Re: [PATCH v9 0/5] make balloon pages movable by compaction
On Sun, Aug 26, 2012 at 06:44:23PM +0300, Michael S. Tsirkin wrote: I am simply asking how was this patchset tested. It would be nice to have this info in commit log. Since this is an optimization patch it is strange to see one with no numbers at all. For example, you probably run some workload and played with the balloon, and then saw less huge pages without the patch and more with? Please put this info in the cover letter. Will do it, for sure. As soon as we get closer to an agreement on how the code has to behave and looks like. I'll use Mel's mmtests bench suite for that. Cheers! ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH v9 0/5] make balloon pages movable by compaction
On Sat, Aug 25, 2012 at 02:24:55AM -0300, Rafael Aquini wrote: Memory fragmentation introduced by ballooning might reduce significantly the number of 2MB contiguous memory blocks that can be used within a guest, thus imposing performance penalties associated with the reduced number of transparent huge pages that could be used by the guest workload. This patch-set follows the main idea discussed at 2012 LSFMMS session: Ballooning for transparent huge pages -- http://lwn.net/Articles/490114/ to introduce the required changes to the virtio_balloon driver, as well as the changes to the core compaction migration bits, in order to make those subsystems aware of ballooned pages and allow memory balloon pages become movable within a guest, thus avoiding the aforementioned fragmentation issue Meta-question: are there any numbers showing gain from this patchset? The reason I ask, on migration we notify host about each page individually. If this is rare maybe the patchset does not help much. If this is common we would be better off building up a list of multiple pages and passing them in one go. Rafael Aquini (5): mm: introduce a common interface for balloon pages mobility mm: introduce compaction and migration for ballooned pages virtio_balloon: introduce migration primitives to balloon pages mm: introduce putback_movable_pages() mm: add vm event counters for balloon pages compaction drivers/virtio/virtio_balloon.c| 287 ++--- include/linux/balloon_compaction.h | 137 ++ include/linux/migrate.h| 2 + include/linux/pagemap.h| 18 +++ include/linux/vm_event_item.h | 8 +- mm/Kconfig | 15 ++ mm/Makefile| 2 +- mm/balloon_compaction.c| 174 ++ mm/compaction.c| 51 --- mm/migrate.c | 57 +++- mm/page_alloc.c| 2 +- mm/vmstat.c| 10 +- 12 files changed, 715 insertions(+), 48 deletions(-) create mode 100644 include/linux/balloon_compaction.h create mode 100644 mm/balloon_compaction.c Change log: v9: * Adjust rcu_dereference usage to leverage page lock protection (Paul, Peter); * Enhance doc on compaction interface introduced to balloon driver (Michael); * Fix issue with isolated pages breaking leak_balloon() logics (Michael); v8: * introduce a common MM interface for balloon driver page compaction (Michael); * remove the global state preventing multiple balloon device support (Michael); * introduce RCU protection/syncrhonization to balloon page-mapping (Michael); v7: * fix a potential page leak case at 'putback_balloon_page' (Mel); * adjust vm-events-counter patch and remove its drop-on-merge message (Rik); * add 'putback_movable_pages' to avoid hacks on 'putback_lru_pages' (Minchan); v6: * rename 'is_balloon_page()' to 'movable_balloon_page()' (Rik); v5: * address Andrew Morton's review comments on the patch series; * address a couple extra nitpick suggestions on PATCH 01 (Minchan); v4: * address Rusty Russel's review comments on PATCH 02; * re-base virtio_balloon patch on 9c378abc5c0c6fc8e3acf5968924d274503819b3; V3: * address reviewers nitpick suggestions on PATCH 01 (Mel, Minchan); V2: * address Mel Gorman's review comments on PATCH 01; Preliminary test results: (2 VCPU 2048mB RAM KVM guest running 3.6.0_rc3+ -- after a reboot) * 64mB balloon: [root@localhost ~]# awk '/compact/ {print}' /proc/vmstat compact_blocks_moved 0 compact_pages_moved 0 compact_pagemigrate_failed 0 compact_stall 0 compact_fail 0 compact_success 0 compact_balloon_isolated 0 compact_balloon_migrated 0 compact_balloon_released 0 compact_balloon_returned 0 [root@localhost ~]# [root@localhost ~]# for i in $(seq 1 6); do echo 1 /proc/sys/vm/compact_memory done /dev/null [1] Doneecho 1 /proc/sys/vm/compact_memory [2] Doneecho 1 /proc/sys/vm/compact_memory [3] Doneecho 1 /proc/sys/vm/compact_memory [4] Doneecho 1 /proc/sys/vm/compact_memory [5]- Doneecho 1 /proc/sys/vm/compact_memory [6]+ Doneecho 1 /proc/sys/vm/compact_memory [root@localhost ~]# [root@localhost ~]# awk '/compact/ {print}' /proc/vmstat compact_blocks_moved 3108 compact_pages_moved 43169 compact_pagemigrate_failed 95 compact_stall 0 compact_fail 0 compact_success 0 compact_balloon_isolated 16384 compact_balloon_migrated 16384 compact_balloon_released 16384 compact_balloon_returned 0 * 128 mB balloon: [root@localhost ~]# awk '/compact/ {print}' /proc/vmstat compact_blocks_moved 0 compact_pages_moved 0 compact_pagemigrate_failed 0 compact_stall 0
Re: [PATCH v9 0/5] make balloon pages movable by compaction
On 08/26/2012 03:58 AM, Michael S. Tsirkin wrote: On Sat, Aug 25, 2012 at 02:24:55AM -0300, Rafael Aquini wrote: Memory fragmentation introduced by ballooning might reduce significantly the number of 2MB contiguous memory blocks that can be used within a guest, thus imposing performance penalties associated with the reduced number of transparent huge pages that could be used by the guest workload. This patch-set follows the main idea discussed at 2012 LSFMMS session: Ballooning for transparent huge pages -- http://lwn.net/Articles/490114/ to introduce the required changes to the virtio_balloon driver, as well as the changes to the core compaction migration bits, in order to make those subsystems aware of ballooned pages and allow memory balloon pages become movable within a guest, thus avoiding the aforementioned fragmentation issue Meta-question: are there any numbers showing gain from this patchset? The reason I ask, on migration we notify host about each page individually. If this is rare maybe the patchset does not help much. If this is common we would be better off building up a list of multiple pages and passing them in one go. The gain is in getting a better THP allocation rate inside the guest, allowing applications to run faster. The rarer it is for this code to run, the better - it means we are getting the benefits without the overhead :) -- All rights reversed ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH v9 0/5] make balloon pages movable by compaction
Memory fragmentation introduced by ballooning might reduce significantly the number of 2MB contiguous memory blocks that can be used within a guest, thus imposing performance penalties associated with the reduced number of transparent huge pages that could be used by the guest workload. This patch-set follows the main idea discussed at 2012 LSFMMS session: Ballooning for transparent huge pages -- http://lwn.net/Articles/490114/ to introduce the required changes to the virtio_balloon driver, as well as the changes to the core compaction migration bits, in order to make those subsystems aware of ballooned pages and allow memory balloon pages become movable within a guest, thus avoiding the aforementioned fragmentation issue Rafael Aquini (5): mm: introduce a common interface for balloon pages mobility mm: introduce compaction and migration for ballooned pages virtio_balloon: introduce migration primitives to balloon pages mm: introduce putback_movable_pages() mm: add vm event counters for balloon pages compaction drivers/virtio/virtio_balloon.c| 287 ++--- include/linux/balloon_compaction.h | 137 ++ include/linux/migrate.h| 2 + include/linux/pagemap.h| 18 +++ include/linux/vm_event_item.h | 8 +- mm/Kconfig | 15 ++ mm/Makefile| 2 +- mm/balloon_compaction.c| 174 ++ mm/compaction.c| 51 --- mm/migrate.c | 57 +++- mm/page_alloc.c| 2 +- mm/vmstat.c| 10 +- 12 files changed, 715 insertions(+), 48 deletions(-) create mode 100644 include/linux/balloon_compaction.h create mode 100644 mm/balloon_compaction.c Change log: v9: * Adjust rcu_dereference usage to leverage page lock protection (Paul, Peter); * Enhance doc on compaction interface introduced to balloon driver (Michael); * Fix issue with isolated pages breaking leak_balloon() logics (Michael); v8: * introduce a common MM interface for balloon driver page compaction (Michael); * remove the global state preventing multiple balloon device support (Michael); * introduce RCU protection/syncrhonization to balloon page-mapping (Michael); v7: * fix a potential page leak case at 'putback_balloon_page' (Mel); * adjust vm-events-counter patch and remove its drop-on-merge message(Rik); * add 'putback_movable_pages' to avoid hacks on 'putback_lru_pages' (Minchan); v6: * rename 'is_balloon_page()' to 'movable_balloon_page()' (Rik); v5: * address Andrew Morton's review comments on the patch series; * address a couple extra nitpick suggestions on PATCH 01 (Minchan); v4: * address Rusty Russel's review comments on PATCH 02; * re-base virtio_balloon patch on 9c378abc5c0c6fc8e3acf5968924d274503819b3; V3: * address reviewers nitpick suggestions on PATCH 01 (Mel, Minchan); V2: * address Mel Gorman's review comments on PATCH 01; Preliminary test results: (2 VCPU 2048mB RAM KVM guest running 3.6.0_rc3+ -- after a reboot) * 64mB balloon: [root@localhost ~]# awk '/compact/ {print}' /proc/vmstat compact_blocks_moved 0 compact_pages_moved 0 compact_pagemigrate_failed 0 compact_stall 0 compact_fail 0 compact_success 0 compact_balloon_isolated 0 compact_balloon_migrated 0 compact_balloon_released 0 compact_balloon_returned 0 [root@localhost ~]# [root@localhost ~]# for i in $(seq 1 6); do echo 1 /proc/sys/vm/compact_memory done /dev/null [1] Doneecho 1 /proc/sys/vm/compact_memory [2] Doneecho 1 /proc/sys/vm/compact_memory [3] Doneecho 1 /proc/sys/vm/compact_memory [4] Doneecho 1 /proc/sys/vm/compact_memory [5]- Doneecho 1 /proc/sys/vm/compact_memory [6]+ Doneecho 1 /proc/sys/vm/compact_memory [root@localhost ~]# [root@localhost ~]# awk '/compact/ {print}' /proc/vmstat compact_blocks_moved 3108 compact_pages_moved 43169 compact_pagemigrate_failed 95 compact_stall 0 compact_fail 0 compact_success 0 compact_balloon_isolated 16384 compact_balloon_migrated 16384 compact_balloon_released 16384 compact_balloon_returned 0 * 128 mB balloon: [root@localhost ~]# awk '/compact/ {print}' /proc/vmstat compact_blocks_moved 0 compact_pages_moved 0 compact_pagemigrate_failed 0 compact_stall 0 compact_fail 0 compact_success 0 compact_balloon_isolated 0 compact_balloon_migrated 0 compact_balloon_released 0 compact_balloon_returned 0 [root@localhost ~]# [root@localhost ~]# for i in $(seq 1 6); do echo 1 /proc/sys/vm/compact_memory done /dev/null [1] Doneecho 1 /proc/sys/vm/compact_memory [2] Doneecho 1 /proc/sys/vm/compact_memory [3] Doneecho 1 /proc/sys/vm/compact_memory [4] Doneecho 1