similar to: Realistic mirror performance expectations?

Hi all, I'm confused of small files (no bigger than 50k ) transfers speed through samba,which is very slow on my machine. Bellow is a real case, -- SuSE professional 9.2, kernel 2.6.11,Samba 3.0.14a,reiserfs -- Dual AMD Opteron,4G mem,Giga byte LAN -- 2 raid 5 make up of 16 SATA hard disks -- set readhead to 1024 I tested raids speed using bonnie++ and get 450 Mbytes/s at 16GB files

Hello, I'm working on a cloud/virtualisation platform and i'd like to know your point of view. I'm dream about a shared file system (or cluster filesystem) for lots of hypervisor with lots of shared disk space (for HA, hot migration,...). Well glusterFS seems very cool, easy configuration, work in only shared storage way (no need for replication). Can I use it for 40 nodes and

Hi, I'm using *CVS Head version and read the dialplan from MySQL. I'm making A-Z termination to over 4000 different country and city codes. I have 3 different dialing rules depending on the price level of the dialed number. Should my extensions table contain 4000 lines? Is this realistic? Or is there any other (more clever) way doing this? Regards, Cenk. -------------- next part

We're trying to setup a dual-primary DRBD environment, with a shared disk with either OCFS2 or GFS. The environment is a Centos 5.3 with DRBD82 (but also tried with DRBD83 from testing) . Setting up a single primary disk and running bonnie++ on it works. Setting up a dual-primary disk, only mounting it on one node (ext3) and running bonnie++ works When setting up ocfs2 on the /dev/drbd0

We're trying to setup a dual-primary DRBD environment, with a shared disk with either OCFS2 or GFS. The environment is a Centos 5.3 with DRBD82 (but also tried with DRBD83 from testing) . Setting up a single primary disk and running bonnie++ on it works. Setting up a dual-primary disk, only mounting it on one node (ext3) and running bonnie++ works When setting up ocfs2 on the /dev/drbd0

Hi Folks, I was wondering if anyone has an pointers/suggestions on how I might increase disk performance of a HVM zvol-backed DomU? - this is my first DomU, so hopefully its something obvious Running bonnie++ shows the DomU''s performance to be 3 orders of magnitude worse than Dom0''s, which itself is half as good as when not running xVM at all (see bottom for bonnie++ results)

On 2019/4/11 19:01, Yuval Shaia wrote: > Signed-off-by: Yuval Shaia <yuval.shaia at oracle.com> > --- > drivers/infiniband/Kconfig | 1 + > drivers/infiniband/hw/Makefile | 1 + > drivers/infiniband/hw/virtio/Kconfig | 6 + > drivers/infiniband/hw/virtio/Makefile | 4 + >

Signed-off-by: Yuval Shaia <yuval.shaia at oracle.com> --- drivers/infiniband/Kconfig | 1 + drivers/infiniband/hw/Makefile | 1 + drivers/infiniband/hw/virtio/Kconfig | 6 + drivers/infiniband/hw/virtio/Makefile | 4 + drivers/infiniband/hw/virtio/virtio_rdma.h | 40 + .../infiniband/hw/virtio/virtio_rdma_device.c | 59 ++

G''day, all, So, I''ve decided to migrate my home server from Linux+swRAID+LVM to Solaris+ZFS, because it seems to hold much better promise for data integrity, which is my primary concern. However, naturally, I decided to do some benchmarks in the process, and I don''t understand why the results are what they are. I though I had a reasonable understanding of ZFS, but now

Greetings I've searched to no avail so far... there is bound to be something more intelligible out there...??? I am playing with bonnie++ for the first time... May I please get some advise and list experience on using this or other disk subsystem benchmark programs properly with or without a GUI ? Test system in this case is a Compaq DL360 with 2 to 4 Gig DRAM and qty (2) 36Gig 10k drives

i'm attempting to rebuild centos51 kernel-xen. (fwiw, because pciback has NOT been compiled into the kernel, http://bugs.centos.org/view.php?id=2767) after, yum install kernel-devel kernel-xen-devel and usual, ln -s /usr/src/kernels/`uname -r`-`uname -m` /usr/src/linux cd /usr/src/linux cp /boot/config-`uname -r` ./.config make oldconfig make menuconfig ... next, make rpm

Hi, I have a problem while doing a "make linux-2.6-xen-install". First of all, i did a "make linux-2.6-xen-config CONFIGMODE=menuconfig" I chose in Device Drivers menu -> Infiniband Support : If i choose all the options in module or built-in, i get the same results with make install. This error appears :

From: Jason Gunthorpe <jgg at mellanox.com> This converts one of the two users of mmu_notifiers to use the new API. The conversion is fairly straightforward, however the existing use of notifiers here seems to be racey. Tested-by: Dennis Dalessandro <dennis.dalessandro at intel.com> Signed-off-by: Jason Gunthorpe <jgg at mellanox.com> --- drivers/infiniband/hw/hfi1/file_ops.c

I have just purchased an HP ProLiant HP ML110 G5 server and install ed CentOS 5.2 x86_64 on it. It has the following spec: Intel(R) Xeon(R) CPU 3065 @ 2.33GHz 4GB ECC memory 4 x 250GB SATA hard disks running at 1.5GB/s Onboard RAID controller is enabled but at the moment I have used mdadm to configure the array. RAID bus controller: Intel Corporation 82801 SATA RAID Controller For a simple

From: Jason Gunthorpe <jgg at mellanox.com> This converts one of the two users of mmu_notifiers to use the new API. The conversion is fairly straightforward, however the existing use of notifiers here seems to be racey. Cc: Mike Marciniszyn <mike.marciniszyn at intel.com> Cc: Dennis Dalessandro <dennis.dalessandro at intel.com> Signed-off-by: Jason Gunthorpe <jgg at

I'm setting up a new fileserver. It has two RAID controllers, a PERC 3/DI providing mirrored system disks and a PERC 3/DC providing a 1TB RAID5 volume consisting of eight 144GB U160 drives. This will serve NFS, Samba and sftp clients for about 200 users. The logical drive was created with the following settings: RAID = 5 stripe size = 32kb write policy = wrback read policy =

Hi Lamia, Currently there is no direct InfiniBand access support in the Official Xen trees. You might want to have a look at our Xen-IB implementation. A preliminary version can be downloaded here: http://xenbits.xensource.com/ext/xen-smartio.hg Some information about its design and applications can be found here: High Performance VMM-Bypass I/O in Virtual Machines (Usenix 06), and A Case for

On 10/28/19 1:10 PM, Jason Gunthorpe wrote: > From: Jason Gunthorpe <jgg at mellanox.com> > > 8 of the mmu_notifier using drivers (i915_gem, radeon_mn, umem_odp, hfi1, > scif_dma, vhost, gntdev, hmm) drivers are using a common pattern where > they only use invalidate_range_start/end and immediately check the > invalidating range against some driver data structure to tell

We seemed to have it a stumbling block when building with the above (supported) versions. Our process... 1. Start with stock rhel5 2.6.18-8.1.14 source tree 2. Configure InfiniBand support out of the the kernel (we will build OFED separately). 3. Apply the 1.6.4.2 kernel patches to the kernel source. 4. Build the kernel. 5. Build OFED 1.2 against the patched kernel 6. Build Lustre using

Hi all, some results from my configuration. I''ve this configuration (I''m not interested in raw top performances but in reliability.. so, I can accept slow MB/sec and prefer to rely on a RAID6, for example): 1 Infortrend iSCSI Array A16E-G2130-4 with: - 1GB DDR cache - RAID6 - 7 x 500GB sataII Seagate ST3500630NS with 16mb (no budget for SAS) - one of the logic volumes (about