From: Tao Xu <tao3.xu@intel.com>
To: imammedo@redhat.com, eblake@redhat.com, ehabkost@redhat.com
Cc: jingqi.liu@intel.com, tao3.xu@intel.com, fan.du@intel.com,
qemu-devel@nongnu.org, jonathan.cameron@huawei.com
Subject: [PATCH v13 07/12] numa: Calculate hmat latency and bandwidth entry list
Date: Sun, 20 Oct 2019 19:11:20 +0800 [thread overview]
Message-ID: <20191020111125.27659-8-tao3.xu@intel.com> (raw)
In-Reply-To: <20191020111125.27659-1-tao3.xu@intel.com>
Compress HMAT latency and bandwidth raw data into uint16_t data,
which can be stored in HMAT table.
Suggested-by: Igor Mammedov <imammedo@redhat.com>
Signed-off-by: Tao Xu <tao3.xu@intel.com>
---
New patch in v13.
---
hw/core/numa.c | 57 +++++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 56 insertions(+), 1 deletion(-)
diff --git a/hw/core/numa.c b/hw/core/numa.c
index 3cf77f6ac9..4033a5a470 100644
--- a/hw/core/numa.c
+++ b/hw/core/numa.c
@@ -474,6 +474,45 @@ static void complete_init_numa_distance(MachineState *ms)
}
}
+static void calculate_hmat_entry_list(HMAT_LB_Info *hmat_lb, int num_nodes)
+{
+ int i, index;
+ uint16_t *entry_list;
+ uint64_t base;
+ GArray *lb_data_list;
+ HMAT_LB_Data *lb_data;
+
+ if (hmat_lb->data_type <= HMAT_LB_DATA_WRITE_LATENCY) {
+ base = hmat_lb->base_latency;
+ lb_data_list = hmat_lb->latency;
+ } else {
+ base = hmat_lb->base_bandwidth;
+ lb_data_list = hmat_lb->bandwidth;
+ }
+
+ entry_list = g_malloc0(lb_data_list->len * sizeof(uint16_t));
+ for (i = 0; i < lb_data_list->len; i++) {
+ lb_data = &g_array_index(lb_data_list, HMAT_LB_Data, i);
+ index = lb_data->initiator * num_nodes + lb_data->target;
+ if (entry_list[index]) {
+ error_report("Duplicate configuration of the latency for "
+ "initiator=%d and target=%d.", lb_data->initiator,
+ lb_data->target);
+ exit(1);
+ }
+
+ entry_list[index] = (uint16_t)(lb_data->rawdata / base);
+ }
+
+ if (hmat_lb->data_type <= HMAT_LB_DATA_WRITE_LATENCY) {
+ hmat_lb->entry_latency = entry_list;
+ } else {
+ /* Convert base from Byte to Megabyte */
+ hmat_lb->base_bandwidth = base / MiB;
+ hmat_lb->entry_bandwidth = entry_list;
+ }
+}
+
void numa_legacy_auto_assign_ram(MachineClass *mc, NodeInfo *nodes,
int nb_nodes, ram_addr_t size)
{
@@ -512,9 +551,10 @@ void numa_default_auto_assign_ram(MachineClass *mc, NodeInfo *nodes,
void numa_complete_configuration(MachineState *ms)
{
- int i;
+ int i, hierarchy, type;
MachineClass *mc = MACHINE_GET_CLASS(ms);
NodeInfo *numa_info = ms->numa_state->nodes;
+ HMAT_LB_Info *numa_hmat_lb;
/*
* If memory hotplug is enabled (slots > 0) but without '-numa'
@@ -611,6 +651,21 @@ void numa_complete_configuration(MachineState *ms)
/* Validation succeeded, now fill in any missing distances. */
complete_init_numa_distance(ms);
}
+
+ if (ms->numa_state->hmat_enabled) {
+ for (hierarchy = HMAT_LB_MEM_MEMORY;
+ hierarchy <= HMAT_LB_MEM_CACHE_3RD_LEVEL; hierarchy++) {
+ for (type = HMAT_LB_DATA_ACCESS_LATENCY;
+ type <= HMAT_LB_DATA_WRITE_BANDWIDTH; type++) {
+ numa_hmat_lb = ms->numa_state->hmat_lb[hierarchy][type];
+
+ if (numa_hmat_lb) {
+ calculate_hmat_entry_list(numa_hmat_lb,
+ ms->numa_state->num_nodes);
+ }
+ }
+ }
+ }
}
}
--
2.20.1
next prev parent reply other threads:[~2019-10-20 11:20 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-10-20 11:11 [PATCH v13 00/12] Build ACPI Heterogeneous Memory Attribute Table (HMAT) Tao Xu
2019-10-20 11:11 ` [PATCH v13 01/12] util/cutils: Add qemu_strtotime_ps() Tao Xu
2019-10-23 1:08 ` Eduardo Habkost
2019-10-23 6:07 ` Tao Xu
2019-10-23 1:13 ` Eric Blake
2019-10-23 1:50 ` Tao Xu
2019-10-24 9:54 ` Daniel P. Berrangé
2019-10-24 13:20 ` Eduardo Habkost
2019-10-25 1:22 ` Tao Xu
2019-10-20 11:11 ` [PATCH v13 02/12] tests/cutils: Add test for qemu_strtotime_ps() Tao Xu
2019-10-20 11:11 ` [PATCH v13 03/12] qapi: Add builtin type time Tao Xu
2019-10-20 11:11 ` [PATCH v13 04/12] tests: Add test for QAPI " Tao Xu
2019-10-20 11:11 ` [PATCH v13 05/12] numa: Extend CLI to provide initiator information for numa nodes Tao Xu
2019-10-21 12:29 ` Igor Mammedov
2019-10-22 1:01 ` Tao Xu
2019-10-20 11:11 ` [PATCH v13 06/12] numa: Extend CLI to provide memory latency and bandwidth information Tao Xu
2019-10-22 7:08 ` Igor Mammedov
2019-10-22 8:22 ` Tao Xu
2019-10-23 15:28 ` Igor Mammedov
2019-10-25 6:33 ` Tao Xu
2019-10-25 13:27 ` Igor Mammedov
2019-10-25 19:44 ` Markus Armbruster
2019-10-25 20:51 ` Eduardo Habkost
2019-10-28 2:05 ` Tao Xu
2019-10-28 5:46 ` Markus Armbruster
2019-10-28 7:25 ` Tao Xu
2019-10-20 11:11 ` Tao Xu [this message]
2019-10-20 11:11 ` [PATCH v13 08/12] numa: Extend CLI to provide memory side cache information Tao Xu
2019-10-20 11:11 ` [PATCH v13 09/12] hmat acpi: Build Memory Proximity Domain Attributes Structure(s) Tao Xu
2019-10-20 11:11 ` [PATCH v13 10/12] hmat acpi: Build System Locality Latency and Bandwidth Information Structure(s) Tao Xu
2019-10-20 11:11 ` [PATCH v13 11/12] hmat acpi: Build Memory Side Cache " Tao Xu
2019-10-20 11:11 ` [PATCH v13 12/12] tests/bios-tables-test: add test cases for ACPI HMAT Tao Xu
2019-10-20 11:43 ` [PATCH v13 00/12] Build ACPI Heterogeneous Memory Attribute Table (HMAT) no-reply
2019-10-20 12:13 ` no-reply
2019-10-20 12:57 ` no-reply
2019-10-20 13:19 ` no-reply
2019-10-22 11:22 ` Markus Armbruster
2019-10-23 1:46 ` Tao Xu
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20191020111125.27659-8-tao3.xu@intel.com \
--to=tao3.xu@intel.com \
--cc=eblake@redhat.com \
--cc=ehabkost@redhat.com \
--cc=fan.du@intel.com \
--cc=imammedo@redhat.com \
--cc=jingqi.liu@intel.com \
--cc=jonathan.cameron@huawei.com \
--cc=qemu-devel@nongnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).