From: "Dr. David Alan Gilbert (git)" <dgilbert@redhat.com>
To: qemu-devel@nongnu.org, berrange@redhat.com,
huangy81@chinatelecom.cn, quintela@redhat.com,
leobras@redhat.com, peterx@redhat.com
Cc: jdenemar@redhat.com
Subject: [PULL 01/25] migration: Remove RDMA_UNREGISTRATION_EXAMPLE
Date: Thu, 23 Jun 2022 17:53:30 +0100 [thread overview]
Message-ID: <20220623165354.197792-2-dgilbert@redhat.com> (raw)
In-Reply-To: <20220623165354.197792-1-dgilbert@redhat.com>
From: Juan Quintela <quintela@redhat.com>
Nobody has ever showed up to unregister individual pages, and another
set of patches written by Daniel P. Berrangé <berrange@redhat.com>
just remove qemu_rdma_signal_unregister() function needed here.
Signed-off-by: Juan Quintela <quintela@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
---
migration/rdma.c | 41 -----------------------------------------
1 file changed, 41 deletions(-)
diff --git a/migration/rdma.c b/migration/rdma.c
index 672d1958a9..8504152f39 100644
--- a/migration/rdma.c
+++ b/migration/rdma.c
@@ -1370,30 +1370,6 @@ const char *print_wrid(int wrid)
return wrid_desc[wrid];
}
-/*
- * RDMA requires memory registration (mlock/pinning), but this is not good for
- * overcommitment.
- *
- * In preparation for the future where LRU information or workload-specific
- * writable writable working set memory access behavior is available to QEMU
- * it would be nice to have in place the ability to UN-register/UN-pin
- * particular memory regions from the RDMA hardware when it is determine that
- * those regions of memory will likely not be accessed again in the near future.
- *
- * While we do not yet have such information right now, the following
- * compile-time option allows us to perform a non-optimized version of this
- * behavior.
- *
- * By uncommenting this option, you will cause *all* RDMA transfers to be
- * unregistered immediately after the transfer completes on both sides of the
- * connection. This has no effect in 'rdma-pin-all' mode, only regular mode.
- *
- * This will have a terrible impact on migration performance, so until future
- * workload information or LRU information is available, do not attempt to use
- * this feature except for basic testing.
- */
-/* #define RDMA_UNREGISTRATION_EXAMPLE */
-
/*
* Perform a non-optimized memory unregistration after every transfer
* for demonstration purposes, only if pin-all is not requested.
@@ -1571,18 +1547,6 @@ static uint64_t qemu_rdma_poll(RDMAContext *rdma, struct ibv_cq *cq,
if (rdma->nb_sent > 0) {
rdma->nb_sent--;
}
-
- if (!rdma->pin_all) {
- /*
- * FYI: If one wanted to signal a specific chunk to be unregistered
- * using LRU or workload-specific information, this is the function
- * you would call to do so. That chunk would then get asynchronously
- * unregistered later.
- */
-#ifdef RDMA_UNREGISTRATION_EXAMPLE
- qemu_rdma_signal_unregister(rdma, index, chunk, wc.wr_id);
-#endif
- }
} else {
trace_qemu_rdma_poll_other(print_wrid(wr_id), wr_id, rdma->nb_sent);
}
@@ -2137,11 +2101,6 @@ retry:
chunk_end = ram_chunk_end(block, chunk + chunks);
- if (!rdma->pin_all) {
-#ifdef RDMA_UNREGISTRATION_EXAMPLE
- qemu_rdma_unregister_waiting(rdma);
-#endif
- }
while (test_bit(chunk, block->transit_bitmap)) {
(void)count;
--
2.36.1
next prev parent reply other threads:[~2022-06-23 16:59 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-06-23 16:53 [PULL 00/25] migration queue Dr. David Alan Gilbert (git)
2022-06-23 16:53 ` Dr. David Alan Gilbert (git) [this message]
2022-06-23 16:53 ` [PULL 02/25] QIOChannelSocket: Introduce assert and reduce ifdefs to improve readability Dr. David Alan Gilbert (git)
2022-06-23 16:53 ` [PULL 03/25] QIOChannelSocket: Fix zero-copy send so socket flush works Dr. David Alan Gilbert (git)
2022-06-23 16:53 ` [PULL 04/25] migration: Change zero_copy_send from migration parameter to migration capability Dr. David Alan Gilbert (git)
2022-06-23 16:53 ` [PULL 05/25] io: add a QIOChannelNull equivalent to /dev/null Dr. David Alan Gilbert (git)
2022-06-23 16:53 ` [PULL 06/25] migration: switch to use QIOChannelNull for dummy channel Dr. David Alan Gilbert (git)
2022-06-23 16:53 ` [PULL 07/25] migration: remove unreachble RDMA code in save_hook impl Dr. David Alan Gilbert (git)
2022-06-23 16:53 ` [PULL 08/25] migration: rename rate limiting fields in QEMUFile Dr. David Alan Gilbert (git)
2022-06-23 16:53 ` [PULL 09/25] migration: rename 'pos' field in QEMUFile to 'bytes_processed' Dr. David Alan Gilbert (git)
2022-06-23 16:53 ` [PULL 10/25] migration: rename qemu_ftell to qemu_file_total_transferred Dr. David Alan Gilbert (git)
2022-06-23 16:53 ` [PULL 11/25] migration: rename qemu_update_position to qemu_file_credit_transfer Dr. David Alan Gilbert (git)
2022-06-23 16:53 ` [PULL 12/25] migration: rename qemu_file_update_transfer to qemu_file_acct_rate_limit Dr. David Alan Gilbert (git)
2022-06-23 16:53 ` [PULL 13/25] migration: introduce a QIOChannel impl for BlockDriverState VMState Dr. David Alan Gilbert (git)
2022-06-23 16:53 ` [PULL 14/25] migration: convert savevm to use QIOChannelBlock for VMState Dr. David Alan Gilbert (git)
2022-06-23 16:53 ` [PULL 15/25] migration: stop passing 'opaque' parameter to QEMUFile hooks Dr. David Alan Gilbert (git)
2022-06-23 16:53 ` [PULL 16/25] migration: hardcode assumption that QEMUFile is backed with QIOChannel Dr. David Alan Gilbert (git)
2022-06-23 16:53 ` [PULL 17/25] migration: introduce new constructors for QEMUFile Dr. David Alan Gilbert (git)
2022-06-23 16:53 ` [PULL 18/25] migration: remove unused QEMUFileGetFD typedef / qemu_get_fd method Dr. David Alan Gilbert (git)
2022-06-23 16:53 ` [PULL 19/25] migration: remove the QEMUFileOps 'shut_down' callback Dr. David Alan Gilbert (git)
2022-06-23 16:53 ` [PULL 20/25] migration: remove the QEMUFileOps 'set_blocking' callback Dr. David Alan Gilbert (git)
2022-06-23 16:53 ` [PULL 21/25] migration: remove the QEMUFileOps 'close' callback Dr. David Alan Gilbert (git)
2022-06-23 16:53 ` [PULL 22/25] migration: remove the QEMUFileOps 'get_buffer' callback Dr. David Alan Gilbert (git)
2022-06-23 16:53 ` [PULL 23/25] migration: remove the QEMUFileOps 'writev_buffer' callback Dr. David Alan Gilbert (git)
2022-06-23 16:53 ` [PULL 24/25] migration: remove the QEMUFileOps 'get_return_path' callback Dr. David Alan Gilbert (git)
2022-06-23 16:53 ` [PULL 25/25] migration: remove the QEMUFileOps abstraction Dr. David Alan Gilbert (git)
2022-06-23 21:37 ` [PULL 00/25] migration queue Richard Henderson
-- strict thread matches above, loose matches on Subject: below --
2022-06-22 0:25 [PULL 00/25] Migration 20220621 patches Juan Quintela
2022-06-22 0:25 ` [PULL 01/25] migration: Remove RDMA_UNREGISTRATION_EXAMPLE Juan Quintela
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=20220623165354.197792-2-dgilbert@redhat.com \
--to=dgilbert@redhat.com \
--cc=berrange@redhat.com \
--cc=huangy81@chinatelecom.cn \
--cc=jdenemar@redhat.com \
--cc=leobras@redhat.com \
--cc=peterx@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=quintela@redhat.com \
/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).