diff options
author | Jeff Darcy <jdarcy@redhat.com> | 2017-01-31 14:49:45 -0500 |
---|---|---|
committer | Shyamsundar Ranganathan <srangana@redhat.com> | 2017-02-01 19:54:58 -0500 |
commit | 83803b4b2d70e9e6e16bb050d7ac8e49ba420893 (patch) | |
tree | 9a6c1f3f9a723bf578f78c624d3ce9f44baac6db /xlators/mount | |
parent | 80b04666ec7019e132f76f734a88559457702f1b (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.
Backport of:
> Change-Id: I45059454e51d6f4cbb29a4953359c09a408695cb
> BUG: 1385758
> Reviewed-on: https://review.gluster.org/14763
Change-Id: I4bce9080f6c93d50171823298fdf920258317ee8
BUG: 1418091
Signed-off-by: Jeff Darcy <jdarcy@redhat.com>
Reviewed-on: https://review.gluster.org/16496
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: Shyamsundar Ranganathan <srangana@redhat.com>
Diffstat (limited to 'xlators/mount')
-rw-r--r-- | xlators/mount/fuse/src/fuse-bridge.c | 10 |
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 { |