X-Git-Url: https://git.camperquake.de/gitweb.cgi?a=blobdiff_plain;f=module%2Fzfs%2Fzio.c;h=ace72a0875be7db5dad1427c0bc6a3e2186e9d93;hb=82f46731fd5a9eef4f87530e94922664b58a6138;hp=149088d939b329154b8766288dd706b016e1dff8;hpb=49be0ccf1fdc2ce852271d4d2f8b7a9c2c4be6db;p=zfs.git

diff --git a/module/zfs/zio.c b/module/zfs/zio.c
index 149088d..ace72a0 100644
--- a/module/zfs/zio.c
+++ b/module/zfs/zio.c
@@ -20,7 +20,7 @@
  */
 /*
  * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
- * Copyright (c) 2011 by Delphix. All rights reserved.
+ * Copyright (c) 2012 by Delphix. All rights reserved.
  * Copyright (c) 2011 Nexenta Systems, Inc. All rights reserved.
  */
 
@@ -73,6 +73,7 @@ char *zio_type_name[ZIO_TYPES] = {
  */
 kmem_cache_t *zio_cache;
 kmem_cache_t *zio_link_cache;
+kmem_cache_t *zio_vdev_cache;
 kmem_cache_t *zio_buf_cache[SPA_MAXBLOCKSIZE >> SPA_MINBLOCKSHIFT];
 kmem_cache_t *zio_data_buf_cache[SPA_MAXBLOCKSIZE >> SPA_MINBLOCKSHIFT];
 int zio_bulk_flags = 0;
@@ -141,6 +142,8 @@ zio_init(void)
 	    zio_cons, zio_dest, NULL, NULL, NULL, KMC_KMEM);
 	zio_link_cache = kmem_cache_create("zio_link_cache",
 	    sizeof (zio_link_t), 0, NULL, NULL, NULL, NULL, NULL, KMC_KMEM);
+	zio_vdev_cache = kmem_cache_create("zio_vdev_cache", sizeof(vdev_io_t),
+	    PAGESIZE, NULL, NULL, NULL, NULL, NULL, KMC_VMEM);
 
 	/*
 	 * For small buffers, we want a cache for each multiple of
@@ -230,6 +233,7 @@ zio_fini(void)
 		zio_data_buf_cache[c] = NULL;
 	}
 
+	kmem_cache_destroy(zio_vdev_cache);
 	kmem_cache_destroy(zio_link_cache);
 	kmem_cache_destroy(zio_cache);
 
@@ -255,7 +259,7 @@ zio_buf_alloc(size_t size)
 
 	ASSERT(c < SPA_MAXBLOCKSIZE >> SPA_MINBLOCKSHIFT);
 
-	return (kmem_cache_alloc(zio_buf_cache[c], KM_PUSHPAGE));
+	return (kmem_cache_alloc(zio_buf_cache[c], KM_PUSHPAGE | KM_NODEBUG));
 }
 
 /*
@@ -271,7 +275,8 @@ zio_data_buf_alloc(size_t size)
 
 	ASSERT(c < SPA_MAXBLOCKSIZE >> SPA_MINBLOCKSHIFT);
 
-	return (kmem_cache_alloc(zio_data_buf_cache[c], KM_PUSHPAGE));
+	return (kmem_cache_alloc(zio_data_buf_cache[c],
+	    KM_PUSHPAGE | KM_NODEBUG));
 }
 
 void
@@ -295,6 +300,24 @@ zio_data_buf_free(void *buf, size_t size)
 }
 
 /*
+ * Dedicated I/O buffers to ensure that memory fragmentation never prevents
+ * or significantly delays the issuing of a zio.   These buffers are used
+ * to aggregate I/O and could be used for raidz stripes.
+ */
+void *
+zio_vdev_alloc(void)
+{
+	return (kmem_cache_alloc(zio_vdev_cache, KM_PUSHPAGE));
+}
+
+void
+zio_vdev_free(void *buf)
+{
+	kmem_cache_free(zio_vdev_cache, buf);
+
+}
+
+/*
  * ==========================================================================
  * Push and pop I/O transform buffers
  * ==========================================================================
@@ -2317,13 +2340,22 @@ zio_alloc_zil(spa_t *spa, uint64_t txg, blkptr_t *new_bp, blkptr_t *old_bp,
 
 	ASSERT(txg > spa_syncing_txg(spa));
 
-	if (use_slog)
+	/*
+	 * ZIL blocks are always contiguous (i.e. not gang blocks) so we
+	 * set the METASLAB_GANG_AVOID flag so that they don't "fast gang"
+	 * when allocating them.
+	 */
+	if (use_slog) {
 		error = metaslab_alloc(spa, spa_log_class(spa), size,
-		    new_bp, 1, txg, old_bp, METASLAB_HINTBP_AVOID);
+		    new_bp, 1, txg, old_bp,
+		    METASLAB_HINTBP_AVOID | METASLAB_GANG_AVOID);
+	}
 
-	if (error)
+	if (error) {
 		error = metaslab_alloc(spa, spa_normal_class(spa), size,
-		    new_bp, 1, txg, old_bp, METASLAB_HINTBP_AVOID);
+		    new_bp, 1, txg, old_bp,
+		    METASLAB_HINTBP_AVOID | METASLAB_GANG_AVOID);
+	}
 
 	if (error == 0) {
 		BP_SET_LSIZE(new_bp, size);
@@ -2400,19 +2432,25 @@ zio_vdev_io_start(zio_t *zio)
 
 	align = 1ULL << vd->vdev_top->vdev_ashift;
 
-	if (P2PHASE(zio->io_size, align) != 0) {
+	/*
+	 * On Linux, we don't care about read alignment. The backing block
+	 * device driver will take care of that for us.
+	 * The only exception is raidz, which needs a full block for parity.
+	 */
+	if (P2PHASE(zio->io_size, align) != 0 &&
+	    (zio->io_type != ZIO_TYPE_READ ||
+	     vd->vdev_ops == &vdev_raidz_ops)) {
 		uint64_t asize = P2ROUNDUP(zio->io_size, align);
 		char *abuf = zio_buf_alloc(asize);
-		ASSERT(vd == vd->vdev_top);
 		if (zio->io_type == ZIO_TYPE_WRITE) {
 			bcopy(zio->io_data, abuf, zio->io_size);
 			bzero(abuf + zio->io_size, asize - zio->io_size);
 		}
 		zio_push_transform(zio, abuf, asize, asize, zio_subblock);
+		ASSERT(P2PHASE(zio->io_size, align) == 0);
 	}
 
 	ASSERT(P2PHASE(zio->io_offset, align) == 0);
-	ASSERT(P2PHASE(zio->io_size, align) == 0);
 	VERIFY(zio->io_type != ZIO_TYPE_WRITE || spa_writeable(spa));
 
 	/*