From: Keir Fraser Date: Tue, 9 Dec 2008 12:44:32 +0000 (+0000) Subject: xend: Fix memory allocation bug after hvm reboot in numa system X-Git-Tag: archive/raspbian/4.8.0-1+rpi1~1^2~14026^2~57 X-Git-Url: https://dgit.raspbian.org/%22http:/www.example.com/cgi/%22https:/%22bookmarks://%22Dat/%22http:/www.example.com/cgi/%22https:/%22bookmarks:/%22Dat?a=commitdiff_plain;h=ce4d300de0f5dd0ff1762e26bed8c008cf784a49;p=xen.git xend: Fix memory allocation bug after hvm reboot in numa system Recently we find a bug on Nahelem machine (totally with two nodes, 6G memory (3G in each node): - Start a HVM guest with its all VCPUS pinned to node1, so all its memory is allocated from node1. - Reboot the HVM. - There will be some memory allocated from node0 even there is enough free memory on node1. Reason: For security issues, xen will not put all the pages of a dying hvm to domheap directly, but put them in scrub list and wait for handled by page_scrub_softirq(). If the dying hvm have a lot of memory, page_scrub_softirq() will not handle all of them before the start the hvm. There are some pages belong to node1 still in scrub list, new hvm can't use pages in it. So this hvm will get different memory distribution than before. Before changeset 18304, page_scrub_softirq() can be excuted parallel between all the cpus. Changeset 18305 serialise page_scrub_softirq() and Changeset 18307 serialise page_scrub_softirq() with a new lock to avoid holding up acquiring page_scrub_lock in free_domheap_pages(). Those changeset slow the ability to handle pages in scrub list. So the bug becomes more obvious after. Patch: This patch modifiers balloon.free to avoid this bug. After patch, balloon.free will check whether current machine is a numa system and the new created hvm has all its vcpus in the same node. If all the conditions above fit, we will wait until all the pages in scrub list are freed (if waiting time go beyond 20s, we will stop waiting it.). This seems to be too restricted at the first glance. We used to only wait for the free memory size of pinned node is bigger than required. But as we know HVM memory alloction granularity is 2M. Even the former condition is satisfied, we still may not find enough 2M-size memory on that node. Signed-off-by: Ting Zhou Signed-off-by: Xiaowei Yang --- diff --git a/tools/python/xen/xend/XendCheckpoint.py b/tools/python/xen/xend/XendCheckpoint.py index af76bdc7e1..ed16c345d2 100644 --- a/tools/python/xen/xend/XendCheckpoint.py +++ b/tools/python/xen/xend/XendCheckpoint.py @@ -253,7 +253,7 @@ def restore(xd, fd, dominfo = None, paused = False, relocating = False): # set memory limit xc.domain_setmaxmem(dominfo.getDomid(), maxmem) - balloon.free(memory + shadow) + balloon.free(memory + shadow, dominfo) shadow_cur = xc.shadow_mem_control(dominfo.getDomid(), shadow / 1024) dominfo.info['shadow_memory'] = shadow_cur diff --git a/tools/python/xen/xend/XendDomainInfo.py b/tools/python/xen/xend/XendDomainInfo.py index 7a8349d035..424e08e65e 100644 --- a/tools/python/xen/xend/XendDomainInfo.py +++ b/tools/python/xen/xend/XendDomainInfo.py @@ -2105,7 +2105,7 @@ class XendDomainInfo: # overhead is greater for some types of domain than others. For # example, an x86 HVM domain will have a default shadow-pagetable # allocation of 1MB. We free up 2MB here to be on the safe side. - balloon.free(2*1024) # 2MB should be plenty + balloon.free(2*1024, self) # 2MB should be plenty ssidref = 0 if security.on() == xsconstants.XS_POLICY_USE: @@ -2299,7 +2299,7 @@ class XendDomainInfo: vtd_mem = ((vtd_mem + 1023) / 1024) * 1024 # Make sure there's enough RAM available for the domain - balloon.free(memory + shadow + vtd_mem) + balloon.free(memory + shadow + vtd_mem, self) # Set up the shadow memory shadow_cur = xc.shadow_mem_control(self.domid, shadow / 1024) @@ -2716,7 +2716,7 @@ class XendDomainInfo: # The domain might already have some shadow memory overhead_kb -= xc.shadow_mem_control(self.domid) * 1024 if overhead_kb > 0: - balloon.free(overhead_kb) + balloon.free(overhead_kb, self) def _unwatchVm(self): """Remove the watch on the VM path, if any. Idempotent. Nothrow diff --git a/tools/python/xen/xend/balloon.py b/tools/python/xen/xend/balloon.py index 828e1bc024..38879affb0 100644 --- a/tools/python/xen/xend/balloon.py +++ b/tools/python/xen/xend/balloon.py @@ -67,7 +67,7 @@ def get_dom0_target_alloc(): raise VmError('Failed to query target memory allocation of dom0.') return kb -def free(need_mem): +def free(need_mem ,self): """Balloon out memory from the privileged domain so that there is the specified required amount (in KiB) free. """ @@ -122,6 +122,40 @@ def free(need_mem): if need_mem >= max_free_mem: retries = rlimit + # Check whethercurrent machine is a numa system and the new + # created hvm has all its vcpus in the same node, if all the + # conditions above are fit. We will wait until all the pages + # in scrub list are freed (if waiting time go beyond 20s, + # we will stop waiting it.) + if physinfo['nr_nodes'] > 1 and retries == 0: + oldnode = -1 + waitscrub = 1 + vcpus = self.info['cpus'][0] + for vcpu in vcpus: + nodenum = 0 + for node in physinfo['node_to_cpu']: + for cpu in node: + if vcpu == cpu: + if oldnode == -1: + oldnode = nodenum + elif oldnode != nodenum: + waitscrub = 0 + nodenum = nodenum + 1 + + if waitscrub == 1 and scrub_mem > 0: + log.debug("wait for scrub %s", scrub_mem) + while scrub_mem > 0 and retries < rlimit: + time.sleep(sleep_time) + physinfo = xc.physinfo() + free_mem = physinfo['free_memory'] + scrub_mem = physinfo['scrub_memory'] + retries += 1 + sleep_time += SLEEP_TIME_GROWTH + log.debug("scrub for %d times", retries) + + retries = 0 + sleep_time = SLEEP_TIME_GROWTH + while retries < rlimit: physinfo = xc.physinfo() free_mem = physinfo['free_memory']