rpcsvc: provide each request handler thread its own queue

A single global per program queue is contended by all request handler
threads and event threads. This can lead to high contention. So,
reduce the contention by providing each request handler thread its own
private queue.

Thanks to "Manoj Pillai"<mpillai@redhat.com> for the idea of pairing a
single queue with a fixed request-handler-thread and event-thread,
which brought down the performance regression due to overhead of
queuing significantly.

Thanks to "Xavi Hernandez"<xhernandez@redhat.com> for discussion on
how to communicate the event-thread death to request-handler-thread.

Thanks to "Karan Sandha"<ksandha@redhat.com> for voluntarily running
the perf benchmarks to qualify that performance regression introduced
by ping-timer-fixes is fixed with this patch and patiently running
many iterations of regression tests while RCAing the issue.

Thanks to "Milind Changire"<mchangir@redhat.com> for patiently running
the many iterations of perf benchmarking tests while RCAing the
regression caused by ping-timer-expiry fixes.

Change-Id: I578c3fc67713f4234bd3abbec5d3fbba19059ea5
Fixes: bz#1644629
Signed-off-by: Raghavendra Gowdappa <rgowdapp@redhat.com>

1 files changed, 3 insertions, 2 deletions

diff --git a/cli/src/cli-rl.c b/cli/src/cli-rl.c
index 7831d0bcb40..38aa6f4b7ae 100644
--- a/cli/src/cli-rl.c
+++ b/cli/src/cli-rl.c
@@ -104,7 +104,7 @@ cli_rl_process_line(char *line)
 
 int
 cli_rl_stdin(int fd, int idx, int gen, void *data, int poll_out, int poll_in,
-             int poll_err)
+             int poll_err, char event_thread_died)
 {
     struct cli_state *state = NULL;
 
@@ -376,7 +376,8 @@ cli_rl_enable(struct cli_state *state)
         goto out;
     }
 
-    ret = event_register(state->ctx->event_pool, 0, cli_rl_stdin, state, 1, 0);
+    ret = event_register(state->ctx->event_pool, 0, cli_rl_stdin, state, 1, 0,
+                         0);
     if (ret == -1)
         goto out;