c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2026-05-24 03:08:51 +03:00
Code Issues Packages Projects Releases Wiki Activity

Improve zfs send performance by bypassing the ARC

Browse Source 
When doing a zfs send on a dataset with small recordsize (e.g. 8K),
performance is dominated by the per-block overheads.  This is especially
true with `zfs send --compressed`, which further reduces the amount of
data sent, for the same number of blocks.  Several threads are involved,
but the limiting factor is the `send_prefetch` thread, which is 100% on
CPU.

The main job of the `send_prefetch` thread is to issue zio's for the
data that will be needed by the main thread.  It does this by calling
`arc_read(ARC_FLAG_PREFETCH)`.  This has an immediate cost of creating
an arc_hdr, which takes around 14% of one CPU.  It also induces later
costs by other threads:

 * Since the data was only prefetched, dmu_send()->dmu_dump_write() will
   need to call arc_read() again to get the data.  This will have to
   look up the arc_hdr in the hash table and copy the data from the
   scatter ABD in the arc_hdr to a linear ABD in arc_buf.  This takes
   27% of one CPU.

 * dmu_dump_write() needs to arc_buf_destroy()  This takes 11% of one
   CPU.

 * arc_adjust() will need to evict this arc_hdr, taking about 50% of one
   CPU.

All of these costs can be avoided by bypassing the ARC if the data is
not already cached.  This commit changes `zfs send` to check for the
data in the ARC, and if it is not found then we directly call
`zio_read()`, reading the data into a linear ABD which is used by
dmu_dump_write() directly.

The performance improvement is best expressed in terms of how many
blocks can be processed by `zfs send` in one second.  This change
increases the metric by 50%, from ~100,000 to ~150,000.  When the amount
of data per block is small (e.g. 2KB), there is a corresponding
reduction in the elapsed time of `zfs send >/dev/null` (from 86 minutes
to 58 minutes in this test case).

In addition to improving the performance of `zfs send`, this change
makes `zfs send` not pollute the ARC cache.  In most cases the data will
not be reused, so this allows us to keep caching useful data in the MRU
(hit-once) part of the ARC.

Reviewed-by: Paul Dagnelie <pcd@delphix.com>
Reviewed-by: Serapheim Dimitropoulos <serapheim@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Closes #10067
This commit is contained in:
Matthew Ahrens
2020-03-10 10:51:04 -07:00
committed by GitHub
parent 9be70c3784
commit 1dc32a67e9
4 changed files with 235 additions and 151 deletions
Download Patch File Download Diff File Expand all files Collapse all files
module/zfs/arc.c
+18 -1
View File
@@ -548,7 +548,8 @@ arc_stats_t arc_stats = {
{ "demand_hit_prescient_prefetch", KSTAT_DATA_UINT64 },
{ "arc_need_free", KSTAT_DATA_UINT64 },
{ "arc_sys_free", KSTAT_DATA_UINT64 },
{ "arc_raw_size", KSTAT_DATA_UINT64 }
{ "arc_raw_size", KSTAT_DATA_UINT64 },
{ "cached_only_in_progress", KSTAT_DATA_UINT64 },
};
#define ARCSTAT_MAX(stat, val) { \
@@ -5563,6 +5564,13 @@ top:
if (HDR_IO_IN_PROGRESS(hdr)) {
zio_t *head_zio = hdr->b_l1hdr.b_acb->acb_zio_head;
if (*arc_flags & ARC_FLAG_CACHED_ONLY) {
mutex_exit(hash_lock);
ARCSTAT_BUMP(arcstat_cached_only_in_progress);
rc = SET_ERROR(ENOENT);
goto out;
}
ASSERT3P(head_zio, !=, NULL);
if ((hdr->b_flags & ARC_FLAG_PRIO_ASYNC_READ) &&
priority == ZIO_PRIORITY_SYNC_READ) {
@@ -5698,12 +5706,21 @@ top:
uint64_t size;
abd_t *hdr_abd;
if (*arc_flags & ARC_FLAG_CACHED_ONLY) {
rc = SET_ERROR(ENOENT);
if (hash_lock != NULL)
mutex_exit(hash_lock);
goto out;
}
/*
* Gracefully handle a damaged logical block size as a
* checksum error.
*/
if (lsize > spa_maxblocksize(spa)) {
rc = SET_ERROR(ECKSUM);
if (hash_lock != NULL)
mutex_exit(hash_lock);
goto out;
}