Hi Furkan, Thanks for your response ! Indeed RAID10 with both mirroring and striping should satisfy the need, but per some benchmarks in the network there is still an impact on write performance on it compared to RAID0 which is considered as much better (attaching a table that summarizes different RAID levels and their pros/cons and capacity ratio).
If we have ~200-320 shards spread by our 7 Solr node servers (part of SolrCloud cluster) on single core/collection configured with replication factor 2, shouldn't it supply applicative level redundancy of indexed data ? Solr will hold each shard in two places with its documents, and will ensure that every shard placed in 2 different servers, no ? If that's the case, why not choosing RAID0 that is the best from both read and write performance ? Thanks, Adi Sent from Workspace ONE Boxer On Jul 30, 2019 20:51, Furkan KAMACI <furkankam...@gmail.com> wrote: Hi Adi, RAID10 is good for satisfying both indexing and query, striping across mirror sets. However, you lose half of your raw disk space, just like with RAID1. Here is a mail thread of mine which discusses RAID levels for Solr specific: https://lists.apache.org/thread.html/462d7467b2f2d064223eb46763a6a6e606ac670fe7f7b40858d97c0d@1366325333@%3Csolr-user.lucene.apache.org%3E Kind Regards, Furkan KAMACI On Mon, Jul 29, 2019 at 10:25 PM Kaminski, Adi <adi.kamin...@verint.com> wrote: > Hi, > We are about to size large environment with 7 nodes/servers with > replication factor 2 of SolrCloud cluster (using Solr 7.6). > > The system contains parent-child (nested documents) schema, and about to > have 40M parent docs with 50-80 child docs each (in total 2-3.2B Solr docs). > > We have a use case that will require to update parent document fields > triggered by an application flow (with re-indexing or atomic/partial update > approach, that will probably require to upgrade to Solr 8.1.1 that supports > this feature and contains some fixes in nested docs handling area). > > Since these updates might be quite heavy from IOPS perspective, we would > like to make sure that the IO hardware and RAID configuration are optimized > (r/w ratio of 50% read and 50% write, to allow balanced search and update > flows). > > Can someone share similar scale/use- case/deployment RAID level > configuration ? > (I assume that RAID5&6 are not an option due to parity/dual parity heavy > impact on write operations, so it leaves RAID 0, 1 or 10). > > Thanks in advance, > Adi > > > > > Sent from Workspace ONE Boxer > > > This electronic message may contain proprietary and confidential > information of Verint Systems Inc., its affiliates and/or subsidiaries. The > information is intended to be for the use of the individual(s) or > entity(ies) named above. If you are not the intended recipient (or > authorized to receive this e-mail for the intended recipient), you may not > use, copy, disclose or distribute to anyone this message or any information > contained in this message. If you have received this electronic message in > error, please notify us by replying to this e-mail. > This electronic message may contain proprietary and confidential information of Verint Systems Inc., its affiliates and/or subsidiaries. The information is intended to be for the use of the individual(s) or entity(ies) named above. If you are not the intended recipient (or authorized to receive this e-mail for the intended recipient), you may not use, copy, disclose or distribute to anyone this message or any information contained in this message. If you have received this electronic message in error, please notify us by replying to this e-mail.
