Groupes de transactions

	for (;;) {
		clock_t timeout = zfs_txg_timeout * hz;
		clock_t timer;
		uint64_t txg;

		/*
		 * We sync when we're scanning, there's someone waiting
		 * on us, or the quiesce thread has handed off a txg to
		 * us, or we have reached our timeout.
		 */
		timer = (delta >= timeout ? 0 : timeout - delta);
		while (!dsl_scan_active(dp->dp_scan) &&
		    !tx->tx_exiting && timer > 0 &&
		    tx->tx_synced_txg >= tx->tx_sync_txg_waiting &&
		    !txg_has_quiesced_to_sync(dp)) {
			dprintf("waiting; tx_synced=%llu waiting=%llu dp=%p\n",
			    (u_longlong_t)tx->tx_synced_txg,
			    (u_longlong_t)tx->tx_sync_txg_waiting, dp);
			txg_thread_wait(tx, &cpr, &tx->tx_sync_more_cv, timer);
			delta = ddi_get_lbolt() - start;
			timer = (delta > timeout ? 0 : timeout - delta);
		}

	/*
	 * Grab all tc_open_locks so nobody else can get into this txg.
	 */
	for (c = 0; c < max_ncpus; c++)
		mutex_enter(&tx->tx_cpu[c].tc_open_lock);

	ASSERT(txg == tx->tx_open_txg);
	tx->tx_open_txg++;
	tx->tx_open_time = tx_open_time = gethrtime();

	DTRACE_PROBE2(txg__quiescing, dsl_pool_t *, dp, uint64_t, txg);
	DTRACE_PROBE2(txg__opened, dsl_pool_t *, dp, uint64_t, tx->tx_open_txg);

	/*
	 * Now that we've incremented tx_open_txg, we can let threads
	 * enter the next transaction group.
	 */
	for (c = 0; c < max_ncpus; c++)
		mutex_exit(&tx->tx_cpu[c].tc_open_lock);

	spa_txg_history_set(dp->dp_spa, txg, TXG_STATE_OPEN, tx_open_time);
	spa_txg_history_add(dp->dp_spa, txg + 1, tx_open_time);

	/*
	 * Quiesce the transaction group by waiting for everyone to
	 * call txg_rele_to_sync() for their open transaction handles.
	 */
	for (c = 0; c < max_ncpus; c++) {
		tx_cpu_t *tc = &tx->tx_cpu[c];
		mutex_enter(&tc->tc_lock);
		while (tc->tc_count[g] != 0)
			cv_wait(&tc->tc_cv[g], &tc->tc_lock);
		mutex_exit(&tc->tc_lock);
	}

	for (;;) {
		uint64_t txg;

		/*
		 * We quiesce when there's someone waiting on us.
		 * However, we can only have one txg in "quiescing" or
		 * "quiesced, waiting to sync" state.  So we wait until
		 * the "quiesced, waiting to sync" txg has been consumed
		 * by the sync thread.
		 */
		while (!tx->tx_exiting &&
		    (tx->tx_open_txg >= tx->tx_quiesce_txg_waiting ||
		    txg_has_quiesced_to_sync(dp)))
			txg_thread_wait(tx, &cpr, &tx->tx_quiesce_more_cv, 0);

		if (tx->tx_exiting)
			txg_thread_exit(tx, &cpr, &tx->tx_quiesce_thread);

		txg = tx->tx_open_txg;
		dprintf("txg=%llu quiesce_txg=%llu sync_txg=%llu\n",
		    (u_longlong_t)txg,
		    (u_longlong_t)tx->tx_quiesce_txg_waiting,
		    (u_longlong_t)tx->tx_sync_txg_waiting);
		tx->tx_quiescing_txg = txg;

		mutex_exit(&tx->tx_sync_lock);
		txg_quiesce(dp, txg);
		mutex_enter(&tx->tx_sync_lock);

		/*
		 * Hand this txg off to the sync thread.
		 */
		dprintf("quiesce done, handing off txg %llu\n",
		    (u_longlong_t)txg);
		tx->tx_quiescing_txg = 0;
		tx->tx_quiesced_txg = txg;
		DTRACE_PROBE2(txg__quiesced, dsl_pool_t *, dp, uint64_t, txg);
		cv_broadcast(&tx->tx_sync_more_cv);
		cv_broadcast(&tx->tx_quiesce_done_cv);
	}

		/*
		 * Consume the quiesced txg which has been handed off to
		 * us.  This may cause the quiescing thread to now be
		 * able to quiesce another txg, so we must signal it.
		 */
		ASSERT(tx->tx_quiesced_txg != 0);
		txg = tx->tx_quiesced_txg;
		tx->tx_quiesced_txg = 0;
		tx->tx_syncing_txg = txg;
		DTRACE_PROBE2(txg__syncing, dsl_pool_t *, dp, uint64_t, txg);
		cv_broadcast(&tx->tx_quiesce_more_cv);

		dprintf("txg=%llu quiesce_txg=%llu sync_txg=%llu\n",
		    (u_longlong_t)txg, (u_longlong_t)tx->tx_quiesce_txg_waiting,
		    (u_longlong_t)tx->tx_sync_txg_waiting);
		mutex_exit(&tx->tx_sync_lock);

		txg_stat_t *ts = spa_txg_history_init_io(spa, txg, dp);
		start = ddi_get_lbolt();
		spa_sync(spa, txg);
		delta = ddi_get_lbolt() - start;
		spa_txg_history_fini_io(spa, ts);

		mutex_enter(&tx->tx_sync_lock);
		tx->tx_synced_txg = txg;
		tx->tx_syncing_txg = 0;
		DTRACE_PROBE2(txg__synced, dsl_pool_t *, dp, uint64_t, txg);
		cv_broadcast(&tx->tx_sync_done_cv);

		 * (e.g. if we have sync tasks but no dirty user data). We need
		 * to check the uberblock's rootbp because it is updated if we
		 * have synced out dirty data (though in this case the MOS will
		 * most likely also be dirty due to second order effects, we
		 * don't want to rely on that here).
		 */
		if (pass == 1 &&
		    BP_GET_LOGICAL_BIRTH(&spa->spa_uberblock.ub_rootbp) < txg &&
		    !dmu_objset_is_dirty(mos, txg)) {
			/*
			 * Nothing changed on the first pass, therefore this
			 * TXG is a no-op. Avoid syncing deferred frees, so
			 * that we can keep this TXG as a no-op.
			 */
			ASSERT(txg_list_empty(&dp->dp_dirty_datasets, txg));
			ASSERT(txg_list_empty(&dp->dp_dirty_dirs, txg));
			ASSERT(txg_list_empty(&dp->dp_sync_tasks, txg));
			ASSERT(txg_list_empty(&dp->dp_early_sync_tasks, txg));
			break;
		}

		spa_sync_deferred_frees(spa, tx);
	} while (dmu_objset_is_dirty(mos, txg));
}