es translog 切换时的延时

从代码来看，translog切换时，需要先关闭旧的，然后打开新的，在这个时间段内（从日志看应该是ms级别）来的请求，延迟是不是比正常情况下要高，从而形成一个小尖峰.
下面是切换translog的源码

public void rollGeneration() throws IOException {

        syncBeforeRollGeneration();

        if (current.totalOperations() == 0 && primaryTermSupplier.getAsLong() == current.getPrimaryTerm()) {

            return;

        }

        try (Releasable ignored = writeLock.acquire()) {

            ensureOpen();

            try {

                final TranslogReader reader = current.closeIntoReader();

                readers.add(reader);

                assert Checkpoint.read(location.resolve(CHECKPOINT_FILE_NAME)).generation == current.getGeneration();

                copyCheckpointTo(location.resolve(getCommitCheckpointFileName(current.getGeneration())));

                // create a new translog file; this will sync it and update the checkpoint data;

                current = createWriter(current.getGeneration() + 1);

                logger.trace("current translog set to [{}]", current.getGeneration());

            } catch (final Exception e) {

                tragedy.setTragicException(e);

                closeOnTragicEvent(e);

                throw e;

            }

        }

    }