summaryrefslogtreecommitdiffstats
path: root/xlators/mount/fuse/src
diff options
context:
space:
mode:
authorJeff Darcy <jdarcy@redhat.com>2016-12-08 16:24:15 -0500
committerVijay Bellur <vbellur@redhat.com>2017-01-30 19:13:58 -0500
commit1a95fc3036db51b82b6a80952f0908bc2019d24a (patch)
treeb983ac196a8165d5cb5e860a5ef97d3e9a41b5c9 /xlators/mount/fuse/src
parent7f7d7a939e46b330a084d974451eee4757ba61b4 (diff)
core: run many bricks within one glusterfsd process
This patch adds support for multiple brick translator stacks running in a single brick server process. This reduces our per-brick memory usage by approximately 3x, and our appetite for TCP ports even more. It also creates potential to avoid process/thread thrashing, and to improve QoS by scheduling more carefully across the bricks, but realizing that potential will require further work. Multiplexing is controlled by the "cluster.brick-multiplex" global option. By default it's off, and bricks are started in separate processes as before. If multiplexing is enabled, then *compatible* bricks (mostly those with the same transport options) will be started in the same process. Change-Id: I45059454e51d6f4cbb29a4953359c09a408695cb BUG: 1385758 Signed-off-by: Jeff Darcy <jdarcy@redhat.com> Reviewed-on: https://review.gluster.org/14763 Smoke: Gluster Build System <jenkins@build.gluster.org> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Vijay Bellur <vbellur@redhat.com>
Diffstat (limited to 'xlators/mount/fuse/src')
-rw-r--r--xlators/mount/fuse/src/fuse-bridge.c10
1 files changed, 10 insertions, 0 deletions
diff --git a/xlators/mount/fuse/src/fuse-bridge.c b/xlators/mount/fuse/src/fuse-bridge.c
index 38b1a74c269..6c4b02900ef 100644
--- a/xlators/mount/fuse/src/fuse-bridge.c
+++ b/xlators/mount/fuse/src/fuse-bridge.c
@@ -5021,6 +5021,16 @@ fuse_thread_proc (void *data)
priv->iobuf = iobuf;
+ /*
+ * This can be moved around a bit, but it's important to do it
+ * *after* the readv. Otherwise, a graph switch could occur
+ * while we're in readv and we'll process the next request on
+ * the old graph before we come to the part of the loop above
+ * readv and check again. That would be wrong.
+ */
+ if (priv->init_recvd)
+ fuse_graph_sync (this);
+
if (finh->opcode == FUSE_WRITE)
msg = iov_in[1].iov_base;
else {