From 9bc9732faeff09828fe38c0ebe2401ee131a6fca Mon Sep 17 00:00:00 2001 From: Changlong Xie Date: Wed, 12 Oct 2016 18:18:28 +0800 Subject: nbd: Use CoQueue for free_sema instead of CoMutex 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 Reported-by: zhanghailiang Suggested-by: Paolo Bonzini Signed-off-by: Changlong Xie Message-Id: <1476267508-19499-1-git-send-email-xiecl.fnst@cn.fujitsu.com> Signed-off-by: Paolo Bonzini --- block/nbd-client.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'block/nbd-client.c') diff --git a/block/nbd-client.c b/block/nbd-client.c index 2cf3237ef3..40b28ab00b 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)); -- cgit v1.2.1