Migration: Make more ram_counters atomic
v6 cover Migration: Make more ram_counters atomic
Hi
Changes in v6:
- Create stat64_set() operation
Impersonating Paolo in "Author" field, as he is the real author.
- Update to stat64_set()
- Everything is consistent and coherent under the sun.
Please review.
[v5]
Not only change the type of the counters, also use the __nocheck() variants of the functions.
Please, review.
[v4]
- Change aligned_uint64_t to size_t to make (some) 32bit hosts happy.
Please review.
[v3]
- Addressed reviews
- All counters are now atomic, either Stat64 or atomic.
- Rename duplicated to zero_pages
- Rename normal to zero_pages.
Please review.
[v2]
- fix typos found by David Edmondson
- Add review-by tags.
Please review.
[v1]
On previous series we cerate ram_atomic_counters. But we basically need that all counters are atomic. So move back to only have ram_counters, just with a new type that allows the atomic counters.
Once there, move update of stats out of RAM mutex. And make multifd_bytes atomic.
Later, Juan.
Juan Quintela (2):
migration: Make dirty_pages_rate atomic
migration: Make dirty_bytes_last_sync atomic
Paolo Bonzini (1):
stat64: Add stat64_set() operation
include/qemu/stats64.h | 6 ++++++ migration/migration.c | 9 ++++++--- migration/ram.c | 7 ++++--- migration/ram.h | 4 ++-- util/stats64.c | 11 +++++++++++ 5 files changed, 29 insertions(+), 8 deletions(-)
Signature · 1 line
2.40.0
PATCH v6 1/3 stat64: Add stat64_set() operation
From: Paolo Bonzini <[email protected]>
--- include/qemu/stats64.h | 6 ++++++ util/stats64.c | 11 +++++++++++ 2 files changed, 17 insertions(+)
include/qemu/stats64.h +6 -0
@@ -40,6 +40,11 @@ static inline uint64_t stat64_get(const Stat64 *s)return qatomic_read__nocheck (&s->value); } +static inline void stat64_set (Stat64 *s,uint64_t value) +{ +qatomic_set__nocheck (&s->value, value); +} +static inline void stat64_add (Stat64 *s,uint64_t value) {qatomic_add (&s->value, value);
@@ -62,6 +67,7 @@ static inline void stat64_max(Stat64 *s, uint64_t value) }#else uint64_t stat64_get (const Stat64 *s); +void stat64_set (Stat64 *s,uint64_t value);bool stat64_min_slow (Stat64 *s,uint64_t value);bool stat64_max_slow (Stat64 *s,uint64_t value);bool stat64_add32_carry (Stat64 *s,uint32_t low,uint32_t high);
util/stats64.c +11 -0
@@ -57,6 +57,17 @@ uint64_t stat64_get(const Stat64 *s)return ((uint64_t )high <<32 ) | low; } +void stat64_set (Stat64 *s,uint64_t val) +{ +while (!stat64_wrtrylock (s)) { +cpu_relax (); + } + +qatomic_set (&s->high, val >>32 ); +qatomic_set (&s->low, val); +stat64_wrunlock (s); +} +bool stat64_add32_carry (Stat64 *s,uint32_t low,uint32_t high) {uint32_t old;
Signature · 1 line
2.40.0
Re: [PATCH v6 1/3] stat64: Add stat64_set() operation
Quoted 9 lines · Juan Quintela
From: Paolo Bonzini<[email protected]>
Signed-off-by Paolo Bonzini<[email protected]>Reviewed-by Juan Quintela<[email protected]>Signed-off-by Juan Quintela<[email protected]>--- include/qemu/stats64.h | 6 ++++++ util/stats64.c | 11 +++++++++++ 2 files changed, 17 insertions(+)
r~
PATCH v6 2/3 migration: Make dirty_pages_rate atomic
In reply to Juan Quintela---
Don't use __nocheck() variants
Use stat64_get()
--- migration/migration.c | 6 ++++-- migration/ram.c | 5 +++-- migration/ram.h | 2 +- 3 files changed, 8 insertions(+), 5 deletions(-)
migration/migration.c +4 -2
@@ -1005,7 +1005,8 @@ static void populate_ram_info(MigrationInfo *info, MigrationState *s)if (s->state !=MIGRATION_STATUS_COMPLETED ) { info->ram->remaining =ram_bytes_remaining (); - info->ram->dirty_pages_rate = ram_counters.dirty_pages_rate; + info->ram->dirty_pages_rate = +stat64_get (&ram_counters.dirty_pages_rate); } }
@@ -2751,7 +2752,8 @@ static void migration_update_counters(MigrationState *s,* if we haven't sent anything, we don't want to * recalculate. 10000 is a small enough number for our purposes */ -if (ram_counters.dirty_pages_rate && transferred >10000 ) { +if (stat64_get (&ram_counters.dirty_pages_rate) && + transferred >10000 ) { s->expected_downtime = ram_counters.remaining / bandwidth; }
migration/ram.c +3 -2
@@ -1129,8 +1129,9 @@ static void migration_update_rates(RAMState *rs, int64_t end_time)double compressed_size;/* calculate period counters */ - ram_counters.dirty_pages_rate = rs->num_dirty_pages_period *1000 - / (end_time - rs->time_last_bitmap_sync); +stat64_set (&ram_counters.dirty_pages_rate, + rs->num_dirty_pages_period *1000 / + (end_time - rs->time_last_bitmap_sync));if (!page_count) {return ;
migration/ram.h +1 -1
@@ -41,7 +41,7 @@* one thread). */ typedef struct { - int64_t dirty_pages_rate; + Stat64 dirty_pages_rate; Stat64 dirty_sync_count; Stat64 dirty_sync_missed_zero_copy; Stat64 downtime_bytes;
Signature · 1 line
2.40.0
Re: [PATCH v6 2/3] migration: Make dirty_pages_rate atomic
Quoted 5 lines · Juan Quintela
Signed-off-by Juan Quintela<[email protected]>Reviewed-by Peter Xu<[email protected]>---
Quoted 7 lines
Don't use
__nocheck()variants
Usestat64_get()--- migration/migration.c | 6 ++++-- migration/ram.c | 5 +++-- migration/ram.h | 2 +- 3 files changed, 8 insertions(+), 5 deletions(-)
r~
PATCH v6 3/3 migration: Make dirty_bytes_last_sync atomic
In reply to Juan QuintelaAs we set its value, it needs to be operated with atomics. We rename it from remaining to better reflect its meaning.
Statistics always return the real reamaining bytes. This was used to store how much pages where dirty on the previous generation, so we can calculate the expected downtime as: dirty_bytes_last_sync / current_bandwith.
If we use the actual remaining bytes, we would see a very small value at the end of the iteration.
---
I am open to use ram_bytes_remaining() in its only use and be more "optimistic" about the downtime.
Don't use __nocheck() functions.
Use stat64_get() now that it exists.
--- migration/migration.c | 3 ++- migration/ram.c | 2 +- migration/ram.h | 2 +- 3 files changed, 4 insertions(+), 3 deletions(-)
migration/migration.c +2 -1
@@ -2754,7 +2754,8 @@ static void migration_update_counters(MigrationState *s,*/ if (stat64_get (&ram_counters.dirty_pages_rate) && transferred >10000 ) { - s->expected_downtime = ram_counters.remaining / bandwidth; + s->expected_downtime = +stat64_get (&ram_counters.dirty_bytes_last_sync) / bandwidth; }qemu_file_reset_rate_limit (s->to_dst_file);
migration/ram.c +1 -1
@@ -1223,7 +1223,7 @@ static void migration_bitmap_sync(RAMState *rs)RAMBLOCK_FOREACH_NOT_IGNORED (block) {ramblock_sync_dirty_bitmap (rs, block); } - ram_counters.remaining =ram_bytes_remaining (); +stat64_set (&ram_counters.dirty_bytes_last_sync,ram_bytes_remaining ()); }qemu_mutex_unlock (&rs->bitmap_mutex);
migration/ram.h +1 -1
@@ -41,6 +41,7 @@* one thread). */ typedef struct { + Stat64 dirty_bytes_last_sync; Stat64 dirty_pages_rate; Stat64 dirty_sync_count; Stat64 dirty_sync_missed_zero_copy;
@@ -51,7 +52,6 @@ typedef struct {Stat64 postcopy_bytes;Stat64 postcopy_requests;Stat64 precopy_bytes; -int64_t remaining;Stat64 transferred; } RAMStats;
Signature · 1 line
2.40.0
Re: [PATCH v6 3/3] migration: Make dirty_bytes_last_sync atomic
Quoted 19 lines · Juan Quintela
As we set its value, it needs to be operated with atomics. We rename it from remaining to better reflect its meaning.
Statistics always return the real reamaining bytes. This was used to store how much pages where dirty on the previous generation, so we can calculate the expected downtime as:
dirty_bytes_last_sync/current_bandwith.If we use the actual remaining bytes, we would see a very small value at the end of the iteration.
Signed-off-by Juan Quintela<[email protected]>Reviewed-by Peter Xu<[email protected]>---
I am open to use
ram_bytes_remaining()in its only use and be more "optimistic" about the downtime.
Quoted 7 lines
Don't use
__nocheck()functions.
Usestat64_get()now that it exists.--- migration/migration.c | 3 ++- migration/ram.c | 2 +- migration/ram.h | 2 +- 3 files changed, 4 insertions(+), 3 deletions(-)
r~