From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
To: Liang Li <liang.z.li@intel.com>
Cc: quintela@redhat.com, armbru@redhat.com, qemu-devel@nongnu.org,
lcapitulino@redhat.com, Yang Zhang <yang.z.zhang@intel.com>,
amit.shah@redhat.com
Subject: Re: [Qemu-devel] [v4 10/13] migration: Add the core code for decompression
Date: Fri, 6 Feb 2015 12:27:25 +0000 [thread overview]
Message-ID: <20150206122725.GJ2364@work-vm> (raw)
In-Reply-To: <1422875149-13198-11-git-send-email-liang.z.li@intel.com>
* Liang Li (liang.z.li@intel.com) wrote:
> Implement the core logic of multiple thread decompression,
> the decompression can work now.
>
> Signed-off-by: Liang Li <liang.z.li@intel.com>
> Signed-off-by: Yang Zhang <yang.z.zhang@intel.com>
> ---
> arch_init.c | 49 +++++++++++++++++++++++++++++++++++++++++++++++--
> 1 file changed, 47 insertions(+), 2 deletions(-)
>
> diff --git a/arch_init.c b/arch_init.c
> index 8ef0315..549fdbb 100644
> --- a/arch_init.c
> +++ b/arch_init.c
> @@ -814,6 +814,13 @@ static inline void start_compression(CompressParam *param)
> qemu_mutex_unlock(¶m->mutex);
> }
>
> +static inline void start_decompression(DecompressParam *param)
> +{
> + qemu_mutex_lock(¶m->mutex);
> + param->busy = true;
> + qemu_cond_signal(¶m->cond);
> + qemu_mutex_unlock(¶m->mutex);
> +}
>
> static uint64_t bytes_transferred;
>
> @@ -1347,8 +1354,27 @@ void ram_handle_compressed(void *host, uint8_t ch, uint64_t size)
>
> static void *do_data_decompress(void *opaque)
> {
> + DecompressParam *param = opaque;
> + size_t pagesize;
> +
> while (!quit_thread) {
> - /* To be done */
> + qemu_mutex_lock(¶m->mutex);
> + while (!param->busy) {
> + qemu_cond_wait(¶m->cond, ¶m->mutex);
> + if (quit_thread) {
> + break;
> + }
> + pagesize = TARGET_PAGE_SIZE;
> + /* uncompress() will return failed in some case, especially
> + * when the page is dirted when doing the compression, it's
> + * not a problem because the dirty page will be retransferred
> + * and uncompress() won't break the data in other pages.
> + */
> + uncompress((Bytef *)param->des, &pagesize,
> + (const Bytef *)param->compbuf, param->len);
> + param->busy = false;
> + }
> + qemu_mutex_unlock(¶m->mutex);
> }
Again, similar question to the compress thread; what ensures that
teh cond_signal for quit_thread happens while this loop is at
the cond_wait? Again mainly in error cases.
Dave
>
> return NULL;
> @@ -1379,6 +1405,9 @@ void migrate_decompress_threads_join(void)
> quit_thread = true;
> thread_count = migrate_decompress_threads();
> for (i = 0; i < thread_count; i++) {
> + qemu_cond_signal(&decomp_param[i].cond);
> + }
> + for (i = 0; i < thread_count; i++) {
> qemu_thread_join(decompress_threads + i);
> qemu_mutex_destroy(&decomp_param[i].mutex);
> qemu_cond_destroy(&decomp_param[i].cond);
> @@ -1395,7 +1424,23 @@ void migrate_decompress_threads_join(void)
> static void decompress_data_with_multi_threads(uint8_t *compbuf,
> void *host, int len)
> {
> - /* To be done */
> + int idx, thread_count;
> +
> + thread_count = migrate_decompress_threads();
> + while (true) {
> + for (idx = 0; idx < thread_count; idx++) {
> + if (!decomp_param[idx].busy) {
> + memcpy(decomp_param[idx].compbuf, compbuf, len);
> + decomp_param[idx].des = host;
> + decomp_param[idx].len = len;
> + start_decompression(&decomp_param[idx]);
> + break;
> + }
> + }
> + if (idx < thread_count) {
> + break;
> + }
> + }
> }
>
> static int ram_load(QEMUFile *f, void *opaque, int version_id)
> --
> 1.9.1
>
--
Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK
next prev parent reply other threads:[~2015-02-06 12:27 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-02-02 11:05 [Qemu-devel] [PATCH v4 0/13] migration: Add a new feature to do live migration Liang Li
2015-02-02 11:05 ` [Qemu-devel] [v4 01/13] docs: Add a doc about multiple thread compression Liang Li
2015-02-02 11:05 ` [Qemu-devel] [v4 02/13] migration: Add the framework of multi-thread compression Liang Li
2015-02-06 10:11 ` Dr. David Alan Gilbert
2015-02-02 11:05 ` [Qemu-devel] [v4 03/13] migration: Add the framework of multi-thread decompression Liang Li
2015-02-06 10:16 ` Dr. David Alan Gilbert
2015-02-02 11:05 ` [Qemu-devel] [v4 04/13] qemu-file: Add compression functions to QEMUFile Liang Li
2015-02-06 10:33 ` Dr. David Alan Gilbert
2015-02-02 11:05 ` [Qemu-devel] [v4 05/13] arch_init: Alloc and free data struct for compression Liang Li
2015-02-06 10:45 ` Dr. David Alan Gilbert
2015-02-02 11:05 ` [Qemu-devel] [v4 06/13] arch_init: Add and free data struct for decompression Liang Li
2015-02-06 10:46 ` Dr. David Alan Gilbert
2015-02-02 11:05 ` [Qemu-devel] [v4 07/13] migration: Split the function ram_save_page Liang Li
2015-02-06 11:01 ` Dr. David Alan Gilbert
2015-02-02 11:05 ` [Qemu-devel] [v4 08/13] migration: Add the core code of multi-thread compression Liang Li
2015-02-06 12:12 ` Dr. David Alan Gilbert
2015-02-02 11:05 ` [Qemu-devel] [v4 09/13] migration: Make compression co-work with xbzrle Liang Li
2015-02-06 12:15 ` Dr. David Alan Gilbert
2015-02-02 11:05 ` [Qemu-devel] [v4 10/13] migration: Add the core code for decompression Liang Li
2015-02-06 12:27 ` Dr. David Alan Gilbert [this message]
2015-02-02 11:05 ` [Qemu-devel] [v4 11/13] migration: Add interface to control compression Liang Li
2015-02-03 22:17 ` Eric Blake
2015-02-02 11:05 ` [Qemu-devel] [v4 12/13] migration: Add command to set migration parameter Liang Li
2015-02-03 23:28 ` Eric Blake
2015-02-04 1:26 ` Li, Liang Z
2015-02-04 2:27 ` Eric Blake
2015-02-02 11:05 ` [Qemu-devel] [v4 13/13] migration: Add command to query " Liang Li
2015-02-03 23:30 ` Eric Blake
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=20150206122725.GJ2364@work-vm \
--to=dgilbert@redhat.com \
--cc=amit.shah@redhat.com \
--cc=armbru@redhat.com \
--cc=lcapitulino@redhat.com \
--cc=liang.z.li@intel.com \
--cc=qemu-devel@nongnu.org \
--cc=quintela@redhat.com \
--cc=yang.z.zhang@intel.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).