path: root/Documentation
diff options
authorSeongJae Park <sjpark@amazon.de>2020-01-27 09:18:10 +0100
committerBoris Ostrovsky <boris.ostrovsky@oracle.com>2020-01-29 07:35:49 -0600
commitcb9369bdbb84440e9a8fded7eb2d0f94014f9a8f (patch)
treed9c7be3ca8f523b7750d86324d2b6c5058d112d4 /Documentation
parentxenbus/backend: Protect xenbus callback with lock (diff)
xen/blkback: Squeeze page pools if a memory pressure is detected
Each `blkif` has a free pages pool for the grant mapping. The size of the pool starts from zero and is increased on demand while processing the I/O requests. If current I/O requests handling is finished or 100 milliseconds has passed since last I/O requests handling, it checks and shrinks the pool to not exceed the size limit, `max_buffer_pages`. Therefore, host administrators can cause memory pressure in blkback by attaching a large number of block devices and inducing I/O. Such problematic situations can be avoided by limiting the maximum number of devices that can be attached, but finding the optimal limit is not so easy. Improper set of the limit can results in memory pressure or a resource underutilization. This commit avoids such problematic situations by squeezing the pools (returns every free page in the pool to the system) for a while (users can set this duration via a module parameter) if memory pressure is detected. Discussions =========== The `blkback`'s original shrinking mechanism returns only pages in the pool which are not currently be used by `blkback` to the system. In other words, the pages that are not mapped with granted pages. Because this commit is changing only the shrink limit but still uses the same freeing mechanism it does not touch pages which are currently mapping grants. Once memory pressure is detected, this commit keeps the squeezing limit for a user-specified time duration. The duration should be neither too long nor too short. If it is too long, the squeezing incurring overhead can reduce the I/O performance. If it is too short, `blkback` will not free enough pages to reduce the memory pressure. This commit sets the value as `10 milliseconds` by default because it is a short time in terms of I/O while it is a long time in terms of memory operations. Also, as the original shrinking mechanism works for at least every 100 milliseconds, this could be a somewhat reasonable choice. I also tested other durations (refer to the below section for more details) and confirmed that 10 milliseconds is the one that works best with the test. That said, the proper duration depends on actual configurations and workloads. That's why this commit allows users to set the duration as a module parameter. Memory Pressure Test ==================== To show how this commit fixes the memory pressure situation well, I configured a test environment on a xen-running virtualization system. On the `blkfront` running guest instances, I attach a large number of network-backed volume devices and induce I/O to those. Meanwhile, I measure the number of pages that swapped in (pswpin) and out (pswpout) on the `blkback` running guest. The test ran twice, once for the `blkback` before this commit and once for that after this commit. As shown below, this commit has dramatically reduced the memory pressure: pswpin pswpout before 76,672 185,799 after 867 3,967 Optimal Aggressive Shrinking Duration ------------------------------------- To find a best squeezing duration, I repeated the test with three different durations (1ms, 10ms, and 100ms). The results are as below: duration pswpin pswpout 1 707 5,095 10 867 3,967 100 362 3,348 As expected, the memory pressure decreases as the duration increases, but the reduction become slow from the `10ms`. Based on this results, I chose the default duration as 10ms. Performance Overhead Test ========================= This commit could incur I/O performance degradation under severe memory pressure because the squeezing will require more page allocations per I/O. To show the overhead, I artificially made a worst-case squeezing situation and measured the I/O performance of a `blkfront` running guest. For the artificial squeezing, I set the `blkback.max_buffer_pages` using the `/sys/module/xen_blkback/parameters/max_buffer_pages` file. In this test, I set the value to `1024` and `0`. The `1024` is the default value. Setting the value as `0` is same to a situation doing the squeezing always (worst-case). If the underlying block device is slow enough, the squeezing overhead could be hidden. For the reason, I use a fast block device, namely the rbd[1]: # xl block-attach guest phy:/dev/ram0 xvdb w For the I/O performance measurement, I run a simple `dd` command 5 times directly to the device as below and collect the 'MB/s' results. $ for i in {1..5}; do dd if=/dev/zero of=/dev/xvdb \ bs=4k count=$((256*512)); sync; done The results are as below. 'max_pgs' represents the value of the `blkback.max_buffer_pages` parameter. max_pgs Min Max Median Avg Stddev 0 417 423 420 419.4 2.5099801 1024 414 425 416 417.8 4.4384682 No difference proven at 95.0% confidence In short, even worst case squeezing on ramdisk based fast block device makes no visible performance degradation. Please note that this is just a very simple and minimal test. On systems using super-fast block devices and a special I/O workload, the results might be different. If you have any doubt, test on your machine with your workload to find the optimal squeezing duration for you. [1] https://www.kernel.org/doc/html/latest/admin-guide/blockdev/ramdisk.html Reviewed-by: Roger Pau Monné <roger.pau@citrix.com> Signed-off-by: SeongJae Park <sjpark@amazon.de> Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Diffstat (limited to 'Documentation')
1 files changed, 10 insertions, 0 deletions
diff --git a/Documentation/ABI/testing/sysfs-driver-xen-blkback b/Documentation/ABI/testing/sysfs-driver-xen-blkback
index 4e7babb3ba1f..ecb7942ff146 100644
--- a/Documentation/ABI/testing/sysfs-driver-xen-blkback
+++ b/Documentation/ABI/testing/sysfs-driver-xen-blkback
@@ -25,3 +25,13 @@ Description:
allocated without being in use. The time is in
seconds, 0 means indefinitely long.
The default is 60 seconds.
+What: /sys/module/xen_blkback/parameters/buffer_squeeze_duration_ms
+Date: December 2019
+KernelVersion: 5.6
+Contact: SeongJae Park <sjpark@amazon.de>
+ When memory pressure is reported to blkback this option
+ controls the duration in milliseconds that blkback will not
+ cache any page not backed by a grant mapping.
+ The default is 10ms.