From owner-freebsd-amd64@FreeBSD.ORG Tue Dec 28 23:26:06 2004 Return-Path: Delivered-To: freebsd-amd64@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 7451616A4CE for ; Tue, 28 Dec 2004 23:26:06 +0000 (GMT) Received: from kong.rascom.ru (kong.rascom.ru [80.64.99.13]) by mx1.FreeBSD.org (Postfix) with ESMTP id 35E6843D46 for ; Tue, 28 Dec 2004 23:26:05 +0000 (GMT) (envelope-from kong@kong.spb.ru) Received: from kong.rascom.ru (localhost [127.0.0.1]) by kong.rascom.ru (8.13.1/8.12.9) with ESMTP id iBSNQ4JF051756; Wed, 29 Dec 2004 02:26:04 +0300 (MSK) (envelope-from kong@kong.spb.ru) Received: from localhost (kong@localhost)iBSNQ46I051753; Wed, 29 Dec 2004 02:26:04 +0300 (MSK) (envelope-from kong@kong.spb.ru) X-Authentication-Warning: kong.rascom.ru: kong owned process doing -bs Date: Wed, 29 Dec 2004 02:26:04 +0300 (MSK) From: Hostas Red X-X-Sender: kong@kong.rascom.ru To: Don Bowman In-Reply-To: <2BCEB9A37A4D354AA276774EE13FB8C219AE70@mailserver.sandvine.com> Message-ID: <20041229022335.R51667@kong.rascom.ru> References: <2BCEB9A37A4D354AA276774EE13FB8C219AE70@mailserver.sandvine.com> X-NCC-RegId: ru.rascom MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed cc: freebsd-amd64@freebsd.org Subject: RE: aac controller in amd64 very slow? X-BeenThere: freebsd-amd64@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Porting FreeBSD to the AMD64 platform List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 28 Dec 2004 23:26:06 -0000 Hi! On Tue, 28 Dec 2004, Don Bowman wrote: > yeah, having the read cache on wrecks the write speed. > Something to do with having it write and then read it back into the > cache. Thanks, I'll try to reset system after container reconfiguration. Hope this helps. Without reboot I cannot see any difference. > This made a dramatic difference for me. I'm a dual Xeon, 5.3 Maybe this is the point. On i386/Dual Xeon I have no problems with raid5 controller speed... > CLI > open aac0 > Executing: open "aac0" > > AAC0> container show cache 0 > Executing: container show cache 0 > > Global Container Read Cache Size : 475136 > Global Container Write Cache Size : 40140800 > > Read Cache Setting : DISABLE > Write Cache Setting : ENABLE ALWAYS > Write Cache Status : Active, not protected, battery not present > > AAC0> container list > Executing: container list > Num Total Oth Stripe Scsi Partition > Label Type Size Ctr Size Usage C:ID:L Offset:Size > ----- ------ ------ --- ------ ------- ------ ------------- > 0 RAID-5 1.73TB 64KB Open 0:00:0 64.0KB: 136GB > /dev/aacd0 all 0:01:0 64.0KB: 136GB > 0:02:0 64.0KB: 136GB > 0:03:0 64.0KB: 136GB > 0:04:0 64.0KB: 136GB > 0:05:0 64.0KB: 136GB > 0:06:0 64.0KB: 136GB > 1:00:0 64.0KB: 136GB > 1:01:0 64.0KB: 136GB > 1:02:0 64.0KB: 136GB > 1:03:0 64.0KB: 136GB > 1:04:0 64.0KB: 136GB > 1:05:0 64.0KB: 136GB > 1:06:0 64.0KB: 136GB > > > AAC0> > > > >> -----Original Message----- >> From: Hostas Red [mailto:kong@kong.spb.ru] >> Sent: December 28, 2004 18:17 PM >> To: Don Bowman >> Subject: RE: aac controller in amd64 very slow? >> >> Hi! >> >> On Tue, 28 Dec 2004, Don Bowman wrote: >> >>> well, on the aac, you need to disable the read-cache >> otherwise it has >>> very very poor performance. >>> I think this can be done from scsi bios. it can also be >> done via aaccli. >> >> As far as I can see from the tests the read speed is not a >> problem - it's a write operations that are VERY slow. Anyway, >> I've disabled a read-cache via aaccli - no effect. Or I need >> to reset a box to apply aac configuration changes? And one >> more - controller has no battery connected, but have an >> enabled write-cache: >> >> AAC0> container show cache 0 >> Executing: container show cache 0 >> >> Global Container Read Cache Size : 0 >> Global Container Write Cache Size : 16203776 >> >> Read Cache Setting : DISABLE >> Write Cache Setting : ENABLE ALWAYS >> Write Cache Status : Active, not protected, battery not present >> >> And that's my contaier config: >> >> AAC0> container list >> Executing: container list >> Num Total Oth Stripe Scsi Partition >> Label Type Size Ctr Size Usage C:ID:L Offset:Size >> ----- ------ ------ --- ------ ------- ------ ------------- >> 0 RAID-5 410GB 64KB Open 0:00:0 64.0KB: 136GB >> /dev/aacd0 raid 5 0:01:0 64.0KB: 136GB >> 0:02:0 64.0KB: 136GB >> 0:03:0 64.0KB: 136GB >> >>>> -----Original Message----- >>>> From: owner-freebsd-amd64@freebsd.org >>>> [mailto:owner-freebsd-amd64@freebsd.org] On Behalf Of Hostas Red >>>> Sent: December 27, 2004 9:02 AM >>>> To: freebsd-amd64@freebsd.org >>>> Subject: aac controller in amd64 very slow? >>>> >>>> Hi! >>>> >>>> 1) I have one Quad Opteron box with FreeBSD 5.3-amd64 >> installed and >>>> have strange downgrade in performance with Adaptec 2120S raid >>>> controller (acc driver, 4-disk RAID5 configured). It is approx. >>>> 30-40% loss in performance of disk operations compared to >> my previous >>>> Dual 2.4 Xeon with Adaptec 2015S with two disks mirrored. >>>> >>>> Is it normal or maybe I need some tweaking? Also one of my >> colleagues >>>> suggested installation of i386 version of 5.3 for speeding >> things up, >>>> that sound strange for me. >>>> >>>> I'm new for amd64 version of freebsd, but using freebsd-i386 for 7 >>>> years or so on i386 platforms. May this problem be an >> amd64-specific? >>>> >>>> Any suggestions how I can resolve this problem? >>>> >>>> >>>> >>>> 2) One more Q - apache is eating a lot of memory when running >>>> - about 64M for each process instead of usual approx 7-10M per >>>> process on previous >>>> i386 with same compiled configuration: >>>> >>>> == from top === >>>> PID USERNAME PRI NICE SIZE RES STATE C TIME WCPU >>>> CPU COMMAND >>>> 3351 www 96 0 69560K 18712K select 3 0:01 0.93% >>>> 0.93% httpd >>>> ========== >>>> >>>> Other programs looks the same or about it. Is it normal for >>>> amd64 platform or also my mistake? >>>> >>>> >>>> >>>> 3) And one more Q - box has 4G of memory, but kernel can see only >>>> 3.5G, as can be seen from following dmesg output. What can be a >>>> problem? >>>> >>>> >>>> >>>> Box is a Tyan's Thunder K8QS Pro (S4882) 4-way AMD Opteron >> platform >>>> (with Tyan S4882UG2NR board). >>>> >>>> Disk split in two parts: >>>> >>>> Filesystem 1K-blocks Used Avail Capacity Mounted on >>>> /dev/aacd0s1a 6090094 1998300 3604588 36% / >>>> devfs 1 1 0 100% /dev >>>> /dev/aacd0s1d 402268316 26148124 343938728 7% /work >>>> >>>> On /, of course, is a system and second one is working partiton. >>>> >>>> Here's boot message of the new box: >>>> >>>> Copyright (c) 1992-2004 The FreeBSD Project. >>>> Copyright (c) 1979, 1980, 1983, 1986, 1988, 1989, 1991, >> 1992, 1993, >>>> 1994 >>>> The Regents of the University of California. All rights >>>> reserved. >>>> FreeBSD 5.3-STABLE #2: Mon Dec 27 08:27:05 GMT 2004 >>>> root@sys154.3fn.net:/usr/obj/usr/src/sys/kong >>>> Timecounter "i8254" frequency 1193182 Hz quality 0 >>>> CPU: AMD Opteron(tm) Processor 846 (1992.22-MHz K8-class CPU) >>>> Origin = "AuthenticAMD" Id = 0xf58 Stepping = 8 >>>> >>>> Features=0x78bfbff>> ,MTRR,PGE,MCA,CMOV,PAT,PSE36,CLFLUSH,MMX,FXSR,SSE,SSE2> >>>> AMD Features=0xe0500800 >>>> real memory = 3757506560 (3583 MB) >>>> avail memory = 3627720704 (3459 MB) >>>> ACPI APIC Table: >>>> FreeBSD/SMP: Multiprocessor System Detected: 4 CPUs >>>> cpu0 (BSP): APIC ID: 0 >>>> cpu1 (AP): APIC ID: 1 >>>> cpu2 (AP): APIC ID: 2 >>>> cpu3 (AP): APIC ID: 3 >>>> MADT: Forcing active-low polarity and level trigger for >> SCI ioapic0 >>>> irqs 0-23 on motherboard >>>> ioapic1 irqs 24-27 on motherboard >>>> ioapic2 irqs 28-31 on motherboard >>>> ioapic3 irqs 32-35 on motherboard >>>> ioapic4 irqs 36-39 on motherboard >>>> acpi0: on motherboard >>>> acpi0: Power Button (fixed) >>>> unknown: I/O range not supported >>>> unknown: I/O range not supported >>>> Timecounter "ACPI-fast" frequency 3579545 Hz quality 1000 >>>> acpi_timer0: <24-bit timer at 3.579545MHz> port 0xc008-0xc00b on >>>> acpi0 >>>> cpu0: on acpi0 >>>> cpu1: on acpi0 >>>> cpu2: on acpi0 >>>> cpu3: on acpi0 >>>> acpi_button0: on acpi0 >>>> pcib0: port >>>> 0xc080-0xc0ff,0xc000-0xc07f,0xcf8-0xcff iomem 0xd8000-0xdbfff on >>>> acpi0 >>>> pci0: on pcib0 >>>> pcib1: at device 6.0 on pci0 >>>> pci1: on pcib1 >>>> ohci0: mem >> 0xe8000000-0xe8000fff irq >>>> 19 at device 0.0 on pci1 >>>> ohci0: [GIANT-LOCKED] >>>> usb0: OHCI version 1.0, legacy support >>>> usb0: SMM does not respond, resetting >>>> usb0: on ohci0 >>>> usb0: USB revision 1.0 AMD OHCI root hub, class 9/0, rev 1.00/1.00, addr 1 >>>> uhub0: 3 ports with 3 removable, self powered >>>> ohci1: mem >> 0xe8001000-0xe8001fff irq >>>> 19 at device 0.1 on pci1 >>>> ohci1: [GIANT-LOCKED] >>>> usb1: OHCI version 1.0, legacy support >>>> usb1: SMM does not respond, resetting >>>> usb1: on ohci1 >>>> usb1: USB revision 1.0 >>>> uhub1: AMD OHCI root hub, class 9/0, rev 1.00/1.00, addr 1 >>>> uhub1: 3 ports with 3 removable, self powered >>>> pci1: at device 4.0 (no driver attached) >>>> isab0: at device 7.0 on pci0 >>>> isa0: on isab0 >>>> atapci0: port >>>> 0x1000-0x100f,0x376,0x170-0x177,0x3f6,0x1f0-0x1f7 at device >>>> 7.1 on pci0 >>>> ata0: channel #0 on atapci0 >>>> ata1: channel #1 on atapci0 >>>> pci0: at device 7.3 (no driver attached) >>>> pcib2: on acpi0 >>>> pci8: on pcib2 >>>> pcib3: at device 1.0 on pci8 >>>> pci9: on pcib3 >>>> aac0: mem 0xf8000000-0xfbffffff irq >>>> 26 at device 2.0 on pci9 >>>> aac0: [FAST] >>>> aac0: Enabling 64-bit address support >>>> aac0: Unknown processor 100MHz, 48MB cache memory, >> optional battery >>>> not installed >>>> aac0: Kernel 4.1-0, Build 7244, S/N be37b0 >>>> aac0: Supported >>>> Options=11d7e>>> ,SOFTERR,SGMAP64,ALARM,NONDASD> >>>> aacp0: on aac0 >>>> pci8: at device 1.1 (no >>>> driver attached) >>>> pcib4: at device 2.0 on pci8 >>>> pci14: on pcib4 >>>> mpt0: port 0x3000-0x30ff mem >>>> 0xed000000-0xed00ffff,0xed010000-0xed01ffff irq 29 at >> device 1.0 on >>>> pci14 >>>> mpt0: [GIANT-LOCKED] >>>> mpt1: port 0x3400-0x34ff mem >>>> 0xed020000-0xed02ffff,0xed030000-0xed03ffff irq 30 at device >>>> 1.1 on pci14 >>>> mpt1: [GIANT-LOCKED] >>>> bge0: >>> 0x2002> mem 0xed040000-0xed04ffff,0xed050000-0xed05ffff irq >>>> 31 at device 3.0 on pci14 >>>> miibus0: on bge0 >>>> brgphy0: on miibus0 >>>> brgphy0: 10baseT, 10baseT-FDX, 100baseTX, 100baseTX-FDX, >> 1000baseTX, >>>> 1000baseTX-FDX, auto >>>> bge0: Ethernet address: 00:00:1a:1a:0d:5a >>>> bge1: >>> 0x2002> mem 0xed060000-0xed06ffff,0xed070000-0xed07ffff irq >>>> 28 at device 3.1 on pci14 >>>> miibus1: on bge1 >>>> brgphy1: on miibus1 >>>> brgphy1: 10baseT, 10baseT-FDX, 100baseTX, 100baseTX-FDX, >> 1000baseTX, >>>> 1000baseTX-FDX, auto >>>> bge1: Ethernet address: 00:00:1a:1a:0d:5b >>>> pci8: at device 2.1 (no >>>> driver attached) >>>> pcib5: mem 0xea202000-0xea202fff irq 32 at >>>> device 3.0 on pci8 >>>> pci19: on pcib5 >>>> pci8: at device 3.1 (no >>>> driver attached) >>>> pcib6: mem 0xea204000-0xea204fff irq 36 at >>>> device 4.0 on pci8 >>>> pci27: on pcib6 >>>> pci8: at device 4.1 (no >>>> driver attached) >>>> atkbdc0: port 0x64,0x60 irq >> 1 on acpi0 >>>> sio0: <16550A-compatible COM port> port 0x3f8-0x3ff irq 4 >> flags 0x10 >>>> on acpi0 >>>> sio0: type 16550A, console >>>> fdc0: port 0x3f7,0x3f0-0x3f5 irq >> 6 drq 2 on >>>> acpi0 >>>> fdc0: [FAST] >>>> fd0: <1440-KB 3.5" drive> on fdc0 drive 0 >>>> orm0: at iomem >>>> 0xcc800-0xd0fff,0xcb000-0xcc7ff,0xc9800-0xcafff,0xc9000-0xc97f >>>> f,0xc8000-0xc8fff,0xc0000-0xc7fff on isa0 >>>> sc0: at flags 0x100 on isa0 >>>> sc0: VGA <16 virtual consoles, flags=0x100> >>>> sio1: configured irq 3 not in bitmap of probed irqs 0 >>>> sio1: port may not be enabled >>>> vga0: at port 0x3c0-0x3df iomem >> 0xa0000-0xbffff on >>>> isa0 Timecounters tick every 1.000 msec >>>> ipfw2 initialized, divert disabled, rule-based forwarding >> disabled, >>>> default to accept, logging disabled >>>> acd0: DVDROM at ata0-master UDMA33 Waiting >> 15 seconds >>>> for SCSI devices to settle >>>> aacd0: on aac0 >>>> aacd0: 419943MB (860045184 sectors) >>>> (probe0:aacp0:0:0:0): INQUIRY. CDB: 12 0 0 0 24 0 >>>> (probe0:aacp0:0:0:0): ILLEGAL REQUEST asc:55,3 >>>> (probe0:aacp0:0:0:0): Reserved ASC/ASCQ pair >>>> (probe5:aacp0:0:5:0): INQUIRY. CDB: 12 0 0 0 24 0 >>>> (probe5:aacp0:0:5:0): ILLEGAL REQUEST asc:55,3 >>>> (probe5:aacp0:0:5:0): Reserved ASC/ASCQ pair >>>> (probe9:aacp0:0:10:0): INQUIRY. CDB: 12 0 0 0 24 0 >>>> (probe9:aacp0:0:10:0): ILLEGAL REQUEST asc:55,3 >>>> (probe9:aacp0:0:10:0): Reserved ASC/ASCQ pair >>>> (probe10:aacp0:0:11:0): INQUIRY. CDB: 12 0 0 0 24 0 >>>> (probe10:aacp0:0:11:0): ILLEGAL REQUEST asc:55,3 >>>> (probe10:aacp0:0:11:0): Reserved ASC/ASCQ pair >>>> (probe13:aacp0:0:14:0): INQUIRY. CDB: 12 0 0 0 24 0 >>>> (probe13:aacp0:0:14:0): ILLEGAL REQUEST asc:55,3 >>>> (probe13:aacp0:0:14:0): Reserved ASC/ASCQ pair >>>> (probe1:aacp0:0:1:0): INQUIRY. CDB: 12 0 0 0 24 0 >>>> (probe1:aacp0:0:1:0): ILLEGAL REQUEST asc:55,3 >>>> (probe1:aacp0:0:1:0): Reserved ASC/ASCQ pair >>>> (probe2:aacp0:0:2:0): INQUIRY. CDB: 12 0 0 0 24 0 >>>> (probe2:aacp0:0:2:0): ILLEGAL REQUEST asc:55,3 >>>> (probe2:aacp0:0:2:0): Reserved ASC/ASCQ pair >>>> (probe3:aacp0:0:3:0): INQUIRY. CDB: 12 0 0 0 24 0 >>>> (probe3:aacp0:0:3:0): ILLEGAL REQUEST asc:55,3 >>>> (probe3:aacp0:0:3:0): Reserved ASC/ASCQ pair >>>> (probe4:aacp0:0:4:0): INQUIRY. CDB: 12 0 0 0 24 0 >>>> (probe4:aacp0:0:4:0): ILLEGAL REQUEST asc:55,3 >>>> (probe4:aacp0:0:4:0): Reserved ASC/ASCQ pair >>>> (probe6:aacp0:0:6:0): INQUIRY. CDB: 12 0 0 0 24 0 >>>> (probe6:aacp0:0:6:0): ILLEGAL REQUEST asc:55,3 >>>> (probe6:aacp0:0:6:0): Reserved ASC/ASCQ pair >>>> (probe7:aacp0:0:8:0): INQUIRY. CDB: 12 0 0 0 24 0 >>>> (probe7:aacp0:0:8:0): ILLEGAL REQUEST asc:55,3 >>>> (probe7:aacp0:0:8:0): Reserved ASC/ASCQ pair >>>> (probe8:aacp0:0:9:0): INQUIRY. CDB: 12 0 0 0 24 0 >>>> (probe8:aacp0:0:9:0): ILLEGAL REQUEST asc:55,3 >>>> (probe8:aacp0:0:9:0): Reserved ASC/ASCQ pair >>>> (probe11:aacp0:0:12:0): INQUIRY. CDB: 12 0 0 0 24 0 >>>> (probe11:aacp0:0:12:0): ILLEGAL REQUEST asc:55,3 >>>> (probe11:aacp0:0:12:0): Reserved ASC/ASCQ pair >>>> (probe12:aacp0:0:13:0): INQUIRY. CDB: 12 0 0 0 24 0 >>>> (probe12:aacp0:0:13:0): ILLEGAL REQUEST asc:55,3 >>>> (probe12:aacp0:0:13:0): Reserved ASC/ASCQ pair >>>> (probe14:aacp0:0:15:0): INQUIRY. CDB: 12 0 0 0 24 0 >>>> (probe14:aacp0:0:15:0): ILLEGAL REQUEST asc:55,3 >>>> (probe14:aacp0:0:15:0): Reserved ASC/ASCQ pair >>>> SMP: AP CPU #2 Launched! >>>> SMP: AP CPU #1 Launched! >>>> SMP: AP CPU #3 Launched! >>>> Mounting root from ufs:/dev/aacd0s1a >>>> >>>> Thank You. >>>> >>>> adios, >>>> /kong >>>> >>>> ============================================================== >>>> ========== >>>> Hostas Red (KVK10, KVK10-RIPE) || IP Networks Administrator, CJSC >>>> Rascom >> ============================================================== >>>> ========== >>>> _______________________________________________ >>>> freebsd-amd64@freebsd.org mailing list >>>> http://lists.freebsd.org/mailman/listinfo/freebsd-amd64 >>>> To unsubscribe, send any mail to >>>> "freebsd-amd64-unsubscribe@freebsd.org" >>>> >>>> >>> >> >> adios, >> /kong >> >> ============================================================== >> ========== >> Hostas Red (KVK10, KVK10-RIPE) || IP Networks Administrator, >> CJSC Rascom >> ============================================================== >> ========== >> > adios, /kong ======================================================================== Hostas Red (KVK10, KVK10-RIPE) || IP Networks Administrator, CJSC Rascom ========================================================================