qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Hailiang Zhang <zhang.zhanghailiang@huawei.com>
To: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: lizhijian@cn.fujitsu.com, quintela@redhat.com,
	yunhong.jiang@intel.com, eddie.dong@intel.com,
	peter.huangpeng@huawei.com, qemu-devel@nongnu.org,
	arei.gonglei@huawei.com, stefanha@redhat.com,
	amit.shah@redhat.com, hongyang.yang@easystack.cn
Subject: Re: [Qemu-devel] [PATCH COLO-Frame v11 15/39] COLO: Load PVM's dirty pages into SVM's RAM cache temporarily
Date: Thu, 3 Dec 2015 16:25:12 +0800	[thread overview]
Message-ID: <565FFC68.901@huawei.com> (raw)
In-Reply-To: <20151201190251.GD31209@work-vm>

On 2015/12/2 3:02, Dr. David Alan Gilbert wrote:
> * zhanghailiang (zhang.zhanghailiang@huawei.com) wrote:
>> We should not load PVM's state directly into SVM, because there maybe some
>> errors happen when SVM is receving data, which will break SVM.
>>
>> We need to ensure receving all data before load the state into SVM. We use
>> an extra memory to cache these data (PVM's ram). The ram cache in secondary side
>> is initially the same as SVM/PVM's memory. And in the process of checkpoint,
>> we cache the dirty pages of PVM into this ram cache firstly, so this ram cache
>> always the same as PVM's memory at every checkpoint, then we flush this cached ram
>> to SVM after we receive all PVM's state.
>>
>> Signed-off-by: zhanghailiang <zhang.zhanghailiang@huawei.com>
>> Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
>> Signed-off-by: Gonglei <arei.gonglei@huawei.com>
>> ---
>> v11:
>> - Rename 'host_cache' to 'colo_cache' (Dave's suggestion)
>> v10:
>> - Split the process of dirty pages recording into a new patch
>> ---
>>   include/exec/ram_addr.h       |  1 +
>>   include/migration/migration.h |  4 +++
>>   migration/colo.c              | 10 +++++++
>>   migration/ram.c               | 69 ++++++++++++++++++++++++++++++++++++++++++-
>>   4 files changed, 83 insertions(+), 1 deletion(-)
>>
>> diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h
>> index 7115154..bb44f66 100644
>> --- a/include/exec/ram_addr.h
>> +++ b/include/exec/ram_addr.h
>> @@ -26,6 +26,7 @@ struct RAMBlock {
>>       struct rcu_head rcu;
>>       struct MemoryRegion *mr;
>>       uint8_t *host;
>> +    uint8_t *colo_cache; /* For colo, VM's ram cache */
>>       ram_addr_t offset;
>>       ram_addr_t used_length;
>>       ram_addr_t max_length;
>> diff --git a/include/migration/migration.h b/include/migration/migration.h
>> index ba5bcec..e41372d 100644
>> --- a/include/migration/migration.h
>> +++ b/include/migration/migration.h
>> @@ -332,4 +332,8 @@ int ram_save_queue_pages(MigrationState *ms, const char *rbname,
>>   PostcopyState postcopy_state_get(void);
>>   /* Set the state and return the old state */
>>   PostcopyState postcopy_state_set(PostcopyState new_state);
>> +
>> +/* ram cache */
>> +int colo_init_ram_cache(void);
>> +void colo_release_ram_cache(void);
>>   #endif
>> diff --git a/migration/colo.c b/migration/colo.c
>> index 012d8e5..6e933fa 100644
>> --- a/migration/colo.c
>> +++ b/migration/colo.c
>> @@ -304,6 +304,12 @@ void *colo_process_incoming_thread(void *opaque)
>>       qemu_set_block(qemu_get_fd(mis->from_src_file));
>>
>>
>> +    ret = colo_init_ram_cache();
>> +    if (ret < 0) {
>> +        error_report("Failed to initialize ram cache");
>> +        goto out;
>> +    }
>> +
>>       ret = colo_ctl_put(mis->to_src_file, COLO_COMMAND_CHECKPOINT_READY, 0);
>>       if (ret < 0) {
>>           goto out;
>> @@ -353,6 +359,10 @@ out:
>>                        strerror(-ret));
>>       }
>>
>> +    qemu_mutex_lock_iothread();
>> +    colo_release_ram_cache();
>> +    qemu_mutex_unlock_iothread();
>> +
>>       if (mis->to_src_file) {
>>           qemu_fclose(mis->to_src_file);
>>       }
>> diff --git a/migration/ram.c b/migration/ram.c
>> index a161620..9d946a1 100644
>> --- a/migration/ram.c
>> +++ b/migration/ram.c
>> @@ -223,6 +223,7 @@ static RAMBlock *last_sent_block;
>>   static ram_addr_t last_offset;
>>   static QemuMutex migration_bitmap_mutex;
>>   static uint64_t migration_dirty_pages;
>> +static bool ram_cache_enable;
>>   static uint32_t last_version;
>>   static bool ram_bulk_stage;
>>
>> @@ -2175,6 +2176,16 @@ static inline void *host_from_ram_block_offset(RAMBlock *block,
>>       return block->host + offset;
>>   }
>>
>> +static inline void *colo_cache_from_block_offset(RAMBlock *block,
>> +                                                 ram_addr_t offset)
>> +{
>> +    if (!block) {
>> +        return NULL;
>> +    }
>> +
>> +    return block->colo_cache + offset;
>> +}
>> +
>>   /*
>>    * If a page (or a whole RDMA chunk) has been
>>    * determined to be zero, then zap it.
>> @@ -2454,7 +2465,12 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
>>                        RAM_SAVE_FLAG_COMPRESS_PAGE | RAM_SAVE_FLAG_XBZRLE)) {
>>               RAMBlock *block = ram_block_from_stream(f, addr, flags);
>>
>> -            host = host_from_ram_block_offset(block, addr);
>> +            /* After going into COLO, we should load the Page into colo_cache */
>> +            if (ram_cache_enable) {
>> +                host = colo_cache_from_block_offset(block, addr);
>> +            } else {
>> +                host = host_from_ram_block_offset(block, addr);
>> +            }
>>               if (!host) {
>>                   error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
>>                   ret = -EINVAL;
>> @@ -2550,6 +2566,57 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
>>       return ret;
>>   }
>>
>> +/*
>> + * colo cache: this is for secondary VM, we cache the whole
>> + * memory of the secondary VM, it will be called after first migration.
>> + */
>> +int colo_init_ram_cache(void)
>> +{
>> +    RAMBlock *block;
>> +
>> +    rcu_read_lock();
>> +    QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
>> +        block->colo_cache = qemu_anon_ram_alloc(block->used_length, NULL);
>> +        if (!block->colo_cache) {
>> +            error_report("%s: Can't alloc memory for colo cache of block %s,"
>> +                         "size %zu", __func__, block->idstr,
>> +                         block->used_length);
>
> Minor one that I didn't spot before;  I think that has to be RAM_ADDR_FMT instead of %zu
>

OK, i will fix it, thanks.

> However, other than that;
>
> Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
>
> Dave
>
>> +            goto out_locked;
>> +        }
>> +        memcpy(block->colo_cache, block->host, block->used_length);
>> +    }
>> +    rcu_read_unlock();
>> +    ram_cache_enable = true;
>> +    return 0;
>> +
>> +out_locked:
>> +    QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
>> +        if (block->colo_cache) {
>> +            qemu_anon_ram_free(block->colo_cache, block->used_length);
>> +            block->colo_cache = NULL;
>> +        }
>> +    }
>> +
>> +    rcu_read_unlock();
>> +    return -errno;
>> +}
>> +
>> +void colo_release_ram_cache(void)
>> +{
>> +    RAMBlock *block;
>> +
>> +    ram_cache_enable = false;
>> +
>> +    rcu_read_lock();
>> +    QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
>> +        if (block->colo_cache) {
>> +            qemu_anon_ram_free(block->colo_cache, block->used_length);
>> +            block->colo_cache = NULL;
>> +        }
>> +    }
>> +    rcu_read_unlock();
>> +}
>> +
>>   static SaveVMHandlers savevm_ram_handlers = {
>>       .save_live_setup = ram_save_setup,
>>       .save_live_iterate = ram_save_iterate,
>> --
>> 1.8.3.1
>>
>>
> --
> Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK
>
> .
>

  reply	other threads:[~2015-12-03  8:25 UTC|newest]

Thread overview: 95+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-11-24  9:25 [Qemu-devel] [PATCH COLO-Frame v11 00/39] COarse-grain LOck-stepping(COLO) Virtual Machines for Non-stop Service (FT) zhanghailiang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 01/39] configure: Add parameter for configure to enable/disable COLO support zhanghailiang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 02/39] migration: Introduce capability 'x-colo' to migration zhanghailiang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 03/39] COLO: migrate colo related info to secondary node zhanghailiang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 04/39] migration: Export migrate_set_state() zhanghailiang
2015-11-24 17:31   ` Dr. David Alan Gilbert
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 05/39] migration: Add state records for migration incoming zhanghailiang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 06/39] migration: Integrate COLO checkpoint process into migration zhanghailiang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 07/39] migration: Integrate COLO checkpoint process into loadvm zhanghailiang
2015-11-24 18:14   ` Dr. David Alan Gilbert
2015-11-25  6:39     ` zhanghailiang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 08/39] migration: Rename the'file' member of MigrationState zhanghailiang
2015-11-24 18:26   ` Dr. David Alan Gilbert
2015-11-25  6:48     ` zhanghailiang
2015-12-10  6:41   ` Wen Congyang
2015-12-11  3:40     ` Hailiang Zhang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 09/39] COLO/migration: Create a new communication path from destination to source zhanghailiang
2015-11-24 18:40   ` Dr. David Alan Gilbert
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 10/39] COLO: Implement colo checkpoint protocol zhanghailiang
2015-11-24 19:00   ` Dr. David Alan Gilbert
2015-11-25 14:01     ` Eric Blake
2015-11-26  6:52       ` Hailiang Zhang
2015-11-26  7:12     ` Hailiang Zhang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 11/39] COLO: Add a new RunState RUN_STATE_COLO zhanghailiang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 12/39] QEMUSizedBuffer: Introduce two help functions for qsb zhanghailiang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 13/39] COLO: Save PVM state to secondary side when do checkpoint zhanghailiang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 14/39] ram: Split host_from_stream_offset() into two helper functions zhanghailiang
2015-12-01 18:19   ` Dr. David Alan Gilbert
2015-12-03  7:19     ` Hailiang Zhang
2015-12-03  7:29       ` Hailiang Zhang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 15/39] COLO: Load PVM's dirty pages into SVM's RAM cache temporarily zhanghailiang
2015-12-01 19:02   ` Dr. David Alan Gilbert
2015-12-03  8:25     ` Hailiang Zhang [this message]
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 16/39] ram/COLO: Record the dirty pages that SVM received zhanghailiang
2015-12-01 19:36   ` Dr. David Alan Gilbert
2015-12-03  8:29     ` Hailiang Zhang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 17/39] COLO: Load VMState into qsb before restore it zhanghailiang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 18/39] COLO: Flush PVM's cached RAM into SVM's memory zhanghailiang
2015-11-27  5:29   ` Li Zhijian
2015-12-01 12:02     ` Hailiang Zhang
2015-12-01 20:06   ` Dr. David Alan Gilbert
2015-12-03  8:50     ` Hailiang Zhang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 19/39] COLO: Add checkpoint-delay parameter for migrate-set-parameters zhanghailiang
2015-12-09 18:50   ` Dr. David Alan Gilbert
2015-12-11  3:20     ` Hailiang Zhang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 20/39] COLO: synchronize PVM's state to SVM periodically zhanghailiang
2015-12-09 18:53   ` Dr. David Alan Gilbert
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 21/39] COLO failover: Introduce a new command to trigger a failover zhanghailiang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 22/39] COLO failover: Introduce state to record failover process zhanghailiang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 23/39] COLO: Implement failover work for Primary VM zhanghailiang
2015-12-10 18:34   ` Dr. David Alan Gilbert
2015-12-11  7:54     ` Hailiang Zhang
2015-12-11  9:22       ` Dr. David Alan Gilbert
2015-12-11  9:38         ` Hailiang Zhang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 24/39] COLO: Implement failover work for Secondary VM zhanghailiang
2015-12-10 18:50   ` Dr. David Alan Gilbert
2015-12-11  8:27     ` Hailiang Zhang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 25/39] COLO: implement default failover treatment zhanghailiang
2015-12-10 19:01   ` Dr. David Alan Gilbert
2015-12-11  9:48     ` Hailiang Zhang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 26/39] qmp event: Add event notification for COLO error zhanghailiang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 27/39] COLO failover: Shutdown related socket fd when do failover zhanghailiang
2015-12-10 20:03   ` Dr. David Alan Gilbert
2015-12-11  8:57     ` Hailiang Zhang
2015-12-11  9:18       ` Dr. David Alan Gilbert
2015-12-11  9:29         ` Hailiang Zhang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 28/39] COLO failover: Don't do failover during loading VM's state zhanghailiang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 29/39] COLO: Process shutdown command for VM in COLO state zhanghailiang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 30/39] COLO: Update the global runstate after going into colo state zhanghailiang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 31/39] savevm: Split load vm state function qemu_loadvm_state zhanghailiang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 32/39] COLO: Separate the process of saving/loading ram and device state zhanghailiang
2015-11-27  5:10   ` Li Zhijian
2015-12-01 12:07     ` Hailiang Zhang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 33/39] COLO: Split qemu_savevm_state_begin out of checkpoint process zhanghailiang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 34/39] net/filter-buffer: Add default filter-buffer for each netdev zhanghailiang
2015-11-27 11:39   ` Yang Hongyang
2015-11-28  5:55     ` Hailiang Zhang
2015-11-30  1:19   ` Li Zhijian
2015-12-01  8:56     ` Hailiang Zhang
2015-12-03  1:17   ` Wen Congyang
2015-12-03  3:53     ` Hailiang Zhang
2015-12-03  6:25       ` Wen Congyang
2015-12-03  6:48         ` Hailiang Zhang
2015-12-03  7:21           ` Yang Hongyang
2015-12-03  8:37             ` Hailiang Zhang
2015-12-07  7:38             ` Hailiang Zhang
2015-12-08  1:49               ` Yang Hongyang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 35/39] filter-buffer: Accept zero interval zhanghailiang
2015-11-27 11:42   ` Yang Hongyang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 36/39] filter-buffer: Introduce a helper function to enable/disable default filter zhanghailiang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 37/39] filter-buffer: Introduce a helper function to release packets zhanghailiang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 38/39] colo: Use default buffer-filter to buffer and " zhanghailiang
2015-11-27 12:51   ` Yang Hongyang
2015-11-28  6:15     ` Hailiang Zhang
2015-11-24  9:25 ` [Qemu-devel] [PATCH COLO-Frame v11 39/39] COLO: Add block replication into colo process zhanghailiang

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=565FFC68.901@huawei.com \
    --to=zhang.zhanghailiang@huawei.com \
    --cc=amit.shah@redhat.com \
    --cc=arei.gonglei@huawei.com \
    --cc=dgilbert@redhat.com \
    --cc=eddie.dong@intel.com \
    --cc=hongyang.yang@easystack.cn \
    --cc=lizhijian@cn.fujitsu.com \
    --cc=peter.huangpeng@huawei.com \
    --cc=qemu-devel@nongnu.org \
    --cc=quintela@redhat.com \
    --cc=stefanha@redhat.com \
    --cc=yunhong.jiang@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).