qcow2: add option to clean unused cache entries after some time

This adds a new 'cache-clean-interval' option that cleans all qcow2
cache entries that haven't been used in a certain interval, given in
seconds.

This allows setting a large L2 cache size so it can handle scenarios
with lots of I/O and at the same time use little memory during periods
of inactivity.

This feature currently relies on MADV_DONTNEED to free that memory, so
it is not useful in systems that don't follow that behavior.

Signed-off-by: Alberto Garcia <berto@igalia.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Message-id: a70d12da60433df9360ada648b3f34b8f6f354ce.1438690126.git.berto@igalia.com
Signed-off-by: Max Reitz <mreitz@redhat.com>

block/qcow2-cache.c

@@ -49,6 +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,
@@ -84,6 +85,40 @@ static void qcow2_cache_table_release(BlockDriverState *bs, Qcow2Cache *c,
 #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;

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)

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,

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' } }
 
 
 ##