Re: [libvirt] [PATCH 1/4] Introduce virNodeAllocPages

A long time ago in a galaxy far, far away it has been decided that libvirt will manage not only domains but host as well. And with my latest work on qemu driver supporting huge pages, we miss the cherry on top: an API to allocate huge pages on the run. Currently users are forced to log into the host and adjust the huge pages pool themselves. However, with this API the problem is gone - they can both size up and size down the pool. Signed-off-by: Michal Privoznik <mprivozn(a)redhat.com&gt; --- daemon/remote.c | 37 ++++++++++++++++++++++++ include/libvirt/libvirt.h.in | 16 +++++++++++ src/driver.h | 10 +++++++ src/libvirt.c | 67 ++++++++++++++++++++++++++++++++++++++++++++ src/libvirt_public.syms | 1 + src/remote/remote_driver.c | 47 +++++++++++++++++++++++++++++++ src/remote/remote_protocol.x | 20 ++++++++++++- src/remote_protocol-structs | 17 +++++++++++ 8 files changed, 214 insertions(+), 1 deletion(-)

diff --git a/include/libvirt/libvirt.h.in b/include/libvirt/libvirt.h.in index 724314e..1a47bae 100644 --- a/include/libvirt/libvirt.h.in +++ b/include/libvirt/libvirt.h.in @@ -5505,6 +5505,22 @@ int virNodeGetFreePages(virConnectPtr conn, unsigned int cellcount, unsigned long long *counts, unsigned int flags); + +typedef enum { + VIR_NODE_ALLOC_PAGES_ADD = 0, /* Add @pageCounts to the pages pool. This + can be used only to size up the pool. */ + VIR_NODE_ALLOC_PAGES_SET = (1 << 0), /* Don't add @pageCounts, instead set + passed number of pages. This can be + used to free allocated pages. */

+} virNodeAllocPagesFlags; + +int virNodeAllocPages(virConnectPtr conn, + unsigned int npages, + unsigned int *pageSizes, + unsigned long long *pageCounts, + int startCell, + unsigned int cellCount, + unsigned int flags); /** * virSchedParameterType: * diff --git a/src/driver.h b/src/driver.h index bb748c4..dc62a8e 100644 --- a/src/driver.h +++ b/src/driver.h @@ -1212,6 +1212,15 @@ typedef int virDomainStatsRecordPtr **retStats, unsigned int flags); +typedef int +(*virDrvNodeAllocPages)(virConnectPtr conn, + unsigned int npages, + unsigned int *pageSizes, + unsigned long long *pageCounts, + int startCell, + unsigned int cellCount, + unsigned int flags); + typedef struct _virDriver virDriver; typedef virDriver *virDriverPtr; @@ -1435,6 +1444,7 @@ struct _virDriver { virDrvNodeGetFreePages nodeGetFreePages; virDrvConnectGetDomainCapabilities connectGetDomainCapabilities; virDrvConnectGetAllDomainStats connectGetAllDomainStats; + virDrvNodeAllocPages nodeAllocPages; }; diff --git a/src/libvirt.c b/src/libvirt.c index 7c63825..27445e5 100644 --- a/src/libvirt.c +++ b/src/libvirt.c @@ -21841,3 +21841,70 @@ virDomainStatsRecordListFree(virDomainStatsRecordPtr *stats) VIR_FREE(stats); } + + +/** + * virNodeAllocPages: + * @conn: pointer to the hypervisor connection + * @npages: number of items in the @pageSizes array + * @pageSizes: which huge page sizes to allocate + * @pageCounts: how many pages should be allocated + * @startCell: index of first cell to allocate pages on + * @cellCount: number of consecutive cells to allocate pages on + * @flags: extra flags; binary-OR of virConnectGetAllDomainStatsFlags

+ * + * Sometimes, when trying to start a new domain, it may be + * necessary to reserve some huge pages in the system pool which + * can be then allocated by the domain. This API serves that + * purpose. On its input, @pageSizes and @pageCounts are arrays + * of the same cardinality of @npages. The @pageSizes contains + * page sizes which are to be allocated in the system (the size + * unit is kibibytes), and @pageCounts then contains the number + * of pages to reserve. Depending on @flags specified, the number + * of pages is either added into the pool and the pool is sized + * up (@flags have VIR_NODE_ALLOC_PAGES_ADD set) or the number of + * pages is looked at the new size of pool and the pool can be + * both sized up or down (@flags have VIR_NODE_ALLOC_PAGES_SET + * set). The pages pool can be allocated over several NUMA nodes + * at once, just point at @startCell and tell how many subsequent + * NUMA nodes should be taken in. + * + * Returns: the number of nodes successfully adjusted or -1 in + * case of an error. + */ +int +virNodeAllocPages(virConnectPtr conn, + unsigned int npages, + unsigned int *pageSizes, + unsigned long long *pageCounts, + int startCell,

+ unsigned int cellCount, + unsigned int flags) +{ + VIR_DEBUG("conn=%p npages=%u pageSizes=%p pageCounts=%p " + "startCell=%d cellCount=%u flagx=%x", + conn, npages, pageSizes, pageCounts, startCell, + cellCount, flags); + + virResetLastError(); + + virCheckConnectReturn(conn, -1); + virCheckNonZeroArgGoto(npages, error); + virCheckNonNullArgGoto(pageSizes, error); + virCheckNonNullArgGoto(pageCounts, error); + + if (conn->driver->nodeAllocPages) { + int ret; + ret = conn->driver->nodeAllocPages(conn, npages, pageSizes, + pageCounts, startCell, + cellCount, flags); + if (ret < 0) + goto error; + return ret; + } + + virReportUnsupportedError(); + error: + virDispatchError(conn); + return -1; +} diff --git a/src/libvirt_public.syms b/src/libvirt_public.syms index e1f013f..89fbc71 100644 --- a/src/libvirt_public.syms +++ b/src/libvirt_public.syms @@ -677,6 +677,7 @@ LIBVIRT_1.2.8 { virDomainListGetStats; virDomainOpenGraphicsFD; virDomainStatsRecordListFree; + virNodeAllocPages; } LIBVIRT_1.2.7;