qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Vivek Goyal <vgoyal@redhat.com>
To: qemu-devel@nongnu.org, virtio-fs-list <virtio-fs@redhat.com>
Cc: jose.carlos.venegas.munoz@intel.com, dgilbert@redhat.com,
	stefanha@redhat.com
Subject: [PATCH v3] virtiofsd: Use --thread-pool-size=0 to mean no thread pool
Date: Tue, 17 Nov 2020 14:41:31 -0500	[thread overview]
Message-ID: <20201117194131.GA96587@redhat.com> (raw)

This is V3 of the patch. A minor change since V2 is to reverse the list
before executing requests. We are prepending elements to the list and that
means when we start processing requests, we are processing these in
the reverse order. Though we don't guarantee any ordering but it does
not hurt to process requests in same order as received as much as
possible.

Right now we create a thread pool and main thread hands over the request
to thread in thread pool to process. Number of threads in thread pool
can be managed by option --thread-pool-size.

In tests we have noted that many of the workloads are getting better
performance if we don't use a thread pool at all and process all
the requests in the context of a thread receiving the request.

Hence give user an option to be able to run virtiofsd without using
a thread pool.

To implement this, I have used existing option --thread-pool-size. This
option defines how many maximum threads can be in the thread pool.
Thread pool size zero freezes thead pool. I can't see why will one
start virtiofsd with a frozen thread pool (hence frozen file system).
So I am redefining --thread-pool-size=0 to mean, don't use a thread pool.
Instead process the request in the context of thread receiving request
from the queue.

Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
---
 tools/virtiofsd/fuse_virtio.c | 37 ++++++++++++++++++++++++++---------
 1 file changed, 28 insertions(+), 9 deletions(-)

diff --git a/tools/virtiofsd/fuse_virtio.c b/tools/virtiofsd/fuse_virtio.c
index 83ba07c6cd..6c56e606ef 100644
--- a/tools/virtiofsd/fuse_virtio.c
+++ b/tools/virtiofsd/fuse_virtio.c
@@ -588,13 +588,18 @@ static void *fv_queue_thread(void *opaque)
     struct VuDev *dev = &qi->virtio_dev->dev;
     struct VuVirtq *q = vu_get_queue(dev, qi->qidx);
     struct fuse_session *se = qi->virtio_dev->se;
-    GThreadPool *pool;
-
-    pool = g_thread_pool_new(fv_queue_worker, qi, se->thread_pool_size, FALSE,
-                             NULL);
-    if (!pool) {
-        fuse_log(FUSE_LOG_ERR, "%s: g_thread_pool_new failed\n", __func__);
-        return NULL;
+    GThreadPool *pool = NULL;
+    GList *req_list = NULL;
+
+    if (se->thread_pool_size) {
+        fuse_log(FUSE_LOG_DEBUG, "%s: Creating thread pool for Queue %d\n",
+                 __func__, qi->qidx);
+        pool = g_thread_pool_new(fv_queue_worker, qi, se->thread_pool_size,
+                                 FALSE, NULL);
+        if (!pool) {
+            fuse_log(FUSE_LOG_ERR, "%s: g_thread_pool_new failed\n", __func__);
+            return NULL;
+        }
     }
 
     fuse_log(FUSE_LOG_INFO, "%s: Start for queue %d kick_fd %d\n", __func__,
@@ -669,14 +674,28 @@ static void *fv_queue_thread(void *opaque)
 
             req->reply_sent = false;
 
-            g_thread_pool_push(pool, req, NULL);
+            if (!se->thread_pool_size) {
+                req_list = g_list_prepend(req_list, req);
+            } else {
+                g_thread_pool_push(pool, req, NULL);
+            }
         }
 
         pthread_mutex_unlock(&qi->vq_lock);
         pthread_rwlock_unlock(&qi->virtio_dev->vu_dispatch_rwlock);
+
+        /* Process all the requests. */
+        if (!se->thread_pool_size && req_list != NULL) {
+            req_list = g_list_reverse(req_list);
+            g_list_foreach(req_list, fv_queue_worker, qi);
+            g_list_free(req_list);
+            req_list = NULL;
+        }
     }
 
-    g_thread_pool_free(pool, FALSE, TRUE);
+    if (pool) {
+        g_thread_pool_free(pool, FALSE, TRUE);
+    }
 
     return NULL;
 }
-- 
2.25.4



             reply	other threads:[~2020-11-17 19:42 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-11-17 19:41 Vivek Goyal [this message]
2020-11-18  8:48 ` [PATCH v3] virtiofsd: Use --thread-pool-size=0 to mean no thread pool Stefan Hajnoczi

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=20201117194131.GA96587@redhat.com \
    --to=vgoyal@redhat.com \
    --cc=dgilbert@redhat.com \
    --cc=jose.carlos.venegas.munoz@intel.com \
    --cc=qemu-devel@nongnu.org \
    --cc=stefanha@redhat.com \
    --cc=virtio-fs@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 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).