From mboxrd@z Thu Jan 1 00:00:00 1970 Return-path: Received: from mx5-phx2.redhat.com ([209.132.183.37]) by bombadil.infradead.org with esmtps (Exim 4.80.1 #2 (Red Hat Linux)) id 1a4mJa-0004mg-4i for kexec@lists.infradead.org; Fri, 04 Dec 2015 09:06:06 +0000 Date: Fri, 4 Dec 2015 04:05:39 -0500 (EST) From: Chao Fan Message-ID: <885095395.27300639.1449219939731.JavaMail.zimbra@redhat.com> In-Reply-To: <1449111011-21749-1-git-send-email-zhouwj-fnst@cn.fujitsu.com> References: <1449111011-21749-1-git-send-email-zhouwj-fnst@cn.fujitsu.com> Subject: Re: [PATCH] Add more description for --num-threads MIME-Version: 1.0 List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: "kexec" Errors-To: kexec-bounces+dwmw2=infradead.org@lists.infradead.org To: Zhou Wenjian Cc: kexec@lists.infradead.org Ack. Since in the condition of "-d 31", it will cost more time with "--num-threads" than without "--num-threads". So I suggest not using "--num-threads" when "-d 31" will be better. Acked-by: Chao Fan ----- Original Message ----- > From: "Zhou Wenjian" > To: kexec@lists.infradead.org > Sent: Thursday, December 3, 2015 10:50:11 AM > Subject: [PATCH] Add more description for --num-threads > > From the test result, we can see when "-d 31" is specified, using > "--num-threads" always spends more time than not. And it occurs at > most of the time in theory. So it should be mentioned in the > description of "--num-threads". > > Signed-off-by: Zhou Wenjian > --- > makedumpfile.8 | 6 ++++-- > print_info.c | 4 ++++ > 2 files changed, 8 insertions(+), 2 deletions(-) > > diff --git a/makedumpfile.8 b/makedumpfile.8 > index 6eff4f1..ec179a5 100644 > --- a/makedumpfile.8 > +++ b/makedumpfile.8 > @@ -378,11 +378,13 @@ Using multiple threads to read and compress data of > each page in parallel. > And it will reduces time for saving \fIDUMPFILE\fR. > This feature only supports creating \fIDUMPFILE\fR in kdump\-comressed > format from \fIVMCORE\fR in kdump\-compressed format or elf format. > +Note that if too many pages are filtered, \'\-\-num\-threads\' may not > improve > +the performance, or even has bad effects. It means if \'\-d 31\' is > specified, > +you should think about whether to use \'\-\-num\-threads\'. > .br > .B Example: > .br > -# makedumpfile \-d 31 \-\-num\-threads 4 /proc/vmcore dumpfile > - > +# makedumpfile \-\-num\-threads 4 /proc/vmcore dumpfile > .TP > \fB\-\-reassemble\fR > Reassemble multiple \fIDUMPFILE\fRs, which are created by \-\-split option, > diff --git a/print_info.c b/print_info.c > index d662c0c..d0302a8 100644 > --- a/print_info.c > +++ b/print_info.c > @@ -194,6 +194,10 @@ print_usage(void) > MSG(" And it will reduces time for saving DUMPFILE.\n"); > MSG(" This feature only supports creating DUMPFILE in kdump-comressed > format from\n"); > MSG(" VMCORE in kdump-compressed format or elf format.\n"); > + MSG(" Note that if too many pages are filtered, '--num-threads' may > not improve\n"); > + MSG(" the performance, or even has bad effects.\n"); > + MSG(" It means if '-d 31' is specified, you should think about whether > to use\n"); > + MSG(" '--num-threads'.\n"); > MSG("\n"); > MSG(" [--reassemble]:\n"); > MSG(" Reassemble multiple DUMPFILEs, which are created by --split > option,\n"); > -- > 1.8.3.1 > > > > > _______________________________________________ > kexec mailing list > kexec@lists.infradead.org > http://lists.infradead.org/mailman/listinfo/kexec > _______________________________________________ kexec mailing list kexec@lists.infradead.org http://lists.infradead.org/mailman/listinfo/kexec