diff options
| author | Jeff Darcy <jdarcy@redhat.com> | 2016-12-08 16:24:15 -0500 |
|---|---|---|
| committer | Vijay Bellur <vbellur@redhat.com> | 2017-01-30 19:13:58 -0500 |
| commit | 1a95fc3036db51b82b6a80952f0908bc2019d24a (patch) | |
| tree | b983ac196a8165d5cb5e860a5ef97d3e9a41b5c9 /xlators/mount/fuse | |
| parent | 7f7d7a939e46b330a084d974451eee4757ba61b4 (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')
| -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 { |