From f212cada55593c16cbfdfce2eee75ccd7b375e38 Mon Sep 17 00:00:00 2001

From: Kevin Wolf <kwolf@redhat.com>

Date: Tue, 19 Feb 2019 17:00:11 +0100

Subject: [PATCH 10/23] qcow2: Give the refcount cache the minimum possible

 size by default

RH-Author: Kevin Wolf <kwolf@redhat.com>

Message-id: <20190219170023.27826-2-kwolf@redhat.com>

Patchwork-id: 84541

O-Subject: [RHEL-7.7 qemu-kvm-rhev PATCH 01/13] qcow2: Give the refcount cache the minimum possible size by default

Bugzilla: 1656913

RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>

RH-Acked-by: Max Reitz <mreitz@redhat.com>

RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>

From: Alberto Garcia <berto@igalia.com>

The L2 and refcount caches have default sizes that can be overridden

using the l2-cache-size and refcount-cache-size (an additional

parameter named cache-size sets the combined size of both caches).

Unless forced by one of the aforementioned parameters, QEMU will set

the unspecified sizes so that the L2 cache is 4 times larger than the

refcount cache.

This is based on the premise that the refcount metadata needs to be

only a fourth of the L2 metadata to cover the same amount of disk

space. This is incorrect for two reasons:

 a) The amount of disk covered by an L2 table depends solely on the

    cluster size, but in the case of a refcount block it depends on

    the cluster size *and* the width of each refcount entry.

    The 4/1 ratio is only valid with 16-bit entries (the default).

 b) When we talk about disk space and L2 tables we are talking about

    guest space (L2 tables map guest clusters to host clusters),

    whereas refcount blocks are used for host clusters (including

    L1/L2 tables and the refcount blocks themselves). On a fully

    populated (and uncompressed) qcow2 file, image size > virtual size

    so there are more refcount entries than L2 entries.

Problem (a) could be fixed by adjusting the algorithm to take into

account the refcount entry width. Problem (b) could be fixed by

increasing a bit the refcount cache size to account for the clusters

used for qcow2 metadata.

However this patch takes a completely different approach and instead

of keeping a ratio between both cache sizes it assigns as much as

possible to the L2 cache and the remainder to the refcount cache.

The reason is that L2 tables are used for every single I/O request

from the guest and the effect of increasing the cache is significant

and clearly measurable. Refcount blocks are however only used for

cluster allocation and internal snapshots and in practice are accessed

sequentially in most cases, so the effect of increasing the cache is

negligible (even when doing random writes from the guest).

So, make the refcount cache as small as possible unless the user

explicitly asks for a larger one.

Signed-off-by: Alberto Garcia <berto@igalia.com>

Reviewed-by: Eric Blake <eblake@redhat.com>

Reviewed-by: Max Reitz <mreitz@redhat.com>

Message-id: 9695182c2eb11b77cb319689a1ebaa4e7c9d6591.1523968389.git.berto@igalia.com

Signed-off-by: Max Reitz <mreitz@redhat.com>

(cherry picked from commit 52253998ec3e523c9e20ae81e2a6431d8ff733ba)

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

Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>

---

 block/qcow2.c              | 31 +++++++++++++++++++------------

 block/qcow2.h              |  4 ----

 tests/qemu-iotests/137.out |  2 +-

 3 files changed, 20 insertions(+), 17 deletions(-)

diff --git a/block/qcow2.c b/block/qcow2.c

index 36d1152..4b65e4c 100644

--- a/block/qcow2.c

+++ b/block/qcow2.c

@@ -809,23 +809,30 @@ static void read_cache_sizes(BlockDriverState *bs, QemuOpts *opts,

         } else if (refcount_cache_size_set) {

             *l2_cache_size = combined_cache_size - *refcount_cache_size;

         } else {

-            *refcount_cache_size = combined_cache_size

-                                 / (DEFAULT_L2_REFCOUNT_SIZE_RATIO + 1);

-            *l2_cache_size = combined_cache_size - *refcount_cache_size;

+            uint64_t virtual_disk_size = bs->total_sectors * BDRV_SECTOR_SIZE;

+            uint64_t max_l2_cache = virtual_disk_size / (s->cluster_size / 8);

+            uint64_t min_refcount_cache =

+                (uint64_t) MIN_REFCOUNT_CACHE_SIZE * s->cluster_size;

+

+            /* Assign as much memory as possible to the L2 cache, and

+             * use the remainder for the refcount cache */

+            if (combined_cache_size >= max_l2_cache + min_refcount_cache) {

+                *l2_cache_size = max_l2_cache;

+                *refcount_cache_size = combined_cache_size - *l2_cache_size;

+            } else {

+                *refcount_cache_size =

+                    MIN(combined_cache_size, min_refcount_cache);

+                *l2_cache_size = combined_cache_size - *refcount_cache_size;

+            }

         }

     } else {

-        if (!l2_cache_size_set && !refcount_cache_size_set) {

+        if (!l2_cache_size_set) {

             *l2_cache_size = MAX(DEFAULT_L2_CACHE_BYTE_SIZE,

                                  (uint64_t)DEFAULT_L2_CACHE_CLUSTERS

                                  * s->cluster_size);

-            *refcount_cache_size = *l2_cache_size

-                                 / DEFAULT_L2_REFCOUNT_SIZE_RATIO;

-        } else if (!l2_cache_size_set) {

-            *l2_cache_size = *refcount_cache_size

-                           * DEFAULT_L2_REFCOUNT_SIZE_RATIO;

-        } else if (!refcount_cache_size_set) {

-            *refcount_cache_size = *l2_cache_size

-                                 / DEFAULT_L2_REFCOUNT_SIZE_RATIO;

+        }

+        if (!refcount_cache_size_set) {

+            *refcount_cache_size = MIN_REFCOUNT_CACHE_SIZE * s->cluster_size;

         }

     }

diff --git a/block/qcow2.h b/block/qcow2.h

index 43163b2..3d92cdb 100644

--- a/block/qcow2.h

+++ b/block/qcow2.h

@@ -77,10 +77,6 @@

 #define DEFAULT_L2_CACHE_CLUSTERS 8 /* clusters */

 #define DEFAULT_L2_CACHE_BYTE_SIZE 1048576 /* bytes */

-/* The refblock cache needs only a fourth of the L2 cache size to cover as many

- * clusters */

-#define DEFAULT_L2_REFCOUNT_SIZE_RATIO 4

-

 #define DEFAULT_CLUSTER_SIZE 65536

diff --git a/tests/qemu-iotests/137.out b/tests/qemu-iotests/137.out

index e28e1ea..96724a6 100644

--- a/tests/qemu-iotests/137.out

+++ b/tests/qemu-iotests/137.out

@@ -22,7 +22,7 @@ refcount-cache-size may not exceed cache-size

 L2 cache size too big

 L2 cache entry size must be a power of two between 512 and the cluster size (65536)

 L2 cache entry size must be a power of two between 512 and the cluster size (65536)

-L2 cache size too big

+Refcount cache size too big

 Conflicting values for qcow2 options 'overlap-check' ('constant') and 'overlap-check.template' ('all')

 Unsupported value 'blubb' for qcow2 option 'overlap-check'. Allowed are any of the following: none, constant, cached, all

 Unsupported value 'blubb' for qcow2 option 'overlap-check'. Allowed are any of the following: none, constant, cached, all

-- 

1.8.3.1