From: Paolo Bonzini <pbonzini@redhat.com>
To: qemu-devel@nongnu.org
Cc: Changlong Xie <xiecl.fnst@cn.fujitsu.com>,
Wen Congyang <wency@cn.fujitsu.com>
Subject: [Qemu-devel] [PULL 02/27] nbd: Use CoQueue for free_sema instead of CoMutex
Date: Mon, 31 Oct 2016 15:37:18 +0100 [thread overview]
Message-ID: <1477924663-30950-3-git-send-email-pbonzini@redhat.com> (raw)
In-Reply-To: <1477924663-30950-1-git-send-email-pbonzini@redhat.com>
From: Changlong Xie <xiecl.fnst@cn.fujitsu.com>
NBD is using the CoMutex in a way that wasn't anticipated. For example, if there are
N(N=26, MAX_NBD_REQUESTS=16) nbd write requests, so we will invoke nbd_client_co_pwritev
N times.
----------------------------------------------------------------------------------------
time request Actions
1 1 in_flight=1, Coroutine=C1
2 2 in_flight=2, Coroutine=C2
...
15 15 in_flight=15, Coroutine=C15
16 16 in_flight=16, Coroutine=C16, free_sema->holder=C16, mutex->locked=true
17 17 in_flight=16, Coroutine=C17, queue C17 into free_sema->queue
18 18 in_flight=16, Coroutine=C18, queue C18 into free_sema->queue
...
26 N in_flight=16, Coroutine=C26, queue C26 into free_sema->queue
----------------------------------------------------------------------------------------
Once nbd client recieves request No.16' reply, we will re-enter C16. It's ok, because
it's equal to 'free_sema->holder'.
----------------------------------------------------------------------------------------
time request Actions
27 16 in_flight=15, Coroutine=C16, free_sema->holder=C16, mutex->locked=false
----------------------------------------------------------------------------------------
Then nbd_coroutine_end invokes qemu_co_mutex_unlock what will pop coroutines from
free_sema->queue's head and enter C17. More free_sema->holder is C17 now.
----------------------------------------------------------------------------------------
time request Actions
28 17 in_flight=16, Coroutine=C17, free_sema->holder=C17, mutex->locked=true
----------------------------------------------------------------------------------------
In above scenario, we only recieves request No.16' reply. As time goes by, nbd client will
almostly recieves replies from requests 1 to 15 rather than request 17 who owns C17. In this
case, we will encounter assert "mutex->holder == self" failed since Kevin's commit 0e438cdc
"coroutine: Let CoMutex remember who holds it". For example, if nbd client recieves request
No.15' reply, qemu will stop unexpectedly:
----------------------------------------------------------------------------------------
time request Actions
29 15(most case) in_flight=15, Coroutine=C15, free_sema->holder=C17, mutex->locked=false
----------------------------------------------------------------------------------------
Per Paolo's suggestion "The simplest fix is to change it to CoQueue, which is like a condition
variable", this patch replaces CoMutex with CoQueue.
Cc: Wen Congyang <wency@cn.fujitsu.com>
Reported-by: zhanghailiang <zhang.zhanghailiang@huawei.com>
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Changlong Xie <xiecl.fnst@cn.fujitsu.com>
Message-Id: <1476267508-19499-1-git-send-email-xiecl.fnst@cn.fujitsu.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
block/nbd-client.c | 8 ++++----
block/nbd-client.h | 2 +-
2 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/block/nbd-client.c b/block/nbd-client.c
index 2cf3237..40b28ab 100644
--- a/block/nbd-client.c
+++ b/block/nbd-client.c
@@ -199,8 +199,8 @@ static void nbd_coroutine_start(NbdClientSession *s,
{
/* Poor man semaphore. The free_sema is locked when no other request
* can be accepted, and unlocked after receiving one reply. */
- if (s->in_flight >= MAX_NBD_REQUESTS - 1) {
- qemu_co_mutex_lock(&s->free_sema);
+ if (s->in_flight == MAX_NBD_REQUESTS) {
+ qemu_co_queue_wait(&s->free_sema);
assert(s->in_flight < MAX_NBD_REQUESTS);
}
s->in_flight++;
@@ -214,7 +214,7 @@ static void nbd_coroutine_end(NbdClientSession *s,
int i = HANDLE_TO_INDEX(s, request->handle);
s->recv_coroutine[i] = NULL;
if (s->in_flight-- == MAX_NBD_REQUESTS) {
- qemu_co_mutex_unlock(&s->free_sema);
+ qemu_co_queue_next(&s->free_sema);
}
}
@@ -386,7 +386,7 @@ int nbd_client_init(BlockDriverState *bs,
}
qemu_co_mutex_init(&client->send_mutex);
- qemu_co_mutex_init(&client->free_sema);
+ qemu_co_queue_init(&client->free_sema);
client->sioc = sioc;
object_ref(OBJECT(client->sioc));
diff --git a/block/nbd-client.h b/block/nbd-client.h
index 044aca4..307b8b1 100644
--- a/block/nbd-client.h
+++ b/block/nbd-client.h
@@ -24,7 +24,7 @@ typedef struct NbdClientSession {
off_t size;
CoMutex send_mutex;
- CoMutex free_sema;
+ CoQueue free_sema;
Coroutine *send_coroutine;
int in_flight;
--
2.7.4
next prev parent reply other threads:[~2016-10-31 14:37 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-10-31 14:37 [Qemu-devel] [PULL 00/27] Misc patches for 2016-10-31 Paolo Bonzini
2016-10-31 14:37 ` [Qemu-devel] [PULL 01/27] checkpatch: tweak "struct should normally be const" warning Paolo Bonzini
2016-10-31 14:37 ` Paolo Bonzini [this message]
2016-10-31 14:37 ` [Qemu-devel] [PULL 03/27] qemu-error: remove dependency of stubs on monitor Paolo Bonzini
2016-10-31 14:37 ` [Qemu-devel] [PULL 04/27] tests: send error_report to test log Paolo Bonzini
2016-10-31 14:37 ` [Qemu-devel] [PULL 05/27] exec.c: ensure all AddressSpaceDispatch updates under RCU Paolo Bonzini
2016-10-31 14:37 ` [Qemu-devel] [PULL 06/27] exec.c: do not truncate non-empty memory backend file Paolo Bonzini
2016-10-31 14:37 ` [Qemu-devel] [PULL 07/27] exec.c: check memory backend file size with 'size' option Paolo Bonzini
2016-10-31 14:37 ` [Qemu-devel] [PULL 08/27] hostmem-file: make option 'size' optional Paolo Bonzini
2016-10-31 18:20 ` Eduardo Habkost
2016-10-31 19:47 ` Paolo Bonzini
2016-10-31 22:22 ` Eduardo Habkost
2016-11-01 9:32 ` Haozhong Zhang
2016-11-01 14:16 ` Eduardo Habkost
2016-11-02 1:27 ` Haozhong Zhang
2016-10-31 14:37 ` [Qemu-devel] [PULL 09/27] nbd: Add qemu-nbd -D for human-readable description Paolo Bonzini
2016-10-31 14:37 ` [Qemu-devel] [PULL 10/27] nbd: Treat flags vs. command type as separate fields Paolo Bonzini
2016-10-31 14:37 ` [Qemu-devel] [PULL 11/27] nbd: Rename NBDRequest to NBDRequestData Paolo Bonzini
2016-10-31 14:37 ` [Qemu-devel] [PULL 12/27] nbd: Rename NbdClientSession to NBDClientSession Paolo Bonzini
2016-10-31 14:37 ` [Qemu-devel] [PULL 13/27] nbd: Rename struct nbd_request and nbd_reply Paolo Bonzini
2016-10-31 14:37 ` [Qemu-devel] [PULL 14/27] nbd: Share common reply-sending code in server Paolo Bonzini
2016-10-31 14:37 ` [Qemu-devel] [PULL 15/27] nbd: Send message along with server NBD_REP_ERR errors Paolo Bonzini
2016-10-31 14:37 ` [Qemu-devel] [PULL 16/27] nbd: Share common option-sending code in client Paolo Bonzini
2016-10-31 14:37 ` [Qemu-devel] [PULL 17/27] nbd: Let server know when client gives up negotiation Paolo Bonzini
2016-10-31 14:37 ` [Qemu-devel] [PULL 18/27] nbd: Let client skip portions of server reply Paolo Bonzini
2016-10-31 14:37 ` [Qemu-devel] [PULL 19/27] nbd: Less allocation during NBD_OPT_LIST Paolo Bonzini
2016-10-31 14:37 ` [Qemu-devel] [PULL 20/27] nbd: Support shorter handshake Paolo Bonzini
2016-10-31 14:37 ` [Qemu-devel] [PULL 21/27] nbd: Refactor conversion to errno to silence checkpatch Paolo Bonzini
2016-10-31 14:37 ` [Qemu-devel] [PULL 22/27] nbd: Improve server handling of shutdown requests Paolo Bonzini
2016-10-31 18:05 ` Eric Blake
2016-10-31 14:37 ` [Qemu-devel] [PULL 23/27] nbd: Implement NBD_CMD_WRITE_ZEROES on server Paolo Bonzini
2016-10-31 14:37 ` [Qemu-devel] [PULL 24/27] nbd: Implement NBD_CMD_WRITE_ZEROES on client Paolo Bonzini
2016-11-15 22:59 ` Eric Blake
2016-10-31 14:37 ` [Qemu-devel] [PULL 25/27] qemu-char: do not forward events through the mux until QEMU has started Paolo Bonzini
2016-10-31 14:37 ` [Qemu-devel] [PULL 26/27] slirp: fix CharDriver breakage Paolo Bonzini
2016-10-31 14:37 ` [Qemu-devel] [PULL 27/27] x86: add AVX512_4VNNIW and AVX512_4FMAPS features Paolo Bonzini
2016-10-31 16:21 ` [Qemu-devel] [PULL 00/27] Misc patches for 2016-10-31 Peter Maydell
2016-10-31 17:18 ` Alex Bennée
2016-10-31 17:20 ` Peter Maydell
2016-10-31 17:57 ` Paolo Bonzini
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=1477924663-30950-3-git-send-email-pbonzini@redhat.com \
--to=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=wency@cn.fujitsu.com \
--cc=xiecl.fnst@cn.fujitsu.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).