qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Juan Quintela <quintela@redhat.com>
To: qemu-devel@nongnu.org
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>,
	Li Zhijian <lizhijian@cn.fujitsu.com>,
	Juan Quintela <quintela@redhat.com>
Subject: [PULL 7/7] migration/rdma: advise prefetch write for ODP region
Date: Tue, 19 Oct 2021 11:29:07 +0200	[thread overview]
Message-ID: <20211019092907.5255-8-quintela@redhat.com> (raw)
In-Reply-To: <20211019092907.5255-1-quintela@redhat.com>

From: Li Zhijian <lizhijian@cn.fujitsu.com>

The responder mr registering with ODP will sent RNR NAK back to
the requester in the face of the page fault.
---------
ibv_poll_cq wc.status=13 RNR retry counter exceeded!
ibv_poll_cq wrid=WRITE RDMA!
---------
ibv_advise_mr(3) helps to make pages present before the actual IO is
conducted so that the responder does page fault as little as possible.

Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Reviewed-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
---
 meson.build            |  6 ++++++
 migration/rdma.c       | 42 ++++++++++++++++++++++++++++++++++++++++++
 migration/trace-events |  1 +
 3 files changed, 49 insertions(+)

diff --git a/meson.build b/meson.build
index 5e7946776d..9ed9a993e2 100644
--- a/meson.build
+++ b/meson.build
@@ -1530,6 +1530,12 @@ config_host_data.set('HAVE_COPY_FILE_RANGE', cc.has_function('copy_file_range'))
 config_host_data.set('HAVE_OPENPTY', cc.has_function('openpty', dependencies: util))
 config_host_data.set('HAVE_STRCHRNUL', cc.has_function('strchrnul'))
 config_host_data.set('HAVE_SYSTEM_FUNCTION', cc.has_function('system', prefix: '#include <stdlib.h>'))
+if rdma.found()
+  config_host_data.set('HAVE_IBV_ADVISE_MR',
+                       cc.has_function('ibv_advise_mr',
+                                       args: config_host['RDMA_LIBS'].split(),
+                                       prefix: '#include <infiniband/verbs.h>'))
+endif
 
 # has_header_symbol
 config_host_data.set('CONFIG_BYTESWAP_H',
diff --git a/migration/rdma.c b/migration/rdma.c
index eb80431aae..2a3c7889b9 100644
--- a/migration/rdma.c
+++ b/migration/rdma.c
@@ -1133,6 +1133,32 @@ static bool rdma_support_odp(struct ibv_context *dev)
     return false;
 }
 
+/*
+ * ibv_advise_mr to avoid RNR NAK error as far as possible.
+ * The responder mr registering with ODP will sent RNR NAK back to
+ * the requester in the face of the page fault.
+ */
+static void qemu_rdma_advise_prefetch_mr(struct ibv_pd *pd, uint64_t addr,
+                                         uint32_t len,  uint32_t lkey,
+                                         const char *name, bool wr)
+{
+#ifdef HAVE_IBV_ADVISE_MR
+    int ret;
+    int advice = wr ? IBV_ADVISE_MR_ADVICE_PREFETCH_WRITE :
+                 IBV_ADVISE_MR_ADVICE_PREFETCH;
+    struct ibv_sge sg_list = {.lkey = lkey, .addr = addr, .length = len};
+
+    ret = ibv_advise_mr(pd, advice,
+                        IBV_ADVISE_MR_FLAG_FLUSH, &sg_list, 1);
+    /* ignore the error */
+    if (ret) {
+        trace_qemu_rdma_advise_mr(name, len, addr, strerror(errno));
+    } else {
+        trace_qemu_rdma_advise_mr(name, len, addr, "successed");
+    }
+#endif
+}
+
 static int qemu_rdma_reg_whole_ram_blocks(RDMAContext *rdma)
 {
     int i;
@@ -1156,6 +1182,15 @@ static int qemu_rdma_reg_whole_ram_blocks(RDMAContext *rdma)
                                local->block[i].local_host_addr,
                                local->block[i].length, access);
                 trace_qemu_rdma_register_odp_mr(local->block[i].block_name);
+
+                if (local->block[i].mr) {
+                    qemu_rdma_advise_prefetch_mr(rdma->pd,
+                                    (uintptr_t)local->block[i].local_host_addr,
+                                    local->block[i].length,
+                                    local->block[i].mr->lkey,
+                                    local->block[i].block_name,
+                                    true);
+                }
         }
 
         if (!local->block[i].mr) {
@@ -1255,6 +1290,13 @@ static int qemu_rdma_register_and_get_keys(RDMAContext *rdma,
             /* register ODP mr */
             block->pmr[chunk] = ibv_reg_mr(rdma->pd, chunk_start, len, access);
             trace_qemu_rdma_register_odp_mr(block->block_name);
+
+            if (block->pmr[chunk]) {
+                qemu_rdma_advise_prefetch_mr(rdma->pd, (uintptr_t)chunk_start,
+                                            len, block->pmr[chunk]->lkey,
+                                            block->block_name, rkey);
+
+            }
         }
     }
     if (!block->pmr[chunk]) {
diff --git a/migration/trace-events b/migration/trace-events
index 5f6aa580de..a8ae163707 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -213,6 +213,7 @@ qemu_rdma_poll_other(const char *compstr, int64_t comp, int left) "other complet
 qemu_rdma_post_send_control(const char *desc) "CONTROL: sending %s.."
 qemu_rdma_register_and_get_keys(uint64_t len, void *start) "Registering %" PRIu64 " bytes @ %p"
 qemu_rdma_register_odp_mr(const char *name) "Try to register On-Demand Paging memory region: %s"
+qemu_rdma_advise_mr(const char *name, uint32_t len, uint64_t addr, const char *res) "Try to advise block %s prefetch at %" PRIu32 "@0x%" PRIx64 ": %s"
 qemu_rdma_registration_handle_compress(int64_t length, int index, int64_t offset) "Zapping zero chunk: %" PRId64 " bytes, index %d, offset %" PRId64
 qemu_rdma_registration_handle_finished(void) ""
 qemu_rdma_registration_handle_ram_blocks(void) ""
-- 
2.31.1



  parent reply	other threads:[~2021-10-19  9:31 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-10-19  9:29 [PULL 0/7] Migration.next patches Juan Quintela
2021-10-19  9:29 ` [PULL 1/7] multifd: Implement yank for multifd send side Juan Quintela
2021-10-19  9:29 ` [PULL 2/7] multifd: Unconditionally unregister yank function Juan Quintela
2021-10-19  9:29 ` [PULL 3/7] migration/ram: Don't passs RAMState to migration_clear_memory_region_dirty_bitmap_*() Juan Quintela
2021-10-19  9:29 ` [PULL 4/7] migration: allow multifd for socket protocol only Juan Quintela
2021-10-19  9:29 ` [PULL 5/7] migration: allow enabling mutilfd for specific " Juan Quintela
2021-10-19  9:29 ` [PULL 6/7] migration/rdma: Try to register On-Demand Paging memory region Juan Quintela
2021-10-19  9:29 ` Juan Quintela [this message]
2021-10-19 16:55 ` [PULL 0/7] Migration.next patches Richard Henderson

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=20211019092907.5255-8-quintela@redhat.com \
    --to=quintela@redhat.com \
    --cc=dgilbert@redhat.com \
    --cc=lizhijian@cn.fujitsu.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).