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

Include scatter_chunk_waste in arc_size

Browse Source 
The ARC caches data in scatter ABD's, which are collections of pages,
which are typically 4K.  Therefore, the space used to cache each block
is rounded up to a multiple of 4K.  The ABD subsystem tracks this wasted
memory in the `scatter_chunk_waste` kstat.  However, the ARC's `size` is
not aware of the memory used by this round-up, it only accounts for the
size that it requested from the ABD subsystem.

Therefore, the ARC is effectively using more memory than it is aware of,
due to the `scatter_chunk_waste`.  This impacts observability, e.g.
`arcstat` will show that the ARC is using less memory than it
effectively is.  It also impacts how the ARC responds to memory
pressure.  As the amount of `scatter_chunk_waste` changes, it appears to
the ARC as memory pressure, so it needs to resize `arc_c`.

If the sector size (`1<<ashift`) is the same as the page size (or
larger), there won't be any waste.  If the (compressed) block size is
relatively large compared to the page size, the amount of
`scatter_chunk_waste` will be small, so the problematic effects are
minimal.

However, if using 512B sectors (`ashift=9`), and the (compressed) block
size is small (e.g. `compression=on` with the default `volblocksize=8k`
or a decreased `recordsize`), the amount of `scatter_chunk_waste` can be
very large.  On a production system, with `arc_size` at a constant 50%
of memory, `scatter_chunk_waste` has been been observed to be 10-30% of
memory.

This commit adds `scatter_chunk_waste` to `arc_size`, and adds a new
`waste` field to `arcstat`.  As a result, the ARC's memory usage is more
observable, and `arc_c` does not need to be adjusted as frequently.

Reviewed-by: Pavel Zakharov <pavel.zakharov@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: George Wilson <gwilson@delphix.com>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Closes #10701
This commit is contained in:
Matthew Ahrens
2020-08-17 20:04:04 -07:00
committed by GitHub
parent 994de7e4b7
commit 85ec5cbae2
6 changed files with 35 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
module/zfs/arc.c
+20 -2
View File
@@ -583,6 +583,7 @@ arc_stats_t arc_stats = {
{ "arc_sys_free", KSTAT_DATA_UINT64 },
{ "arc_raw_size", KSTAT_DATA_UINT64 },
{ "cached_only_in_progress", KSTAT_DATA_UINT64 },
{ "abd_chunk_waste_size", KSTAT_DATA_UINT64 },
};
#define ARCSTAT_MAX(stat, val) { \
@@ -685,6 +686,7 @@ aggsum_t astat_dnode_size;
aggsum_t astat_bonus_size;
aggsum_t astat_hdr_size;
aggsum_t astat_l2_hdr_size;
aggsum_t astat_abd_chunk_waste_size;
hrtime_t arc_growtime;
list_t arc_prune_list;
@@ -2611,9 +2613,18 @@ arc_space_consume(uint64_t space, arc_space_type_t type)
case ARC_SPACE_L2HDRS:
aggsum_add(&astat_l2_hdr_size, space);
break;
case ARC_SPACE_ABD_CHUNK_WASTE:
/*
* Note: this includes space wasted by all scatter ABD's, not
* just those allocated by the ARC. But the vast majority of
* scatter ABD's come from the ARC, because other users are
* very short-lived.
*/
aggsum_add(&astat_abd_chunk_waste_size, space);
break;
}
if (type != ARC_SPACE_DATA)
if (type != ARC_SPACE_DATA && type != ARC_SPACE_ABD_CHUNK_WASTE)
aggsum_add(&arc_meta_used, space);
aggsum_add(&arc_size, space);
@@ -2648,9 +2659,12 @@ arc_space_return(uint64_t space, arc_space_type_t type)
case ARC_SPACE_L2HDRS:
aggsum_add(&astat_l2_hdr_size, -space);
break;
case ARC_SPACE_ABD_CHUNK_WASTE:
aggsum_add(&astat_abd_chunk_waste_size, -space);
break;
}
if (type != ARC_SPACE_DATA) {
if (type != ARC_SPACE_DATA && type != ARC_SPACE_ABD_CHUNK_WASTE) {
ASSERT(aggsum_compare(&arc_meta_used, space) >= 0);
/*
* We use the upper bound here rather than the precise value
@@ -7090,6 +7104,8 @@ arc_kstat_update(kstat_t *ksp, int rw)
ARCSTAT(arcstat_dbuf_size) = aggsum_value(&astat_dbuf_size);
ARCSTAT(arcstat_dnode_size) = aggsum_value(&astat_dnode_size);
ARCSTAT(arcstat_bonus_size) = aggsum_value(&astat_bonus_size);
ARCSTAT(arcstat_abd_chunk_waste_size) =
aggsum_value(&astat_abd_chunk_waste_size);
as->arcstat_memory_all_bytes.value.ui64 =
arc_all_memory();
@@ -7329,6 +7345,7 @@ arc_state_init(void)
aggsum_init(&astat_bonus_size, 0);
aggsum_init(&astat_dnode_size, 0);
aggsum_init(&astat_dbuf_size, 0);
aggsum_init(&astat_abd_chunk_waste_size, 0);
arc_anon->arcs_state = ARC_STATE_ANON;
arc_mru->arcs_state = ARC_STATE_MRU;
@@ -7381,6 +7398,7 @@ arc_state_fini(void)
aggsum_fini(&astat_bonus_size);
aggsum_fini(&astat_dnode_size);
aggsum_fini(&astat_dbuf_size);
aggsum_fini(&astat_abd_chunk_waste_size);
}
uint64_t