Tag Info

Hot answers tagged

31

I've found that when I've had to tune for lower latency vs throughput, I've tuned nr_requests down from it's default (to as low as 32). The idea being smaller batches equals lower latency. Also for read_ahead_kb I've found that for sequential reads/writes, increasing this value offers better throughput, but I've found that this option really depends on ...


22

The HP Smart Array P410 is a fine controller, but you will get poor performance out of it if you don't have the battery-backed or flash-backed cache units installed. The cache makes a tremendous difference in that writes are buffered by the cache memory before being committed to disk. You get the write confirmation to the application without having to incur ...


19

It depends on your controller. If it supports hot-swap the yes. If not then you might blow the controller and kill the whole array. If you do take a drive out of the array (either while running or powered off) you will have a full re-build to do once you put it back in which will take a while and degrade performance while it happens. Testing your RAID ...


16

While the other answer here beings up some points, your specific issues are due to platform limitations and OS configuration: You're throughput-limited by the use of consumer SATA SSDs on an HP Smart Array P410 RAID controller. SATA disks run at 3.0Gbps (3G) on these controllers rather than 6.0Gbps (6G). So that's a barrier that impacts the read speeds of ...


13

The Storageworks MSA60 enclosure has a "soft" power button. It does not power on automatically. When the power cables are connected, the unit defaults to a standby state. Here's the rear of the HP StorageWorks MSA60 enclosure... On the right side of the rear of the unit, there's a module next to the right power supply which has a soft power button in ...


13

As ewwhite points out they'll physically fit into the servers with the correct disk caddies but you don't have to look far online to read the tales of woe that people run into when using non-HP disks with HP controllers as HP-branded disks have specific firmware on them that extend the functionality, reliability and in some cases performance of their disks. ...


12

This depends slightly on the operating systems you're running on the servers, but in general, it is possible to obtain alerts from HP ProLiant servers and Smart Array RAID controllers. The full driver and software support listing for your DL380 G5 systems is listed here. SNMP and a monitoring solution is the best approach... But you can augment that with ...


12

Please don't do this. If you're going to run ZFS on Linux, do it bare metal without a virtualization layer. All-on-one virtualization and ZFS solutions are cute, but it's not worth the effort in production. As far as drives are concerned, you can use SATA disks on an HP Smart Array controller as well as the LSI 9211-8i controller. In a ZFS configuration, ...


12

Oh dear, where to begin? There is so much involved, and you need a good understanding of everything. Just throwing a bunch of disks against a RAID controller won't yield the results you're looking for. This can't be easily answered. But at least, here is a list of stuff you have to look at: Does the Controller even have the throughput needed? (-> ...


11

I'd start here: HP Smart Array P400 controller - Questions & Answers Honestly though almost every decent RAID controller acts the same in the case of a single drive failure in a two disk RAID 1 array. Since the Smart Array is a true hardware RAID controller either drive can fail and the OS will still work just about as fast as it did with two drives. If ...


11

So let me summarise, correct me if I've missed something out; You're running unsupported disks You're running an unsupported OS You pulled a disk for fun You've lost your array Is that right? If so then you want to know how to debug this right? This site is for professional sysadmins, not amateurs, it says so in the top line of our FAQ (which you read ...


11

This is a hard lesson. You really should not be managing HP logical drives from the BIOS utility. It's far too inflexible and isn't Operating System aware, like the Online Array Configuration Utilities for Windows and Linux. Those tools show the logical drive mount points and lock specific actions if the logical drive is mounted. Furthermore, the BIOS ...


10

Okay. This is an interesting question, as there are a number of options available to you. Some concepts to clarify and understand, as they relate to this situation: Perceptions of "speed" or "fast". RAID controller performance. SAS topology. Benchmarking a system and/or identifying bottlenecks. In order to get the maximum performance, we really ...


10

All modern Linux distributions should see the disk array using the HPSA driver module (older distros would see the outgoing CCISS driver). The reason you're not seeing any disks is that you may not have configured a logical drive. You can do this in the BIOS by following the prompts when the HP Smart Array controller shows up (usually, press F8). Create a ...


10

You will be constrained by the slowest speed and smallest size for disks in the same RAID group. Since you're talking about having three separate mirrors, this doesn't apply to you. Each mirrored pair is a separate array/group/whatever-you-want-to-call-it. You'll end up with three logical volumes, two with 500GB and the other with 1TB with no performance hit ...


10

Thank you for updating the post with more information. You're running on ProLiant systems, so there's a certain amount of work required to optimize your controller and I/O situation. Also, your XFS mounts are using the default options. Remember that you're using a different driver between these operating systems. The EL5 server has cciss, while the EL6 ...


9

Your system is definitely underperforming based on your hardware specifications. I loaded the sysbench utility on a couple of idle HP ProLiant DL380 G6/G7 servers running CentOS 5/6 to check their performance. These are normal fixed partitions instead of LVM. (I don't typically use LVM, because of the flexibility offered by HP Smart Array controllers) The ...


9

How do you know one of the drives has failed? On our ProLiant servers the LEDs on the individual drive trays that turn orange and flash angrily when the drive fails. On your DL380 if one of the drives has failed it should be giving you a visual cue on the font of the unit. To get more information, you could try the Array Configuration Utility Software ...


9

You can just pull the dead disk and replace it - there's no need for OS involvement at all.


9

Yes, you can. (It's tacky, but it will work) Here's a very good reason not to... But if you choose to move forward... You'll need to place the drive in an HP drive carrier/caddy/tray. This is what secures the disk in the hard drive bay and provides hotplug connections to power and the SATA/SAS connection. This interfaces with the SAS SFF-8482 connector ...


9

This is an HP ProLiant server with a Smart Array P420i RAID controller. My immediate advice is to not change any of the default configuration settings unless you have a very specific reason to... In short, don't worry about it. The concept of sectors/tracks in the context of this controller and disk geometry isn't very useful here. Lots of layers of ...


9

You really can't monitor the array status that well on your platform. One tacky option is cciss_vol_status, but it's far from the mainstream approach. This is kind of a bad combination of hardware and software. FreeBSD ProLiant support is a bit Meh... Okay, it's actually worse than that... So a few things to consider: ZFS is a software RAID and volume ...


8

Interesting issue... So the HP RAID controller driver from around 2001 to ~2009 was the CCISS driver. There was a transition to the HPSA driver at some point, moving the Smart Array controller support back into the regular SCSI subsystem versus the dedicated block driver... HP servers from the G1 to G5 era used the CCISS driver. On newer operating systems ...


8

If the disks are grouped together in one array, your capacity and performance will be determined by the smallest, slowest disk. Here's an example from a setup that started with 4 x 750GB disks in a RAID 1+0. As disks failed, HP sent 1TB disks as replacements, so now the array is comprised of 2 x 750GB disks and 2 x 1TB disks. This is what HP does, so the ...


8

A few items... You obviously will not be able to address all of them with your existing P410 controller, but: *Do you need all 16 drives in one array?* I ask, because there isn't much utility in having that many disks in a single array unless you know your read/write patterns and are designing around it. If you don't need all 16 disks in a single array, ...


8

HP has a good write-up of what the differences are here: http://h20000.www2.hp.com/bc/docs/support/SupportManual/c02677069/c02677069.pdf (PDF) High points: Puts devices in the standard /dev namespace, which you already noticed. Modernized interaction with the SCSI layer in newer kernels. hpsa is a SCSI driver, cciss is a block-driver. This will change ...


8

Yes, in this case, you would pull the bad drive and insert the new drive. HP Smart Array controllers initiate the rebuild process automatically. This can be done hot, while the system is running. A description of the HP Smart Array RAID controller technology is available here.


8

My favorite example: This can be run from the shell or within the tool. hpacucli ctrl all show config (use hpacucli.exe for Windows) Or hpacucli ctrl all show config detail But, if you have the HP Management Agents installed anyway, you should have realtime monitoring of RAID status pushing back to email alerts or an external monitoring system. Either ...


7

I wouldn't invest much into getting this server working. The DL585 G1 is a bit old and was end-of-life in 2006. It's not supported under ESXi 5 and I'm not sure you'd be able to use 64-bit virtual machines within it. The VMWare hardware compatibility list implies that support for that model was limited to ESX 3.5. Either way, the model you have was designed ...


7

It is not possible to disable the RAID functionality of HP Smart Array controllers. A common "solution" to this problem is to create single-disk RAID-0 volumes at the controller level. This is not a good solution and is not equivalent to a JBOD arrangement. There's RAID metadata on the disks, and the failures will produce unexpected results. In this case, ...



Only top voted, non community-wiki answers of a minimum length are eligible