On Wed, Jan 14, 2015 at 01:56:56AM +0100, Alexander Graf wrote:
> On hosts with limited virtual address space (32bit pointers), we can very
> easily run out of virtual memory with big thread pools.
>
> Instead, we should limit ourselves to small pools to keep memory footprint
> low on those systems.
>
> This patch fixes random VM stalls like
>
> (process:25114): GLib-ERROR **: gmem.c:103: failed to allocate 1048576 bytes
>
> on 32bit ARM systems for me.
>
> Signed-off-by: Alexander Graf <ag...@suse.de>
> ---
> thread-pool.c | 7 ++++++-
> 1 file changed, 6 insertions(+), 1 deletion(-)
>
> diff --git a/thread-pool.c b/thread-pool.c
> index e2cac8e..87a3ea9 100644
> --- a/thread-pool.c
> +++ b/thread-pool.c
> @@ -299,7 +299,12 @@ static void thread_pool_init_one(ThreadPool *pool,
> AioContext *ctx)
> qemu_mutex_init(&pool->lock);
> qemu_cond_init(&pool->worker_stopped);
> qemu_sem_init(&pool->sem, 0);
> - pool->max_threads = 64;
> + if (sizeof(pool) == 4) {
> + /* 32bit systems run out of virtual memory quickly */
> + pool->max_threads = 4;
> + } else {
> + pool->max_threads = 64;
> + }
> pool->new_thread_bh = aio_bh_new(ctx, spawn_thread_bh_fn, pool);
>
> QLIST_INIT(&pool->head);This patch has not been applied. Have there been any changes in this area? Stefan
pgpN4R7b9yt74.pgp
Description: PGP signature
