[dm-devel] [PATCH] dm-writecache: improve performance on Optane-based persistent memory

[Mikulas Patocka]

Hi

This is the clflushopt patch for the next merge window.

Mikulas


From: Mikulas Patocka <mpatocka at redhat.com>

When testing the dm-writecache target on a real Optane-based persistent
memory, it turned out that explicit cache flushing using the clflushopt
instruction performs better than non-temporal stores for block sizes 1k,
2k and 4k.

This patch adds a new function memcpy_flushcache_optimized that tests if
clflushopt is present - and if it is, we use it instead of
memcpy_flushcache.

Signed-off-by: Mikulas Patocka <mpatocka at redhat.com>

---
 drivers/md/dm-writecache.c |   29 ++++++++++++++++++++++++++++-
 1 file changed, 28 insertions(+), 1 deletion(-)

Index: linux-2.6/drivers/md/dm-writecache.c
===================================================================
--- linux-2.6.orig/drivers/md/dm-writecache.c	2020-04-29 18:09:53.599999000 +0200
+++ linux-2.6/drivers/md/dm-writecache.c	2020-04-29 18:22:36.139999000 +0200
@@ -1137,6 +1137,33 @@ static int writecache_message(struct dm_
 	return r;
 }
 
+static void memcpy_flushcache_optimized(void *dest, void *source, size_t size)
+{
+	/*
+	 * clufhsopt performs better with block size 1024, 2048, 4096
+	 * non-temporal stores perform better with block size 512
+	 *
+	 * block size   512             1024            2048            4096
+	 * movnti       496 MB/s        642 MB/s        725 MB/s        744 MB/s
+	 * clflushopt   373 MB/s        688 MB/s        1.1 GB/s        1.2 GB/s
+	 */
+#ifdef CONFIG_X86
+	if (static_cpu_has(X86_FEATURE_CLFLUSHOPT) &&
+	    likely(boot_cpu_data.x86_clflush_size == 64) &&
+	    likely(size >= 768)) {
+		do {
+			memcpy((void *)dest, (void *)source, 64);
+			clflushopt((void *)dest);
+			dest += 64;
+			source += 64;
+			size -= 64;
+		} while (size >= 64);
+		return;
+	}
+#endif
+	memcpy_flushcache(dest, source, size);
+}
+
 static void bio_copy_block(struct dm_writecache *wc, struct bio *bio, void *data)
 {
 	void *buf;
@@ -1162,7 +1189,7 @@ static void bio_copy_block(struct dm_wri
 			}
 		} else {
 			flush_dcache_page(bio_page(bio));
-			memcpy_flushcache(data, buf, size);
+			memcpy_flushcache_optimized(data, buf, size);
 		}
 
 		bvec_kunmap_irq(buf, &flags);