE (ZIL_MAX_LOG_DATA / 8)
/*
* Maximum amount of write data for WR_COPIED. Fall back to WR_NEED_COPY
* as more space efficient if we can't fit at least two log records into
* maximum sized log block.
*/
#define ZIL_MAX_COPIED_DATA ((SPA_OLD_MAXBLOCKSIZE - \
sizeof (zil_chain_t)) / 2 - sizeof (lr_write_t))
#ifdef __cplusplus
}
#endif