util/u_queue: track job size and limit the size of queue growth

When both UTIL_QUEUE_INIT_RESIZE_IF_FULL and
UTIL_QUEUE_INIT_USE_MINIMUM_PRIORITY are set, we can get into a
situation where the queue never executes and grows to a huge size
due to all other threads being busy.

This is the case with the shader cache when attempting to compile a
huge number of shaders up front. If all threads are busy compiling
shaders the cache queues memory use can climb into the many GBs
very fast.

The use of these two flags with the shader cache is intended to
allow shaders compiled at runtime to be compiled as fast as possible.
To avoid huge memory use but still allow the queue to perform
optimally in the run time compilation case, we now add the ability
to track memory consumed by the jobs in the queue and limit it to
a hardcoded 256MB which should be more than enough.

Reviewed-by: Marek Olšák <[email protected]>

1 files changed, 14 insertions, 3 deletions

diff --git a/src/util/u_queue.c b/src/util/u_queue.c
index 81225a80faa..ca72968053a 100644
--- a/src/util/u_queue.c
+++ b/src/util/u_queue.c
@@ -33,6 +33,9 @@
 #include "util/u_thread.h"
 #include "u_process.h"
 
+/* Define 256MB */
+#define S_256MB (256 * 1024 * 1024)
+
 static void
 util_queue_kill_threads(struct util_queue *queue, unsigned keep_num_threads,
                         bool finish_locked);
@@ -290,6 +293,8 @@ util_queue_thread_func(void *input)
          util_queue_fence_signal(job.fence);
          if (job.cleanup)
             job.cleanup(job.job, thread_index);
+
+         queue->total_jobs_size -= job.job_size;
       }
    }
 
@@ -513,7 +518,8 @@ util_queue_add_job(struct util_queue *queue,
                    void *job,
                    struct util_queue_fence *fence,
                    util_queue_execute_func execute,
-                   util_queue_execute_func cleanup)
+                   util_queue_execute_func cleanup,
+                   const size_t job_size)
 {
    struct util_queue_job *ptr;
 
@@ -531,7 +537,8 @@ util_queue_add_job(struct util_queue *queue,
    assert(queue->num_queued >= 0 && queue->num_queued <= queue->max_jobs);
 
    if (queue->num_queued == queue->max_jobs) {
-      if (queue->flags & UTIL_QUEUE_INIT_RESIZE_IF_FULL) {
+      if (queue->flags & UTIL_QUEUE_INIT_RESIZE_IF_FULL &&
+          queue->total_jobs_size + job_size < S_256MB) {
          /* If the queue is full, make it larger to avoid waiting for a free
           * slot.
           */
@@ -570,7 +577,10 @@ util_queue_add_job(struct util_queue *queue,
    ptr->fence = fence;
    ptr->execute = execute;
    ptr->cleanup = cleanup;
+   ptr->job_size = job_size;
+
    queue->write_idx = (queue->write_idx + 1) % queue->max_jobs;
+   queue->total_jobs_size += ptr->job_size;
 
    queue->num_queued++;
    cnd_signal(&queue->has_queued_cond);
@@ -642,7 +652,8 @@ util_queue_finish(struct util_queue *queue)
 
    for (unsigned i = 0; i < queue->num_threads; ++i) {
       util_queue_fence_init(&fences[i]);
-      util_queue_add_job(queue, &barrier, &fences[i], util_queue_finish_execute, NULL);
+      util_queue_add_job(queue, &barrier, &fences[i],
+                         util_queue_finish_execute, NULL, 0);
    }
 
    for (unsigned i = 0; i < queue->num_threads; ++i) {