Merge remote-tracking branch 'mreitz/tags/pull-block-for-kevin-2015-09-04' into queue-block

Block patches from 2015-08-24 until 2015-09-04.

# gpg: Signature made Fri Sep  4 21:02:10 2015 CEST using RSA key ID E838ACAD
# gpg: Good signature from "Max Reitz <mreitz@redhat.com>"

* mreitz/tags/pull-block-for-kevin-2015-09-04:
  quorum: validate vote threshold against num_children even if read-pattern is fifo
  qcow2: reorder fields in Qcow2CachedTable to reduce padding
  docs: document how to configure the qcow2 L2/refcount caches
  qcow2: add option to clean unused cache entries after some time
  qcow2: mark the memory as no longer needed after qcow2_cache_empty()

Signed-off-by: Kevin Wolf <kwolf@redhat.com>

6 files changed, 306 insertions, 8 deletions

diff --git a/block/qcow2-cache.c b/block/qcow2-cache.c
index 53b8afc3d3..046f5b8e48 100644
--- a/block/qcow2-cache.c
+++ b/block/qcow2-cache.c
@@ -22,16 +22,24 @@
  * THE SOFTWARE.
  */
 
+/* Needed for CONFIG_MADVISE */
+#include "config-host.h"
+
+#if defined(CONFIG_MADVISE) || defined(CONFIG_POSIX_MADVISE)
+#include <sys/mman.h>
+#endif
+
 #include "block/block_int.h"
 #include "qemu-common.h"
+#include "qemu/osdep.h"
 #include "qcow2.h"
 #include "trace.h"
 
 typedef struct Qcow2CachedTable {
     int64_t  offset;
-    bool     dirty;
     uint64_t lru_counter;
     int      ref;
+    bool     dirty;
 } Qcow2CachedTable;
 
 struct Qcow2Cache {
@@ -41,6 +49,7 @@ struct Qcow2Cache {
     bool                    depends_on_flush;
     void                   *table_array;
     uint64_t                lru_counter;
+    uint64_t                cache_clean_lru_counter;
 };
 
 static inline void *qcow2_cache_get_table_addr(BlockDriverState *bs,
@@ -60,6 +69,56 @@ static inline int qcow2_cache_get_table_idx(BlockDriverState *bs,
     return idx;
 }
 
+static void qcow2_cache_table_release(BlockDriverState *bs, Qcow2Cache *c,
+                                      int i, int num_tables)
+{
+#if QEMU_MADV_DONTNEED != QEMU_MADV_INVALID
+    BDRVQcowState *s = bs->opaque;
+    void *t = qcow2_cache_get_table_addr(bs, c, i);
+    int align = getpagesize();
+    size_t mem_size = (size_t) s->cluster_size * num_tables;
+    size_t offset = QEMU_ALIGN_UP((uintptr_t) t, align) - (uintptr_t) t;
+    size_t length = QEMU_ALIGN_DOWN(mem_size - offset, align);
+    if (length > 0) {
+        qemu_madvise((uint8_t *) t + offset, length, QEMU_MADV_DONTNEED);
+    }
+#endif
+}
+
+static inline bool can_clean_entry(Qcow2Cache *c, int i)
+{
+    Qcow2CachedTable *t = &c->entries[i];
+    return t->ref == 0 && !t->dirty && t->offset != 0 &&
+        t->lru_counter <= c->cache_clean_lru_counter;
+}
+
+void qcow2_cache_clean_unused(BlockDriverState *bs, Qcow2Cache *c)
+{
+    int i = 0;
+    while (i < c->size) {
+        int to_clean = 0;
+
+        /* Skip the entries that we don't need to clean */
+        while (i < c->size && !can_clean_entry(c, i)) {
+            i++;
+        }
+
+        /* And count how many we can clean in a row */
+        while (i < c->size && can_clean_entry(c, i)) {
+            c->entries[i].offset = 0;
+            c->entries[i].lru_counter = 0;
+            i++;
+            to_clean++;
+        }
+
+        if (to_clean > 0) {
+            qcow2_cache_table_release(bs, c, i - to_clean, to_clean);
+        }
+    }
+
+    c->cache_clean_lru_counter = c->lru_counter;
+}
+
 Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables)
 {
     BDRVQcowState *s = bs->opaque;
@@ -237,6 +296,8 @@ int qcow2_cache_empty(BlockDriverState *bs, Qcow2Cache *c)
         c->entries[i].lru_counter = 0;
     }
 
+    qcow2_cache_table_release(bs, c, 0, c->size);
+
     c->lru_counter = 0;
 
     return 0;
diff --git a/block/qcow2.c b/block/qcow2.c
index 76c331b387..ea34ae2da5 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -467,6 +467,11 @@ static QemuOptsList qcow2_runtime_opts = {
             .type = QEMU_OPT_SIZE,
             .help = "Maximum refcount block cache size",
         },
+        {
+            .name = QCOW2_OPT_CACHE_CLEAN_INTERVAL,
+            .type = QEMU_OPT_NUMBER,
+            .help = "Clean unused cache entries after this time (in seconds)",
+        },
         { /* end of list */ }
     },
 };
@@ -482,6 +487,49 @@ static const char *overlap_bool_option_names[QCOW2_OL_MAX_BITNR] = {
     [QCOW2_OL_INACTIVE_L2_BITNR]    = QCOW2_OPT_OVERLAP_INACTIVE_L2,
 };
 
+static void cache_clean_timer_cb(void *opaque)
+{
+    BlockDriverState *bs = opaque;
+    BDRVQcowState *s = bs->opaque;
+    qcow2_cache_clean_unused(bs, s->l2_table_cache);
+    qcow2_cache_clean_unused(bs, s->refcount_block_cache);
+    timer_mod(s->cache_clean_timer, qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) +
+              (int64_t) s->cache_clean_interval * 1000);
+}
+
+static void cache_clean_timer_init(BlockDriverState *bs, AioContext *context)
+{
+    BDRVQcowState *s = bs->opaque;
+    if (s->cache_clean_interval > 0) {
+        s->cache_clean_timer = aio_timer_new(context, QEMU_CLOCK_VIRTUAL,
+                                             SCALE_MS, cache_clean_timer_cb,
+                                             bs);
+        timer_mod(s->cache_clean_timer, qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) +
+                  (int64_t) s->cache_clean_interval * 1000);
+    }
+}
+
+static void cache_clean_timer_del(BlockDriverState *bs)
+{
+    BDRVQcowState *s = bs->opaque;
+    if (s->cache_clean_timer) {
+        timer_del(s->cache_clean_timer);
+        timer_free(s->cache_clean_timer);
+        s->cache_clean_timer = NULL;
+    }
+}
+
+static void qcow2_detach_aio_context(BlockDriverState *bs)
+{
+    cache_clean_timer_del(bs);
+}
+
+static void qcow2_attach_aio_context(BlockDriverState *bs,
+                                     AioContext *new_context)
+{
+    cache_clean_timer_init(bs, new_context);
+}
+
 static void read_cache_sizes(BlockDriverState *bs, QemuOpts *opts,
                              uint64_t *l2_cache_size,
                              uint64_t *refcount_cache_size, Error **errp)
@@ -555,6 +603,7 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
     const char *opt_overlap_check, *opt_overlap_check_template;
     int overlap_check_template = 0;
     uint64_t l2_cache_size, refcount_cache_size;
+    uint64_t cache_clean_interval;
 
     ret = bdrv_pread(bs->file, 0, &header, sizeof(header));
     if (ret < 0) {
@@ -848,6 +897,16 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
         goto fail;
     }
 
+    cache_clean_interval =
+        qemu_opt_get_number(opts, QCOW2_OPT_CACHE_CLEAN_INTERVAL, 0);
+    if (cache_clean_interval > UINT_MAX) {
+        error_setg(errp, "Cache clean interval too big");
+        ret = -EINVAL;
+        goto fail;
+    }
+    s->cache_clean_interval = cache_clean_interval;
+    cache_clean_timer_init(bs, bdrv_get_aio_context(bs));
+
     s->cluster_cache = g_malloc(s->cluster_size);
     /* one more sector for decompressed data alignment */
     s->cluster_data = qemu_try_blockalign(bs->file, QCOW_MAX_CRYPT_CLUSTERS
@@ -1013,6 +1072,7 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
     qemu_vfree(s->l1_table);
     /* else pre-write overlap checks in cache_destroy may crash */
     s->l1_table = NULL;
+    cache_clean_timer_del(bs);
     if (s->l2_table_cache) {
         qcow2_cache_destroy(bs, s->l2_table_cache);
     }
@@ -1471,6 +1531,7 @@ static void qcow2_close(BlockDriverState *bs)
         }
     }
 
+    cache_clean_timer_del(bs);
     qcow2_cache_destroy(bs, s->l2_table_cache);
     qcow2_cache_destroy(bs, s->refcount_block_cache);
 
@@ -2977,6 +3038,9 @@ BlockDriver bdrv_qcow2 = {
     .create_opts         = &qcow2_create_opts,
     .bdrv_check          = qcow2_check,
     .bdrv_amend_options  = qcow2_amend_options,
+
+    .bdrv_detach_aio_context  = qcow2_detach_aio_context,
+    .bdrv_attach_aio_context  = qcow2_attach_aio_context,
 };
 
 static void bdrv_qcow2_init(void)
diff --git a/block/qcow2.h b/block/qcow2.h
index 72e132838a..71dafd6dc9 100644
--- a/block/qcow2.h
+++ b/block/qcow2.h
@@ -96,6 +96,7 @@
 #define QCOW2_OPT_CACHE_SIZE "cache-size"
 #define QCOW2_OPT_L2_CACHE_SIZE "l2-cache-size"
 #define QCOW2_OPT_REFCOUNT_CACHE_SIZE "refcount-cache-size"
+#define QCOW2_OPT_CACHE_CLEAN_INTERVAL "cache-clean-interval"
 
 typedef struct QCowHeader {
     uint32_t magic;
@@ -239,6 +240,8 @@ typedef struct BDRVQcowState {
 
     Qcow2Cache* l2_table_cache;
     Qcow2Cache* refcount_block_cache;
+    QEMUTimer *cache_clean_timer;
+    unsigned cache_clean_interval;
 
     uint8_t *cluster_cache;
     uint8_t *cluster_data;
@@ -581,6 +584,7 @@ int qcow2_cache_set_dependency(BlockDriverState *bs, Qcow2Cache *c,
     Qcow2Cache *dependency);
 void qcow2_cache_depends_on_flush(Qcow2Cache *c);
 
+void qcow2_cache_clean_unused(BlockDriverState *bs, Qcow2Cache *c);
 int qcow2_cache_empty(BlockDriverState *bs, Qcow2Cache *c);
 
 int qcow2_cache_get(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset,
diff --git a/block/quorum.c b/block/quorum.c
index 2f6c45f760..8fe53b4272 100644
--- a/block/quorum.c
+++ b/block/quorum.c
@@ -889,6 +889,12 @@ static int quorum_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     s->threshold = qemu_opt_get_number(opts, QUORUM_OPT_VOTE_THRESHOLD, 0);
+    /* and validate it against s->num_children */
+    ret = quorum_valid_threshold(s->threshold, s->num_children, &local_err);
+    if (ret < 0) {
+        goto exit;
+    }
+
     ret = parse_read_pattern(qemu_opt_get(opts, QUORUM_OPT_READ_PATTERN));
     if (ret < 0) {
         error_setg(&local_err, "Please set read-pattern as fifo or quorum");
@@ -897,12 +903,6 @@ static int quorum_open(BlockDriverState *bs, QDict *options, int flags,
     s->read_pattern = ret;
 
     if (s->read_pattern == QUORUM_READ_PATTERN_QUORUM) {
-        /* and validate it against s->num_children */
-        ret = quorum_valid_threshold(s->threshold, s->num_children, &local_err);
-        if (ret < 0) {
-            goto exit;
-        }
-
         /* is the driver in blkverify mode */
         if (qemu_opt_get_bool(opts, QUORUM_OPT_BLKVERIFY, false) &&
             s->num_children == 2 && s->threshold == 2) {
diff --git a/docs/qcow2-cache.txt b/docs/qcow2-cache.txt
new file mode 100644
index 0000000000..5bb06072d3
--- /dev/null
+++ b/docs/qcow2-cache.txt
@@ -0,0 +1,164 @@
+qcow2 L2/refcount cache configuration
+=====================================
+Copyright (C) 2015 Igalia, S.L.
+Author: Alberto Garcia <berto@igalia.com>
+
+This work is licensed under the terms of the GNU GPL, version 2 or
+later. See the COPYING file in the top-level directory.
+
+Introduction
+------------
+The QEMU qcow2 driver has two caches that can improve the I/O
+performance significantly. However, setting the right cache sizes is
+not a straightforward operation.
+
+This document attempts to give an overview of the L2 and refcount
+caches, and how to configure them.
+
+Please refer to the docs/specs/qcow2.txt file for an in-depth
+technical description of the qcow2 file format.
+
+
+Clusters
+--------
+A qcow2 file is organized in units of constant size called clusters.
+
+The cluster size is configurable, but it must be a power of two and
+its value 512 bytes or higher. QEMU currently defaults to 64 KB
+clusters, and it does not support sizes larger than 2MB.
+
+The 'qemu-img create' command supports specifying the size using the
+cluster_size option:
+
+   qemu-img create -f qcow2 -o cluster_size=128K hd.qcow2 4G
+
+
+The L2 tables
+-------------
+The qcow2 format uses a two-level structure to map the virtual disk as
+seen by the guest to the disk image in the host. These structures are
+called the L1 and L2 tables.
+
+There is one single L1 table per disk image. The table is small and is
+always kept in memory.
+
+There can be many L2 tables, depending on how much space has been
+allocated in the image. Each table is one cluster in size. In order to
+read or write data from the virtual disk, QEMU needs to read its
+corresponding L2 table to find out where that data is located. Since
+reading the table for each I/O operation can be expensive, QEMU keeps
+an L2 cache in memory to speed up disk access.
+
+The size of the L2 cache can be configured, and setting the right
+value can improve the I/O performance significantly.
+
+
+The refcount blocks
+-------------------
+The qcow2 format also mantains a reference count for each cluster.
+Reference counts are used for cluster allocation and internal
+snapshots. The data is stored in a two-level structure similar to the
+L1/L2 tables described above.
+
+The second level structures are called refcount blocks, are also one
+cluster in size and the number is also variable and dependent on the
+amount of allocated space.
+
+Each block contains a number of refcount entries. Their size (in bits)
+is a power of two and must not be higher than 64. It defaults to 16
+bits, but a different value can be set using the refcount_bits option:
+
+   qemu-img create -f qcow2 -o refcount_bits=8 hd.qcow2 4G
+
+QEMU keeps a refcount cache to speed up I/O much like the
+aforementioned L2 cache, and its size can also be configured.
+
+
+Choosing the right cache sizes
+------------------------------
+In order to choose the cache sizes we need to know how they relate to
+the amount of allocated space.
+
+The amount of virtual disk that can be mapped by the L2 and refcount
+caches (in bytes) is:
+
+   disk_size = l2_cache_size * cluster_size / 8
+   disk_size = refcount_cache_size * cluster_size * 8 / refcount_bits
+
+With the default values for cluster_size (64KB) and refcount_bits
+(16), that is
+
+   disk_size = l2_cache_size * 8192
+   disk_size = refcount_cache_size * 32768
+
+So in order to cover n GB of disk space with the default values we
+need:
+
+   l2_cache_size = disk_size_GB * 131072
+   refcount_cache_size = disk_size_GB * 32768
+
+QEMU has a default L2 cache of 1MB (1048576 bytes) and a refcount
+cache of 256KB (262144 bytes), so using the formulas we've just seen
+we have
+
+   1048576 / 131072 = 8 GB of virtual disk covered by that cache
+    262144 /  32768 = 8 GB
+
+
+How to configure the cache sizes
+--------------------------------
+Cache sizes can be configured using the -drive option in the
+command-line, or the 'blockdev-add' QMP command.
+
+There are three options available, and all of them take bytes:
+
+"l2-cache-size":         maximum size of the L2 table cache
+"refcount-cache-size":   maximum size of the refcount block cache
+"cache-size":            maximum size of both caches combined
+
+There are two things that need to be taken into account:
+
+ - Both caches must have a size that is a multiple of the cluster
+   size.
+
+ - If you only set one of the options above, QEMU will automatically
+   adjust the others so that the L2 cache is 4 times bigger than the
+   refcount cache.
+
+This means that these options are equivalent:
+
+   -drive file=hd.qcow2,l2-cache-size=2097152
+   -drive file=hd.qcow2,refcount-cache-size=524288
+   -drive file=hd.qcow2,cache-size=2621440
+
+The reason for this 1/4 ratio is to ensure that both caches cover the
+same amount of disk space. Note however that this is only valid with
+the default value of refcount_bits (16). If you are using a different
+value you might want to calculate both cache sizes yourself since QEMU
+will always use the same 1/4 ratio.
+
+It's also worth mentioning that there's no strict need for both caches
+to cover the same amount of disk space. The refcount cache is used
+much less often than the L2 cache, so it's perfectly reasonable to
+keep it small.
+
+
+Reducing the memory usage
+-------------------------
+It is possible to clean unused cache entries in order to reduce the
+memory usage during periods of low I/O activity.
+
+The parameter "cache-clean-interval" defines an interval (in seconds).
+All cache entries that haven't been accessed during that interval are
+removed from memory.
+
+This example removes all unused cache entries every 15 minutes:
+
+   -drive file=hd.qcow2,cache-clean-interval=900
+
+If unset, the default value for this parameter is 0 and it disables
+this feature.
+
+Note that this functionality currently relies on the MADV_DONTNEED
+argument for madvise() to actually free the memory, so it is not
+useful in systems that don't follow that behavior.
diff --git a/qapi/block-core.json b/qapi/block-core.json
index 7b2efb8678..bb2189ef3a 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -1592,6 +1592,10 @@
 # @refcount-cache-size:   #optional the maximum size of the refcount block cache
 #                         in bytes (since 2.2)
 #
+# @cache-clean-interval:  #optional clean unused entries in the L2 and refcount
+#                         caches. The interval is in seconds. The default value
+#                         is 0 and it disables this feature (since 2.5)
+#
 # Since: 1.7
 ##
 { 'struct': 'BlockdevOptionsQcow2',
@@ -1603,7 +1607,8 @@
             '*overlap-check': 'Qcow2OverlapChecks',
             '*cache-size': 'int',
             '*l2-cache-size': 'int',
-            '*refcount-cache-size': 'int' } }
+            '*refcount-cache-size': 'int',
+            '*cache-clean-interval': 'int' } }
 
 
 ##