Cut release 1.3.6.

cut-and-paste from it, that's fine with us.

NEWS

@@ -1,3 +1,46 @@
+WiredTiger release 1.3.6, 2012-11-06
+------------------------------------
+
+This is a bugfix and performance tuning release. The changes are as follows:
+
+* Rename the WiredTiger installed modules to libwiredtiger_XXX.  Don't install
+  the nop and reverse collator modules.
+
+* Replace test/format's bzip configuration string with compression, which can
+  take one of four arguments (none, bzip, ext, snappy), change format to run
+  snappy compression if the library is available.
+
+* Rename the builtin block compressor names from "bzip2_compress" to "bzip2",
+  and from "snappy_compress" to "snappy".
+
+* Support multiple LSM merge threads with the "lsm_merge_threads" config key.
+  Use IDs rather than array index to mark the start chunk in a merge, in case
+  we race with another thread.
+
+* Cache the hash values used for Bloom filter lookups, rather than hashing for
+  each Bloom filter in an LSM tree.
+
+* Only switch trees in an LSM cursor if the primary chunk is on disk.
+
+* Add a per-btree cache priority, currently only used to make it more likely
+  for Bloom filter pages to stay in cache.
+
+* Only evict pages with read generations in the bottom quarter of the range we
+  see.  Fix a 32-bit wrapping bug in assigning read generations.
+
+* For update-only LSM cursors, only open a cursor in the primary chunk.
+
+* LSM: Report errors from the checkpoint thread.
+
+* LSM: only save a Bloom URI in the metadata after it is successfully created.
+
+* LSM: Create missing Bloom filters when reading from an LSM tree if
+  "lsm_bloom_newest"is set.
+
+* LSM: Include all of the chosen chunks in a merge.  Only pin the current chunk
+  in an LSM cursor if it is writeable.
+
+
 WiredTiger release 1.3.5, 2012-10-26
 ------------------------------------
 

README

@@ -1,6 +1,6 @@
-WiredTiger 1.3.5: (October 26, 2012)
+WiredTiger 1.3.6: (November  6, 2012)
 
-This is version 1.3.5 of WiredTiger.
+This is version 1.3.6 of WiredTiger.
 
 WiredTiger documentation can be found at:
 

RELEASE

@@ -1,6 +1,6 @@
 WIREDTIGER_VERSION_MAJOR=1
 WIREDTIGER_VERSION_MINOR=3
-WIREDTIGER_VERSION_PATCH=5
+WIREDTIGER_VERSION_PATCH=6
 WIREDTIGER_VERSION="$WIREDTIGER_VERSION_MAJOR.$WIREDTIGER_VERSION_MINOR.$WIREDTIGER_VERSION_PATCH"
 
 WIREDTIGER_RELEASE_DATE=`date "+%B %e, %Y"`

build_posix/Make.subdirs

@@ -8,9 +8,9 @@
 bench/tcbench
 examples/c
 ext/collators/reverse
-ext/compressors/bzip2_compress BZIP2
-ext/compressors/nop_compress
-ext/compressors/snappy_compress SNAPPY
+ext/compressors/bzip2 BZIP2
+ext/compressors/nop
+ext/compressors/snappy SNAPPY
 lang/python PYTHON
 test/bloom
 test/fops

build_posix/aclocal/version-set.m4

@@ -2,8 +2,8 @@ dnl build by dist/s_version
 
 VERSION_MAJOR=1
 VERSION_MINOR=3
-VERSION_PATCH=5
-VERSION_STRING='"WiredTiger 1.3.5: (October 26, 2012)"'
+VERSION_PATCH=6
+VERSION_STRING='"WiredTiger 1.3.6: (November  6, 2012)"'
 
 AC_SUBST(VERSION_MAJOR)
 AC_SUBST(VERSION_MINOR)

build_posix/aclocal/version.m4

@@ -1,2 +1,2 @@
 dnl WiredTiger product version for AC_INIT.  Maintained by dist/s_version
-1.3.5
+1.3.6

dist/api_data.py

@@ -113,6 +113,9 @@ lsm_config = [
 	Config('lsm_merge_max', '15', r'''
 		the maximum number of chunks to include in a merge operation''',
 		min='2', max='100'),
+	Config('lsm_merge_threads', '1', r'''
+		the number of thread to perform merge operations''',
+		min='1', max='10'), # !!! max must match WT_LSM_MAX_WORKERS
 ]
 
 # Per-file configuration
@@ -462,13 +465,15 @@ methods = {
 		list, such as <code>"direct_io=[data]"</code>''',
 		type='list', choices=['data', 'log']),
 	Config('extensions', '', r'''
-		list of extensions to load.  Optional values are passed as the
-		\c config parameter to WT_CONNECTION::load_extension.  Complex
-		paths may need quoting, for example,
-		<code>extensions=("/path/to/ext.so"="entry=my_entry")</code>''',
+		list of shared library extensions to load (using dlopen).
+		Optional values are passed as the \c config parameter to
+		WT_CONNECTION::load_extension.  Complex paths may require
+		quoting, for example,
+		<code>extensions=("/path/ext.so"="entry=my_entry")</code>''',
 		type='list'),
 	Config('hazard_max', '1000', r'''
-		maximum number of simultaneous hazard references per session handle''',
+		maximum number of simultaneous hazard references per session
+		handle''',
 		min='15'),
 	Config('logging', 'false', r'''
 		enable logging''',

dist/s_funcs.list

@@ -3,6 +3,7 @@ WT_CURDUMP_PASS
 __bit_ffs
 __bit_nclr
 __wt_bloom_drop
+__wt_bloom_get
 __wt_bm_addr_stderr
 __wt_btree_lex_compare
 __wt_config_getone

dist/s_string.ok

@@ -9,6 +9,7 @@ ADDR
 AJZ
 API
 APIs
+ARGS
 Alakuijala
 Alloc
 Athlon
@@ -205,6 +206,7 @@ WinNT
 WiredTiger
 WiredTiger's
 WiredTigerCheckpoint
+WiredTigerHome
 WithSeeds
 Wuninitialized
 XP

examples/c/ex_all.c

@@ -395,6 +395,25 @@ session_ops(WT_SESSION *session)
 	    "table:mytable", "key_format=S,value_format=S");
 	/*! [Create a table] */
 
+	/*
+	 * This example code gets run, and the compression libraries might not
+	 * be loaded, causing the create to fail.  The documentation requires
+	 * the code snippets, use #ifdef's to avoid running it.
+	 */
+#ifdef MIGHT_NOT_RUN
+	/*! [Create a bzip2 compressed table] */
+	ret = session->create(session,
+	    "table:mytable",
+	    "block_compressor=bzip2,key_format=S,value_format=S");
+	/*! [Create a bzip2 compressed table] */
+
+	/*! [Create a snappy compressed table] */
+	ret = session->create(session,
+	    "table:mytable",
+	    "block_compressor=snappy,key_format=S,value_format=S");
+	/*! [Create a snappy compressed table] */
+#endif
+
 	/*! [Create a cache-resident object] */
 	ret = session->create(session,
 	    "table:mytable", "key_format=r,value_format=S,cache_resident=true");
@@ -891,16 +910,44 @@ main(void)
 {
 	int ret;
 
+	system("rm -rf WiredTigerHome && mkdir WiredTigerHome");
+
 	{
 	/*! [Open a connection] */
 	WT_CONNECTION *conn;
-	const char *home = "WT_TEST";
-	ret = wiredtiger_open(home, NULL, "create,transactional", &conn);
-	/*! [Open a connection] */
 
-	(void)conn->close(conn, NULL);
+	ret = wiredtiger_open(
+	    "WiredTigerHome", NULL, "create,transactional", &conn);
+	/*! [Open a connection] */
 	}
 
+	/*
+	 * This example code gets run, and the compression libraries might not
+	 * be installed, causing the open to fail.  The documentation requires
+	 * the code snippets, use #ifdef's to avoid running it.
+	 */
+#ifdef MIGHT_NOT_RUN
+	{
+	/*! [Configure bzip2 extension] */
+	WT_CONNECTION *conn;
+
+	ret = wiredtiger_open("WiredTigerHome", NULL,
+	    "create,"
+	    "extensions=[\"/usr/local/lib/wiredtiger_bzip2.so\"]", &conn);
+	/*! [Configure bzip2 extension] */
+	}
+
+	{
+	/*! [Configure snappy extension] */
+	WT_CONNECTION *conn;
+
+	ret = wiredtiger_open("WiredTigerHome", NULL,
+	    "create,"
+	    "extensions=[\"/usr/local/lib/wiredtiger_snappy.so\"]", &conn);
+	/*! [Configure snappy extension] */
+	}
+#endif
+
 	/*! [Get the WiredTiger library version #1] */
 	printf("WiredTiger version %s\n", wiredtiger_version(NULL, NULL, NULL));
 	/*! [Get the WiredTiger library version #1] */

ext/collators/reverse/Makefile.am

@@ -1,4 +1,10 @@
 AM_CPPFLAGS = -I$(top_builddir) -I$(top_srcdir)/src/include
 
-lib_LTLIBRARIES = reverse_collator.la
-reverse_collator_la_LDFLAGS = -avoid-version -module
+noinst_LTLIBRARIES = libwiredtiger_reverse_collator.la
+libwiredtiger_reverse_collator_la_SOURCES = reverse_collator.c
+
+# libtool hack: noinst_LTLIBRARIES turns off building shared libraries as well
+# as installation, it will only build static libraries.  As far as I can tell,
+# the "approved" libtool way to turn them back on is by adding -rpath.
+libwiredtiger_reverse_collator_la_LDFLAGS = \
+	-avoid-version -module -rpath /nowhere

ext/compressors/bzip2/Makefile.am

@@ -0,0 +1,6 @@
+AM_CPPFLAGS = -I$(top_builddir) -I$(top_srcdir)/src/include
+
+lib_LTLIBRARIES = libwiredtiger_bzip2.la
+libwiredtiger_bzip2_la_SOURCES = bzip2_compress.c
+libwiredtiger_bzip2_la_LDFLAGS = -avoid-version -module
+libwiredtiger_bzip2_la_LIBADD = -lbz2

ext/compressors/bzip2/bzip2_compress.c

@@ -72,8 +72,7 @@ wiredtiger_extension_init(
 	wt_api = api;
 	conn = session->connection;
 
-	return (conn->add_compressor(
-	    conn, "bzip2_compress", &bzip2_compressor, NULL));
+	return (conn->add_compressor(conn, "bzip2", &bzip2_compressor, NULL));
 }
 
 /* Bzip2 WT_COMPRESSOR implementation for WT_CONNECTION::add_compressor. */

ext/compressors/bzip2_compress/Makefile.am

@@ -1,5 +0,0 @@
-AM_CPPFLAGS = -I$(top_builddir) -I$(top_srcdir)/src/include
-
-lib_LTLIBRARIES = bzip2_compress.la
-bzip2_compress_la_LDFLAGS = -avoid-version -module
-bzip2_compress_la_LIBADD = -lbz2

ext/compressors/nop/Makefile.am

@@ -0,0 +1,9 @@
+AM_CPPFLAGS = -I$(top_builddir) -I$(top_srcdir)/src/include
+
+noinst_LTLIBRARIES = libwiredtiger_nop.la
+libwiredtiger_nop_la_SOURCES = nop_compress.c
+
+# libtool hack: noinst_LTLIBRARIES turns off building shared libraries as well
+# as installation, it will only build static libraries.  As far as I can tell,
+# the "approved" libtool way to turn them back on is by adding -rpath.
+libwiredtiger_nop_la_LDFLAGS = -avoid-version -module -rpath /nowhere

ext/compressors/nop/nop_compress.c

@@ -55,8 +55,7 @@ wiredtiger_extension_init(
 	wt_api = api;
 	conn = session->connection;
 
-	return (
-	    conn->add_compressor(conn, "nop_compress", &nop_compressor, NULL));
+	return (conn->add_compressor(conn, "nop", &nop_compressor, NULL));
 }
 
 /* Implementation of WT_COMPRESSOR for WT_CONNECTION::add_compressor. */

ext/compressors/nop_compress/Makefile.am

@@ -1,4 +0,0 @@
-AM_CPPFLAGS = -I$(top_builddir) -I$(top_srcdir)/src/include
-
-lib_LTLIBRARIES = nop_compress.la
-nop_compress_la_LDFLAGS = -avoid-version -module

ext/compressors/snappy/Makefile.am

@@ -0,0 +1,6 @@
+AM_CPPFLAGS = -I$(top_builddir) -I$(top_srcdir)/src/include
+
+lib_LTLIBRARIES = libwiredtiger_snappy.la
+libwiredtiger_snappy_la_SOURCES = snappy_compress.c
+libwiredtiger_snappy_la_LDFLAGS = -avoid-version -module
+libwiredtiger_snappy_la_LIBADD = -lsnappy

ext/compressors/snappy/snappy_compress.c

@@ -59,8 +59,8 @@ wiredtiger_extension_init(
 	wt_api = api;
 	conn = session->connection;
 
-	return (conn->add_compressor(
-	    conn, "snappy_compress", &wt_snappy_compressor, NULL));
+	return (
+	    conn->add_compressor(conn, "snappy", &wt_snappy_compressor, NULL));
 }
 
 /* Snappy WT_COMPRESSOR for WT_CONNECTION::add_compressor. */

ext/compressors/snappy_compress/Makefile.am

@@ -1,5 +0,0 @@
-AM_CPPFLAGS = -I$(top_builddir) -I$(top_srcdir)/src/include
-
-lib_LTLIBRARIES = snappy_compress.la
-snappy_compress_la_LDFLAGS = -avoid-version -module
-snappy_compress_la_LIBADD = -lsnappy

src/bloom/bloom.c

@@ -6,7 +6,6 @@
  */
 
 #include "wt_internal.h"
-#include "bloom.h"
 
 #define	WT_BLOOM_TABLE_CONFIG "key_format=r,value_format=1t,exclusive=true"
 
@@ -125,6 +124,10 @@ __wt_bloom_open(WT_SESSION_IMPL *session,
 	/* Find the largest key, to get the size of the filter. */
 	cfg[1] = bloom->config;
 	WT_RET(__wt_open_cursor(session, bloom->uri, owner, cfg, &c));
+
+	/* XXX Layering violation: bump the cache priority for Bloom filters. */
+	session->btree->evict_priority = (1 << 19);
+
 	WT_RET(c->prev(c));
 	WT_RET(c->get_key(c, &size));
 
@@ -199,12 +202,27 @@ err:	WT_TRET(c->close(c));
 }
 
 /*
- * __wt_bloom_get --
- *	Tests whether the given key is in the Bloom filter.
- *	Returns zero if found, WT_NOTFOUND if not.
+ * __wt_bloom_hash --
+ *	Calculate the hash values for a given key.
  */
 int
-__wt_bloom_get(WT_BLOOM *bloom, WT_ITEM *key)
+__wt_bloom_hash(WT_BLOOM *bloom, WT_ITEM *key, WT_BLOOM_HASH *bhash)
+{
+	WT_UNUSED(bloom);
+
+	bhash->h1 = __wt_hash_fnv64(key->data, key->size);
+	bhash->h2 = __wt_hash_city64(key->data, key->size);
+
+	return (0);
+}
+
+/*
+ * __wt_bloom_hash_get --
+ *	Tests whether the key (as given by its hash signature) is in the Bloom
+ *	filter.  Returns zero if found, WT_NOTFOUND if not.
+ */
+int
+__wt_bloom_hash_get(WT_BLOOM *bloom, WT_BLOOM_HASH *bhash)
 {
 	WT_CURSOR *c;
 	WT_DECL_RET;
@@ -226,24 +244,15 @@ __wt_bloom_get(WT_BLOOM *bloom, WT_ITEM *key)
 	} else
 		c = bloom->c;
 
-	/*
-	 * This comparison code is complex to avoid calculating the second
-	 * hash if possible.
-	 */
-	h1 = __wt_hash_fnv64(key->data, key->size);
+	h1 = bhash->h1;
+	h2 = bhash->h2;
 
-	/*
-	 * Add 1 to the hash because Wired Tiger tables are 1 based, and the
-	 * original bitstring array was 0 based.
-	 */
-	c->set_key(c, (h1 % bloom->m) + 1);
-	WT_RET(c->search(c));
-	WT_RET(c->get_value(c, &bit));
-	if (bit == 0)
-		return (WT_NOTFOUND);
-	h2 = __wt_hash_city64(key->data, key->size);
 	result = 0;
-	for (i = 0, h1 += h2; i < bloom->k - 1; i++, h1 += h2) {
+	for (i = 0; i < bloom->k; i++, h1 += h2) {
+		/*
+		 * Add 1 to the hash because Wired Tiger tables are 1 based and
+		 * the original bitstring array was 0 based.
+		 */
 		c->set_key(c, (h1 % bloom->m) + 1);
 		WT_ERR(c->search(c));
 		WT_ERR(c->get_value(c, &bit));
@@ -263,6 +272,20 @@ err:	/* Don't return WT_NOTFOUND from a failed search. */
 	return (ret);
 }
 
+/*
+ * __wt_bloom_get --
+ *	Tests whether the given key is in the Bloom filter.
+ *	Returns zero if found, WT_NOTFOUND if not.
+ */
+int
+__wt_bloom_get(WT_BLOOM *bloom, WT_ITEM *key)
+{
+	WT_BLOOM_HASH bhash;
+
+	WT_RET(__wt_bloom_hash(bloom, key, &bhash));
+	return (__wt_bloom_hash_get(bloom, &bhash));
+}
+
 /*
  * __wt_bloom_close --
  *	Close the Bloom filter, release any resources.

src/btree/bt_evict.c

@@ -12,7 +12,7 @@ static int  __evict_file_request(WT_SESSION_IMPL *, int);
 static int  __evict_file_request_walk(WT_SESSION_IMPL *);
 static int  __evict_lru(WT_SESSION_IMPL *);
 static int  __evict_lru_cmp(const void *, const void *);
-static int  __evict_walk(WT_SESSION_IMPL *);
+static int  __evict_walk(WT_SESSION_IMPL *, uint32_t *);
 static int  __evict_walk_file(WT_SESSION_IMPL *, u_int *);
 static int  __evict_worker(WT_SESSION_IMPL *);
 
@@ -20,14 +20,48 @@ static int  __evict_worker(WT_SESSION_IMPL *);
  * Tuning constants: I hesitate to call this tuning, but we want to review some
  * number of pages from each file's in-memory tree for each page we evict.
  */
-#define	WT_EVICT_GROUP		30	/* Consider N pages as LRU candidates */
-#define	WT_EVICT_INT_SKEW	(1<<20)	/* Prefer leaf pages over internal
+#define	WT_EVICT_INT_SKEW  (1<<20)	/* Prefer leaf pages over internal
 					   pages by this many increments of the
 					   read generation. */
 #define	WT_EVICT_WALK_PER_FILE	 5	/* Pages to visit per file */
-#define	WT_EVICT_WALK_BASE	50	/* Pages tracked across file visits */
+#define	WT_EVICT_WALK_BASE     100	/* Pages tracked across file visits */
 #define	WT_EVICT_WALK_INCR     100	/* Pages added each walk */
 
+/*
+ * __evict_read_gen --
+ *	Get the adjusted read generation for an eviction entry.
+ */
+static inline uint64_t
+__evict_read_gen(const WT_EVICT_ENTRY *entry)
+{
+	uint64_t read_gen;
+
+	if (entry->page == NULL)
+		return (UINT64_MAX);
+
+	read_gen = entry->page->read_gen + entry->btree->evict_priority;
+	if (entry->page->type == WT_PAGE_ROW_INT ||
+	    entry->page->type == WT_PAGE_COL_INT)
+		read_gen += WT_EVICT_INT_SKEW;
+
+	return (read_gen);
+}
+
+/*
+ * __evict_lru_cmp --
+ *	Qsort function: sort the eviction array.
+ */
+static int
+__evict_lru_cmp(const void *a, const void *b)
+{
+	uint64_t a_lru, b_lru;
+
+	a_lru = __evict_read_gen(a);
+	b_lru = __evict_read_gen(b);
+
+	return ((a_lru < b_lru) ? -1 : (a_lru == b_lru) ? 0 : 1);
+}
+
 /*
  * __evict_list_clr --
  *	Clear an entry in the LRU eviction list.
@@ -488,16 +522,43 @@ static int
 __evict_lru(WT_SESSION_IMPL *session)
 {
 	WT_CACHE *cache;
+	uint64_t cutoff;
+	uint32_t i, candidates;
 
 	cache = S2C(session)->cache;
 
 	/* Get some more pages to consider for eviction. */
-	WT_RET(__evict_walk(session));
+	WT_RET(__evict_walk(session, &candidates));
 
 	/* Sort the list into LRU order and restart. */
 	__wt_spin_lock(session, &cache->evict_lock);
+	while (candidates > 0 && cache->evict[candidates - 1].page == NULL)
+		--candidates;
+	if (candidates == 0) {
+		__wt_spin_unlock(session, &cache->evict_lock);
+		return (0);
+	}
+
 	qsort(cache->evict,
-	    cache->evict_entries, sizeof(WT_EVICT_ENTRY), __evict_lru_cmp);
+	    candidates, sizeof(WT_EVICT_ENTRY), __evict_lru_cmp);
+
+	/* Find the bottom 25% */
+	while (candidates > 0 && cache->evict[candidates - 1].page == NULL)
+		--candidates;
+
+	cutoff = (3 * __evict_read_gen(&cache->evict[0]) +
+	    __evict_read_gen(&cache->evict[candidates - 1])) / 4;
+
+	/*
+	 * Don't take more than half, regardless.  That said, if there is only
+	 * one candidate page, which is normal when populating an empty file,
+	 * don't exclude it.
+	 */
+	for (i = 0; i < candidates / 2; i++)
+		if (cache->evict[i].page->read_gen > cutoff)
+			break;
+	cache->evict_candidates = i + 1;
+
 	__evict_list_clr_all(session, WT_EVICT_WALK_BASE);
 
 	cache->evict_current = cache->evict;
@@ -515,7 +576,7 @@ __evict_lru(WT_SESSION_IMPL *session)
  *	Fill in the array by walking the next set of pages.
  */
 static int
-__evict_walk(WT_SESSION_IMPL *session)
+__evict_walk(WT_SESSION_IMPL *session, u_int *entriesp)
 {
 	WT_BTREE *btree;
 	WT_CACHE *cache;
@@ -586,6 +647,7 @@ retry:	file_count = 0;
 	    retries++ < WT_EVICT_WALK_INCR / WT_EVICT_WALK_PER_FILE)
 		goto retry;
 
+	*entriesp = i;
 	if (0) {
 err:		__wt_spin_unlock(session, &cache->evict_lock);
 	}
@@ -683,7 +745,10 @@ __evict_get_page(
 	*btreep = NULL;
 	*pagep = NULL;
 
-	candidates = (is_app ? WT_EVICT_GROUP : WT_EVICT_GROUP / 2);
+	candidates = cache->evict_candidates;
+	/* The eviction server only considers half of the entries. */
+	if (!is_app)
+		candidates /= 2;
 
 	/*
 	 * Avoid the LRU lock if no pages are available.  If there are pages
@@ -787,44 +852,3 @@ __wt_evict_lru_page(WT_SESSION_IMPL *session, int is_app)
 
 	return (ret);
 }
-
-/*
- * __evict_lru_cmp --
- *	Qsort function: sort the eviction array.
- */
-static int
-__evict_lru_cmp(const void *a, const void *b)
-{
-	WT_PAGE *a_page, *b_page;
-	uint64_t a_lru, b_lru;
-
-	/*
-	 * There may be NULL references in the array; sort them as greater than
-	 * anything else so they migrate to the end of the array.
-	 */
-	a_page = ((WT_EVICT_ENTRY *)a)->page;
-	b_page = ((WT_EVICT_ENTRY *)b)->page;
-	if (a_page == NULL)
-		return (b_page == NULL ? 0 : 1);
-	if (b_page == NULL)
-		return (-1);
-
-	/*
-	 * Sort by the LRU in ascending order.
-	 *
-	 * Bias in favor of leaf pages.  Otherwise, we can waste time
-	 * considering parent pages for eviction while their child pages are
-	 * still in memory.
-	 *
-	 * Bump the LRU generation by a small fixed amount: the idea being that
-	 * if we have enough good leaf page candidates, we should evict them
-	 * first, but not completely ignore an old internal page.
-	 */
-	a_lru = a_page->read_gen;
-	b_lru = b_page->read_gen;
-	if (a_page->type == WT_PAGE_ROW_INT || a_page->type == WT_PAGE_COL_INT)
-		a_lru += WT_EVICT_INT_SKEW;
-	if (b_page->type == WT_PAGE_ROW_INT || b_page->type == WT_PAGE_COL_INT)
-		b_lru += WT_EVICT_INT_SKEW;
-	return (a_lru > b_lru ? 1 : (a_lru < b_lru ? -1 : 0));
-}

src/btree/rec_write.c

@@ -1247,12 +1247,13 @@ __rec_split_row_promote(WT_SESSION_IMPL *session, WT_RECONCILE *r, uint8_t type)
 	 * a copy.  For a row-store, it's the first key on the page, a variable-
 	 * length byte string, get a copy.
 	 *
-	 * This function is called from __rec_split at each split boundary, but
-	 * that means we're not called before the first boundary.  It's painful,
-	 * but we need to detect that case and copy the key from the page we're
-	 * building.  We could simplify this by grabbing a copy of the first key
-	 * we put on a page, perhaps in the function building keys for a page,
-	 * but that's going to be uglier than this.
+	 * This function is called from the split code at each split boundary,
+	 * but that means we're not called before the first boundary.  When we
+	 * do the split work at the second boundary, we need to copy the key
+	 * for the first boundary from the page we're building.  Alternatively,
+	 * we could store a copy of the first key we put on a page somewhere,
+	 * perhaps while building the keys for a page, but that's likely to be
+	 * even uglier.
 	 */
 	if (r->bnd_next == 1) {
 		/*
@@ -1270,7 +1271,11 @@ __rec_split_row_promote(WT_SESSION_IMPL *session, WT_RECONCILE *r, uint8_t type)
 
 	/*
 	 * For the current slot, take the last key we built, after doing suffix
-	 * compression.
+	 * compression.  The "last key we built" describes some process: before
+	 * calling the split code, we must place the last key on the page before
+	 * the boundary into the "last" key structure, and the first key on the
+	 * page after the boundary into the "current" key structure, we're going
+	 * to compare them for suffix compression.
 	 *
 	 * Suffix compression is a hack to shorten keys on internal pages.  We
 	 * only need enough bytes in the promoted key to ensure searches go to

src/config/config_def.c

@@ -115,8 +115,9 @@ __wt_confdfl_file_meta =
 	"internal_page_max=2KB,key_format=u,key_gap=10,leaf_item_max=0,"
 	"leaf_page_max=1MB,lsm_bloom=,lsm_bloom_bit_count=8,lsm_bloom_config="
 	",lsm_bloom_hash_count=4,lsm_bloom_newest=0,lsm_bloom_oldest=0,"
-	"lsm_chunk_size=2MB,lsm_merge_max=15,prefix_compression=,split_pct=75"
-	",value_format=u,version=(major=0,minor=0)";
+	"lsm_chunk_size=2MB,lsm_merge_max=15,lsm_merge_threads=1,"
+	"prefix_compression=,split_pct=75,value_format=u,version=(major=0,"
+	"minor=0)";
 
 WT_CONFIG_CHECK
 __wt_confchk_file_meta[] = {
@@ -146,6 +147,7 @@ __wt_confchk_file_meta[] = {
 	{ "lsm_bloom_oldest", "boolean", NULL },
 	{ "lsm_chunk_size", "int", "min=512K,max=500MB" },
 	{ "lsm_merge_max", "int", "min=2,max=100" },
+	{ "lsm_merge_threads", "int", "min=1,max=10" },
 	{ "prefix_compression", "boolean", NULL },
 	{ "split_pct", "int", "min=25,max=100" },
 	{ "value_format", "format", NULL },
@@ -232,8 +234,8 @@ __wt_confdfl_session_create =
 	"key_format=u,key_gap=10,leaf_item_max=0,leaf_page_max=1MB,lsm_bloom="
 	",lsm_bloom_bit_count=8,lsm_bloom_config=,lsm_bloom_hash_count=4,"
 	"lsm_bloom_newest=0,lsm_bloom_oldest=0,lsm_chunk_size=2MB,"
-	"lsm_merge_max=15,prefix_compression=,source=,split_pct=75,type=file,"
-	"value_format=u,value_format=u";
+	"lsm_merge_max=15,lsm_merge_threads=1,prefix_compression=,source=,"
+	"split_pct=75,type=file,value_format=u,value_format=u";
 
 WT_CONFIG_CHECK
 __wt_confchk_session_create[] = {
@@ -266,6 +268,7 @@ __wt_confchk_session_create[] = {
 	{ "lsm_bloom_oldest", "boolean", NULL },
 	{ "lsm_chunk_size", "int", "min=512K,max=500MB" },
 	{ "lsm_merge_max", "int", "min=2,max=100" },
+	{ "lsm_merge_threads", "int", "min=1,max=10" },
 	{ "prefix_compression", "boolean", NULL },
 	{ "source", "string", NULL },
 	{ "split_pct", "int", "min=25,max=100" },

src/docs/compression.dox

@@ -5,22 +5,35 @@ the bzip2 and snappy compression engines.
 
 @section compression_bzip2 Using bzip2 compression
 
-To use the builtin support for <a href="http://www.bzip.org/">bzip2</a>
+To use the builtin support for
+<a href="http://www.bzip.org/">Julian Seward's bzip2</a>
 compression, first check that bzip2 is installed in include and library
 directories searched by the compiler.  Once bzip2 is installed, you can
 enable bzip2 using the \c --enable-bzip2 option to configure.
 
-If bzip2 is installed in a non-standard location, you'll need to modify
-the \c CPPFLAGS and \c LDFLAGS to indicate these locations.  For example,
-with the bzip2 includes and libraries installed in \c /usr/local/include
-and \c /usr/local/lib, you should run configure as follows:
+If bzip2 is installed in a location not normally searched by the
+compiler toolchain, you'll need to modify the \c CPPFLAGS and \c LDFLAGS
+to indicate these locations.  For example, with the bzip2 includes and
+libraries installed in \c /usr/local/include and \c /usr/local/lib, you
+should run configure as follows:
 
 @code
 cd build_posix
-../dist/configure --enable-bzip2 CPPFLAGS="-I/usr/local/include" LDFLAGS="-L/usr/local/include"
+../configure --enable-bzip2 CPPFLAGS="-I/usr/local/include" LDFLAGS="-L/usr/local/include"
 @endcode
 
-After building, you can confirm the compressor is working by running the
+When opening the WiredTiger database, load the bzip2 shared library as
+an extension.  For example, with the bzip2 library installed in
+\c /usr/local/lib, you would use the following extension:
+
+@snippet ex_all.c Configure bzip2 extension
+
+Finally, when creating the WiredTiger object, set \c block_compressor
+to \c bzip2:
+
+@snippet ex_all.c Create a bzip2 compressed table
+
+If necessary, you can confirm the compressor is working by running the
 compression part of the test suite:
 
 @code
@@ -33,23 +46,35 @@ was not skipped.
 
 @section compression_snappy Using snappy compression
 
-To use the builtin support for Google's
-<a href="http://code.google.com/p/snappy/">snappy</a> compression, first
-check that snappy is installed in include and library directories
-searched by the compiler.  Once snappy is installed, you can enable
-snappy using the \c --enable-snappy option to configure.
+To use the builtin support for
+<a href="http://code.google.com/p/snappy/">Google's snappy</a>
+compression, first check that snappy is installed in include and library
+directories searched by the compiler.  Once snappy is installed, you can
+enable snappy using the \c --enable-snappy option to configure.
 
-If snappy is installed in a non-standard location, you'll need to modify
-the \c CPPFLAGS and \c LDFLAGS to indicate these locations.  For example,
-with the snappy includes and libraries installed in \c /usr/local/include
-and \c /usr/local/lib, you should run configure as follows:
+If snappy is installed in a location not normally searched by the
+compiler toolchain, you'll need to modify the \c CPPFLAGS and \c LDFLAGS
+to indicate these locations.  For example, with the snappy includes and
+libraries installed in \c /usr/local/include and \c /usr/local/lib, you
+should run configure as follows:
 
 @code
 cd build_posix
-../dist/configure --enable-snappy CPPFLAGS="-I/usr/local/include" LDFLAGS="-L/usr/local/include"
+../configure --enable-snappy CPPFLAGS="-I/usr/local/include" LDFLAGS="-L/usr/local/include"
 @endcode
 
-After building, you can confirm the compressor is working by running the
+When opening the WiredTiger database, load the snappy shared library as
+an extension.  For example, with the snappy library installed in
+\c /usr/local/lib, you would use the following extension:
+
+@snippet ex_all.c Configure snappy extension
+
+Finally, when creating the WiredTiger object, set \c block_compressor
+to \c snappy:
+
+@snippet ex_all.c Create a snappy compressed table
+
+If necessary, you can confirm the compressor is working by running the
 compression part of the test suite:
 
 @code

src/docs/spell.ok

@@ -13,8 +13,8 @@ DbMultiple
 EB
 EmpId
 FreeBSD
-Gawlick
 GCC
+Gawlick
 GitHub
 IEC
 LDFLAGS
@@ -28,6 +28,7 @@ Mewhort
 NoSQL
 RepMgr
 Rrx
+Seward's
 URIs
 Vv
 WiredTiger
@@ -193,6 +194,7 @@ mutexes
 mutexing
 mvcc
 mygcc
+namespace
 ndary
 ndbm
 newsite

src/docs/top/main.dox

@@ -13,7 +13,7 @@ To ask questions or discuss issues related to using WiredTiger, visit our
 
 View the documentation online:
 
-- <a href="1.3.5/index.html"><b>WiredTiger 1.3.5 (current release)</b></a>
+- <a href="1.3.6/index.html"><b>WiredTiger 1.3.6 (current release)</b></a>
 - <a href="1.2.2/index.html"><b>WiredTiger 1.2.2</b></a>
 - <a href="1.1.5/index.html"><b>WiredTiger 1.1.5</b></a>
 

src/docs/upgrading.dox

@@ -1,9 +1,48 @@
 /*! @page upgrading Upgrading WiredTiger applications
 
+@section version_136 Upgrading to Version 1.3.6
+<dl>
+
+<dt>Installed library names</dt>
+<dd>
+The installed WiredTiger extension library names changed to limit
+namespace pollution:
+
+<table>
+@hrow{Library, Previous Name, New Name}
+@row{Bzip2 compression, bzip2_compress.a, libwiredtiger_bzip2.a}
+@row{, bzip2_compress.la, libwiredtiger_bzip2.la}
+@row{, bzip2_compress.so, libwiredtiger_bzip2.so}
+@row{Snappy compression, snappy_compress.a, libwiredtiger_snappy.a}
+@row{, snappy_compress.la, libwiredtiger_snappy.la}
+@row{, snappy_compress.so, libwiredtiger_snappy.so}
+@row{No-op compression, nop_compress.a, No longer installed}
+@row{, nop_compress.la, No longer installed}
+@row{, nop_compress.so, No longer installed}
+@row{Reverse order collator, reverse_collator.a, No longer installed}
+@row{, reverse_collator.la, No longer installed}
+@row{, reverse_collator.so, No longer installed}
+</table>
+</dd>
+
+<dt>Built-in compression names</dt>
+<dd>
+The built-in compression name arguments to the WT_SESSION:create
+\c block_compressor configuration string changed for consistency:
+
+<table>
+@hrow{Extension, Previous Name, New Name}
+@row{Bzip2 compression, "bzip2_compress", "bzip2"}
+@row{Snappy compression, "snappy_compress", "snappy"}
+</table>
+</dd>
+
+</dl>
+<hr>
 @section version_135 Upgrading to Version 1.3.5
 <dl>
 
-<dt>Version 1.3.5 file format changes</dt>
+<dt>File format changes</dt>
 <dd>
 The underlying file formats changed in the 1.3.5 release; tables and files
 should be dumped and re-loaded into a new database.
@@ -100,7 +139,7 @@ returns a cursor comparison status (less than 0, equal to 0, or greater than
 0) depending on the cursors' key order.
 </dd>
 
-<dt>Version 1.3 file format changes</dt>
+<dt>File format changes</dt>
 <dd>
 The underlying file formats changed in the 1.3 release; tables and files
 should be dumped and re-loaded into a new database.

src/include/bloom.h

@@ -22,3 +22,7 @@ struct __wt_bloom {
 	uint64_t m;		/* The number of slots in the bit string. */
 	uint64_t n;		/* The number of items to be inserted. */
 };
+
+struct __wt_bloom_hash {
+	uint64_t h1, h2;	/* The two hashes used to calculate bits. */
+};

src/include/btmem.h

@@ -271,7 +271,7 @@ struct __wt_page {
 	 * The read-generation is not declared volatile: read-generation is set
 	 * a lot (on every access), and we don't want to write it that much.
 	 */
-	 uint64_t read_gen;
+	uint64_t read_gen;
 
 	/*
 	 * In-memory pages optionally reference a number of entries originally

src/include/btree.h

@@ -119,6 +119,7 @@ struct __wt_btree {
 	u_int block_header;		/* Block manager header length */
 
 	WT_PAGE *evict_page;		/* Eviction thread's location */
+	uint64_t evict_priority;	/* Relative priority of cached pages. */
 	volatile uint32_t lru_count;	/* Count of threads in LRU eviction */
 
 	WT_BTREE_STATS *stats;		/* Btree statistics */

src/include/cache.h

@@ -34,7 +34,7 @@ struct __wt_cache {
 	/*
 	 * Read information.
 	 */
-	uint32_t   read_gen;		/* Page read generation (LRU) */
+	uint64_t   read_gen;		/* Page read generation (LRU) */
 
 	/*
 	 * Eviction thread information.
@@ -52,6 +52,7 @@ struct __wt_cache {
 	WT_EVICT_ENTRY *evict_current;	/* LRU current page to be evicted */
 	size_t   evict_allocated;	/* LRU list bytes allocated */
 	uint32_t evict_entries;		/* LRU list eviction slots */
+	uint32_t evict_candidates;	/* LRU list pages to evict */
 	u_int    evict_file_next;	/* LRU: next file to search */
 
 	/*

src/include/extern.h

@@ -259,6 +259,8 @@ extern int __wt_bloom_open(WT_SESSION_IMPL *session,
     WT_BLOOM **bloomp);
 extern int __wt_bloom_insert(WT_BLOOM *bloom, WT_ITEM *key);
 extern int __wt_bloom_finalize(WT_BLOOM *bloom);
+extern int __wt_bloom_hash(WT_BLOOM *bloom, WT_ITEM *key, WT_BLOOM_HASH *bhash);
+extern int __wt_bloom_hash_get(WT_BLOOM *bloom, WT_BLOOM_HASH *bhash);
 extern int __wt_bloom_get(WT_BLOOM *bloom, WT_ITEM *key);
 extern int __wt_bloom_close(WT_BLOOM *bloom);
 extern int __wt_bloom_drop(WT_BLOOM *bloom, const char *config);
@@ -704,8 +706,9 @@ extern int __wt_log_printf(WT_SESSION_IMPL *session,
     2,
     3)));
 extern WT_LOGREC_DESC __wt_logdesc_debug;
-extern int __wt_clsm_init_merge(WT_CURSOR *cursor,
+extern int __wt_clsm_init_merge( WT_CURSOR *cursor,
     int start_chunk,
+    uint32_t start_id,
     int nchunks);
 extern int __wt_clsm_open(WT_SESSION_IMPL *session,
     const char *uri,
@@ -719,8 +722,9 @@ extern int __wt_lsm_merge_update_tree(WT_SESSION_IMPL *session,
     int start_chunk,
     int nchunks,
     WT_LSM_CHUNK *chunk);
-extern int __wt_lsm_merge(WT_SESSION_IMPL *session,
+extern int __wt_lsm_merge( WT_SESSION_IMPL *session,
     WT_LSM_TREE *lsm_tree,
+    uint32_t id,
     int stalls);
 extern int __wt_lsm_meta_read(WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree);
 extern int __wt_lsm_meta_write(WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree);
@@ -730,15 +734,14 @@ extern int __wt_lsm_stat_init( WT_SESSION_IMPL *session,
 extern int __wt_lsm_tree_close_all(WT_SESSION_IMPL *session);
 extern int __wt_lsm_tree_bloom_name( WT_SESSION_IMPL *session,
     WT_LSM_TREE *lsm_tree,
-    int i,
+    uint32_t id,
     WT_ITEM *buf);
 extern int __wt_lsm_tree_chunk_name( WT_SESSION_IMPL *session,
     WT_LSM_TREE *lsm_tree,
-    int i,
+    uint32_t id,
     WT_ITEM *buf);
 extern int __wt_lsm_tree_setup_chunk(WT_SESSION_IMPL *session,
     WT_LSM_TREE *lsm_tree,
-    int i,
     WT_LSM_CHUNK *chunk,
     int create_bloom);
 extern int __wt_lsm_tree_create(WT_SESSION_IMPL *session,
@@ -769,7 +772,7 @@ extern int __wt_lsm_tree_worker(WT_SESSION_IMPL *session,
     const char *[]),
     const char *cfg[],
     uint32_t open_flags);
-extern void *__wt_lsm_worker(void *arg);
+extern void *__wt_lsm_worker(void *vargs);
 extern void *__wt_lsm_checkpoint_worker(void *arg);
 extern int __wt_lsm_copy_chunks(WT_SESSION_IMPL *session,
     WT_LSM_TREE *lsm_tree,

src/include/lsm.h

@@ -20,15 +20,15 @@ struct __wt_cursor_lsm {
 	WT_CURSOR **cursors;
 	WT_CURSOR *current;     	/* The current cursor for iteration */
 
-	WT_LSM_CHUNK *primary_chunk;	/* The current primary chunk. */
+	WT_LSM_CHUNK *primary_chunk;	/* The current primary chunk */
 
 #define	WT_CLSM_ITERATE_NEXT    0x01    /* Forward iteration */
 #define	WT_CLSM_ITERATE_PREV    0x02    /* Backward iteration */
-#define	WT_CLSM_MERGE           0x04    /* Merge cursor, don't update. */
-#define	WT_CLSM_MINOR_MERGE	0x08    /* Minor merge, include tombstones. */
+#define	WT_CLSM_MERGE           0x04    /* Merge cursor, don't update */
+#define	WT_CLSM_MINOR_MERGE	0x08    /* Minor merge, include tombstones */
 #define	WT_CLSM_MULTIPLE        0x10    /* Multiple cursors have values for the
 					   current key */
-#define	WT_CLSM_UPDATED		0x20    /* Cursor has done updates */
+#define	WT_CLSM_OPEN_READ	0x20    /* Open for reads */
 	uint32_t flags;
 };
 
@@ -37,14 +37,16 @@ struct __wt_cursor_lsm {
  *	A single chunk (file) in an LSM tree.
  */
 struct __wt_lsm_chunk {
-	const char *uri;		/* Data source for this chunk. */
-	const char *bloom_uri;		/* URI of Bloom filter, if any. */
-	uint64_t count;			/* Approximate count of records. */
-	uint32_t generation;		/* Merge generation. */
+	uint32_t id;			/* ID used to generate URIs */
+	uint32_t generation;		/* Merge generation */
+	const char *uri;		/* Data source for this chunk */
+	const char *bloom_uri;		/* URI of Bloom filter, if any */
+	uint64_t count;			/* Approximate count of records */
 
-	uint32_t ncursor;		/* Cursors with the chunk as primary. */
-#define	WT_LSM_CHUNK_ONDISK	0x01
-#define	WT_LSM_CHUNK_BLOOM	0x02
+	uint32_t ncursor;		/* Cursors with the chunk as primary */
+#define	WT_LSM_CHUNK_BLOOM	0x01
+#define	WT_LSM_CHUNK_MERGING	0x02
+#define	WT_LSM_CHUNK_ONDISK	0x04
 	uint32_t flags;
 };
 
@@ -59,7 +61,7 @@ struct __wt_lsm_tree {
 
 	WT_COLLATOR *collator;
 
-	int refcnt;			/* Number of users of the tree. */
+	int refcnt;			/* Number of users of the tree */
 	WT_RWLOCK *rwlock;
 	TAILQ_ENTRY(__wt_lsm_tree) q;
 
@@ -74,21 +76,26 @@ struct __wt_lsm_tree {
 	uint32_t bloom_hash_count;
 	uint32_t chunk_size;
 	uint32_t merge_max;
+	uint32_t merge_threads;
+
 #define	WT_LSM_BLOOM_MERGED				0x00000001
 #define	WT_LSM_BLOOM_NEWEST				0x00000002
 #define	WT_LSM_BLOOM_OFF				0x00000004
 #define	WT_LSM_BLOOM_OLDEST				0x00000008
-	uint32_t bloom;			/* Bloom creation policy. */
+	uint32_t bloom;			/* Bloom creation policy */
 
-	WT_SESSION_IMPL *worker_session;/* Passed to thread_create */
-	pthread_t worker_tid;		/* LSM worker thread */
+#define	WT_LSM_MAX_WORKERS	10
+					/* Passed to thread_create */
+	WT_SESSION_IMPL *worker_sessions[WT_LSM_MAX_WORKERS];
+					/* LSM worker thread(s) */
+	pthread_t worker_tids[WT_LSM_MAX_WORKERS];
 	WT_SESSION_IMPL *ckpt_session;	/* For checkpoint worker */
 	pthread_t ckpt_tid;		/* LSM checkpoint worker thread */
 
-	int nchunks;			/* Number of active chunks */
-	int last;			/* Last allocated ID. */
 	WT_LSM_CHUNK **chunk;		/* Array of active LSM chunks */
 	size_t chunk_alloc;		/* Space allocated for chunks */
+	int nchunks;			/* Number of active chunks */
+	uint32_t last;			/* Last allocated ID */
 
 	WT_LSM_CHUNK **old_chunks;	/* Array of old LSM chunks */
 	size_t old_alloc;		/* Space allocated for old chunks */
@@ -115,7 +122,16 @@ struct __wt_lsm_data_source {
  *	State for an LSM worker thread.
  */
 struct __wt_lsm_worker_cookie {
-    WT_LSM_CHUNK **chunk_array;
-    size_t chunk_alloc;
-    int nchunks;
+	WT_LSM_CHUNK **chunk_array;
+	size_t chunk_alloc;
+	int nchunks;
+};
+
+/*
+ * WT_LSM_WORKER_ARGS --
+ *	State for an LSM worker thread.
+ */
+struct __wt_lsm_worker_args {
+	WT_LSM_TREE *lsm_tree;
+	int id;
 };

src/include/wiredtiger.in

@@ -685,6 +685,8 @@ struct __wt_session {
 	 * LSM tree.,an integer between 512K and 500MB; default \c 2MB.}
 	 * @config{lsm_merge_max, the maximum number of chunks to include in a
 	 * merge operation.,an integer between 2 and 100; default \c 15.}
+	 * @config{lsm_merge_threads, the number of thread to perform merge
+	 * operations.,an integer between 1 and 10; default \c 1.}
 	 * @config{prefix_compression, configure row-store format key prefix
 	 * compression.,a boolean flag; default \c true.}
 	 * @config{source, override the default data source URI derived from the
@@ -1177,11 +1179,11 @@ struct __wt_connection {
  * integer between 10 and 99; default \c 80.}
  * @config{eviction_trigger, trigger eviction when the cache becomes this full
  * (as a percentage).,an integer between 10 and 99; default \c 95.}
- * @config{extensions, list of extensions to load.  Optional values are passed
- * as the \c config parameter to WT_CONNECTION::load_extension.  Complex paths
- * may need quoting\, for example\,
- * <code>extensions=("/path/to/ext.so"="entry=my_entry")</code>.,a list of
- * strings; default empty.}
+ * @config{extensions, list of shared library extensions to load (using dlopen).
+ * Optional values are passed as the \c config parameter to
+ * WT_CONNECTION::load_extension.  Complex paths may require quoting\, for
+ * example\, <code>extensions=("/path/ext.so"="entry=my_entry")</code>.,a list
+ * of strings; default empty.}
  * @config{hazard_max, maximum number of simultaneous hazard references per
  * session handle.,an integer greater than or equal to 15; default \c 1000.}
  * @config{logging, enable logging.,a boolean flag; default \c false.}

src/include/wt_internal.h

@@ -59,6 +59,8 @@ struct __wt_block_header;
     typedef struct __wt_block_header WT_BLOCK_HEADER;
 struct __wt_bloom;
     typedef struct __wt_bloom WT_BLOOM;
+struct __wt_bloom_hash;
+    typedef struct __wt_bloom_hash WT_BLOOM_HASH;
 struct __wt_btree;
     typedef struct __wt_btree WT_BTREE;
 struct __wt_btree_session;
@@ -137,6 +139,8 @@ struct __wt_lsm_stats;
     typedef struct __wt_lsm_stats WT_LSM_STATS;
 struct __wt_lsm_tree;
     typedef struct __wt_lsm_tree WT_LSM_TREE;
+struct __wt_lsm_worker_args;
+    typedef struct __wt_lsm_worker_args WT_LSM_WORKER_ARGS;
 struct __wt_lsm_worker_cookie;
     typedef struct __wt_lsm_worker_cookie WT_LSM_WORKER_COOKIE;
 struct __wt_named_collator;
@@ -206,6 +210,7 @@ struct __wt_update;
 #include "stat.h"
 
 #include "api.h"
+#include "bloom.h"
 #include "cursor.h"
 #include "lsm.h"
 #include "meta.h"

src/lsm/lsm_cursor.c

@@ -26,22 +26,23 @@
 #define	WT_LSM_ENTER(clsm, cursor, session, n)				\
 	clsm = (WT_CURSOR_LSM *)cursor;					\
 	CURSOR_API_CALL(cursor, session, n, NULL);			\
-	WT_ERR(__clsm_enter(clsm))
+	WT_ERR(__clsm_enter(clsm, 0))
 
 #define	WT_LSM_UPDATE_ENTER(clsm, cursor, session, n)			\
 	clsm = (WT_CURSOR_LSM *)cursor;					\
 	CURSOR_UPDATE_API_CALL(cursor, session, n, NULL);		\
-	WT_ERR(__clsm_enter(clsm))
+	WT_ERR(__clsm_enter(clsm, 1))
 
-static int __clsm_open_cursors(WT_CURSOR_LSM *, int);
+static int __clsm_open_cursors(WT_CURSOR_LSM *, int, int, uint32_t);
 static int __clsm_search(WT_CURSOR *);
 
 static inline int
-__clsm_enter(WT_CURSOR_LSM *clsm)
+__clsm_enter(WT_CURSOR_LSM *clsm, int update)
 {
 	if (!F_ISSET(clsm, WT_CLSM_MERGE) &&
-	    clsm->dsk_gen != clsm->lsm_tree->dsk_gen)
-		WT_RET(__clsm_open_cursors(clsm, 0));
+	    (clsm->dsk_gen != clsm->lsm_tree->dsk_gen ||
+	    (!update && !F_ISSET(clsm, WT_CLSM_OPEN_READ))))
+		WT_RET(__clsm_open_cursors(clsm, update, 0, 0));
 
 	return (0);
 }
@@ -106,7 +107,8 @@ __clsm_close_cursors(WT_CURSOR_LSM *clsm)
  *	Open cursors for the current set of files.
  */
 static int
-__clsm_open_cursors(WT_CURSOR_LSM *clsm, int start_chunk)
+__clsm_open_cursors(
+    WT_CURSOR_LSM *clsm, int update, int start_chunk, uint32_t start_id)
 {
 	WT_CURSOR *c, **cp;
 	WT_DECL_RET;
@@ -124,6 +126,9 @@ __clsm_open_cursors(WT_CURSOR_LSM *clsm, int start_chunk)
 	c = &clsm->iface;
 	chunk = NULL;
 
+	if (!update)
+		F_SET(clsm, WT_CLSM_OPEN_READ);
+
 	/* Copy the key, so we don't lose the cursor position. */
 	if (F_ISSET(c, WT_CURSTD_KEY_SET)) {
 		if (c->key.data != c->key.mem)
@@ -135,10 +140,27 @@ __clsm_open_cursors(WT_CURSOR_LSM *clsm, int start_chunk)
 	WT_RET(__clsm_close_cursors(clsm));
 
 	__wt_spin_lock(session, &lsm_tree->lock);
+
 	/* Merge cursors have already figured out how many chunks they need. */
-	if (F_ISSET(clsm, WT_CLSM_MERGE))
+	if (F_ISSET(clsm, WT_CLSM_MERGE)) {
 		nchunks = clsm->nchunks;
-	else
+
+		/*
+		 * We may have raced with another merge completing.  Check that
+		 * we're starting at the right offset in the chunk array.
+		 */
+		if (start_chunk >= lsm_tree->nchunks ||
+		    lsm_tree->chunk[start_chunk]->id != start_id)
+			for (start_chunk = 0;
+			    start_chunk < lsm_tree->nchunks;
+			    start_chunk++) {
+				chunk = lsm_tree->chunk[start_chunk];
+				if (chunk->id == start_id)
+					break;
+			}
+
+		WT_ASSERT(session, start_chunk + nchunks <= lsm_tree->nchunks);
+	} else
 		nchunks = lsm_tree->nchunks;
 
 	if (clsm->cursors == NULL || nchunks > clsm->nchunks) {
@@ -150,6 +172,9 @@ __clsm_open_cursors(WT_CURSOR_LSM *clsm, int start_chunk)
 	clsm->nchunks = nchunks;
 
 	for (i = 0, cp = clsm->cursors; i != clsm->nchunks; i++, cp++) {
+		if (!F_ISSET(clsm, WT_CLSM_OPEN_READ) && i < clsm->nchunks - 1)
+			continue;
+
 		/*
 		 * Read from the checkpoint if the file has been written.
 		 * Once all cursors switch, the in-memory tree can be evicted.
@@ -182,18 +207,15 @@ __clsm_open_cursors(WT_CURSOR_LSM *clsm, int start_chunk)
 	}
 
 	/* The last chunk is our new primary. */
-	if ((clsm->primary_chunk = chunk) != NULL) {
-		WT_ASSERT(session,
-		    !F_ISSET(clsm, WT_CLSM_UPDATED) ||
-		    !F_ISSET(chunk, WT_LSM_CHUNK_ONDISK));
-
+	if (chunk != NULL && !F_ISSET(chunk, WT_LSM_CHUNK_ONDISK)) {
+		clsm->primary_chunk = chunk;
 		(void)WT_ATOMIC_ADD(clsm->primary_chunk->ncursor, 1);
-	}
 
-	/* Peek into the btree layer to track the in-memory size. */
-	if (lsm_tree->memsizep == NULL)
-		(void)__wt_btree_get_memsize(
-		    session, session->btree, &lsm_tree->memsizep);
+		/* Peek into the btree layer to track the in-memory size. */
+		if (lsm_tree->memsizep == NULL)
+			(void)__wt_btree_get_memsize(
+			    session, session->btree, &lsm_tree->memsizep);
+	}
 
 	clsm->dsk_gen = lsm_tree->dsk_gen;
 err:	__wt_spin_unlock(session, &lsm_tree->lock);
@@ -204,7 +226,8 @@ err:	__wt_spin_unlock(session, &lsm_tree->lock);
  *	Initialize an LSM cursor for a merge.
  */
 int
-__wt_clsm_init_merge(WT_CURSOR *cursor, int start_chunk, int nchunks)
+__wt_clsm_init_merge(
+    WT_CURSOR *cursor, int start_chunk, uint32_t start_id, int nchunks)
 {
 	WT_CURSOR_LSM *clsm;
 
@@ -214,7 +237,7 @@ __wt_clsm_init_merge(WT_CURSOR *cursor, int start_chunk, int nchunks)
 		F_SET(clsm, WT_CLSM_MINOR_MERGE);
 	clsm->nchunks = nchunks;
 
-	return (__clsm_open_cursors(clsm, start_chunk));
+	return (__clsm_open_cursors(clsm, 0, start_chunk, start_id));
 }
 
 /*
@@ -502,11 +525,14 @@ static int
 __clsm_search(WT_CURSOR *cursor)
 {
 	WT_BLOOM *bloom;
+	WT_BLOOM_HASH bhash;
 	WT_CURSOR *c;
 	WT_CURSOR_LSM *clsm;
 	WT_DECL_RET;
 	WT_SESSION_IMPL *session;
-	int i;
+	int have_hash, i;
+
+	have_hash = 0;
 
 	WT_LSM_ENTER(clsm, cursor, session, search);
 	WT_CURSOR_NEEDKEY(cursor);
@@ -526,7 +552,13 @@ __clsm_search(WT_CURSOR *cursor)
 	FORALL_CURSORS(clsm, c, i) {
 		/* If there is a Bloom filter, see if we can skip the read. */
 		if ((bloom = clsm->blooms[i]) != NULL) {
-			ret = __wt_bloom_get(bloom, &cursor->key);
+			if (!have_hash) {
+				WT_ERR(__wt_bloom_hash(
+				    bloom, &cursor->key, &bhash));
+				have_hash = 1;
+			}
+
+			ret = __wt_bloom_hash_get(bloom, &bhash);
 			if (ret == WT_NOTFOUND) {
 				WT_STAT_INCR(
 				    clsm->lsm_tree->stats, bloom_misses);
@@ -748,17 +780,18 @@ __clsm_put(
 	 * If this is the first update in this cursor, check if a new in-memory
 	 * chunk is needed.
 	 */
-	if (!F_ISSET(clsm, WT_CLSM_UPDATED)) {
+	if (clsm->primary_chunk == NULL) {
 		__wt_spin_lock(session, &lsm_tree->lock);
 		if (clsm->dsk_gen == lsm_tree->dsk_gen)
 			WT_WITH_SCHEMA_LOCK(session,
 			    ret = __wt_lsm_tree_switch(session, lsm_tree));
 		__wt_spin_unlock(session, &lsm_tree->lock);
 		WT_RET(ret);
-		F_SET(clsm, WT_CLSM_UPDATED);
 
 		/* We changed the structure, or someone else did: update. */
-		WT_RET(__clsm_enter(clsm));
+		WT_RET(__clsm_enter(clsm, 1));
+
+		WT_ASSERT(session, clsm->primary_chunk != NULL);
 	}
 
 	primary = clsm->cursors[clsm->nchunks - 1];

src/lsm/lsm_merge.c

@@ -19,6 +19,8 @@ __wt_lsm_merge_update_tree(WT_SESSION_IMPL *session,
 	size_t chunk_sz, chunks_after_merge;
 	int i, j;
 
+	WT_ASSERT(session, start_chunk + nchunks <= lsm_tree->nchunks);
+
 	/* Setup the array of obsolete chunks. */
 	if (nchunks > lsm_tree->old_avail) {
 		chunk_sz = sizeof(*lsm_tree->old_chunks);
@@ -61,7 +63,8 @@ __wt_lsm_merge_update_tree(WT_SESSION_IMPL *session,
  *	Merge a set of chunks of an LSM tree.
  */
 int
-__wt_lsm_merge(WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree, int stalls)
+__wt_lsm_merge(
+    WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree, uint32_t id, int stalls)
 {
 	WT_BLOOM *bloom;
 	WT_CURSOR *src, *dest;
@@ -71,7 +74,7 @@ __wt_lsm_merge(WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree, int stalls)
 	WT_LSM_CHUNK *chunk;
 	const char *cur_cfg[] =
 	    API_CONF_DEFAULTS(session, open_cursor, "bulk,raw");
-	uint32_t generation;
+	uint32_t generation, start_id;
 	uint64_t insert_count, record_count;
 	int create_bloom, dest_id, end_chunk, i;
 	int max_chunks, nchunks, start_chunk;
@@ -81,20 +84,13 @@ __wt_lsm_merge(WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree, int stalls)
 	max_chunks = (int)lsm_tree->merge_max;
 	create_bloom = 0;
 
-	/*
-	 * Take a copy of the latest chunk id. This value needs to be atomically
-	 * read. We need a copy, since other threads may alter the chunk count
-	 * while we are doing a merge.
-	 */
-	nchunks = lsm_tree->nchunks;
-
 	/*
 	 * If there aren't any chunks to merge, or some of the chunks aren't
 	 * yet written, we're done.  A non-zero error indicates that the worker
 	 * should assume there is no work to do: if there are unwritten chunks,
 	 * the worker should write them immediately.
 	 */
-	if (nchunks <= 1)
+	if (lsm_tree->nchunks <= 1)
 		return (WT_NOTFOUND);
 
 	/*
@@ -104,10 +100,14 @@ __wt_lsm_merge(WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree, int stalls)
 	 */
 	__wt_spin_lock(session, &lsm_tree->lock);
 
-	/* Only include chunks that are stable on disk. */
-	end_chunk = nchunks - 1;
+	/*
+	 * Only include chunks that are stable on disk and not involved in a
+	 * merge.
+	 */
+	end_chunk = lsm_tree->nchunks - 1;
 	while (end_chunk > 0 &&
-	    !F_ISSET(lsm_tree->chunk[end_chunk], WT_LSM_CHUNK_ONDISK))
+	    (!F_ISSET(lsm_tree->chunk[end_chunk], WT_LSM_CHUNK_ONDISK) ||
+	    F_ISSET(lsm_tree->chunk[end_chunk], WT_LSM_CHUNK_MERGING)))
 		--end_chunk;
 
 	/*
@@ -129,6 +129,10 @@ __wt_lsm_merge(WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree, int stalls)
 		chunk = lsm_tree->chunk[start_chunk - 1];
 		nchunks = end_chunk - start_chunk + 1;
 
+		/* If the chunk is already involved in a merge, stop. */
+		if (F_ISSET(chunk, WT_LSM_CHUNK_MERGING))
+			break;
+
 		/*
 		 * If the next chunk is more than double the average size of
 		 * the chunks we have so far, stop.
@@ -136,23 +140,46 @@ __wt_lsm_merge(WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree, int stalls)
 		if (nchunks > 2 && chunk->count > 2 * record_count / nchunks)
 			break;
 
-		/* Don't do any big merges until we have waited for 10s. */
-		if (nchunks > 0 && stalls < 10 &&
-		    chunk->count > lsm_tree->chunk[end_chunk]->count * 2)
+		/*
+		 * Never do big merges in the first thread if there are
+		 * multiple threads.  If there is a single thread, wait for 10
+		 * seconds looking for small merges before trying a big one.
+		 */
+		if (id == 0 && nchunks > 0 &&
+		    chunk->count > lsm_tree->chunk[end_chunk]->count * 2 &&
+		    (lsm_tree->merge_threads > 1 || stalls < 10))
 			break;
 
+		F_SET(chunk, WT_LSM_CHUNK_MERGING);
 		record_count += chunk->count;
 		--start_chunk;
 
-		if (nchunks == max_chunks)
+		if (nchunks == max_chunks) {
+			F_CLR(lsm_tree->chunk[end_chunk], WT_LSM_CHUNK_MERGING);
 			record_count -= lsm_tree->chunk[end_chunk--]->count;
+		}
 	}
-	__wt_spin_unlock(session, &lsm_tree->lock);
 
+	nchunks = end_chunk - start_chunk + 1;
 	WT_ASSERT(session, nchunks <= max_chunks);
 
 	/* Don't do small merges unless we have waited for 2s. */
-	if (nchunks <= 1 || (stalls < 2 && nchunks < max_chunks / 2))
+	if (nchunks <= 1 ||
+	    (id == 0 && stalls < 2 && nchunks < max_chunks / 2)) {
+		for (i = start_chunk; i <= end_chunk; i++)
+			F_CLR(lsm_tree->chunk[i], WT_LSM_CHUNK_MERGING);
+		nchunks = 0;
+	}
+
+	/* Find the merge generation. */
+	for (generation = 0, i = 0; i < nchunks; i++)
+		if (lsm_tree->chunk[start_chunk + i]->generation > generation)
+			generation = lsm_tree->chunk[i]->generation;
+
+	start_id = lsm_tree->chunk[start_chunk]->id;
+	__wt_spin_unlock(session, &lsm_tree->lock);
+
+	if (nchunks == 0)
 		return (WT_NOTFOUND);
 
 	/* Allocate an ID for the merge. */
@@ -163,17 +190,13 @@ __wt_lsm_merge(WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree, int stalls)
 	    start_chunk, end_chunk, dest_id, record_count);
 
 	WT_RET(__wt_calloc_def(session, 1, &chunk));
+	chunk->id = dest_id;
 
 	if (FLD_ISSET(lsm_tree->bloom, WT_LSM_BLOOM_MERGED) &&
 	    (FLD_ISSET(lsm_tree->bloom, WT_LSM_BLOOM_OLDEST) ||
 	    start_chunk > 0) && record_count > 0)
 		create_bloom = 1;
 
-	/* Find the merge generation. */
-	for (generation = 0, i = start_chunk; i < end_chunk; i++)
-		if (lsm_tree->chunk[i]->generation > generation)
-			generation = lsm_tree->chunk[i]->generation;
-
 	/*
 	 * Special setup for the merge cursor:
 	 * first, reset to open the dependent cursors;
@@ -182,10 +205,10 @@ __wt_lsm_merge(WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree, int stalls)
 	 */
 	WT_ERR(__wt_open_cursor(session, lsm_tree->name, NULL, NULL, &src));
 	F_SET(src, WT_CURSTD_RAW);
-	WT_ERR(__wt_clsm_init_merge(src, start_chunk, nchunks));
+	WT_ERR(__wt_clsm_init_merge(src, start_chunk, start_id, nchunks));
 
 	WT_WITH_SCHEMA_LOCK(session, ret = __wt_lsm_tree_setup_chunk(
-	    session, lsm_tree, dest_id, chunk, create_bloom));
+	    session, lsm_tree, chunk, create_bloom));
 	WT_ERR(ret);
 	if (create_bloom)
 		WT_ERR(__wt_bloom_create(session, chunk->bloom_uri,
@@ -226,6 +249,19 @@ __wt_lsm_merge(WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree, int stalls)
 	WT_ERR(ret);
 
 	__wt_spin_lock(session, &lsm_tree->lock);
+
+	/*
+	 * Check whether we raced with another merge, and adjust the chunk
+	 * array offset as necessary.
+	 */
+	if (start_chunk >= lsm_tree->nchunks ||
+	    lsm_tree->chunk[start_chunk]->id != start_id)
+		for (start_chunk = 0;
+		    start_chunk < lsm_tree->nchunks;
+		    start_chunk++)
+			if (lsm_tree->chunk[start_chunk]->id == start_id)
+				break;
+
 	ret = __wt_lsm_merge_update_tree(
 	    session, lsm_tree, start_chunk, nchunks, chunk);
 

src/lsm/lsm_meta.c

@@ -17,11 +17,15 @@ __wt_lsm_meta_read(WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree)
 	WT_CONFIG cparser, lparser;
 	WT_CONFIG_ITEM ck, cv, lk, lv;
 	WT_DECL_RET;
+	WT_ITEM buf;
 	WT_LSM_CHUNK *chunk;
 	const char *config;
 	int nchunks;
 	size_t chunk_sz, alloc;
 
+	WT_CLEAR(buf);
+	chunk_sz = sizeof(WT_LSM_CHUNK);
+
 	WT_RET(__wt_metadata_read(session, lsm_tree->name, &config));
 	WT_ERR(__wt_config_init(session, &cparser, config));
 	while ((ret = __wt_config_next(&cparser, &ck, &cv)) == 0) {
@@ -55,46 +59,54 @@ __wt_lsm_meta_read(WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree)
 			lsm_tree->chunk_size = (uint32_t)cv.val;
 		else if (WT_STRING_MATCH("lsm_merge_max", ck.str, ck.len))
 			lsm_tree->merge_max = (uint32_t)cv.val;
+		else if (WT_STRING_MATCH("lsm_merge_threads", ck.str, ck.len))
+			lsm_tree->merge_threads = (uint32_t)cv.val;
 		else if (WT_STRING_MATCH("last", ck.str, ck.len))
 			lsm_tree->last = (int)cv.val;
 		else if (WT_STRING_MATCH("chunks", ck.str, ck.len)) {
 			WT_ERR(__wt_config_subinit(session, &lparser, &cv));
-			chunk_sz = sizeof(*lsm_tree->chunk);
 			for (nchunks = 0; (ret =
 			    __wt_config_next(&lparser, &lk, &lv)) == 0; ) {
-				if (WT_STRING_MATCH("bloom", lk.str, lk.len)) {
-					WT_ERR(__wt_strndup(session,
-					    lv.str, lv.len, &chunk->bloom_uri));
+				if (WT_STRING_MATCH("id", lk.str, lk.len)) {
+					if ((nchunks + 1) * chunk_sz >
+					    lsm_tree->chunk_alloc)
+						WT_ERR(__wt_realloc(session,
+						    &lsm_tree->chunk_alloc,
+						    WT_MAX(10 * chunk_sz,
+						    2 * lsm_tree->chunk_alloc),
+						    &lsm_tree->chunk));
+					WT_ERR(__wt_calloc_def(
+					    session, 1, &chunk));
+					lsm_tree->chunk[nchunks++] = chunk;
+					chunk->id = (uint32_t)lv.val;
+					WT_ERR(__wt_lsm_tree_chunk_name(session,
+					    lsm_tree, chunk->id, &buf));
+					chunk->uri =
+					    __wt_buf_steal(session, &buf, NULL);
+					F_SET(chunk, WT_LSM_CHUNK_ONDISK);
+
+				} else if (WT_STRING_MATCH(
+				    "bloom", lk.str, lk.len)) {
+					WT_ERR(__wt_lsm_tree_bloom_name(session,
+					    lsm_tree, chunk->id, &buf));
+					chunk->bloom_uri =
+					    __wt_buf_steal(session, &buf, NULL);
 					F_SET(chunk, WT_LSM_CHUNK_BLOOM);
 					continue;
-				}
-				if (WT_STRING_MATCH("count", lk.str, lk.len)) {
+				} else if (WT_STRING_MATCH(
+				    "count", lk.str, lk.len)) {
 					chunk->count = lv.val;
 					continue;
-				}
-				if (WT_STRING_MATCH(
+				} else if (WT_STRING_MATCH(
 				    "generation", lk.str, lk.len)) {
 					chunk->generation = (uint32_t)lv.val;
 					continue;
 				}
-				if ((nchunks + 1) * chunk_sz >
-				    lsm_tree->chunk_alloc)
-					WT_ERR(__wt_realloc(session,
-					    &lsm_tree->chunk_alloc,
-					    WT_MAX(10 * chunk_sz,
-					    2 * lsm_tree->chunk_alloc),
-					    &lsm_tree->chunk));
-				WT_ERR(__wt_calloc_def(session, 1, &chunk));
-				lsm_tree->chunk[nchunks++] = chunk;
-				WT_ERR(__wt_strndup(session,
-				    lk.str, lk.len, &chunk->uri));
-				F_SET(chunk, WT_LSM_CHUNK_ONDISK);
 			}
 			WT_ERR_NOTFOUND_OK(ret);
 			lsm_tree->nchunks = nchunks;
 		} else if (WT_STRING_MATCH("old_chunks", ck.str, ck.len)) {
 			WT_ERR(__wt_config_subinit(session, &lparser, &cv));
-			chunk_sz = sizeof(*lsm_tree->old_chunks);
 			for (nchunks = 0; (ret =
 			    __wt_config_next(&lparser, &lk, &lv)) == 0; ) {
 				if (WT_STRING_MATCH("bloom", lk.str, lk.len)) {
@@ -157,20 +169,20 @@ __wt_lsm_meta_write(WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree)
 	    lsm_tree->key_format, lsm_tree->value_format));
 	WT_ERR(__wt_buf_catfmt(session, buf,
 	    ",last=%" PRIu32 ",lsm_chunk_size=%" PRIu64
-	    ",lsm_merge_max=%" PRIu32 ",lsm_bloom=%" PRIu32
+	    ",lsm_merge_max=%" PRIu32 ",lsm_merge_threads=%" PRIu32
+	    ",lsm_bloom=%" PRIu32
 	    ",lsm_bloom_bit_count=%" PRIu32 ",lsm_bloom_hash_count=%" PRIu32,
 	    lsm_tree->last, (uint64_t)lsm_tree->chunk_size,
-	    lsm_tree->merge_max, lsm_tree->bloom,
+	    lsm_tree->merge_max, lsm_tree->merge_threads, lsm_tree->bloom,
 	    lsm_tree->bloom_bit_count, lsm_tree->bloom_hash_count));
 	WT_ERR(__wt_buf_catfmt(session, buf, ",chunks=["));
 	for (i = 0; i < lsm_tree->nchunks; i++) {
 		chunk = lsm_tree->chunk[i];
 		if (i > 0)
 			WT_ERR(__wt_buf_catfmt(session, buf, ","));
-		WT_ERR(__wt_buf_catfmt(session, buf, "\"%s\"", chunk->uri));
-		if (chunk->bloom_uri != NULL)
-			WT_ERR(__wt_buf_catfmt(
-			    session, buf, ",bloom=\"%s\"", chunk->bloom_uri));
+		WT_ERR(__wt_buf_catfmt(session, buf, "id=%" PRIu32, chunk->id));
+		if (F_ISSET(chunk, WT_LSM_CHUNK_BLOOM))
+			WT_ERR(__wt_buf_catfmt(session, buf, ",bloom"));
 		if (chunk->count != 0)
 			WT_ERR(__wt_buf_catfmt(
 			    session, buf, ",count=%" PRIu64, chunk->count));

src/lsm/lsm_tree.c

@@ -68,11 +68,15 @@ __lsm_tree_close(WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree)
 {
 	WT_DECL_RET;
 	WT_SESSION *wt_session;
+	WT_SESSION_IMPL *s;
+	uint32_t i;
 
 	if (F_ISSET(lsm_tree, WT_LSM_TREE_WORKING)) {
 		F_CLR(lsm_tree, WT_LSM_TREE_WORKING);
 		if (F_ISSET(S2C(session), WT_CONN_LSM_MERGE))
-			WT_TRET(__wt_thread_join(lsm_tree->worker_tid));
+			for (i = 0; i < lsm_tree->merge_threads; i++)
+				WT_TRET(__wt_thread_join(
+				    lsm_tree->worker_tids[i]));
 		WT_TRET(__wt_thread_join(lsm_tree->ckpt_tid));
 	}
 
@@ -83,18 +87,19 @@ __lsm_tree_close(WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree)
 	 *
 	 * Do this in the main thread to avoid deadlocks.
 	 */
-	if (lsm_tree->worker_session != NULL) {
-		F_SET(lsm_tree->worker_session,
-		    F_ISSET(session, WT_SESSION_SCHEMA_LOCKED));
-
-		wt_session = &lsm_tree->worker_session->iface;
+	for (i = 0; i < lsm_tree->merge_threads; i++) {
+		if ((s = lsm_tree->worker_sessions[i]) == NULL)
+			continue;
+		lsm_tree->worker_sessions[i] = NULL;
+		F_SET(s, F_ISSET(session, WT_SESSION_SCHEMA_LOCKED));
+		wt_session = &s->iface;
 		WT_TRET(wt_session->close(wt_session, NULL));
 
 		/*
 		 * This is safe after the close because session handles are
 		 * not freed, but are managed by the connection.
 		 */
-		__wt_free(NULL, lsm_tree->worker_session->hazard);
+		__wt_free(NULL, s->hazard);
 	}
 	if (lsm_tree->ckpt_session != NULL) {
 		F_SET(lsm_tree->ckpt_session,
@@ -137,10 +142,10 @@ __wt_lsm_tree_close_all(WT_SESSION_IMPL *session)
  */
 int
 __wt_lsm_tree_bloom_name(
-    WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree, int i, WT_ITEM *buf)
+    WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree, uint32_t id, WT_ITEM *buf)
 {
-	WT_RET(__wt_buf_fmt(session, buf, "file:%s-%06d.bf",
-	    lsm_tree->filename, i));
+	WT_RET(__wt_buf_fmt(session, buf, "file:%s-%06" PRIu32 ".bf",
+	    lsm_tree->filename, id));
 	return (0);
 }
 
@@ -150,10 +155,10 @@ __wt_lsm_tree_bloom_name(
  */
 int
 __wt_lsm_tree_chunk_name(
-    WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree, int i, WT_ITEM *buf)
+    WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree, uint32_t id, WT_ITEM *buf)
 {
-	WT_RET(__wt_buf_fmt(session, buf, "file:%s-%06d.lsm",
-	    lsm_tree->filename, i));
+	WT_RET(__wt_buf_fmt(session, buf, "file:%s-%06" PRIu32 ".lsm",
+	    lsm_tree->filename, id));
 	return (0);
 }
 
@@ -163,15 +168,16 @@ __wt_lsm_tree_chunk_name(
  */
 int
 __wt_lsm_tree_setup_chunk(WT_SESSION_IMPL *session,
-    WT_LSM_TREE *lsm_tree, int i, WT_LSM_CHUNK *chunk, int create_bloom)
+    WT_LSM_TREE *lsm_tree, WT_LSM_CHUNK *chunk, int create_bloom)
 {
-	WT_DECL_ITEM(buf);
-	WT_DECL_ITEM(bbuf);
 	WT_DECL_RET;
+	WT_ITEM buf;
 	const char *cfg[] = API_CONF_DEFAULTS(session, drop, "force");
 
-	WT_RET(__wt_scr_alloc(session, 0, &buf));
-	WT_ERR(__wt_lsm_tree_chunk_name(session, lsm_tree, i, buf));
+	WT_CLEAR(buf);
+	WT_RET(__wt_lsm_tree_chunk_name(session, lsm_tree, chunk->id, &buf));
+	chunk->uri = __wt_buf_steal(session, &buf, NULL);
+
 	/*
 	 * Drop the chunk first - there may be some content hanging over from
 	 * an aborted merge.
@@ -181,20 +187,16 @@ __wt_lsm_tree_setup_chunk(WT_SESSION_IMPL *session,
 	 * things with handle locks and metadata tracking.  It can never have
 	 * been the result of an interrupted merge, anyway.
 	 */
-	if (i > 1)
-		WT_ERR(__wt_schema_drop(session, buf->data, cfg));
-	WT_ERR(__wt_schema_create(session, buf->data, lsm_tree->file_config));
-	chunk->uri = __wt_buf_steal(session, buf, NULL);
+	if (chunk->id > 1)
+		WT_ERR(__wt_schema_drop(session, chunk->uri, cfg));
+	WT_ERR(__wt_schema_create(session, chunk->uri, lsm_tree->file_config));
 	if (create_bloom) {
-		WT_ERR(__wt_scr_alloc(session, 0, &bbuf));
 		WT_ERR(__wt_lsm_tree_bloom_name(
-		    session, lsm_tree, i, bbuf));
-		chunk->bloom_uri = __wt_buf_steal(session, bbuf, NULL);
+		    session, lsm_tree, chunk->id, &buf));
+		chunk->bloom_uri = __wt_buf_steal(session, &buf, NULL);
 	}
 
-err:	__wt_scr_free(&buf);
-	__wt_scr_free(&bbuf);
-	return (ret);
+err:	return (ret);
 }
 
 /*
@@ -205,12 +207,12 @@ static int
 __lsm_tree_start_worker(WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree)
 {
 	WT_CONNECTION *wt_conn;
+	WT_LSM_WORKER_ARGS *wargs;
 	WT_SESSION *wt_session;
+	WT_SESSION_IMPL *s;
+	uint32_t i;
 
 	wt_conn = &S2C(session)->iface;
-	WT_RET(wt_conn->open_session(wt_conn, NULL, NULL, &wt_session));
-	lsm_tree->worker_session = (WT_SESSION_IMPL *)wt_session;
-	F_SET(lsm_tree->worker_session, WT_SESSION_INTERNAL);
 
 	WT_RET(wt_conn->open_session(wt_conn, NULL, NULL, &wt_session));
 	lsm_tree->ckpt_session = (WT_SESSION_IMPL *)wt_session;
@@ -220,8 +222,19 @@ __lsm_tree_start_worker(WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree)
 	/* The new thread will rely on the WORKING value being visible. */
 	WT_FULL_BARRIER();
 	if (F_ISSET(S2C(session), WT_CONN_LSM_MERGE))
-		WT_RET(__wt_thread_create(
-		    &lsm_tree->worker_tid, __wt_lsm_worker, lsm_tree));
+		for (i = 0; i < lsm_tree->merge_threads; i++) {
+			WT_RET(wt_conn->open_session(
+			    wt_conn, NULL, NULL, &wt_session));
+			s = (WT_SESSION_IMPL *)wt_session;
+			F_SET(s, WT_SESSION_INTERNAL);
+			lsm_tree->worker_sessions[i] = s;
+
+			WT_RET(__wt_calloc_def(session, 1, &wargs));
+			wargs->lsm_tree = lsm_tree;
+			wargs->id = i;
+			WT_RET(__wt_thread_create(
+			    &lsm_tree->worker_tids[i], __wt_lsm_worker, wargs));
+		}
 	WT_RET(__wt_thread_create(
 	    &lsm_tree->ckpt_tid, __wt_lsm_checkpoint_worker, lsm_tree));
 
@@ -306,6 +319,10 @@ __wt_lsm_tree_create(WT_SESSION_IMPL *session,
 	lsm_tree->chunk_size = (uint32_t)cval.val;
 	WT_ERR(__wt_config_gets(session, cfg, "lsm_merge_max", &cval));
 	lsm_tree->merge_max = (uint32_t)cval.val;
+	WT_ERR(__wt_config_gets(session, cfg, "lsm_merge_threads", &cval));
+	lsm_tree->merge_threads = (uint32_t)cval.val;
+	/* Sanity check that api_data.py is in sync with lsm.h */
+	WT_ASSERT(session, lsm_tree->merge_threads <= WT_LSM_MAX_WORKERS);
 
 	WT_ERR(__wt_scr_alloc(session, 0, &buf));
 	WT_ERR(__wt_buf_fmt(session, buf,
@@ -346,20 +363,21 @@ __lsm_tree_open_check(
 	WT_CONFIG_ITEM cval;
 	const char *cfg[] = API_CONF_DEFAULTS(
 	    session, create, lsm_tree->file_config);
+	uint64_t required;
 	uint32_t maxleafpage;
-	uint64_t req;
 
 	WT_RET(__wt_config_gets(
 	    session, cfg, "leaf_page_max", &cval));
 	maxleafpage = (uint32_t)cval.val;
 
 	/* Three chunks, plus one page for each participant in a merge. */
-	req = 3 * lsm_tree->chunk_size + (lsm_tree->merge_max *  maxleafpage);
-	if (S2C(session)->cache_size < req)
+	required = 3 * lsm_tree->chunk_size +
+	    lsm_tree->merge_threads * (lsm_tree->merge_max *  maxleafpage);
+	if (S2C(session)->cache_size < required)
 		WT_RET_MSG(session, EINVAL,
 		    "The LSM configuration requires a cache size of at least %"
 		    PRIu64 ". Configured size is %" PRIu64,
-		    req, S2C(session)->cache_size);
+		    required, S2C(session)->cache_size);
 	return (0);
 }
 
@@ -433,7 +451,7 @@ __wt_lsm_tree_get(WT_SESSION_IMPL *session,
 			if (exclusive && lsm_tree->refcnt)
 				return (EBUSY);
 
-			WT_ATOMIC_ADD(lsm_tree->refcnt, 1);
+			(void)WT_ATOMIC_ADD(lsm_tree->refcnt, 1);
 			*treep = lsm_tree;
 			return (0);
 		}
@@ -453,7 +471,7 @@ void
 __wt_lsm_tree_release(WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree)
 {
 	WT_ASSERT(session, lsm_tree->refcnt > 0);
-	WT_ATOMIC_SUB(lsm_tree->refcnt, 1);
+	(void)WT_ATOMIC_SUB(lsm_tree->refcnt, 1);
 }
 
 /*
@@ -466,7 +484,7 @@ __wt_lsm_tree_switch(
 {
 	WT_DECL_RET;
 	WT_LSM_CHUNK *chunk;
-	int new_id;
+	uint32_t new_id;
 
 	new_id = WT_ATOMIC_ADD(lsm_tree->last, 1); 
 
@@ -486,9 +504,9 @@ __wt_lsm_tree_switch(
 		    &lsm_tree->chunk));
 
 	WT_ERR(__wt_calloc_def(session, 1, &chunk));
+	chunk->id = new_id;
 	lsm_tree->chunk[lsm_tree->nchunks++] = chunk;
-	WT_ERR(__wt_lsm_tree_setup_chunk(
-	    session, lsm_tree, new_id, chunk,
+	WT_ERR(__wt_lsm_tree_setup_chunk(session, lsm_tree, chunk,
 	    FLD_ISSET(lsm_tree->bloom, WT_LSM_BLOOM_NEWEST) ? 1 : 0));
 
 	++lsm_tree->dsk_gen;
@@ -556,14 +574,15 @@ int
 __wt_lsm_tree_rename(WT_SESSION_IMPL *session,
     const char *oldname, const char *newname, const char *cfg[])
 {
-	WT_DECL_ITEM(buf);
 	WT_DECL_RET;
+	WT_ITEM buf;
 	WT_LSM_CHUNK *chunk;
 	WT_LSM_TREE *lsm_tree;
 	const char *old;
 	int i;
 
 	old = NULL;
+	WT_CLEAR(buf);
 
 	/* Get the LSM tree. */
 	WT_RET(__wt_lsm_tree_get(session, oldname, 1, &lsm_tree));
@@ -574,8 +593,6 @@ __wt_lsm_tree_rename(WT_SESSION_IMPL *session,
 	/* Prevent any new opens. */
 	WT_RET(__wt_spin_trylock(session, &lsm_tree->lock));
 
-	WT_ERR(__wt_scr_alloc(session, 0, &buf));
-
 	/* Set the new name. */
 	__wt_free(session, lsm_tree->name);
 	WT_ERR(__wt_strdup(session, newname, &lsm_tree->name));
@@ -586,16 +603,18 @@ __wt_lsm_tree_rename(WT_SESSION_IMPL *session,
 		old = chunk->uri;
 		chunk->uri = NULL;
 
-		WT_ERR(__wt_lsm_tree_chunk_name(session, lsm_tree, i, buf));
-		chunk->uri = __wt_buf_steal(session, buf, NULL);
+		WT_ERR(__wt_lsm_tree_chunk_name(
+		    session, lsm_tree, (uint32_t)i, &buf));
+		chunk->uri = __wt_buf_steal(session, &buf, NULL);
 		WT_ERR(__wt_schema_rename(session, old, chunk->uri, cfg));
 		__wt_free(session, old);
 
-		if ((old = chunk->bloom_uri) != NULL) {
+		if (F_ISSET(chunk, WT_LSM_CHUNK_BLOOM)) {
+			old = chunk->bloom_uri;
 			chunk->bloom_uri = NULL;
 			WT_ERR(__wt_lsm_tree_bloom_name(
-			    session, lsm_tree, i, buf));
-			chunk->bloom_uri = __wt_buf_steal(session, buf, NULL);
+			    session, lsm_tree, (uint32_t)i, &buf));
+			chunk->bloom_uri = __wt_buf_steal(session, &buf, NULL);
 			F_SET(chunk, WT_LSM_CHUNK_BLOOM);
 			WT_ERR(__wt_schema_rename(
 			    session, old, chunk->uri, cfg));
@@ -610,7 +629,6 @@ __wt_lsm_tree_rename(WT_SESSION_IMPL *session,
 	if (0) {
 err:		__wt_spin_unlock(session, &lsm_tree->lock);
 	}
-	__wt_scr_free(&buf);
 	if (old != NULL)
 		__wt_free(session, old);
 	__lsm_tree_discard(session, lsm_tree);
@@ -640,15 +658,15 @@ __wt_lsm_tree_truncate(
 	/* Prevent any new opens. */
 	WT_RET(__wt_spin_trylock(session, &lsm_tree->lock));
 
-	/* Mark all chunks old. */
+	/* Create the new chunk. */
 	WT_ERR(__wt_calloc_def(session, 1, &chunk));
+	chunk->id = WT_ATOMIC_ADD(lsm_tree->last, 1);
+	WT_ERR(__wt_lsm_tree_setup_chunk(session, lsm_tree, chunk, 0));
+
+	/* Mark all chunks old. */
 	WT_ERR(__wt_lsm_merge_update_tree(
 	    session, lsm_tree, 0, lsm_tree->nchunks, chunk));
 
-	/* Create the new chunk. */
-	WT_ERR(__wt_lsm_tree_setup_chunk(
-	    session, lsm_tree, WT_ATOMIC_ADD(lsm_tree->last, 1), chunk, 0));
-
 	WT_ERR(__wt_lsm_meta_write(session, lsm_tree));
 
 	WT_ERR(__lsm_tree_start_worker(session, lsm_tree));

src/lsm/lsm_worker.c

@@ -17,14 +17,18 @@ static int __lsm_free_chunks(WT_SESSION_IMPL *, WT_LSM_TREE *);
  *	trees to disk and merging on-disk trees.
  */
 void *
-__wt_lsm_worker(void *arg)
+__wt_lsm_worker(void *vargs)
 {
+	WT_LSM_WORKER_ARGS *args;
 	WT_LSM_TREE *lsm_tree;
 	WT_SESSION_IMPL *session;
-	int progress, stalls;
+	int id, progress, stalls;
 
-	lsm_tree = arg;
-	session = lsm_tree->worker_session;
+	args = vargs;
+	lsm_tree = args->lsm_tree;
+	id = args->id;
+	session = lsm_tree->worker_sessions[id];
+	__wt_free(session, args);
 	stalls = 0;
 
 	while (F_ISSET(lsm_tree, WT_LSM_TREE_WORKING)) {
@@ -34,13 +38,18 @@ __wt_lsm_worker(void *arg)
 		session->btree = NULL;
 
 		/* Report stalls to merge in seconds. */
-		if (__wt_lsm_merge(session, lsm_tree, stalls / 1000) == 0)
+		if (__wt_lsm_merge(session, lsm_tree, id, stalls / 1000) == 0)
 			progress = 1;
 
 		/* Clear any state from previous worker thread iterations. */
 		session->btree = NULL;
 
-		if (lsm_tree->nold_chunks != lsm_tree->old_avail &&
+		/*
+		 * Only have one thread freeing old chunks, and only if there
+		 * are chunks to free.
+		 */
+		if (id == 0 &&
+		    lsm_tree->nold_chunks != lsm_tree->old_avail &&
 		    __lsm_free_chunks(session, lsm_tree) == 0)
 			progress = 1;
 
@@ -82,14 +91,23 @@ __wt_lsm_checkpoint_worker(void *arg)
 		/* Write checkpoints in all completed files. */
 		for (i = 0, j = 0; i < cookie.nchunks; i++) {
 			chunk = cookie.chunk_array[i];
-			if (F_ISSET(chunk, WT_LSM_CHUNK_ONDISK))
-				continue;
 			/* Stop if a thread is still active in the chunk. */
-			if (chunk->ncursor != 0)
+			if (chunk->ncursor != 0 ||
+			    (i == cookie.nchunks - 1 &&
+			    !F_ISSET(chunk, WT_LSM_CHUNK_ONDISK)))
 				break;
 
-			WT_ERR(__lsm_bloom_create(
-			    session, lsm_tree, chunk));
+			if (!F_ISSET(chunk, WT_LSM_CHUNK_BLOOM) &&
+			    (ret = __lsm_bloom_create(
+			    session, lsm_tree, chunk)) != 0) {
+				(void)__wt_err(
+				   session, ret, "bloom creation failed");
+				break;
+			}
+
+			if (F_ISSET(chunk, WT_LSM_CHUNK_ONDISK))
+				continue;
+
 			/*
 			 * NOTE: we pass a non-NULL config, because otherwise
 			 * __wt_checkpoint thinks we're closing the file.
@@ -101,14 +119,18 @@ __wt_lsm_checkpoint_worker(void *arg)
 				++j;
 				__wt_spin_lock(session, &lsm_tree->lock);
 				F_SET(chunk, WT_LSM_CHUNK_ONDISK);
-				lsm_tree->dsk_gen++;
+				++lsm_tree->dsk_gen;
 				__wt_spin_unlock(session, &lsm_tree->lock);
 				WT_VERBOSE_ERR(session, lsm,
 				     "LSM worker checkpointed %d.", i);
+			} else {
+				(void)__wt_err(
+				   session, ret, "LSM checkpoint failed");
+				break;
 			}
 		}
 		if (j == 0)
-			__wt_sleep(0, 10);
+			__wt_sleep(0, 1000);
 	}
 err:	__wt_free(session, cookie.chunk_array);
 
@@ -136,12 +158,9 @@ __wt_lsm_copy_chunks(WT_SESSION_IMPL *session,
 		/* The actual error value is ignored. */
 		return (WT_ERROR);
 	}
-	/*
-	 * Take a copy of the current state of the LSM tree. Skip
-	 * the last chunk - since it is the active one and not relevant
-	 * to merge operations.
-	 */
-	nchunks = lsm_tree->nchunks - 1;
+
+	/* Take a copy of the current state of the LSM tree. */
+	nchunks = lsm_tree->nchunks;
 
 	/*
 	 * If the tree array of active chunks is larger than our current buffer,
@@ -173,7 +192,7 @@ __lsm_bloom_create(WT_SESSION_IMPL *session,
 	WT_BLOOM *bloom;
 	WT_CURSOR *src;
 	WT_DECL_RET;
-	WT_ITEM key;
+	WT_ITEM buf, key;
 	const char *cur_cfg[] = API_CONF_DEFAULTS(session, open_cursor, "raw");
 	uint64_t insert_count;
 
@@ -181,11 +200,21 @@ __lsm_bloom_create(WT_SESSION_IMPL *session,
 	    chunk->count == 0)
 		return (0);
 
-	WT_ASSERT(session, chunk->bloom_uri != NULL);
+	/*
+	 * Normally, the Bloom URI is populated when the chunk struct is
+	 * allocated.  After an open, however, it may not have been.
+	 * Deal with that here.
+	 */
+	if (chunk->bloom_uri == NULL) {
+		WT_CLEAR(buf);
+		WT_RET(__wt_lsm_tree_bloom_name(
+		    session, lsm_tree, chunk->id, &buf));
+		chunk->bloom_uri = __wt_buf_steal(session, &buf, NULL);
+	}
 
 	bloom = NULL;
 
-	WT_ERR(__wt_bloom_create(session, chunk->bloom_uri,
+	WT_RET(__wt_bloom_create(session, chunk->bloom_uri,
 	    lsm_tree->bloom_config, chunk->count,
 	    lsm_tree->bloom_bit_count, lsm_tree->bloom_hash_count, &bloom));
 
@@ -236,17 +265,15 @@ __lsm_free_chunks(WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree)
 			 * An EBUSY return is acceptable - a cursor may still
 			 * be positioned on this old chunk.
 			 */
-			if (ret == 0) {
-				progress = 1;
-				F_CLR(chunk, WT_LSM_CHUNK_BLOOM);
-				__wt_free(session, chunk->bloom_uri);
-				chunk->bloom_uri = NULL;
-			} else if (ret != EBUSY)
-				goto err;
-			if (ret == EBUSY)
+			if (ret == EBUSY) {
 				WT_VERBOSE_ERR(session, lsm,
 				    "LSM worker bloom drop busy: %s.",
 				    chunk->bloom_uri);
+				continue;
+			} else
+				WT_ERR(ret);
+
+			F_CLR(chunk, WT_LSM_CHUNK_BLOOM);
 		}
 		if (chunk->uri != NULL) {
 			WT_WITH_SCHEMA_LOCK(session, ret =
@@ -255,19 +282,20 @@ __lsm_free_chunks(WT_SESSION_IMPL *session, WT_LSM_TREE *lsm_tree)
 			 * An EBUSY return is acceptable - a cursor may still
 			 * be positioned on this old chunk.
 			 */
-			if (ret == 0) {
-				progress = 1;
-				__wt_free(session, chunk->uri);
-				chunk->uri = NULL;
-			} else if (ret != EBUSY)
-				goto err;
+			if (ret == EBUSY) {
+				WT_VERBOSE_ERR(session, lsm,
+				    "LSM worker drop busy: %s.",
+				    chunk->uri);
+				continue;
+			} else
+				WT_ERR(ret);
 		}
 
-		if (chunk->uri == NULL &&
-		    !F_ISSET(chunk, WT_LSM_CHUNK_BLOOM)) {
-			__wt_free(session, lsm_tree->old_chunks[i]);
-			++lsm_tree->old_avail;
-		}
+		progress = 1;
+		__wt_free(session, chunk->bloom_uri);
+		__wt_free(session, chunk->uri);
+		__wt_free(session, lsm_tree->old_chunks[i]);
+		++lsm_tree->old_avail;
 	}
 	if (locked) {
 err:		WT_TRET(__wt_lsm_meta_write(session, lsm_tree));

test/bloom/test_bloom.c

@@ -1,8 +1,28 @@
 /*-
- * Copyright (c) 2008-2012 WiredTiger, Inc.
- *	All rights reserved.
+ * Public Domain 2008-2012 WiredTiger, Inc.
  *
- * See the file LICENSE for redistribution information.
+ * This is free and unencumbered software released into the public domain.
+ *
+ * Anyone is free to copy, modify, publish, use, compile, sell, or
+ * distribute this software, either in source code form or as a compiled
+ * binary, for any purpose, commercial or non-commercial, and by any
+ * means.
+ *
+ * In jurisdictions that recognize copyright laws, the author or authors
+ * of this software dedicate any and all copyright interest in the
+ * software to the public domain. We make this dedication for the benefit
+ * of the public at large and to the detriment of our heirs and
+ * successors. We intend this dedication to be an overt act of
+ * relinquishment in perpetuity of all present and future rights to this
+ * software under copyright law.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+ * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
  */
 
 #include <signal.h>

test/fops/file.c

@@ -1,8 +1,28 @@
 /*-
- * Copyright (c) 2008-2012 WiredTiger, Inc.
- *	All rights reserved.
+ * Public Domain 2008-2012 WiredTiger, Inc.
  *
- * See the file LICENSE for redistribution information.
+ * This is free and unencumbered software released into the public domain.
+ *
+ * Anyone is free to copy, modify, publish, use, compile, sell, or
+ * distribute this software, either in source code form or as a compiled
+ * binary, for any purpose, commercial or non-commercial, and by any
+ * means.
+ *
+ * In jurisdictions that recognize copyright laws, the author or authors
+ * of this software dedicate any and all copyright interest in the
+ * software to the public domain. We make this dedication for the benefit
+ * of the public at large and to the detriment of our heirs and
+ * successors. We intend this dedication to be an overt act of
+ * relinquishment in perpetuity of all present and future rights to this
+ * software under copyright law.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+ * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
  */
 
 #include "thread.h"

test/fops/fops.c

@@ -1,8 +1,28 @@
 /*-
- * Copyright (c) 2008-2012 WiredTiger, Inc.
- *	All rights reserved.
+ * Public Domain 2008-2012 WiredTiger, Inc.
  *
- * See the file LICENSE for redistribution information.
+ * This is free and unencumbered software released into the public domain.
+ *
+ * Anyone is free to copy, modify, publish, use, compile, sell, or
+ * distribute this software, either in source code form or as a compiled
+ * binary, for any purpose, commercial or non-commercial, and by any
+ * means.
+ *
+ * In jurisdictions that recognize copyright laws, the author or authors
+ * of this software dedicate any and all copyright interest in the
+ * software to the public domain. We make this dedication for the benefit
+ * of the public at large and to the detriment of our heirs and
+ * successors. We intend this dedication to be an overt act of
+ * relinquishment in perpetuity of all present and future rights to this
+ * software under copyright law.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+ * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
  */
 
 #include "thread.h"

test/fops/t.c

@@ -1,8 +1,28 @@
 /*-
- * Copyright (c) 2008-2012 WiredTiger, Inc.
- *	All rights reserved.
+ * Public Domain 2008-2012 WiredTiger, Inc.
  *
- * See the file LICENSE for redistribution information.
+ * This is free and unencumbered software released into the public domain.
+ *
+ * Anyone is free to copy, modify, publish, use, compile, sell, or
+ * distribute this software, either in source code form or as a compiled
+ * binary, for any purpose, commercial or non-commercial, and by any
+ * means.
+ *
+ * In jurisdictions that recognize copyright laws, the author or authors
+ * of this software dedicate any and all copyright interest in the
+ * software to the public domain. We make this dedication for the benefit
+ * of the public at large and to the detriment of our heirs and
+ * successors. We intend this dedication to be an overt act of
+ * relinquishment in perpetuity of all present and future rights to this
+ * software under copyright law.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+ * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
  */
 
 #include "thread.h"

test/fops/thread.h

@@ -1,8 +1,28 @@
 /*-
- * Copyright (c) 2008-2012 WiredTiger, Inc.
- *	All rights reserved.
+ * Public Domain 2008-2012 WiredTiger, Inc.
  *
- * See the file LICENSE for redistribution information.
+ * This is free and unencumbered software released into the public domain.
+ *
+ * Anyone is free to copy, modify, publish, use, compile, sell, or
+ * distribute this software, either in source code form or as a compiled
+ * binary, for any purpose, commercial or non-commercial, and by any
+ * means.
+ *
+ * In jurisdictions that recognize copyright laws, the author or authors
+ * of this software dedicate any and all copyright interest in the
+ * software to the public domain. We make this dedication for the benefit
+ * of the public at large and to the detriment of our heirs and
+ * successors. We intend this dedication to be an overt act of
+ * relinquishment in perpetuity of all present and future rights to this
+ * software under copyright law.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+ * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
  */
 
 #include <sys/types.h>

test/format/bdb.c

@@ -1,8 +1,28 @@
 /*-
- * Copyright (c) 2008-2012 WiredTiger, Inc.
- *	All rights reserved.
+ * Public Domain 2008-2012 WiredTiger, Inc.
  *
- * See the file LICENSE for redistribution information.
+ * This is free and unencumbered software released into the public domain.
+ *
+ * Anyone is free to copy, modify, publish, use, compile, sell, or
+ * distribute this software, either in source code form or as a compiled
+ * binary, for any purpose, commercial or non-commercial, and by any
+ * means.
+ *
+ * In jurisdictions that recognize copyright laws, the author or authors
+ * of this software dedicate any and all copyright interest in the
+ * software to the public domain. We make this dedication for the benefit
+ * of the public at large and to the detriment of our heirs and
+ * successors. We intend this dedication to be an overt act of
+ * relinquishment in perpetuity of all present and future rights to this
+ * software under copyright law.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+ * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
  */
 
 #define	BDB	1			/* Berkeley DB header files */

test/format/config.c

@@ -1,16 +1,36 @@
 /*-
- * Copyright (c) 2008-2012 WiredTiger, Inc.
- *	All rights reserved.
+ * Public Domain 2008-2012 WiredTiger, Inc.
  *
- * See the file LICENSE for redistribution information.
+ * This is free and unencumbered software released into the public domain.
+ *
+ * Anyone is free to copy, modify, publish, use, compile, sell, or
+ * distribute this software, either in source code form or as a compiled
+ * binary, for any purpose, commercial or non-commercial, and by any
+ * means.
+ *
+ * In jurisdictions that recognize copyright laws, the author or authors
+ * of this software dedicate any and all copyright interest in the
+ * software to the public domain. We make this dedication for the benefit
+ * of the public at large and to the detriment of our heirs and
+ * successors. We intend this dedication to be an overt act of
+ * relinquishment in perpetuity of all present and future rights to this
+ * software under copyright law.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+ * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
  */
 
 #include "format.h"
 #include "config.h"
 
-static const char *config_file_type(int);
+static const char *config_file_type(u_int);
 static CONFIG	  *config_find(const char *, size_t);
-static uint32_t	   config_translate(const char *);
+static u_int	   config_translate(const char *);
 
 /*
  * config_setup --
@@ -20,6 +40,7 @@ void
 config_setup(void)
 {
 	CONFIG *cp;
+	const char *cstr;
 
 	/* Clear any temporary values. */
 	config_clear();
@@ -30,7 +51,7 @@ config_setup(void)
 	 * them.
 	 */
 	cp = config_find("data_source", strlen("data_source"));
-	if (!(cp->flags & C_PERM)) {
+	if (!(cp->flags & C_PERM))
 		switch (MMRAND(0, 2)) {
 		case 0:
 			config_single("data_source=file", 0);
@@ -44,7 +65,6 @@ config_setup(void)
 			config_single("data_source=table", 0);
 			break;
 		}
-	}
 
 	cp = config_find("file_type", strlen("file_type"));
 	if (!(cp->flags & C_PERM)) {
@@ -62,8 +82,8 @@ config_setup(void)
 				config_single("file_type=row", 0);
 				break;
 			}
-		}
-	g.type = (int)config_translate(g.c_file_type);
+	}
+	g.type = config_translate(g.c_file_type);
 
 	/*
 	 * If data_source and file_type were both "permanent", we may still
@@ -76,6 +96,48 @@ config_setup(void)
 		exit(EXIT_FAILURE);
 	}
 
+	/*
+	 * Compression: choose something if compression wasn't specified,
+	 * otherwise confirm the appropriate shared library is available.
+	 */
+	cp = config_find("compression", strlen("compression"));
+	if (!(cp->flags & C_PERM)) {
+		cstr = "compression=none";
+		switch (MMRAND(0, 9)) {
+		case 0:					/* 10% */
+			break;
+		case 1: case 2: case 3: case 4:		/* 40% */
+			if (access(BZIP_PATH, R_OK) == 0)
+				cstr = "compression=bzip";
+			break;
+		case 5:					/* 10% */
+#if 0
+			cstr = "compression=ext";
+#endif
+			break;
+		case 6: case 7: case 8: case 9:		/* 40% */
+			if (access(SNAPPY_PATH, R_OK) == 0)
+				cstr = "compression=snappy";
+			break;
+		}
+		config_single(cstr, 0);
+	}
+	g.compression = config_translate(g.c_compression);
+	if (cp->flags & C_PERM) {
+		if (g.compression == COMPRESS_BZIP &&
+		    access(BZIP_PATH, R_OK) != 0) {
+			fprintf(stderr,
+			    "bzip library not found or not readable\n");
+			exit(EXIT_FAILURE);
+		}
+		if (g.compression == COMPRESS_SNAPPY &&
+		    access(SNAPPY_PATH, R_OK) != 0) {
+			fprintf(stderr,
+			    "snappy library not found or not readable\n");
+			exit(EXIT_FAILURE);
+		}
+	}
+
 	/* Build the object name. */
 	if ((g.uri = malloc(
 	    strlen(g.c_data_source) + strlen(WT_NAME) + 2)) == NULL)
@@ -274,7 +336,9 @@ config_single(const char *s, int perm)
 		}
 		else if (strncmp(s, "file_type", strlen("file_type")) == 0)
 			*cp->vstr = strdup(
-			    config_file_type((int)config_translate(ep)));
+			    config_file_type(config_translate(ep)));
+		else if (strncmp(s, "compression", strlen("compression")) == 0)
+			*cp->vstr = strdup(ep);
 		if (*cp->vstr == NULL)
 			syserr("strdup");
 		return;
@@ -299,25 +363,35 @@ config_single(const char *s, int perm)
  * config_translate --
  *	Return an integer value representing the argument.
  */
-static uint32_t
+static u_int
 config_translate(const char *s)
 {
 	/* If it's already a integer value, we're done. */
 	if (isdigit(s[0]))
-		return (uint32_t)atoi(s);
+		return ((u_int)atoi(s));
 
-	/* Currently, all we translate are the file type names. */
+	/* File type names. */
 	if (strcmp(s, "fix") == 0 ||
 	    strcmp(s, "flcs") == 0 ||		/* Deprecated */
 	    strcmp(s, "fixed-length column-store") == 0)
-		return ((uint32_t)FIX);
+		return (FIX);
 	if (strcmp(s, "var") == 0 ||
 	    strcmp(s, "vlcs") == 0 ||		/* Deprecated */
 	    strcmp(s, "variable-length column-store") == 0)
-		return ((uint32_t)VAR);
+		return (VAR);
 	if (strcmp(s, "row") == 0 ||
 	    strcmp(s, "row-store") == 0)
-		return ((uint32_t)ROW);
+		return (ROW);
+
+	/* Compression type names. */
+	if (strcmp(s, "none") == 0)
+		return (COMPRESS_NONE);
+	if (strcmp(s, "bzip") == 0)
+		return (COMPRESS_BZIP);
+	if (strcmp(s, "ext") == 0)
+		return (COMPRESS_EXT);
+	if (strcmp(s, "snappy") == 0)
+		return (COMPRESS_SNAPPY);
 
 	fprintf(stderr, "%s: %s: unknown configuration value\n", g.progname, s);
 	exit(EXIT_FAILURE);
@@ -347,7 +421,7 @@ config_find(const char *s, size_t len)
  *	Return the file type as a string.
  */
 static const char *
-config_file_type(int type)
+config_file_type(u_int type)
 {
 	switch (type) {
 	case FIX:

test/format/config.h

@@ -1,8 +1,28 @@
 /*-
- * Copyright (c) 2008-2012 WiredTiger, Inc.
- *	All rights reserved.
+ * Public Domain 2008-2012 WiredTiger, Inc.
  *
- * See the file LICENSE for redistribution information.
+ * This is free and unencumbered software released into the public domain.
+ *
+ * Anyone is free to copy, modify, publish, use, compile, sell, or
+ * distribute this software, either in source code form or as a compiled
+ * binary, for any purpose, commercial or non-commercial, and by any
+ * means.
+ *
+ * In jurisdictions that recognize copyright laws, the author or authors
+ * of this software dedicate any and all copyright interest in the
+ * software to the public domain. We make this dedication for the benefit
+ * of the public at large and to the detriment of our heirs and
+ * successors. We intend this dedication to be an overt act of
+ * relinquishment in perpetuity of all present and future rights to this
+ * software under copyright law.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+ * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
  */
 
 /*
@@ -39,7 +59,7 @@ typedef struct {
 
 	uint32_t	min;			/* Minimum value */
 	uint32_t	max;			/* Maximum value */
-	uint32_t	*v;			/* Value for this run */
+	u_int		*v;			/* Value for this run */
 	char		**vstr;			/* Value for string options */
 } CONFIG;
 
@@ -54,14 +74,14 @@ static CONFIG c[] = {
 	  "number of bits for fixed-length column-store files",
 	  C_FIX, 0, 1, 8, &g.c_bitcnt, NULL },
 
-	{ "bzip",
-	  "if blocks are BZIP2 encoded",		/* 80% */
-	  0, C_BOOL, 80, 0, &g.c_bzip, NULL },
-
 	{ "cache",
 	  "size of the cache in MB",
 	  0, 0, 1, 100, &g.c_cache, NULL },
 
+	{ "compression",
+	  "type of compression (none | bzip | ext | snappy)",
+	  0, C_IGNORE|C_STRING, 1, 4, NULL, &g.c_compression },
+
 	{ "data_source",
 	  "type of data source to create (file | table | lsm)",
 	  0, C_IGNORE | C_STRING, 0, 0, NULL, &g.c_data_source },

test/format/format.h

@@ -1,12 +1,33 @@
 /*-
- * Copyright (c) 2008-2012 WiredTiger, Inc.
- *	All rights reserved.
+ * Public Domain 2008-2012 WiredTiger, Inc.
  *
- * See the file LICENSE for redistribution information.
+ * This is free and unencumbered software released into the public domain.
+ *
+ * Anyone is free to copy, modify, publish, use, compile, sell, or
+ * distribute this software, either in source code form or as a compiled
+ * binary, for any purpose, commercial or non-commercial, and by any
+ * means.
+ *
+ * In jurisdictions that recognize copyright laws, the author or authors
+ * of this software dedicate any and all copyright interest in the
+ * software to the public domain. We make this dedication for the benefit
+ * of the public at large and to the detriment of our heirs and
+ * successors. We intend this dedication to be an overt act of
+ * relinquishment in perpetuity of all present and future rights to this
+ * software under copyright law.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+ * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
  */
 
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <sys/time.h>
 
 #include <assert.h>
 #include <ctype.h>
@@ -26,6 +47,14 @@
 #include <wiredtiger.h>
 #endif
 
+#define	EXTPATH	"../../ext/"			/* Extensions path */
+#define	BZIP_PATH							\
+	EXTPATH "compressors/bzip2/.libs/libwiredtiger_bzip2.so"
+#define	SNAPPY_PATH							\
+	EXTPATH "compressors/snappy/.libs/libwiredtiger_snappy.so"
+#define	REVERSE_PATH							\
+	EXTPATH "collators/reverse/.libs/libwiredtiger_reverse_collator.so"
+
 #define	M(v)		((v) * 1000000)		/* Million */
 #define	UNUSED(var)	(void)(var)		/* Quiet unused var warnings */
 
@@ -59,37 +88,44 @@ typedef struct {
 	int replay;				/* Replaying a run. */
 	int track;				/* Track progress */
 
+	char *uri;				/* Object name */
+
 #define	FIX		1			/* File types */
 #define	ROW		2
 #define	VAR		3
-	int   type;				/* File type */
-	char *uri;				/* Object name */
+	u_int   type;				/* File type */
+
+#define	COMPRESS_NONE	1
+#define	COMPRESS_BZIP	2
+#define	COMPRESS_EXT	3
+#define	COMPRESS_SNAPPY	4
+	u_int compression;			/* Compression type */
 
 	char *config_open;			/* Command-line configuration */
 
-	uint32_t c_bitcnt;			/* Config values */
-	uint32_t c_bzip;
-	uint32_t c_cache;
-	char    *c_data_source;
-	uint32_t c_delete_pct;
-	uint32_t c_dictionary;
-	char    *c_file_type;
-	uint32_t c_huffman_key;
-	uint32_t c_huffman_value;
-	uint32_t c_insert_pct;
-	uint32_t c_intl_page_max;
-	uint32_t c_key_max;
-	uint32_t c_key_min;
-	uint32_t c_leaf_page_max;
-	uint32_t c_ops;
-	uint32_t c_repeat_data_pct;
-	uint32_t c_reverse;
-	uint32_t c_rows;
-	uint32_t c_runs;
-	uint32_t c_threads;
-	uint32_t c_value_max;
-	uint32_t c_value_min;
-	uint32_t c_write_pct;
+	u_int c_bitcnt;				/* Config values */
+	u_int c_cache;
+	char *c_compression;
+	char *c_data_source;
+	u_int c_delete_pct;
+	u_int c_dictionary;
+	char *c_file_type;
+	u_int c_huffman_key;
+	u_int c_huffman_value;
+	u_int c_insert_pct;
+	u_int c_intl_page_max;
+	u_int c_key_max;
+	u_int c_key_min;
+	u_int c_leaf_page_max;
+	u_int c_ops;
+	u_int c_repeat_data_pct;
+	u_int c_reverse;
+	u_int c_rows;
+	u_int c_runs;
+	u_int c_threads;
+	u_int c_value_max;
+	u_int c_value_min;
+	u_int c_write_pct;
 
 	uint32_t key_cnt;			/* Keys loaded so far */
 	uint32_t rows;				/* Total rows */

test/format/s_dumpcmp.sh

@@ -32,13 +32,16 @@ if test $# -ne 0; then
 	exit 1
 fi
 
-revext="$top/ext/collators/reverse/.libs/reverse_collator.so"
-bzext="$top/ext/compressors/bzip2_compress/.libs/bzip2_compress.so"
-if test -e $bzext ; then
-        ext="\"$revext\",\"$bzext\""
-else
-        ext="\"$revext\""
+ext="\"$top/ext/collators/reverse/.libs/libwiredtiger_reverse_collator.so\""
+bz_ext="$top/ext/compressors/bzip2/.libs/libwiredtiger_bzip2.so"
+if test -e $bz_ext ; then
+        ext="$ext,\"$bz_ext\""
 fi
+sn_ext="$top/ext/compressors/snappy/.libs/libwiredtiger_snappy.so"
+if test -e $sn_ext ; then
+        ext="$ext,\"$sn_ext\""
+fi
+
 config='extensions=['$ext']'
 
 $top/wt -h RUNDIR -C "$config" dump $wt_name |

test/format/t.c

@@ -1,8 +1,28 @@
 /*-
- * Copyright (c) 2008-2012 WiredTiger, Inc.
- *	All rights reserved.
+ * Public Domain 2008-2012 WiredTiger, Inc.
  *
- * See the file LICENSE for redistribution information.
+ * This is free and unencumbered software released into the public domain.
+ *
+ * Anyone is free to copy, modify, publish, use, compile, sell, or
+ * distribute this software, either in source code form or as a compiled
+ * binary, for any purpose, commercial or non-commercial, and by any
+ * means.
+ *
+ * In jurisdictions that recognize copyright laws, the author or authors
+ * of this software dedicate any and all copyright interest in the
+ * software to the public domain. We make this dedication for the benefit
+ * of the public at large and to the detriment of our heirs and
+ * successors. We intend this dedication to be an overt act of
+ * relinquishment in perpetuity of all present and future rights to this
+ * software under copyright law.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+ * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
  */
 
 #include "format.h"

test/format/util.c

@@ -1,8 +1,28 @@
 /*-
- * Copyright (c) 2008-2012 WiredTiger, Inc.
- *	All rights reserved.
+ * Public Domain 2008-2012 WiredTiger, Inc.
  *
- * See the file LICENSE for redistribution information.
+ * This is free and unencumbered software released into the public domain.
+ *
+ * Anyone is free to copy, modify, publish, use, compile, sell, or
+ * distribute this software, either in source code form or as a compiled
+ * binary, for any purpose, commercial or non-commercial, and by any
+ * means.
+ *
+ * In jurisdictions that recognize copyright laws, the author or authors
+ * of this software dedicate any and all copyright interest in the
+ * software to the public domain. We make this dedication for the benefit
+ * of the public at large and to the detriment of our heirs and
+ * successors. We intend this dedication to be an overt act of
+ * relinquishment in perpetuity of all present and future rights to this
+ * software under copyright law.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+ * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
  */
 
 #include "format.h"
@@ -183,9 +203,17 @@ track(const char *tag, uint64_t cnt, TINFO *tinfo)
 uint32_t
 wts_rand(void)
 {
+	struct timeval t;
 	char buf[64];
 	uint32_t r;
 
+	/* If it's not a replay, seed the random number generator. */
+	if (!g.replay) {
+		if (gettimeofday(&t, NULL) != 0)
+			die(errno, "gettimeofday");
+		srand((u_int)(0xdeadbeef ^ (u_int)t.tv_usec));
+	}
+
 	/* If we're threaded, it's not repeatable, ignore the log. */
 	if (!SINGLETHREADED)
 		return ((uint32_t)rand());
@@ -202,10 +230,8 @@ wts_rand(void)
 		if ((g.rand_log =
 		    fopen("RUNDIR/rand", g.replay ? "r" : "w")) == NULL)
 			die(errno, "fopen: RUNDIR/rand");
-		if (!g.replay) {
-			srand((u_int)(0xdeadbeef ^ (u_int)time(NULL)));
+		if (!g.replay)
 			(void)setvbuf(g.rand_log, NULL, _IOLBF, 0);
-		}
 	}
 	if (g.replay) {
 		if (fgets(buf, sizeof(buf), g.rand_log) == NULL) {

test/format/wts.c

@@ -1,8 +1,28 @@
 /*-
- * Copyright (c) 2008-2012 WiredTiger, Inc.
- *	All rights reserved.
+ * Public Domain 2008-2012 WiredTiger, Inc.
  *
- * See the file LICENSE for redistribution information.
+ * This is free and unencumbered software released into the public domain.
+ *
+ * Anyone is free to copy, modify, publish, use, compile, sell, or
+ * distribute this software, either in source code form or as a compiled
+ * binary, for any purpose, commercial or non-commercial, and by any
+ * means.
+ *
+ * In jurisdictions that recognize copyright laws, the author or authors
+ * of this software dedicate any and all copyright interest in the
+ * software to the public domain. We make this dedication for the benefit
+ * of the public at large and to the detriment of our heirs and
+ * successors. We intend this dedication to be an overt act of
+ * relinquishment in perpetuity of all present and future rights to this
+ * software under copyright law.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+ * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
  */
 
 #include "format.h"
@@ -45,44 +65,45 @@ wts_open(void)
 	WT_SESSION *session;
 	uint32_t maxintlpage, maxintlitem, maxleafpage, maxleafitem;
 	int ret;
-	const char *ext1, *ext2;
-	char config[512], *end, *p;
-
-	/* If the bzip2 compression module has been built, use it. */
-#define	EXTPATH	"../../ext"
-	ext1 = EXTPATH "compressors/bzip2_compress/.libs/bzip2_compress.so";
-	if (access(ext1, R_OK) != 0) {
-		ext1 = "";
-		g.c_bzip = 0;
-	}
-	ext2 = EXTPATH "/collators/reverse/.libs/reverse_collator.so";
+	char config[1024], *end, *p;
 
 	/*
-	 * Open configuration -- put command line configuration options at the
-	 * end so they can override "standard" configuration.
+	 * Open configuration.
+	 *
+	 * Put command line configuration options at the end so they override
+	 * the standard configuration.
 	 */
 	snprintf(config, sizeof(config),
 	    "create,error_prefix=\"%s\",cache_size=%" PRIu32 "MB,sync=false,"
-	    "extensions=[\"%s\",\"%s\"],%s",
-	    g.progname, g.c_cache, ext1, ext2,
+	    "extensions=[\"%s\",\"%s\", \"%s\"],%s",
+	    g.progname, g.c_cache,
+	    access(BZIP_PATH, R_OK) == 0 ? BZIP_PATH : "",
+	    access(SNAPPY_PATH, R_OK) == 0 ? SNAPPY_PATH : "",
+	    REVERSE_PATH,
 	    g.config_open == NULL ? "" : g.config_open);
 
 	if ((ret =
 	    wiredtiger_open("RUNDIR", &event_handler, config, &conn)) != 0)
 		die(ret, "wiredtiger_open");
+	g.wts_conn = conn;
 
 	if ((ret = conn->open_session(conn, NULL, NULL, &session)) != 0)
 		die(ret, "connection.open_session");
 
+	/*
+	 * Create the object.
+	 *
+	 * Make sure at least 2 internal page per thread can fit in cache.
+	 */
 	maxintlpage = 1U << g.c_intl_page_max;
-	/* Make sure at least 2 internal page per thread can fit in cache. */
 	while (2 * g.c_threads * maxintlpage > g.c_cache << 20)
 		maxintlpage >>= 1;
 	maxintlitem = MMRAND(maxintlpage / 50, maxintlpage / 40);
 	if (maxintlitem < 40)
 		maxintlitem = 40;
-	maxleafpage = 1U << g.c_leaf_page_max;
+
 	/* Make sure at least one leaf page per thread can fit in cache. */
+	maxleafpage = 1U << g.c_leaf_page_max;
 	while (g.c_threads * (maxintlpage + maxleafpage) > g.c_cache << 20)
 		maxleafpage >>= 1;
 	maxleafitem = MMRAND(maxleafpage / 50, maxleafpage / 40);
@@ -98,10 +119,6 @@ wts_open(void)
 	    (g.type == ROW) ? "u" : "r",
 	    maxintlpage, maxintlitem, maxleafpage, maxleafitem);
 
-	if (g.c_bzip)
-		p += snprintf(p, (size_t)(end - p),
-		    ",block_compressor=\"bzip2_compress\"");
-
 	switch (g.type) {
 	case FIX:
 		p += snprintf(p, (size_t)(end - p),
@@ -125,13 +142,27 @@ wts_open(void)
 		break;
 	}
 
+	/* Configure compression. */
+	switch (g.compression) {
+	case COMPRESS_NONE:
+		break;
+	case COMPRESS_BZIP:
+		p += snprintf(p, (size_t)(end - p),
+		    ",block_compressor=\"bzip2\"");
+		break;
+	case COMPRESS_EXT:
+		break;
+	case COMPRESS_SNAPPY:
+		p += snprintf(p, (size_t)(end - p),
+		    ",block_compressor=\"snappy\"");
+		break;
+	}
+
 	if ((ret = session->create(session, g.uri, config)) != 0)
 		die(ret, "session.create: %s", g.uri);
 
 	if ((ret = session->close(session, NULL)) != 0)
 		die(ret, "session.close");
-
-	g.wts_conn = conn;
 }
 
 void

test/format/wts_bulk.c

@@ -1,8 +1,28 @@
 /*-
- * Copyright (c) 2008-2012 WiredTiger, Inc.
- *	All rights reserved.
+ * Public Domain 2008-2012 WiredTiger, Inc.
  *
- * See the file LICENSE for redistribution information.
+ * This is free and unencumbered software released into the public domain.
+ *
+ * Anyone is free to copy, modify, publish, use, compile, sell, or
+ * distribute this software, either in source code form or as a compiled
+ * binary, for any purpose, commercial or non-commercial, and by any
+ * means.
+ *
+ * In jurisdictions that recognize copyright laws, the author or authors
+ * of this software dedicate any and all copyright interest in the
+ * software to the public domain. We make this dedication for the benefit
+ * of the public at large and to the detriment of our heirs and
+ * successors. We intend this dedication to be an overt act of
+ * relinquishment in perpetuity of all present and future rights to this
+ * software under copyright law.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+ * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
  */
 
 #include "format.h"

test/format/wts_ops.c

@@ -1,8 +1,28 @@
 /*-
- * Copyright (c) 2008-2012 WiredTiger, Inc.
- *	All rights reserved.
+ * Public Domain 2008-2012 WiredTiger, Inc.
  *
- * See the file LICENSE for redistribution information.
+ * This is free and unencumbered software released into the public domain.
+ *
+ * Anyone is free to copy, modify, publish, use, compile, sell, or
+ * distribute this software, either in source code form or as a compiled
+ * binary, for any purpose, commercial or non-commercial, and by any
+ * means.
+ *
+ * In jurisdictions that recognize copyright laws, the author or authors
+ * of this software dedicate any and all copyright interest in the
+ * software to the public domain. We make this dedication for the benefit
+ * of the public at large and to the detriment of our heirs and
+ * successors. We intend this dedication to be an overt act of
+ * relinquishment in perpetuity of all present and future rights to this
+ * software under copyright law.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+ * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
  */
 
 #include "format.h"
@@ -120,8 +140,11 @@ ops(void *arg)
 	memset(&value, 0, sizeof(value));
 	val_gen_setup(&valbuf);
 
-	/* Each thread does its share of the total operations. */
-	thread_ops = g.c_ops / g.c_threads;
+	/*
+	 * Each thread does its share of the total operations, and make sure
+	 * that it's not 0 (testing runs: threads might be larger than ops).
+	 */
+	thread_ops = g.c_threads + g.c_ops / g.c_threads;
 
 	/* Pick a period for re-opening the session and cursors. */
 	session = NULL;

test/packing/intpack-test.c

@@ -1,3 +1,30 @@
+/*-
+ * Public Domain 2008-2012 WiredTiger, Inc.
+ *
+ * This is free and unencumbered software released into the public domain.
+ *
+ * Anyone is free to copy, modify, publish, use, compile, sell, or
+ * distribute this software, either in source code form or as a compiled
+ * binary, for any purpose, commercial or non-commercial, and by any
+ * means.
+ *
+ * In jurisdictions that recognize copyright laws, the author or authors
+ * of this software dedicate any and all copyright interest in the
+ * software to the public domain. We make this dedication for the benefit
+ * of the public at large and to the detriment of our heirs and
+ * successors. We intend this dedication to be an overt act of
+ * relinquishment in perpetuity of all present and future rights to this
+ * software under copyright law.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+ * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
 #include <assert.h>
 #include <stdlib.h>
 #include <time.h>

test/packing/intpack-test2.c

@@ -1,3 +1,30 @@
+/*-
+ * Public Domain 2008-2012 WiredTiger, Inc.
+ *
+ * This is free and unencumbered software released into the public domain.
+ *
+ * Anyone is free to copy, modify, publish, use, compile, sell, or
+ * distribute this software, either in source code form or as a compiled
+ * binary, for any purpose, commercial or non-commercial, and by any
+ * means.
+ *
+ * In jurisdictions that recognize copyright laws, the author or authors
+ * of this software dedicate any and all copyright interest in the
+ * software to the public domain. We make this dedication for the benefit
+ * of the public at large and to the detriment of our heirs and
+ * successors. We intend this dedication to be an overt act of
+ * relinquishment in perpetuity of all present and future rights to this
+ * software under copyright law.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+ * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
 #include <assert.h>
 #include <stdlib.h>
 #include <time.h>

test/packing/packing-test.c

@@ -1,3 +1,30 @@
+/*-
+ * Public Domain 2008-2012 WiredTiger, Inc.
+ *
+ * This is free and unencumbered software released into the public domain.
+ *
+ * Anyone is free to copy, modify, publish, use, compile, sell, or
+ * distribute this software, either in source code form or as a compiled
+ * binary, for any purpose, commercial or non-commercial, and by any
+ * means.
+ *
+ * In jurisdictions that recognize copyright laws, the author or authors
+ * of this software dedicate any and all copyright interest in the
+ * software to the public domain. We make this dedication for the benefit
+ * of the public at large and to the detriment of our heirs and
+ * successors. We intend this dedication to be an overt act of
+ * relinquishment in perpetuity of all present and future rights to this
+ * software under copyright law.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+ * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
 #include <assert.h>
 #include <stdlib.h>
 #include <time.h>

test/salvage/salvage.c

@@ -1,8 +1,28 @@
 /*-
- * Copyright (c) 2008-2012 WiredTiger, Inc.
- *	All rights reserved.
+ * Public Domain 2008-2012 WiredTiger, Inc.
  *
- * See the file LICENSE for redistribution information.
+ * This is free and unencumbered software released into the public domain.
+ *
+ * Anyone is free to copy, modify, publish, use, compile, sell, or
+ * distribute this software, either in source code form or as a compiled
+ * binary, for any purpose, commercial or non-commercial, and by any
+ * means.
+ *
+ * In jurisdictions that recognize copyright laws, the author or authors
+ * of this software dedicate any and all copyright interest in the
+ * software to the public domain. We make this dedication for the benefit
+ * of the public at large and to the detriment of our heirs and
+ * successors. We intend this dedication to be an overt act of
+ * relinquishment in perpetuity of all present and future rights to this
+ * software under copyright law.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+ * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
  */
 
 #include "wt_internal.h"

test/suite/test_compress01.py

@@ -97,7 +97,8 @@ class test_compress01_base(wttest.WiredTigerTestCase):
             testdir = os.path.dirname(__file__)
             import run
             extdir = os.path.join(run.wt_builddir, 'ext/compressors')
-            extfile = os.path.join(extdir, name, '.libs', name + '.so')
+            extfile = os.path.join(
+                extdir, name, '.libs', 'libwiredtiger_' + name + '.so')
             if not os.path.exists(extfile):
                 self.skipTest('Extension "' + extfile + '" not built')
             return 'extensions=["' + extfile + '"]'
@@ -130,15 +131,15 @@ class compress01_tests(object):
 
 class test_compress01_1_nop(test_compress01_base, compress01_tests):
     def __init__(self, testname):
-        test_compress01_base.__init__(self, testname, 'nop_compress', 'nop')
+        test_compress01_base.__init__(self, testname, 'nop', 'nop')
 
 class test_compress01_2_bz(test_compress01_base, compress01_tests):
     def __init__(self, testname):
-        test_compress01_base.__init__(self, testname, 'bzip2_compress', 'bz')
+        test_compress01_base.__init__(self, testname, 'bzip2', 'bz')
 
 class test_compress01_3_sn(test_compress01_base, compress01_tests):
     def __init__(self, testname):
-        test_compress01_base.__init__(self, testname, 'snappy_compress', 'sn')
+        test_compress01_base.__init__(self, testname, 'snappy', 'sn')
 
 
 if __name__ == '__main__':

test/thread/file.c

@@ -1,8 +1,28 @@
 /*-
- * Copyright (c) 2008-2012 WiredTiger, Inc.
- *	All rights reserved.
+ * Public Domain 2008-2012 WiredTiger, Inc.
  *
- * See the file LICENSE for redistribution information.
+ * This is free and unencumbered software released into the public domain.
+ *
+ * Anyone is free to copy, modify, publish, use, compile, sell, or
+ * distribute this software, either in source code form or as a compiled
+ * binary, for any purpose, commercial or non-commercial, and by any
+ * means.
+ *
+ * In jurisdictions that recognize copyright laws, the author or authors
+ * of this software dedicate any and all copyright interest in the
+ * software to the public domain. We make this dedication for the benefit
+ * of the public at large and to the detriment of our heirs and
+ * successors. We intend this dedication to be an overt act of
+ * relinquishment in perpetuity of all present and future rights to this
+ * software under copyright law.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+ * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
  */
 
 #include "thread.h"

test/thread/rw.c

@@ -1,8 +1,28 @@
 /*-
- * Copyright (c) 2008-2012 WiredTiger, Inc.
- *	All rights reserved.
+ * Public Domain 2008-2012 WiredTiger, Inc.
  *
- * See the file LICENSE for redistribution information.
+ * This is free and unencumbered software released into the public domain.
+ *
+ * Anyone is free to copy, modify, publish, use, compile, sell, or
+ * distribute this software, either in source code form or as a compiled
+ * binary, for any purpose, commercial or non-commercial, and by any
+ * means.
+ *
+ * In jurisdictions that recognize copyright laws, the author or authors
+ * of this software dedicate any and all copyright interest in the
+ * software to the public domain. We make this dedication for the benefit
+ * of the public at large and to the detriment of our heirs and
+ * successors. We intend this dedication to be an overt act of
+ * relinquishment in perpetuity of all present and future rights to this
+ * software under copyright law.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+ * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
  */
 
 #include "thread.h"

test/thread/stats.c

@@ -1,8 +1,28 @@
 /*-
- * Copyright (c) 2008-2012 WiredTiger, Inc.
- *	All rights reserved.
+ * Public Domain 2008-2012 WiredTiger, Inc.
  *
- * See the file LICENSE for redistribution information.
+ * This is free and unencumbered software released into the public domain.
+ *
+ * Anyone is free to copy, modify, publish, use, compile, sell, or
+ * distribute this software, either in source code form or as a compiled
+ * binary, for any purpose, commercial or non-commercial, and by any
+ * means.
+ *
+ * In jurisdictions that recognize copyright laws, the author or authors
+ * of this software dedicate any and all copyright interest in the
+ * software to the public domain. We make this dedication for the benefit
+ * of the public at large and to the detriment of our heirs and
+ * successors. We intend this dedication to be an overt act of
+ * relinquishment in perpetuity of all present and future rights to this
+ * software under copyright law.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+ * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
  */
 
 #include "thread.h"

test/thread/t.c

@@ -1,8 +1,28 @@
 /*-
- * Copyright (c) 2008-2012 WiredTiger, Inc.
- *	All rights reserved.
+ * Public Domain 2008-2012 WiredTiger, Inc.
  *
- * See the file LICENSE for redistribution information.
+ * This is free and unencumbered software released into the public domain.
+ *
+ * Anyone is free to copy, modify, publish, use, compile, sell, or
+ * distribute this software, either in source code form or as a compiled
+ * binary, for any purpose, commercial or non-commercial, and by any
+ * means.
+ *
+ * In jurisdictions that recognize copyright laws, the author or authors
+ * of this software dedicate any and all copyright interest in the
+ * software to the public domain. We make this dedication for the benefit
+ * of the public at large and to the detriment of our heirs and
+ * successors. We intend this dedication to be an overt act of
+ * relinquishment in perpetuity of all present and future rights to this
+ * software under copyright law.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+ * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
  */
 
 #include "thread.h"

test/thread/thread.h

@@ -1,8 +1,28 @@
 /*-
- * Copyright (c) 2008-2012 WiredTiger, Inc.
- *	All rights reserved.
+ * Public Domain 2008-2012 WiredTiger, Inc.
  *
- * See the file LICENSE for redistribution information.
+ * This is free and unencumbered software released into the public domain.
+ *
+ * Anyone is free to copy, modify, publish, use, compile, sell, or
+ * distribute this software, either in source code form or as a compiled
+ * binary, for any purpose, commercial or non-commercial, and by any
+ * means.
+ *
+ * In jurisdictions that recognize copyright laws, the author or authors
+ * of this software dedicate any and all copyright interest in the
+ * software to the public domain. We make this dedication for the benefit
+ * of the public at large and to the detriment of our heirs and
+ * successors. We intend this dedication to be an overt act of
+ * relinquishment in perpetuity of all present and future rights to this
+ * software under copyright law.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+ * IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
  */
 
 #include <sys/types.h>