1. 21 Oct, 2021 1 commit
    • Stefan Hajnoczi's avatar
      coroutine: resize pool periodically instead of limiting size · 4b2b3d26
      Stefan Hajnoczi authored
      
      
      It was reported that enabling SafeStack reduces IOPS significantly
      (>25%) with the following fio benchmark on virtio-blk using a NVMe host
      block device:
      
        # fio --rw=randrw --bs=4k --iodepth=64 --runtime=1m --direct=1 \
      	--filename=/dev/vdb --name=job1 --ioengine=libaio --thread \
      	--group_reporting --numjobs=16 --time_based \
              --output=/tmp/fio_result
      
      Serge Guelton and I found that SafeStack is not really at fault, it just
      increases the cost of coroutine creation. This fio workload exhausts the
      coroutine pool and coroutine creation becomes a bottleneck. Previous
      work by Honghao Wang also pointed to excessive coroutine creation.
      
      Creating new coroutines is expensive due to allocating new stacks with
      mmap(2) and mprotect(2). Currently there are thread-local and global
      pools that recycle old Coroutine objects and their stacks but the
      hardcoded size limit of 64 for thread-local pools and 128 for the global
      pool is insufficient for the fio benchmark shown above.
      
      This patch changes the coroutine pool algorithm to a simple thread-local
      pool without a maximum size limit. Threads periodically shrink the pool
      down to a size sufficient for the maximum observed number of coroutines.
      
      The global pool is removed by this patch. It can help to hide the fact
      that local pools are easily exhausted, but it's doesn't fix the root
      cause. I don't think there is a need for a global pool because QEMU's
      threads are long-lived, so let's keep things simple.
      
      Performance of the above fio benchmark is as follows:
      
            Before   After
      IOPS     60k     97k
      
      Memory usage varies over time as needed by the workload:
      
                  VSZ (KB)             RSS (KB)
      Before fio  4705248              843128
      During fio  5747668 (+ ~100 MB)  849280
      After fio   4694996 (- ~100 MB)  845184
      
      This confirms that coroutines are indeed being freed when no longer
      needed.
      
      Thanks to Serge Guelton for working on identifying the bottleneck with
      me!
      Reported-by: Tingting Mao's avatarTingting Mao <timao@redhat.com>
      Signed-off-by: Stefan Hajnoczi's avatarStefan Hajnoczi <stefanha@redhat.com>
      Message-id: 20210913153524.1190696-1-stefanha@redhat.com
      Cc: Serge Guelton <sguelton@redhat.com>
      Cc: Honghao Wang <wanghonghao@bytedance.com>
      Cc: Paolo Bonzini <pbonzini@redhat.com>
      Cc: Daniele Buono <dbuono@linux.vnet.ibm.com>
      Signed-off-by: Stefan Hajnoczi's avatarStefan Hajnoczi <stefanha@redhat.com>
      
      [Moved atexit notifier to coroutine_delete() after GitLab CI reported a
      memory leak in tests/unit/test-aio-multithread because the Coroutine
      object was created in the main thread but runs in an IOThread (where
      it's also deleted).
      --Stefan]
      4b2b3d26
  2. 20 Oct, 2021 39 commits