Tag Archives: SSD drives

Adding a RAMDISK as SLOG ZIL to ZFS

If you use ZFS with spinning drives and you share iSCSI, you will need to use a SLOG device for ZIL otherwise you’ll see your iSCSI connections interrupted.

What is a ZIL?

  • ZIL: Acronym for ZFS Intended Log. Logs synchronous operations to disk
  • SLOG: Acronym for (S)eperate (LOG) Device

In ZFS Data is first written and stored in-memory, then it’s flushed to drives. This can take 10 seconds or more.

So without SLOG it can happen that if a power loss occurs, you may loss the last 10 seconds of Data submitted.

The SLOG device brings security that if there is a power loss, after remounting the pool, the information in the SLOG, acknowledged to iSCSI clients, is not lost and flushed to the Hard drives conforming the pool. Basically this device keeps the writings that come from network and flushes to the Hard drives and then clears this data from the SLOG.

Normally I’m describing configurations with a fast device for SLOG ZIL, like one or a pair of NVMe drive or SAS SSD, most commonly in mirror a pool of 12 HDD drives or more SAS preferentially, maybe SATA, with 14TB or more each.

As the SLOG device will persist your Data if there is a power off, and submit to the pool the accepted transactions, it is clear that you cannot spare your SLOG ZIL device. It is needed to bring security when remotely writing.

But what happens if we have a kind of business where we don’t care about that the last 10 seconds writings may be lost? (ZFS will never get corrupted due to its kinda journal system), just because we are filling a Server the fastest possible, migrating from another, or because we are running workouts that can be retaken is some data is lost… do we really need to have the speed constrain of an SSD?. Examples are a Hadoop node, or a SETI@Home client. Tasks will be resumed if something failed.

Let me put in another way, we have 2 NIC 100Gbps, in bonding, so 200Gbps (equivalent to (25GB/s Gigabytes per second), 90 HDD drives that can work in parallel up to 250 MB/s each (22.5GB/s) and our Server has a pair or SAS SSD ZIL in mirror, that writes at 900 MB/s (Megabytes per second, so 0.9 GB/s), so our bottleneck or constraint is the SLOG ZIL.

Adding one RAMDISK, or better two RAMDISKs in mirror, we can get to much more highers speeds. I cannot tell you how much, but in my tests with regular configurations (8D+3P) I was achieving more than 2 GB (Gigabytes) per second sustained of Data to the pool. Take in count that the speed writing to the pool does not only depend on the speed on the ZIL, and the speed of the HDD spinning drives (slow, between 100 and 250 MB/s), but also about the config of the pool (number of vdevs, distributions of data and parity drives) and the throughput of your IOC (Input Output Controller), and the number of them.

Live real scenarios use to be more in the line of having 2x10GbpE cards, combined in bonding making 20Gbps, so being able to transmit 2.5GB/s. So to get the max speed of our Network this Ramdrive will do it. Also NVMe devices used as ZIL will do it.

The problem with the NVMe is that they are connected to the PCI Express bus, and so they are not hot swap. If one dies, you cannot replace without stopping the Server.

The problem with the SSD is that they are not made for writing, they will die, so you need at least a mirror and for heavy IO I strongly recommend you to go with Enterprise grade SAS SSD drives. Those are made to last.

SSD Enterprise grade are double price versus one common SSD, but that peace of mind and extra lasting is worth it. And you don’t need a very big device, only has to hold 10 seconds of Data at max speed. So if you can ingest Data through the Network at 20 Gbps (2.5GB/s) you only need approximately 25 GB of space of the SLOG. 50 GB if you want to be more than safe.

Also you can use partitions instead of complete devices for the SLOG (like for the ZFS pool, where you can add complete drives, or partitions).

If you write locally, and you have 4 IOC’s capable of delivering 8 GB/s each, and you write to a Dataset to the pool, and not to a ZVOL which are slow by nature, you can get astonishing combined speed writing to the drives. If you are migrating a Server to another new, where you can resume if power goes down, then it’s safe to disable sync (set async) while this process runs, and turn sync on when going live to production. If you use async you don’t need to use a SLOG.

4 IOC’s able to deliver 8 GB/s are enough to provide sustained speed to 90 HDD SAS drives. 90x200MB/s=18GB/s required at max speed or 90x250MB/s=22.5GB/s.

The HDD drives provide different speeds in the inner and in the outer areas of the drive, so normally those drives up to 8TB perform between 100 and 200 MB/s, and the drives from 10TB SAS to 14TB SAS perform between 145 and 250 MB/s. I cannot tell about the 16 TB as I’ve not tested them.

The instructions to set a Ramdrive and to assign to a pool are like this:

#!/usr/bin/env bash
RAM_GB=1
RAM_DRIVE_SIZE_IN_BYTES=$((RAM_GB*1048576))

if [[ $(id -u) -ne 0 ]] ; then
    echo "Please run as root"
    exit 1
fi

modprobe brd rd_nr=1 rd_size=${RAM_DRIVE_SIZE_IN_BYTES} max_part=0

echo "Use it like: zpool add carlespool log ram0"

If you created more than one Ramdisk you can add a mirror for the slog to the pool with:

zpool add carlespool log mirror /dev/ram0 /dev/ram1

You can partition the Ramdrive and add a partition but we want to add the whole ram device.

Obviously you cannot put other things to that Ramdisk (like the Metadata) as you need persistence for that.

In any case, please, avoid JBODs loaded of big HDD drives with low bandwidth micro SATA like 3Gbps per channel to the Server, and RAID. The bandwidth is too low. Your rebuilds will take forever.

With ZFS you’ll resilver (rebuild) only the actual data, not the whole drive.

Dealing with Performance degradation on ZFS (DRAID) Rebuilds when migrating from a single processor to a multiprocessor platform

This is the history it happen to me some time ago, and so the commands I used to troubleshot. The purpose is to share knowledge in a interactive way. There are some hidden gems that you’ll acquire if you have the patience to go over all the document and read it all…

I had qualified Intel Xeon single processor platform to run my DRAID (ZFS Declustered RAID) project for my employer.

The platforms I qualified were:

1) single processor for Cold Storage (SAS Spinning drives): 4U60, newest models 4602

2) for multiprocessor: the 4U90 (90 Spinning drives) and Flash: All-Flash-Arrays.

The amounts of RAM I was using for my tests range for 64GB to 384GB.

Somebody in the company, at executive level, assembled an experimental config that was totally new for us and wanted to try by their own. It was the 4602 with multiprocessor and 32GB of RAM.

When they were unable to make it work at the expected speed, they required me to troubleshot and to make it work.

The 4602 single processor had two IOC (Input Output Controller, LSI Logic / Symbios Logic SAS3008 PCI-Express Fusion-MPT SAS-3 (rev 02) ), while the 4602 double processor had four IOC, so given that each of those IOC can perform at peaks of 6GB/s, with a maximum total of 24 GB/s, the performance when reading/writing from all the drives should be better.

But this Server was returning double times for Rebuilding, respect the single processor version, which didn’t make any sense.

I had to check everything. There was the commands I ran:

Check the upgrade of the CPU:

htop
lscpu

Changing the Zoning.

Those Servers use SAS drives dual ported, which means that two different computers can be connected to the same drive and operate at the same time. Is up to you to make sure you don’t introduce corruption. Those systems are used mainly for HA (High Availability).

Those Systems allow to be configured in different zoning modes. That’s the way on how each of the two servers (Controllers) see the disk. In one zoning each Controller sees only 30 drives, in another each IOC sees all the drives (for redundancy but performance constrained to 1 IOC Speed).

The config I set is each IOC will see 15 drives, so each one of the 4 IOC will have 6GB/s for 15 drives. Given that these spinning drives perform in the outtermost part of the cylinder at 265MB/s, that means that at maximum speed one IOC will be using 3.97 GB/s, will say 4GB/s. Plenty of bandwidth.

Note: Spinning drives have different performance depending on how close you’re to the cylinder. In the innermost part it goes under 145 MB/s, and if you read all of those drive sequentially with dd it will return an average speed of 145 MB/s.

With this command you can sive live how it performs and the average read speed in real time. Use skip to jump to that position (relative to bs) in the drive, so you can test directly the speed at the innermost close to the cylinder part of t.

dd if=/dev/sda of=/dev/null bs=1M status=progress

I saw that the zoning was not right one, so I set it correctly:

[root@4602Carles ~]# sg_map -i | grep NEWISYS
/dev/sg30  NEWISYS   NDS-4602-CS       0112
/dev/sg61  NEWISYS   NDS-4602-CS       0112
/dev/sg63  NEWISYS   NDS-4602-CS       0112
/dev/sg64  NEWISYS   NDS-4602-CS       0112
[root@4602Carles10 ~]# sg_senddiag /dev/sg30  --pf --raw=04,00,00,01,53
[root@4602Carles10 ~]# sleep 50
[root@4602Carles10 ~]# sg_senddiag /dev/sg30 --pf -r 04,00,00,01,43
[root@4602Carles10 ~]# sleep 50
[root@4602Carles10 ~]# reboot

The sleeps after rebooting the expanders are recommended. Rebooting the Operating System too, to avoid problems with some Software as the expanders changed live.

If you have ZFS pools or workloads stop them and export the pool before messing with the expanders.

In order to check to which drives is connected each IOC:

[root@4602Carles10 ~]# sg_map -i -x
/dev/sg0  0 0 0 0  0  /dev/sda  TOSHIBA   MG07SCA14TA       0101
/dev/sg1  0 0 1 0  0  /dev/sdb  TOSHIBA   MG07SCA14TA       0101
/dev/sg2  0 0 2 0  0  /dev/sdc  TOSHIBA   MG07SCA14TA       0101
/dev/sg3  0 0 3 0  0  /dev/sdd  TOSHIBA   MG07SCA14TA       0101
/dev/sg4  0 0 4 0  0  /dev/sde  TOSHIBA   MG07SCA14TA       0101
/dev/sg5  0 0 5 0  0  /dev/sdf  TOSHIBA   MG07SCA14TA       0101
/dev/sg6  0 0 6 0  0  /dev/sdg  TOSHIBA   MG07SCA14TA       0101
/dev/sg7  0 0 7 0  0  /dev/sdh  TOSHIBA   MG07SCA14TA       0101
/dev/sg8  1 0 8 0  0  /dev/sdi  TOSHIBA   MG07SCA14TA       0101
/dev/sg9  1 0 9 0  0  /dev/sdj  TOSHIBA   MG07SCA14TA       0101
/dev/sg10  1 0 10 0  0  /dev/sdk  TOSHIBA   MG07SCA14TA       0101
/dev/sg11  1 0 11 0  0  /dev/sdl  TOSHIBA   MG07SCA14TA       0101
[...]
/dev/sg16  4 0 16 0  0  /dev/sdq  TOSHIBA   MG07SCA14TA       0101
/dev/sg17  4 0 17 0  0  /dev/sdr  TOSHIBA   MG07SCA14TA       0101
[...]
/dev/sg30  0 0 30 0  13  NEWISYS   NDS-4602-CS       0112
[...]

Still after setting the right zone the Rebuilds were slow, the scan rate half of the obtained with a single processor.

I tested that the system was able to provide the expected performance by reading from all the drives at the same time. This is done with:

dd if=/dev/sda of=/dev/null bs=1M status=progress &
dd if=/dev/sdb of=/dev/null bs=1M status=progress &
dd if=/dev/sdc of=/dev/null bs=1M status=progress &
dd if=/dev/sdd of=/dev/null bs=1M status=progress &
[...]

I do this for all the drives at the same time and with iostat:

iostat -y 1 1

I check the status of the memory with:

slabtop
free
htop

I checked the memory and htop during a Rebuild. Memory was more than enough. However CPU usage was higher than expected.

The red bars in the image correspond to kernel processes, in this case is the DRAID Rebuild. I see that the load is higher than the usual with a single processor.

I capture all the parameters from ZFS with:

zfs get all

All this information is logged into my forensics document, so later can be checked by my Team or I can share with other Architects or other members of the company. I started this methodology after I knew how Google do their SRE forensics / postmortem documents. Also for myself is useful for the future to have a log of the commands I executed and a verbose output of the results.

I install the smp_utils

yum install smp_utils

Check things:

ls -al  /dev/bsg/
total 0drwxr-xr-x.  2 root root     3020 May 22 10:16 .
drwxr-xr-x. 20 root root     8680 May 22 10:16 ..
crw-------.  1 root root 248,  76 May 22 10:00 1:0:0:0
crw-------.  1 root root 248, 126 May 22 10:00 10:0:0:0
crw-------.  1 root root 248, 127 May 22 10:00 10:0:1:0
crw-------.  1 root root 248, 136 May 22 10:00 10:0:10:0
crw-------.  1 root root 248, 137 May 22 10:00 10:0:11:0
crw-------.  1 root root 248, 138 May 22 10:00 10:0:12:0
crw-------.  1 root root 248, 139 May 22 10:00 10:0:13:0
[...]
[root@4602Carles10 ~]# smp_discover /dev/bsg/expander-1:0
[...]
[root@4602Carles10 ~]# smp_discover /dev/bsg/expander-1:1

I check for errors in the expander that could justify the problems of performance:

for i in `seq 0 64`; do smp_rep_phy_err_log -p $i /dev/bsg/expander-1\:0 ; done
Report phy error log response:
  Expander change count: 567
  phy identifier: 0
  invalid dword count: 0
  running disparity error count: 0
  loss of dword synchronization count: 0
  phy reset problem count: 0
[...]
Report phy error log response:
  Expander change count: 567
  phy identifier: 52
  invalid dword count: 168
  running disparity error count: 172
  loss of dword synchronization count: 5
  phy reset problem count: 0
Report phy error log response:
  Expander change count: 567
  phy identifier: 53
  invalid dword count: 6
  running disparity error count: 6
  loss of dword synchronization count: 0
  phy reset problem count: 0
Report phy error log response:
  Expander change count: 567
  phy identifier: 54
  invalid dword count: 267
  running disparity error count: 270
  loss of dword synchronization count: 4
  phy reset problem count: 0
Report phy error log response:
  Expander change count: 567
  phy identifier: 55
  invalid dword count: 127
  running disparity error count: 131
  loss of dword synchronization count: 5
  phy reset problem count: 0
Report phy error log result: Phy vacant
Report phy error log result: Phy vacant
Report phy error log result: Phy vacant
Report phy error log result: Phy vacant
Report phy error log result: Phy vacant
Report phy error log result: Phy vacant
Report phy error log result: Phy vacant
Report phy error log result: Phy vacant
Report phy error log result: Phy vacant

There are some errors, and I check with the Hardware Team, which pass a battery of tests on the machine and say that the machine passes. They tell me that if the errors counted were in order of millions then it would be a problem, but having few of them is usual.

My colleagues previously reported that the memory was performing well, and the CPU too. They told me that the speed was exactly double respect a platform with one single CPU of the same kind.

Even if they told me that, I ran cmips tests to make sure.

git clone https://github.com/cmips/cmips_bin

It scored 16,000. The performance was Ok in general terms but the problem is that I didn’t have a baseline for that processor in single processor, so I cannot make sure that the memory bandwidth was Ok. The performance was less that an Amazon c3.8xlarge. The system I was testing is a two processor system, but each CPU is cheap, around USD $400.

Still my gut feeling was telling me that this double processor server should score more.

lscpu
[root@DRAID-1135-14TB-2CPU ~]# lscpu
 Architecture:          x86_64
 CPU op-mode(s):        32-bit, 64-bit
 Byte Order:            Little Endian
 CPU(s):                32
 On-line CPU(s) list:   0-31
 Thread(s) per core:    2
 Core(s) per socket:    8
 Socket(s):             2
 NUMA node(s):          2
 Vendor ID:             GenuineIntel
 CPU family:            6
 Model:                 79
 Model name:            Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
 Stepping:              1
 CPU MHz:               2299.951
 CPU max MHz:           3000.0000
 CPU min MHz:           1200.0000
 BogoMIPS:              4199.73
 Virtualization:        VT-x
 L1d cache:             32K
 L1i cache:             32K
 L2 cache:              256K
 L3 cache:              20480K
 NUMA node0 CPU(s):     0-7,16-23
 NUMA node1 CPU(s):     8-15,24-31
 Flags:                 fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch epb cat_l3 cdp_l3 intel_ppin intel_pt ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm rdt_a rdseed adx smap xsaveopt cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts spec_ctrl intel_stibp

I check the memory configuration with:

dmidecode -t memory

I examined the results, I see that the processor can only operate the DDR4 ECC 2400 Memory at 2133 and… I see something!. This Controller before was a single processor with 2 Memory Sticks of 16GB each, dual rank.

I see that now I have the same number of sticks in that machine, but I have two CPU!. So 2 Memory sticks in total, for 2 CPU.

That’s no good. The memory must be in pairs and in the right slots to get the maximum performance.

1 memory module for 1 CPU doesn’t allow to have Dual Channel and probably is affecting the performance. Many Servers will not even boot if you add an odd number of memory sticks per CPU.

And many Servers can operate at full speed only if all the banks are filled.

I request to the Engineers in Silicon Valley to add 4 modules in the right slots. They did, and I repeated the tests and the performance was doubled then.

After some days I had some time with the machine, I repeated the test and I got a CMIPS Score of around 20,000.

Multiprocessor world is far more complicated than single processor. Some times things can work not as expected, and not be evident, for example cache pipeline can act diferent for a program working in multiprocessor and single processor. Or the QPI could be saturated.

After this I shared my forensics document with as many Engineers as I could, so they could learn how I did to troubleshot the problem, and what was the origin of it, and I asked them to do the same so we can track their steps and progress if something needs to be troubleshoot.

After proper intensive testing the Server was qualified. Lesson here is that changes cannot be commited quickly, need their time.