Changes between Version 11 and Version 12 of LLM

Timestamp:

10/06/11 02:27:01 (13 years ago)

Author:

lvpeng

Comment:

--

LLM

@@ -5 +5 @@
 == LLM's Architecture ==
 [[Image(figure1.jpg)]]
+
+      Figure 1. LLM Architecture.
 
 We design the implementation architecture of LLM as shown in Figure 1. Beyond Remus, we also migrate the change in network driver buffers. The entire process works as follows:
@@ -20 +22 @@
 
 [[Image(figure2.jpg)]]
+
+        Figure 2. Checkpointing Sequence.
 
 Figure 2 shows the time sequence of migrating the checkpointed resources and the incoming service requests at different frequencies on a single network socket. The entire sequence within an epoch is described as follows:
@@ -42 +46 @@
 [[Image(figure3.jpg)]]
 
+          Figure 3. Downtime under highNet and highsys.
+ 
 We observe that under highsys, LLM demonstrates a downtime that is longer than, yet comparable to, that of Remus. The reason is that LLM runs at low frequency, hence the migration traffic in each period will be higher than that of Remus. Under highnet, the downtime of LLM and Remus show a reverse relationship where LLM outperforms Remus. This is because, from the client side, there are too many duplicated packets to be served again by the backup machine in Remus. In LLM, on the contrary, the primary machine migrates the request packets as well as boundaries to the backup machine, i.e., only those packets yet to be served will be served by the backup. Thus the client does not need to re-transmit the requests, therefore will experience a much shorter downtime.
 
 [[Image(figure4.jpg)]]
 
-We evaluated the network delay under highnet and highsys as shown in Figures 4. In both cases, we observe that LLM significantly reduces the network delay by removing the egress queue management and releasing responses immediately. In Figure 4, we only recorded the average network delay in a migration period. Next, we show the details of the network delay in a specific migration period in Figure 4, in which the interval between two adjacent peak values represents one migration period.We observe that the network delay of Remus decreases linearly within a period but remains at a plateau. In LLM, on the contrary, the network delay is very high at the beginning of a period, then quickly decrease to nearly zero after a system update is over. Therefore, most of the time, LLM demonstrates a much shorter network delay than Remus.
+             Figure 4. Network Delay under highNet and highsys.
+
+We evaluated the network delay under highnet and highsys as shown in Figure 4. In both cases, we observe that LLM significantly reduces the network delay by removing the egress queue management and releasing responses immediately. In Figure 4, we only recorded the average network delay in a migration period. Next, we show the details of the network delay in a specific migration period in Figure 4, in which the interval between two adjacent peak values represents one migration period.We observe that the network delay of Remus decreases linearly within a period but remains at a plateau. In LLM, on the contrary, the network delay is very high at the beginning of a period, then quickly decrease to nearly zero after a system update is over. Therefore, most of the time, LLM demonstrates a much shorter network delay than Remus.
 
 [[Image(figure5.jpg)]]
 
+             Figure 5. Overhead under Kernel Compilation.
+
 Figure 5 shows the overhead under kernel compilation. Actually, the overhead significantly changes only in the checkpointing period interval of [1;60] seconds, as shown in the figure. For checkpointing with shorter periods, the migration of system updates may last longer than a configured checkpointing period, therefore the kernel compilation time for these cases are almost the same with minor fluctuation. For checkpointing with longer periods, especially when it is longer than the baseline (i.e., kernel compilation without any checkpointing), a VM suspension may or may not occur during one compilation process. Therefore, the kernel compilation time will be very close to the baseline, meaning a zero percent overhead. Right in this interval, LLM’s overhead due to the suspension of domain U is significantly lower than that of Remus, as it runs at much lower frequency than Remus.