The sysctl vm.compress-batching parameter is 0 by default. If the platform
has Intel IAA, the user can run experiments with IAA compress batching of
large folios in zswap_store() as follows:
sysctl vm.compress-batching=1
echo deflate-iaa > /sys/module/zswap/parameters/compressor
This is expected to significantly improve zswap_store() latency of swapping
out large folios due to parallel compression of 8 pages in the large folio
at a time, in hardware.
Setting vm.compress-batching to "1" takes effect only if the zswap
compression algorithm's crypto_acomp registers implementations for the
batch_compress() and batch_decompress() API. In other words, compress
batching works only with the iaa_crypto driver, that does register these
new batching API. It is a no-op for compressors that do not register the
batching API.
The sysctl vm.compress-batching acts as a switch because it takes effect
upon future zswap_store() calls on any given core. If the switch is "1",
large folios will use parallel batched compression of the folio's pages.
If the switch is "0", zswap_store() will use sequential compression for
storing every page in a large folio.
Signed-off-by: Kanchana P Sridhar <kanchana.p.sridhar@xxxxxxxxx>
---
include/linux/mm.h | 2 ++
kernel/sysctl.c | 9 +++++++++
mm/swap.c | 6 ++++++
3 files changed, 17 insertions(+)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index fecd47239fa9..f61915aa2f37 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -82,8 +82,10 @@ extern const int page_cluster_max;
#ifdef CONFIG_SYSCTL
extern int sysctl_legacy_va_layout;
+extern unsigned int compress_batching;
#else
#define sysctl_legacy_va_layout 0
+#define compress_batching 0
#endif
#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 79e6cb1d5c48..e298857595b4 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2064,6 +2064,15 @@ static struct ctl_table vm_table[] = {
.extra1 = SYSCTL_ZERO,
.extra2 = (void *)&page_cluster_max,
},
+ {
+ .procname = "compress-batching",
+ .data = &compress_batching,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_douintvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
+ },
{
.procname = "dirtytime_expire_seconds",
.data = &dirtytime_expire_interval,
diff --git a/mm/swap.c b/mm/swap.c
index 638a3f001676..bc4c9079769e 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -47,6 +47,9 @@
int page_cluster;
const int page_cluster_max = 31;
+/* Enable/disable compress batching during swapout. */
+unsigned int compress_batching;
+
struct cpu_fbatches {
/*
* The following folio batches are grouped together because they are protected
@@ -1074,4 +1077,7 @@ void __init swap_setup(void)
* Right now other parts of the system means that we
* _really_ don't want to cluster much more
*/
+
+ /* Disable compress batching during swapout by default. */
+ compress_batching = 0;
}
--
2.27.0
