All of lore.kernel.org
 help / color / mirror / Atom feed
From: Alexander Yarygin <yarygin@linux.vnet.ibm.com>
To: Paolo Bonzini <pbonzini@redhat.com>
Cc: Kevin Wolf <kwolf@redhat.com>,
	qemu-block@nongnu.org, qemu-devel@nongnu.org,
	Christian Borntraeger <borntraeger@de.ibm.com>,
	Stefan Hajnoczi <stefanha@redhat.com>,
	Cornelia Huck <cornelia.huck@de.ibm.com>
Subject: Re: [Qemu-devel] [PATCH] block: Let bdrv_drain_all() to call aio_poll() for each AioContext
Date: Wed, 13 May 2015 19:34:40 +0300	[thread overview]
Message-ID: <87vbfw77xb.fsf@linux.vnet.ibm.com> (raw)
In-Reply-To: <55536C6B.4040400@redhat.com> (Paolo Bonzini's message of "Wed, 13 May 2015 17:23:23 +0200")

Paolo Bonzini <pbonzini@redhat.com> writes:

> On 13/05/2015 17:18, Alexander Yarygin wrote:
>> After the commit 9b536adc ("block: acquire AioContext in
>> bdrv_drain_all()") the aio_poll() function got called for every
>> BlockDriverState, in assumption that every device may have its own
>> AioContext. The bdrv_drain_all() function is called in each
>> virtio_reset() call,
>
> ... which should actually call bdrv_drain().  Can you fix that?
>

I thought about it, but couldn't come to conclusion that it's safe. The
comment above bdrv_drain_all() states "... it is not possible to have a
function to drain a single device's I/O queue.", besides that what if we
have several virtual disks that share host file?
Or I'm wrong and it's ok to do?

>> which in turn is called for every virtio-blk
>> device on initialization, so we got aio_poll() called
>> 'length(device_list)^2' times.
>> 
>> If we have thousands of disks attached, there are a lot of
>> BlockDriverStates but only a few AioContexts, leading to tons of
>> unnecessary aio_poll() calls. For example, startup times with 1000 disks
>> takes over 13 minutes.
>> 
>> This patch changes the bdrv_drain_all() function allowing it find shared
>> AioContexts and to call aio_poll() only for unique ones. This results in
>> much better startup times, e.g. 1000 disks do come up within 5 seconds.
>
> I'm not sure this patch is correct.  You may have to call aio_poll
> multiple times before a BlockDriverState is drained.
>
> Paolo
>


Ah, right. We need second loop, something like this:

@@ -2030,20 +2033,33 @@ void bdrv_drain(BlockDriverState *bs)
 void bdrv_drain_all(void)
 {
     /* Always run first iteration so any pending completion BHs run */
-    bool busy = true;
+    bool busy = true, pending = false;
     BlockDriverState *bs;
+    GList *aio_ctxs = NULL, *ctx;
+    AioContext *aio_context;

     while (busy) {
         busy = false;

         QTAILQ_FOREACH(bs, &bdrv_states, device_list) {
-            AioContext *aio_context = bdrv_get_aio_context(bs);
+            aio_context = bdrv_get_aio_context(bs);

             aio_context_acquire(aio_context);
             busy |= bdrv_drain_one(bs);
             aio_context_release(aio_context);
+            if (!aio_ctxs || !g_list_find(aio_ctxs, aio_context))
+                aio_ctxs = g_list_append(aio_ctxs, aio_context);
+        }
+        pending = busy;
+
+        for (ctx = aio_ctxs; ctx != NULL; ctx = ctx->next) {
+            aio_context = ctx->data;
+            aio_context_acquire(aio_context);
+            busy |= aio_poll(aio_context, pending);
+            aio_context_release(aio_context);
         }
     }
+    g_list_free(aio_ctxs);
 }

That looks quite ugly for me and breaks consistence of bdrv_drain_one()
since it doesn't call aio_poll() anymore...


>> Cc: Christian Borntraeger <borntraeger@de.ibm.com>
>> Cc: Cornelia Huck <cornelia.huck@de.ibm.com>
>> Cc: Kevin Wolf <kwolf@redhat.com>
>> Cc: Paolo Bonzini <pbonzini@redhat.com>
>> Cc: Stefan Hajnoczi <stefanha@redhat.com>
>> Signed-off-by: Alexander Yarygin <yarygin@linux.vnet.ibm.com>
>> ---
>>  block.c | 13 +++++++++++--
>>  1 file changed, 11 insertions(+), 2 deletions(-)
>> 
>> diff --git a/block.c b/block.c
>> index f2f8ae7..7414815 100644
>> --- a/block.c
>> +++ b/block.c
>> @@ -1994,7 +1994,6 @@ static bool bdrv_drain_one(BlockDriverState *bs)
>>      bdrv_flush_io_queue(bs);
>>      bdrv_start_throttled_reqs(bs);
>>      bs_busy = bdrv_requests_pending(bs);
>> -    bs_busy |= aio_poll(bdrv_get_aio_context(bs), bs_busy);
>>      return bs_busy;
>>  }
>>  
>> @@ -2010,8 +2009,12 @@ static bool bdrv_drain_one(BlockDriverState *bs)
>>   */
>>  void bdrv_drain(BlockDriverState *bs)
>>  {
>> -    while (bdrv_drain_one(bs)) {
>> +    bool busy = true;
>> +
>> +    while (busy) {
>>          /* Keep iterating */
>> +        busy = bdrv_drain_one(bs);
>> +        busy |= aio_poll(bdrv_get_aio_context(bs), busy);
>>      }
>>  }
>>  
>> @@ -2032,6 +2035,7 @@ void bdrv_drain_all(void)
>>      /* Always run first iteration so any pending completion BHs run */
>>      bool busy = true;
>>      BlockDriverState *bs;
>> +    GList *aio_ctxs = NULL;
>>  
>>      while (busy) {
>>          busy = false;
>> @@ -2041,9 +2045,14 @@ void bdrv_drain_all(void)
>>  
>>              aio_context_acquire(aio_context);
>>              busy |= bdrv_drain_one(bs);
>> +            if (!aio_ctxs || !g_list_find(aio_ctxs, aio_context)) {
>> +                busy |= aio_poll(aio_context, busy);
>> +                aio_ctxs = g_list_append(aio_ctxs, aio_context);
>> +            }
>>              aio_context_release(aio_context);
>>          }
>>      }
>> +    g_list_free(aio_ctxs);
>>  }
>>  
>>  /* make a BlockDriverState anonymous by removing from bdrv_state and
>> 

  reply	other threads:[~2015-05-13 16:34 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-05-13 15:18 [Qemu-devel] [PATCH] block: Let bdrv_drain_all() to call aio_poll() for each AioContext Alexander Yarygin
2015-05-13 15:23 ` Paolo Bonzini
2015-05-13 16:34   ` Alexander Yarygin [this message]
2015-05-14  2:25     ` Fam Zheng
2015-05-14 10:57       ` Alexander Yarygin
2015-05-14 12:05     ` Paolo Bonzini
2015-05-14 14:29       ` Alexander Yarygin
2015-05-14 14:34         ` Paolo Bonzini
2015-05-13 16:02 ` [Qemu-devel] [Qemu-block] " Alberto Garcia
2015-05-13 16:37   ` Alexander Yarygin

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=87vbfw77xb.fsf@linux.vnet.ibm.com \
    --to=yarygin@linux.vnet.ibm.com \
    --cc=borntraeger@de.ibm.com \
    --cc=cornelia.huck@de.ibm.com \
    --cc=kwolf@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=qemu-block@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    --cc=stefanha@redhat.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.